Training in progress, epoch 0, checkpoint
Browse files- last-checkpoint/README.md +202 -0
- last-checkpoint/adapter_config.json +34 -0
- last-checkpoint/adapter_model.safetensors +3 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/rng_state_0.pth +3 -0
- last-checkpoint/rng_state_1.pth +3 -0
- last-checkpoint/rng_state_2.pth +3 -0
- last-checkpoint/rng_state_3.pth +3 -0
- last-checkpoint/rng_state_4.pth +3 -0
- last-checkpoint/rng_state_5.pth +3 -0
- last-checkpoint/rng_state_6.pth +3 -0
- last-checkpoint/rng_state_7.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/special_tokens_map.json +30 -0
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +81 -0
- last-checkpoint/trainer_state.json +3533 -0
- last-checkpoint/training_args.bin +3 -0
last-checkpoint/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: oopsung/llama2-7b-n-ox-test-v1
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.13.2
|
last-checkpoint/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "oopsung/llama2-7b-n-ox-test-v1",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": null,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 64,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"down_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"up_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"q_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
last-checkpoint/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83b3dee010194bc7e240595485d95794307e9b507af80667a70f9aab02b6c3ee
|
| 3 |
+
size 319876032
|
last-checkpoint/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7493831a7faf060f5761b525ff9f8eef4f600dd35483e01c147064ee0ae86180
|
| 3 |
+
size 162933844
|
last-checkpoint/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ad880d8d74b0a61eb1f2ad84cb15481bc34fe8ecc5e761a8761b94c254f8717
|
| 3 |
+
size 15984
|
last-checkpoint/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18f851717eb0e7db487a6899e82f0da44d9842be5730cace374bce4c31a5d5ea
|
| 3 |
+
size 15984
|
last-checkpoint/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2e76b32879828b64df4e123b2630b40a652c897e07ba33e72d88a5feedb2a2b
|
| 3 |
+
size 15984
|
last-checkpoint/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e40fd42d74900c0372624e91a961414da4bb0b3f6138910bced46089f68a2eb5
|
| 3 |
+
size 15984
|
last-checkpoint/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4686350ba473c08a7abcbf83f4c0df01ae61c94864d6baefbe76dd54205cfbd7
|
| 3 |
+
size 15984
|
last-checkpoint/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e171a1b751857ceb76626270f7a20c06552f0be030670a38793d15609f3fc6aa
|
| 3 |
+
size 15984
|
last-checkpoint/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7dfd50a556b04e208bd9c4b97b59044bc2c4a0b0ef743dc4442b87dfdd72fb1e
|
| 3 |
+
size 15984
|
last-checkpoint/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d6089f183077288307a9bcbfc78cfb1f18c6ad5c55e41af13225db5b6633e31
|
| 3 |
+
size 15984
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:043092824777602976966449c2a2a96527a878ad10507a3b4d0f461ea2b8d14e
|
| 3 |
+
size 1064
|
last-checkpoint/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
last-checkpoint/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last-checkpoint/tokenizer_config.json
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"46331": {
|
| 31 |
+
"content": "<|sep|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"46332": {
|
| 39 |
+
"content": "<|endoftext|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"46333": {
|
| 47 |
+
"content": "<|acc|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"46334": {
|
| 55 |
+
"content": "<|rrn|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"46335": {
|
| 63 |
+
"content": "<|tel|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
}
|
| 70 |
+
},
|
| 71 |
+
"bos_token": "<s>",
|
| 72 |
+
"clean_up_tokenization_spaces": false,
|
| 73 |
+
"eos_token": "</s>",
|
| 74 |
+
"legacy": false,
|
| 75 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 76 |
+
"pad_token": "</s>",
|
| 77 |
+
"sp_model_kwargs": {},
|
| 78 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 79 |
+
"unk_token": "<unk>",
|
| 80 |
+
"use_default_system_prompt": false
|
| 81 |
+
}
|
last-checkpoint/trainer_state.json
ADDED
|
@@ -0,0 +1,3533 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.8463817181548878,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0016927634363097758,
|
| 13 |
+
"grad_norm": 0.21856777369976044,
|
| 14 |
+
"learning_rate": 2.02e-06,
|
| 15 |
+
"loss": 2.0481,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0033855268726195515,
|
| 20 |
+
"grad_norm": 0.23913073539733887,
|
| 21 |
+
"learning_rate": 4.04e-06,
|
| 22 |
+
"loss": 2.0244,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0050782903089293275,
|
| 27 |
+
"grad_norm": 0.2251112014055252,
|
| 28 |
+
"learning_rate": 6.06e-06,
|
| 29 |
+
"loss": 2.0831,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.006771053745239103,
|
| 34 |
+
"grad_norm": 0.22981800138950348,
|
| 35 |
+
"learning_rate": 8.08e-06,
|
| 36 |
+
"loss": 2.0097,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.008463817181548879,
|
| 41 |
+
"grad_norm": 0.24785353243350983,
|
| 42 |
+
"learning_rate": 1.0100000000000002e-05,
|
| 43 |
+
"loss": 2.1596,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.010156580617858655,
|
| 48 |
+
"grad_norm": 0.2091209888458252,
|
| 49 |
+
"learning_rate": 1.212e-05,
|
| 50 |
+
"loss": 2.0497,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.01184934405416843,
|
| 55 |
+
"grad_norm": 0.2210516482591629,
|
| 56 |
+
"learning_rate": 1.4140000000000002e-05,
|
| 57 |
+
"loss": 2.0596,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.013542107490478206,
|
| 62 |
+
"grad_norm": 0.21174772083759308,
|
| 63 |
+
"learning_rate": 1.616e-05,
|
| 64 |
+
"loss": 2.017,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.01523487092678798,
|
| 69 |
+
"grad_norm": 0.22919593751430511,
|
| 70 |
+
"learning_rate": 1.818e-05,
|
| 71 |
+
"loss": 2.0424,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.016927634363097757,
|
| 76 |
+
"grad_norm": 0.21787938475608826,
|
| 77 |
+
"learning_rate": 2.0200000000000003e-05,
|
| 78 |
+
"loss": 2.0222,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.018620397799407534,
|
| 83 |
+
"grad_norm": 0.2346174418926239,
|
| 84 |
+
"learning_rate": 2.222e-05,
|
| 85 |
+
"loss": 2.1,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.02031316123571731,
|
| 90 |
+
"grad_norm": 0.21451573073863983,
|
| 91 |
+
"learning_rate": 2.424e-05,
|
| 92 |
+
"loss": 2.027,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.022005924672027083,
|
| 97 |
+
"grad_norm": 0.19577345252037048,
|
| 98 |
+
"learning_rate": 2.6260000000000003e-05,
|
| 99 |
+
"loss": 2.0718,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.02369868810833686,
|
| 104 |
+
"grad_norm": 0.20922431349754333,
|
| 105 |
+
"learning_rate": 2.8280000000000004e-05,
|
| 106 |
+
"loss": 2.1276,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.025391451544646636,
|
| 111 |
+
"grad_norm": 0.16791805624961853,
|
| 112 |
+
"learning_rate": 3.0299999999999998e-05,
|
| 113 |
+
"loss": 2.0778,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.027084214980956412,
|
| 118 |
+
"grad_norm": 0.21578575670719147,
|
| 119 |
+
"learning_rate": 3.232e-05,
|
| 120 |
+
"loss": 2.0501,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.02877697841726619,
|
| 125 |
+
"grad_norm": 0.20047278702259064,
|
| 126 |
+
"learning_rate": 3.434e-05,
|
| 127 |
+
"loss": 2.0688,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.03046974185357596,
|
| 132 |
+
"grad_norm": 0.1888180375099182,
|
| 133 |
+
"learning_rate": 3.636e-05,
|
| 134 |
+
"loss": 2.004,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.03216250528988574,
|
| 139 |
+
"grad_norm": 0.2372732013463974,
|
| 140 |
+
"learning_rate": 3.838e-05,
|
| 141 |
+
"loss": 2.0889,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.033855268726195514,
|
| 146 |
+
"grad_norm": 0.22184057533740997,
|
| 147 |
+
"learning_rate": 4.0400000000000006e-05,
|
| 148 |
+
"loss": 1.8746,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.03554803216250529,
|
| 153 |
+
"grad_norm": 0.2352249026298523,
|
| 154 |
+
"learning_rate": 4.242e-05,
|
| 155 |
+
"loss": 2.0653,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.03724079559881507,
|
| 160 |
+
"grad_norm": 0.19941262900829315,
|
| 161 |
+
"learning_rate": 4.444e-05,
|
| 162 |
+
"loss": 2.0372,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.03893355903512484,
|
| 167 |
+
"grad_norm": 0.19495126605033875,
|
| 168 |
+
"learning_rate": 4.6460000000000006e-05,
|
| 169 |
+
"loss": 1.9998,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.04062632247143462,
|
| 174 |
+
"grad_norm": 0.1923140585422516,
|
| 175 |
+
"learning_rate": 4.848e-05,
|
| 176 |
+
"loss": 1.9869,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.04231908590774439,
|
| 181 |
+
"grad_norm": 0.18755634129047394,
|
| 182 |
+
"learning_rate": 5.05e-05,
|
| 183 |
+
"loss": 1.9735,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.044011849344054166,
|
| 188 |
+
"grad_norm": 0.17831045389175415,
|
| 189 |
+
"learning_rate": 5.2520000000000005e-05,
|
| 190 |
+
"loss": 1.9195,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.045704612780363946,
|
| 195 |
+
"grad_norm": 0.18653540313243866,
|
| 196 |
+
"learning_rate": 5.454e-05,
|
| 197 |
+
"loss": 1.9599,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.04739737621667372,
|
| 202 |
+
"grad_norm": 0.18552574515342712,
|
| 203 |
+
"learning_rate": 5.656000000000001e-05,
|
| 204 |
+
"loss": 2.0633,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.0490901396529835,
|
| 209 |
+
"grad_norm": 0.18219119310379028,
|
| 210 |
+
"learning_rate": 5.858e-05,
|
| 211 |
+
"loss": 1.9686,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.05078290308929327,
|
| 216 |
+
"grad_norm": 0.1793995052576065,
|
| 217 |
+
"learning_rate": 6.0599999999999996e-05,
|
| 218 |
+
"loss": 2.0293,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.052475666525603044,
|
| 223 |
+
"grad_norm": 0.1970832496881485,
|
| 224 |
+
"learning_rate": 6.262000000000001e-05,
|
| 225 |
+
"loss": 1.8754,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.054168429961912824,
|
| 230 |
+
"grad_norm": 0.18978503346443176,
|
| 231 |
+
"learning_rate": 6.464e-05,
|
| 232 |
+
"loss": 2.0828,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.0558611933982226,
|
| 237 |
+
"grad_norm": 0.18691568076610565,
|
| 238 |
+
"learning_rate": 6.666e-05,
|
| 239 |
+
"loss": 1.9331,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.05755395683453238,
|
| 244 |
+
"grad_norm": 0.20160901546478271,
|
| 245 |
+
"learning_rate": 6.868e-05,
|
| 246 |
+
"loss": 2.007,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.05924672027084215,
|
| 251 |
+
"grad_norm": 0.180143803358078,
|
| 252 |
+
"learning_rate": 7.07e-05,
|
| 253 |
+
"loss": 1.9634,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.06093948370715192,
|
| 258 |
+
"grad_norm": 0.18108704686164856,
|
| 259 |
+
"learning_rate": 7.272e-05,
|
| 260 |
+
"loss": 2.1212,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.0626322471434617,
|
| 265 |
+
"grad_norm": 0.17915402352809906,
|
| 266 |
+
"learning_rate": 7.474e-05,
|
| 267 |
+
"loss": 2.0112,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.06432501057977148,
|
| 272 |
+
"grad_norm": 0.19328810274600983,
|
| 273 |
+
"learning_rate": 7.676e-05,
|
| 274 |
+
"loss": 1.9586,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.06601777401608125,
|
| 279 |
+
"grad_norm": 0.18603388965129852,
|
| 280 |
+
"learning_rate": 7.878e-05,
|
| 281 |
+
"loss": 2.0371,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.06771053745239103,
|
| 286 |
+
"grad_norm": 0.1937795877456665,
|
| 287 |
+
"learning_rate": 8.080000000000001e-05,
|
| 288 |
+
"loss": 2.0589,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.06940330088870081,
|
| 293 |
+
"grad_norm": 0.16889318823814392,
|
| 294 |
+
"learning_rate": 8.282e-05,
|
| 295 |
+
"loss": 1.9922,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.07109606432501057,
|
| 300 |
+
"grad_norm": 0.19249765574932098,
|
| 301 |
+
"learning_rate": 8.484e-05,
|
| 302 |
+
"loss": 2.0219,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.07278882776132035,
|
| 307 |
+
"grad_norm": 0.1795249879360199,
|
| 308 |
+
"learning_rate": 8.686e-05,
|
| 309 |
+
"loss": 2.0005,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.07448159119763013,
|
| 314 |
+
"grad_norm": 0.21890012919902802,
|
| 315 |
+
"learning_rate": 8.888e-05,
|
| 316 |
+
"loss": 2.0732,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.0761743546339399,
|
| 321 |
+
"grad_norm": 0.2015288770198822,
|
| 322 |
+
"learning_rate": 9.09e-05,
|
| 323 |
+
"loss": 1.9067,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.07786711807024968,
|
| 328 |
+
"grad_norm": 0.19771352410316467,
|
| 329 |
+
"learning_rate": 9.292000000000001e-05,
|
| 330 |
+
"loss": 1.9698,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.07955988150655946,
|
| 335 |
+
"grad_norm": 0.22185812890529633,
|
| 336 |
+
"learning_rate": 9.494e-05,
|
| 337 |
+
"loss": 2.1254,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.08125264494286924,
|
| 342 |
+
"grad_norm": 0.19680249691009521,
|
| 343 |
+
"learning_rate": 9.696e-05,
|
| 344 |
+
"loss": 2.0022,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.082945408379179,
|
| 349 |
+
"grad_norm": 0.21367794275283813,
|
| 350 |
+
"learning_rate": 9.898e-05,
|
| 351 |
+
"loss": 1.8728,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.08463817181548879,
|
| 356 |
+
"grad_norm": 0.2153550088405609,
|
| 357 |
+
"learning_rate": 0.000101,
|
| 358 |
+
"loss": 2.0168,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.08633093525179857,
|
| 363 |
+
"grad_norm": 0.20331734418869019,
|
| 364 |
+
"learning_rate": 0.00010302,
|
| 365 |
+
"loss": 2.0049,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.08802369868810833,
|
| 370 |
+
"grad_norm": 0.19431838393211365,
|
| 371 |
+
"learning_rate": 0.00010504000000000001,
|
| 372 |
+
"loss": 1.8976,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.08971646212441811,
|
| 377 |
+
"grad_norm": 0.19682154059410095,
|
| 378 |
+
"learning_rate": 0.00010706000000000001,
|
| 379 |
+
"loss": 1.898,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.09140922556072789,
|
| 384 |
+
"grad_norm": 0.20410743355751038,
|
| 385 |
+
"learning_rate": 0.00010908,
|
| 386 |
+
"loss": 1.9067,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.09310198899703766,
|
| 391 |
+
"grad_norm": 0.21040071547031403,
|
| 392 |
+
"learning_rate": 0.00011110000000000002,
|
| 393 |
+
"loss": 2.0007,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.09479475243334744,
|
| 398 |
+
"grad_norm": 0.2420426458120346,
|
| 399 |
+
"learning_rate": 0.00011312000000000001,
|
| 400 |
+
"loss": 1.9398,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.09648751586965722,
|
| 405 |
+
"grad_norm": 0.24033543467521667,
|
| 406 |
+
"learning_rate": 0.00011514,
|
| 407 |
+
"loss": 2.001,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.098180279305967,
|
| 412 |
+
"grad_norm": 0.23176445066928864,
|
| 413 |
+
"learning_rate": 0.00011716,
|
| 414 |
+
"loss": 2.081,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.09987304274227676,
|
| 419 |
+
"grad_norm": 0.21144893765449524,
|
| 420 |
+
"learning_rate": 0.00011918,
|
| 421 |
+
"loss": 1.8212,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.10156580617858654,
|
| 426 |
+
"grad_norm": 0.23067671060562134,
|
| 427 |
+
"learning_rate": 0.00012119999999999999,
|
| 428 |
+
"loss": 1.9066,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.10325856961489632,
|
| 433 |
+
"grad_norm": 0.26889732480049133,
|
| 434 |
+
"learning_rate": 0.00012322,
|
| 435 |
+
"loss": 1.8263,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.10495133305120609,
|
| 440 |
+
"grad_norm": 0.21251942217350006,
|
| 441 |
+
"learning_rate": 0.00012524000000000001,
|
| 442 |
+
"loss": 1.9031,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.10664409648751587,
|
| 447 |
+
"grad_norm": 0.21674378216266632,
|
| 448 |
+
"learning_rate": 0.00012726,
|
| 449 |
+
"loss": 1.8843,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.10833685992382565,
|
| 454 |
+
"grad_norm": 0.2463655322790146,
|
| 455 |
+
"learning_rate": 0.00012928,
|
| 456 |
+
"loss": 1.9816,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.11002962336013541,
|
| 461 |
+
"grad_norm": 0.2431013435125351,
|
| 462 |
+
"learning_rate": 0.00013130000000000002,
|
| 463 |
+
"loss": 1.9958,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.1117223867964452,
|
| 468 |
+
"grad_norm": 0.21589888632297516,
|
| 469 |
+
"learning_rate": 0.00013332,
|
| 470 |
+
"loss": 1.9283,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.11341515023275497,
|
| 475 |
+
"grad_norm": 0.2475602626800537,
|
| 476 |
+
"learning_rate": 0.00013534000000000002,
|
| 477 |
+
"loss": 1.8687,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.11510791366906475,
|
| 482 |
+
"grad_norm": 0.22713498771190643,
|
| 483 |
+
"learning_rate": 0.00013736,
|
| 484 |
+
"loss": 1.8763,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.11680067710537452,
|
| 489 |
+
"grad_norm": 0.21402622759342194,
|
| 490 |
+
"learning_rate": 0.00013937999999999998,
|
| 491 |
+
"loss": 1.9201,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.1184934405416843,
|
| 496 |
+
"grad_norm": 0.24653713405132294,
|
| 497 |
+
"learning_rate": 0.0001414,
|
| 498 |
+
"loss": 1.9369,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.12018620397799408,
|
| 503 |
+
"grad_norm": 0.23254817724227905,
|
| 504 |
+
"learning_rate": 0.00014342,
|
| 505 |
+
"loss": 1.9923,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.12187896741430385,
|
| 510 |
+
"grad_norm": 0.22863097488880157,
|
| 511 |
+
"learning_rate": 0.00014544,
|
| 512 |
+
"loss": 1.9701,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.12357173085061363,
|
| 517 |
+
"grad_norm": 0.2209753394126892,
|
| 518 |
+
"learning_rate": 0.00014746,
|
| 519 |
+
"loss": 1.8904,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.1252644942869234,
|
| 524 |
+
"grad_norm": 0.2530592381954193,
|
| 525 |
+
"learning_rate": 0.00014948,
|
| 526 |
+
"loss": 1.9259,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.12695725772323319,
|
| 531 |
+
"grad_norm": 0.23368902504444122,
|
| 532 |
+
"learning_rate": 0.0001515,
|
| 533 |
+
"loss": 1.9462,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.12865002115954297,
|
| 538 |
+
"grad_norm": 0.24833092093467712,
|
| 539 |
+
"learning_rate": 0.00015352,
|
| 540 |
+
"loss": 1.9063,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.13034278459585272,
|
| 545 |
+
"grad_norm": 0.23310640454292297,
|
| 546 |
+
"learning_rate": 0.00015554000000000002,
|
| 547 |
+
"loss": 1.9147,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.1320355480321625,
|
| 552 |
+
"grad_norm": 0.2354939877986908,
|
| 553 |
+
"learning_rate": 0.00015756,
|
| 554 |
+
"loss": 2.0259,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.13372831146847228,
|
| 559 |
+
"grad_norm": 0.24625660479068756,
|
| 560 |
+
"learning_rate": 0.00015958000000000001,
|
| 561 |
+
"loss": 1.9424,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.13542107490478206,
|
| 566 |
+
"grad_norm": 0.26915672421455383,
|
| 567 |
+
"learning_rate": 0.00016160000000000002,
|
| 568 |
+
"loss": 1.9616,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.13711383834109184,
|
| 573 |
+
"grad_norm": 0.20115861296653748,
|
| 574 |
+
"learning_rate": 0.00016362,
|
| 575 |
+
"loss": 1.8272,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.13880660177740162,
|
| 580 |
+
"grad_norm": 0.21742068231105804,
|
| 581 |
+
"learning_rate": 0.00016564,
|
| 582 |
+
"loss": 1.9483,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.1404993652137114,
|
| 587 |
+
"grad_norm": 0.21801471710205078,
|
| 588 |
+
"learning_rate": 0.00016766,
|
| 589 |
+
"loss": 1.9739,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.14219212865002115,
|
| 594 |
+
"grad_norm": 0.23018628358840942,
|
| 595 |
+
"learning_rate": 0.00016968,
|
| 596 |
+
"loss": 1.9386,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.14388489208633093,
|
| 601 |
+
"grad_norm": 0.24194473028182983,
|
| 602 |
+
"learning_rate": 0.0001717,
|
| 603 |
+
"loss": 1.8877,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.1455776555226407,
|
| 608 |
+
"grad_norm": 0.2352004051208496,
|
| 609 |
+
"learning_rate": 0.00017372,
|
| 610 |
+
"loss": 1.9368,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.1472704189589505,
|
| 615 |
+
"grad_norm": 0.20487657189369202,
|
| 616 |
+
"learning_rate": 0.00017574,
|
| 617 |
+
"loss": 1.8582,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.14896318239526027,
|
| 622 |
+
"grad_norm": 0.24406185746192932,
|
| 623 |
+
"learning_rate": 0.00017776,
|
| 624 |
+
"loss": 1.9033,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.15065594583157005,
|
| 629 |
+
"grad_norm": 0.235113725066185,
|
| 630 |
+
"learning_rate": 0.00017978000000000002,
|
| 631 |
+
"loss": 1.9519,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.1523487092678798,
|
| 636 |
+
"grad_norm": 0.22690711915493011,
|
| 637 |
+
"learning_rate": 0.0001818,
|
| 638 |
+
"loss": 1.8798,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.15404147270418958,
|
| 643 |
+
"grad_norm": 0.2338939756155014,
|
| 644 |
+
"learning_rate": 0.00018382,
|
| 645 |
+
"loss": 1.938,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.15573423614049936,
|
| 650 |
+
"grad_norm": 0.2826458811759949,
|
| 651 |
+
"learning_rate": 0.00018584000000000002,
|
| 652 |
+
"loss": 1.8859,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.15742699957680914,
|
| 657 |
+
"grad_norm": 0.23302127420902252,
|
| 658 |
+
"learning_rate": 0.00018786,
|
| 659 |
+
"loss": 1.9253,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.15911976301311892,
|
| 664 |
+
"grad_norm": 0.22500993311405182,
|
| 665 |
+
"learning_rate": 0.00018988,
|
| 666 |
+
"loss": 1.8338,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.1608125264494287,
|
| 671 |
+
"grad_norm": 0.2076253741979599,
|
| 672 |
+
"learning_rate": 0.0001919,
|
| 673 |
+
"loss": 1.7979,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.16250528988573848,
|
| 678 |
+
"grad_norm": 0.23616939783096313,
|
| 679 |
+
"learning_rate": 0.00019392,
|
| 680 |
+
"loss": 1.9603,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.16419805332204823,
|
| 685 |
+
"grad_norm": 0.20899280905723572,
|
| 686 |
+
"learning_rate": 0.00019594,
|
| 687 |
+
"loss": 1.8669,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.165890816758358,
|
| 692 |
+
"grad_norm": 0.23518052697181702,
|
| 693 |
+
"learning_rate": 0.00019796,
|
| 694 |
+
"loss": 1.9586,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.1675835801946678,
|
| 699 |
+
"grad_norm": 0.2177092283964157,
|
| 700 |
+
"learning_rate": 0.00019998,
|
| 701 |
+
"loss": 1.8993,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.16927634363097757,
|
| 706 |
+
"grad_norm": 0.22413797676563263,
|
| 707 |
+
"learning_rate": 0.000202,
|
| 708 |
+
"loss": 1.9742,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.17096910706728735,
|
| 713 |
+
"grad_norm": 0.21205808222293854,
|
| 714 |
+
"learning_rate": 0.00020199688492212377,
|
| 715 |
+
"loss": 1.8326,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.17266187050359713,
|
| 720 |
+
"grad_norm": 0.20058460533618927,
|
| 721 |
+
"learning_rate": 0.00020198753988064772,
|
| 722 |
+
"loss": 1.9229,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.1743546339399069,
|
| 727 |
+
"grad_norm": 0.21106334030628204,
|
| 728 |
+
"learning_rate": 0.00020197196545201806,
|
| 729 |
+
"loss": 1.8479,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.17604739737621666,
|
| 734 |
+
"grad_norm": 0.20998717844486237,
|
| 735 |
+
"learning_rate": 0.0002019501625969389,
|
| 736 |
+
"loss": 1.9287,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.17774016081252644,
|
| 741 |
+
"grad_norm": 0.20730508863925934,
|
| 742 |
+
"learning_rate": 0.00020192213266031304,
|
| 743 |
+
"loss": 1.9189,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.17943292424883622,
|
| 748 |
+
"grad_norm": 0.20150446891784668,
|
| 749 |
+
"learning_rate": 0.00020188787737115897,
|
| 750 |
+
"loss": 1.9076,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.181125687685146,
|
| 755 |
+
"grad_norm": 0.20014949142932892,
|
| 756 |
+
"learning_rate": 0.00020184739884250436,
|
| 757 |
+
"loss": 1.8554,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.18281845112145578,
|
| 762 |
+
"grad_norm": 0.20369713008403778,
|
| 763 |
+
"learning_rate": 0.00020180069957125544,
|
| 764 |
+
"loss": 1.8424,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.18451121455776556,
|
| 769 |
+
"grad_norm": 0.20155616104602814,
|
| 770 |
+
"learning_rate": 0.0002017477824380433,
|
| 771 |
+
"loss": 1.8932,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.18620397799407531,
|
| 776 |
+
"grad_norm": 0.242130309343338,
|
| 777 |
+
"learning_rate": 0.00020168865070704594,
|
| 778 |
+
"loss": 1.9801,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.1878967414303851,
|
| 783 |
+
"grad_norm": 0.1840430349111557,
|
| 784 |
+
"learning_rate": 0.00020162330802578706,
|
| 785 |
+
"loss": 1.7834,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.18958950486669487,
|
| 790 |
+
"grad_norm": 0.19342510402202606,
|
| 791 |
+
"learning_rate": 0.00020155175842491107,
|
| 792 |
+
"loss": 1.8983,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.19128226830300465,
|
| 797 |
+
"grad_norm": 0.19883695244789124,
|
| 798 |
+
"learning_rate": 0.0002014740063179344,
|
| 799 |
+
"loss": 1.9457,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.19297503173931443,
|
| 804 |
+
"grad_norm": 0.19686879217624664,
|
| 805 |
+
"learning_rate": 0.00020139005650097317,
|
| 806 |
+
"loss": 1.8999,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.19466779517562421,
|
| 811 |
+
"grad_norm": 0.208403542637825,
|
| 812 |
+
"learning_rate": 0.00020129991415244756,
|
| 813 |
+
"loss": 1.8663,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.196360558611934,
|
| 818 |
+
"grad_norm": 0.2095002382993698,
|
| 819 |
+
"learning_rate": 0.00020120358483276227,
|
| 820 |
+
"loss": 1.826,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.19805332204824375,
|
| 825 |
+
"grad_norm": 0.21314266324043274,
|
| 826 |
+
"learning_rate": 0.00020110107448396346,
|
| 827 |
+
"loss": 1.8932,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.19974608548455353,
|
| 832 |
+
"grad_norm": 0.17742839455604553,
|
| 833 |
+
"learning_rate": 0.0002009923894293723,
|
| 834 |
+
"loss": 1.8937,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.2014388489208633,
|
| 839 |
+
"grad_norm": 0.21836084127426147,
|
| 840 |
+
"learning_rate": 0.00020087753637319499,
|
| 841 |
+
"loss": 1.8692,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.20313161235717309,
|
| 846 |
+
"grad_norm": 0.22461658716201782,
|
| 847 |
+
"learning_rate": 0.00020075652240010892,
|
| 848 |
+
"loss": 1.8752,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.20482437579348287,
|
| 853 |
+
"grad_norm": 0.19782739877700806,
|
| 854 |
+
"learning_rate": 0.00020062935497482606,
|
| 855 |
+
"loss": 1.9125,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.20651713922979265,
|
| 860 |
+
"grad_norm": 0.19714659452438354,
|
| 861 |
+
"learning_rate": 0.00020049604194163217,
|
| 862 |
+
"loss": 1.9299,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.20820990266610243,
|
| 867 |
+
"grad_norm": 0.22192247211933136,
|
| 868 |
+
"learning_rate": 0.00020035659152390313,
|
| 869 |
+
"loss": 1.9318,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.20990266610241218,
|
| 874 |
+
"grad_norm": 0.18889577686786652,
|
| 875 |
+
"learning_rate": 0.00020021101232359757,
|
| 876 |
+
"loss": 1.7885,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.21159542953872196,
|
| 881 |
+
"grad_norm": 0.20050236582756042,
|
| 882 |
+
"learning_rate": 0.0002000593133207263,
|
| 883 |
+
"loss": 1.8929,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.21328819297503174,
|
| 888 |
+
"grad_norm": 0.20882593095302582,
|
| 889 |
+
"learning_rate": 0.00019990150387279835,
|
| 890 |
+
"loss": 1.9149,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.21498095641134152,
|
| 895 |
+
"grad_norm": 0.20735543966293335,
|
| 896 |
+
"learning_rate": 0.00019973759371424388,
|
| 897 |
+
"loss": 1.8702,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.2166737198476513,
|
| 902 |
+
"grad_norm": 0.2120111733675003,
|
| 903 |
+
"learning_rate": 0.0001995675929558135,
|
| 904 |
+
"loss": 1.8855,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.21836648328396108,
|
| 909 |
+
"grad_norm": 0.19814302027225494,
|
| 910 |
+
"learning_rate": 0.0001993915120839548,
|
| 911 |
+
"loss": 1.931,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.22005924672027083,
|
| 916 |
+
"grad_norm": 0.20039153099060059,
|
| 917 |
+
"learning_rate": 0.00019920936196016534,
|
| 918 |
+
"loss": 1.9007,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.2217520101565806,
|
| 923 |
+
"grad_norm": 0.21088403463363647,
|
| 924 |
+
"learning_rate": 0.0001990211538203228,
|
| 925 |
+
"loss": 1.8372,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.2234447735928904,
|
| 930 |
+
"grad_norm": 0.18757721781730652,
|
| 931 |
+
"learning_rate": 0.00019882689927399174,
|
| 932 |
+
"loss": 1.9023,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.22513753702920017,
|
| 937 |
+
"grad_norm": 0.23472613096237183,
|
| 938 |
+
"learning_rate": 0.00019862661030370764,
|
| 939 |
+
"loss": 1.974,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.22683030046550995,
|
| 944 |
+
"grad_norm": 0.20689590275287628,
|
| 945 |
+
"learning_rate": 0.00019842029926423762,
|
| 946 |
+
"loss": 1.906,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.22852306390181973,
|
| 951 |
+
"grad_norm": 0.23491977155208588,
|
| 952 |
+
"learning_rate": 0.00019820797888181837,
|
| 953 |
+
"loss": 1.9676,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.2302158273381295,
|
| 958 |
+
"grad_norm": 0.22469407320022583,
|
| 959 |
+
"learning_rate": 0.00019798966225337126,
|
| 960 |
+
"loss": 1.9104,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.23190859077443926,
|
| 965 |
+
"grad_norm": 0.18836864829063416,
|
| 966 |
+
"learning_rate": 0.00019776536284569425,
|
| 967 |
+
"loss": 1.7995,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.23360135421074904,
|
| 972 |
+
"grad_norm": 0.22445032000541687,
|
| 973 |
+
"learning_rate": 0.00019753509449463134,
|
| 974 |
+
"loss": 1.8465,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.23529411764705882,
|
| 979 |
+
"grad_norm": 0.213129460811615,
|
| 980 |
+
"learning_rate": 0.00019729887140421912,
|
| 981 |
+
"loss": 1.8709,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.2369868810833686,
|
| 986 |
+
"grad_norm": 0.19376549124717712,
|
| 987 |
+
"learning_rate": 0.00019705670814581052,
|
| 988 |
+
"loss": 1.8593,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.23867964451967838,
|
| 993 |
+
"grad_norm": 0.21564675867557526,
|
| 994 |
+
"learning_rate": 0.00019680861965717597,
|
| 995 |
+
"loss": 1.8758,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.24037240795598816,
|
| 1000 |
+
"grad_norm": 0.19630011916160583,
|
| 1001 |
+
"learning_rate": 0.0001965546212415821,
|
| 1002 |
+
"loss": 1.876,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.24206517139229794,
|
| 1007 |
+
"grad_norm": 0.21326979994773865,
|
| 1008 |
+
"learning_rate": 0.00019629472856684755,
|
| 1009 |
+
"loss": 1.8627,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.2437579348286077,
|
| 1014 |
+
"grad_norm": 0.2283921092748642,
|
| 1015 |
+
"learning_rate": 0.00019602895766437678,
|
| 1016 |
+
"loss": 1.9001,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.24545069826491747,
|
| 1021 |
+
"grad_norm": 0.18760521709918976,
|
| 1022 |
+
"learning_rate": 0.00019575732492817092,
|
| 1023 |
+
"loss": 1.8366,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.24714346170122725,
|
| 1028 |
+
"grad_norm": 0.19644710421562195,
|
| 1029 |
+
"learning_rate": 0.00019547984711381662,
|
| 1030 |
+
"loss": 1.8523,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.24883622513753703,
|
| 1035 |
+
"grad_norm": 0.20750153064727783,
|
| 1036 |
+
"learning_rate": 0.0001951965413374525,
|
| 1037 |
+
"loss": 1.9252,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.2505289885738468,
|
| 1042 |
+
"grad_norm": 0.21898148953914642,
|
| 1043 |
+
"learning_rate": 0.00019490742507471338,
|
| 1044 |
+
"loss": 1.9337,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.25222175201015656,
|
| 1049 |
+
"grad_norm": 0.2055978775024414,
|
| 1050 |
+
"learning_rate": 0.0001946125161596522,
|
| 1051 |
+
"loss": 1.8522,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.25391451544646637,
|
| 1056 |
+
"grad_norm": 0.1978798359632492,
|
| 1057 |
+
"learning_rate": 0.00019431183278363997,
|
| 1058 |
+
"loss": 1.9232,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.2556072788827761,
|
| 1063 |
+
"grad_norm": 0.2158019244670868,
|
| 1064 |
+
"learning_rate": 0.00019400539349424367,
|
| 1065 |
+
"loss": 1.8611,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.25730004231908593,
|
| 1070 |
+
"grad_norm": 0.20386692881584167,
|
| 1071 |
+
"learning_rate": 0.0001936932171940821,
|
| 1072 |
+
"loss": 1.7308,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.2589928057553957,
|
| 1077 |
+
"grad_norm": 0.20035216212272644,
|
| 1078 |
+
"learning_rate": 0.00019337532313966,
|
| 1079 |
+
"loss": 1.8862,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.26068556919170544,
|
| 1084 |
+
"grad_norm": 0.23695775866508484,
|
| 1085 |
+
"learning_rate": 0.00019305173094017996,
|
| 1086 |
+
"loss": 1.8447,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.26237833262801524,
|
| 1091 |
+
"grad_norm": 0.1999625414609909,
|
| 1092 |
+
"learning_rate": 0.0001927224605563332,
|
| 1093 |
+
"loss": 1.8646,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.264071096064325,
|
| 1098 |
+
"grad_norm": 0.22056512534618378,
|
| 1099 |
+
"learning_rate": 0.00019238753229906797,
|
| 1100 |
+
"loss": 1.8067,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.2657638595006348,
|
| 1105 |
+
"grad_norm": 0.20931819081306458,
|
| 1106 |
+
"learning_rate": 0.00019204696682833682,
|
| 1107 |
+
"loss": 1.8779,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.26745662293694455,
|
| 1112 |
+
"grad_norm": 0.20790903270244598,
|
| 1113 |
+
"learning_rate": 0.00019170078515182216,
|
| 1114 |
+
"loss": 1.9015,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.26914938637325436,
|
| 1119 |
+
"grad_norm": 0.19034312665462494,
|
| 1120 |
+
"learning_rate": 0.00019134900862364054,
|
| 1121 |
+
"loss": 1.8891,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.2708421498095641,
|
| 1126 |
+
"grad_norm": 0.2115480899810791,
|
| 1127 |
+
"learning_rate": 0.00019099165894302515,
|
| 1128 |
+
"loss": 1.8202,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.27253491324587387,
|
| 1133 |
+
"grad_norm": 0.2177758514881134,
|
| 1134 |
+
"learning_rate": 0.00019062875815298763,
|
| 1135 |
+
"loss": 1.9587,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.2742276766821837,
|
| 1140 |
+
"grad_norm": 0.21036648750305176,
|
| 1141 |
+
"learning_rate": 0.00019026032863895805,
|
| 1142 |
+
"loss": 1.8691,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.2759204401184934,
|
| 1147 |
+
"grad_norm": 0.22222432494163513,
|
| 1148 |
+
"learning_rate": 0.00018988639312740433,
|
| 1149 |
+
"loss": 1.8823,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.27761320355480323,
|
| 1154 |
+
"grad_norm": 0.21436412632465363,
|
| 1155 |
+
"learning_rate": 0.0001895069746844302,
|
| 1156 |
+
"loss": 1.9104,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.279305966991113,
|
| 1161 |
+
"grad_norm": 0.20456653833389282,
|
| 1162 |
+
"learning_rate": 0.00018912209671435252,
|
| 1163 |
+
"loss": 1.8959,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.2809987304274228,
|
| 1168 |
+
"grad_norm": 0.2090640515089035,
|
| 1169 |
+
"learning_rate": 0.00018873178295825732,
|
| 1170 |
+
"loss": 1.8681,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.28269149386373255,
|
| 1175 |
+
"grad_norm": 0.21788451075553894,
|
| 1176 |
+
"learning_rate": 0.00018833605749253566,
|
| 1177 |
+
"loss": 1.8757,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.2843842573000423,
|
| 1182 |
+
"grad_norm": 0.1906866878271103,
|
| 1183 |
+
"learning_rate": 0.00018793494472739831,
|
| 1184 |
+
"loss": 1.8193,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.2860770207363521,
|
| 1189 |
+
"grad_norm": 0.19513285160064697,
|
| 1190 |
+
"learning_rate": 0.00018752846940537003,
|
| 1191 |
+
"loss": 1.795,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.28776978417266186,
|
| 1196 |
+
"grad_norm": 0.21061134338378906,
|
| 1197 |
+
"learning_rate": 0.0001871166565997633,
|
| 1198 |
+
"loss": 1.874,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.28946254760897167,
|
| 1203 |
+
"grad_norm": 0.1909717321395874,
|
| 1204 |
+
"learning_rate": 0.00018669953171313188,
|
| 1205 |
+
"loss": 1.9205,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.2911553110452814,
|
| 1210 |
+
"grad_norm": 0.21319589018821716,
|
| 1211 |
+
"learning_rate": 0.00018627712047570352,
|
| 1212 |
+
"loss": 1.9476,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.2928480744815912,
|
| 1217 |
+
"grad_norm": 0.1932004988193512,
|
| 1218 |
+
"learning_rate": 0.0001858494489437931,
|
| 1219 |
+
"loss": 1.9107,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.294540837917901,
|
| 1224 |
+
"grad_norm": 0.2236086130142212,
|
| 1225 |
+
"learning_rate": 0.0001854165434981953,
|
| 1226 |
+
"loss": 1.9591,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.29623360135421073,
|
| 1231 |
+
"grad_norm": 0.2074287086725235,
|
| 1232 |
+
"learning_rate": 0.00018497843084255708,
|
| 1233 |
+
"loss": 1.8827,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.29792636479052054,
|
| 1238 |
+
"grad_norm": 0.20944799482822418,
|
| 1239 |
+
"learning_rate": 0.00018453513800173072,
|
| 1240 |
+
"loss": 1.9349,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.2996191282268303,
|
| 1245 |
+
"grad_norm": 0.2134864628314972,
|
| 1246 |
+
"learning_rate": 0.00018408669232010684,
|
| 1247 |
+
"loss": 1.936,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.3013118916631401,
|
| 1252 |
+
"grad_norm": 0.19440272450447083,
|
| 1253 |
+
"learning_rate": 0.00018363312145992737,
|
| 1254 |
+
"loss": 1.9071,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.30300465509944985,
|
| 1259 |
+
"grad_norm": 0.20118582248687744,
|
| 1260 |
+
"learning_rate": 0.0001831744533995795,
|
| 1261 |
+
"loss": 1.8357,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.3046974185357596,
|
| 1266 |
+
"grad_norm": 0.19037730991840363,
|
| 1267 |
+
"learning_rate": 0.00018271071643186968,
|
| 1268 |
+
"loss": 1.8208,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.3063901819720694,
|
| 1273 |
+
"grad_norm": 0.23469118773937225,
|
| 1274 |
+
"learning_rate": 0.00018224193916227852,
|
| 1275 |
+
"loss": 1.91,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.30808294540837916,
|
| 1280 |
+
"grad_norm": 0.2068597376346588,
|
| 1281 |
+
"learning_rate": 0.00018176815050719615,
|
| 1282 |
+
"loss": 1.8396,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.30977570884468897,
|
| 1287 |
+
"grad_norm": 0.199380561709404,
|
| 1288 |
+
"learning_rate": 0.00018128937969213852,
|
| 1289 |
+
"loss": 1.9452,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.3114684722809987,
|
| 1294 |
+
"grad_norm": 0.21270886063575745,
|
| 1295 |
+
"learning_rate": 0.00018080565624994474,
|
| 1296 |
+
"loss": 1.8638,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.31316123571730853,
|
| 1301 |
+
"grad_norm": 0.2130834311246872,
|
| 1302 |
+
"learning_rate": 0.00018031701001895524,
|
| 1303 |
+
"loss": 1.8948,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.3148539991536183,
|
| 1308 |
+
"grad_norm": 0.23766449093818665,
|
| 1309 |
+
"learning_rate": 0.0001798234711411713,
|
| 1310 |
+
"loss": 1.8991,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.31654676258992803,
|
| 1315 |
+
"grad_norm": 0.22095240652561188,
|
| 1316 |
+
"learning_rate": 0.00017932507006039567,
|
| 1317 |
+
"loss": 1.8994,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.31823952602623784,
|
| 1322 |
+
"grad_norm": 0.21079136431217194,
|
| 1323 |
+
"learning_rate": 0.0001788218375203547,
|
| 1324 |
+
"loss": 1.8416,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.3199322894625476,
|
| 1329 |
+
"grad_norm": 0.21459782123565674,
|
| 1330 |
+
"learning_rate": 0.00017831380456280192,
|
| 1331 |
+
"loss": 1.8634,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.3216250528988574,
|
| 1336 |
+
"grad_norm": 0.20663154125213623,
|
| 1337 |
+
"learning_rate": 0.00017780100252560313,
|
| 1338 |
+
"loss": 1.8175,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.32331781633516715,
|
| 1343 |
+
"grad_norm": 0.19480010867118835,
|
| 1344 |
+
"learning_rate": 0.00017728346304080357,
|
| 1345 |
+
"loss": 1.8805,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.32501057977147696,
|
| 1350 |
+
"grad_norm": 0.19441437721252441,
|
| 1351 |
+
"learning_rate": 0.0001767612180326764,
|
| 1352 |
+
"loss": 1.8417,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.3267033432077867,
|
| 1357 |
+
"grad_norm": 0.19535009562969208,
|
| 1358 |
+
"learning_rate": 0.00017623429971575384,
|
| 1359 |
+
"loss": 1.8304,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.32839610664409646,
|
| 1364 |
+
"grad_norm": 0.1960291713476181,
|
| 1365 |
+
"learning_rate": 0.0001757027405928396,
|
| 1366 |
+
"loss": 1.8123,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.33008887008040627,
|
| 1371 |
+
"grad_norm": 0.20072749257087708,
|
| 1372 |
+
"learning_rate": 0.00017516657345300425,
|
| 1373 |
+
"loss": 1.8054,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.331781633516716,
|
| 1378 |
+
"grad_norm": 0.2007756382226944,
|
| 1379 |
+
"learning_rate": 0.00017462583136956258,
|
| 1380 |
+
"loss": 1.9027,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.33347439695302583,
|
| 1385 |
+
"grad_norm": 0.19728228449821472,
|
| 1386 |
+
"learning_rate": 0.00017408054769803337,
|
| 1387 |
+
"loss": 1.7665,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.3351671603893356,
|
| 1392 |
+
"grad_norm": 0.20155274868011475,
|
| 1393 |
+
"learning_rate": 0.00017353075607408209,
|
| 1394 |
+
"loss": 1.8861,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.3368599238256454,
|
| 1399 |
+
"grad_norm": 0.220042422413826,
|
| 1400 |
+
"learning_rate": 0.00017297649041144575,
|
| 1401 |
+
"loss": 1.8939,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.33855268726195514,
|
| 1406 |
+
"grad_norm": 0.198530912399292,
|
| 1407 |
+
"learning_rate": 0.0001724177848998413,
|
| 1408 |
+
"loss": 1.9187,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.3402454506982649,
|
| 1413 |
+
"grad_norm": 0.21299457550048828,
|
| 1414 |
+
"learning_rate": 0.00017185467400285644,
|
| 1415 |
+
"loss": 1.8911,
|
| 1416 |
+
"step": 201
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.3419382141345747,
|
| 1420 |
+
"grad_norm": 0.2029038816690445,
|
| 1421 |
+
"learning_rate": 0.00017128719245582374,
|
| 1422 |
+
"loss": 1.8675,
|
| 1423 |
+
"step": 202
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.34363097757088445,
|
| 1427 |
+
"grad_norm": 0.19144582748413086,
|
| 1428 |
+
"learning_rate": 0.00017071537526367817,
|
| 1429 |
+
"loss": 1.8579,
|
| 1430 |
+
"step": 203
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.34532374100719426,
|
| 1434 |
+
"grad_norm": 0.18448671698570251,
|
| 1435 |
+
"learning_rate": 0.00017013925769879755,
|
| 1436 |
+
"loss": 1.8343,
|
| 1437 |
+
"step": 204
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.347016504443504,
|
| 1441 |
+
"grad_norm": 0.19850729405879974,
|
| 1442 |
+
"learning_rate": 0.00016955887529882714,
|
| 1443 |
+
"loss": 1.908,
|
| 1444 |
+
"step": 205
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.3487092678798138,
|
| 1448 |
+
"grad_norm": 0.22133758664131165,
|
| 1449 |
+
"learning_rate": 0.0001689742638644871,
|
| 1450 |
+
"loss": 1.7839,
|
| 1451 |
+
"step": 206
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.3504020313161236,
|
| 1455 |
+
"grad_norm": 0.22666744887828827,
|
| 1456 |
+
"learning_rate": 0.00016838545945736458,
|
| 1457 |
+
"loss": 1.8686,
|
| 1458 |
+
"step": 207
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.3520947947524333,
|
| 1462 |
+
"grad_norm": 0.21209904551506042,
|
| 1463 |
+
"learning_rate": 0.00016779249839768884,
|
| 1464 |
+
"loss": 1.8597,
|
| 1465 |
+
"step": 208
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.35378755818874313,
|
| 1469 |
+
"grad_norm": 0.24644292891025543,
|
| 1470 |
+
"learning_rate": 0.00016719541726209117,
|
| 1471 |
+
"loss": 1.9405,
|
| 1472 |
+
"step": 209
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.3554803216250529,
|
| 1476 |
+
"grad_norm": 0.2024543285369873,
|
| 1477 |
+
"learning_rate": 0.00016659425288134854,
|
| 1478 |
+
"loss": 1.8438,
|
| 1479 |
+
"step": 210
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.3571730850613627,
|
| 1483 |
+
"grad_norm": 0.19772209227085114,
|
| 1484 |
+
"learning_rate": 0.00016598904233811168,
|
| 1485 |
+
"loss": 1.7444,
|
| 1486 |
+
"step": 211
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.35886584849767245,
|
| 1490 |
+
"grad_norm": 0.21736018359661102,
|
| 1491 |
+
"learning_rate": 0.00016537982296461768,
|
| 1492 |
+
"loss": 1.8738,
|
| 1493 |
+
"step": 212
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.36055861193398225,
|
| 1497 |
+
"grad_norm": 0.21007020771503448,
|
| 1498 |
+
"learning_rate": 0.00016476663234038717,
|
| 1499 |
+
"loss": 1.8198,
|
| 1500 |
+
"step": 213
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.362251375370292,
|
| 1504 |
+
"grad_norm": 0.19021974503993988,
|
| 1505 |
+
"learning_rate": 0.00016414950828990625,
|
| 1506 |
+
"loss": 1.8837,
|
| 1507 |
+
"step": 214
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.36394413880660176,
|
| 1511 |
+
"grad_norm": 0.19724875688552856,
|
| 1512 |
+
"learning_rate": 0.00016352848888029326,
|
| 1513 |
+
"loss": 1.82,
|
| 1514 |
+
"step": 215
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.36563690224291157,
|
| 1518 |
+
"grad_norm": 0.21668016910552979,
|
| 1519 |
+
"learning_rate": 0.00016290361241895064,
|
| 1520 |
+
"loss": 1.8376,
|
| 1521 |
+
"step": 216
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.3673296656792213,
|
| 1525 |
+
"grad_norm": 0.19902758300304413,
|
| 1526 |
+
"learning_rate": 0.00016227491745120196,
|
| 1527 |
+
"loss": 1.8129,
|
| 1528 |
+
"step": 217
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.3690224291155311,
|
| 1532 |
+
"grad_norm": 0.19672639667987823,
|
| 1533 |
+
"learning_rate": 0.0001616424427579143,
|
| 1534 |
+
"loss": 1.8121,
|
| 1535 |
+
"step": 218
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.3707151925518409,
|
| 1539 |
+
"grad_norm": 0.20111984014511108,
|
| 1540 |
+
"learning_rate": 0.0001610062273531059,
|
| 1541 |
+
"loss": 1.7883,
|
| 1542 |
+
"step": 219
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.37240795598815063,
|
| 1546 |
+
"grad_norm": 0.19124211370944977,
|
| 1547 |
+
"learning_rate": 0.00016036631048153979,
|
| 1548 |
+
"loss": 1.839,
|
| 1549 |
+
"step": 220
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.37410071942446044,
|
| 1553 |
+
"grad_norm": 0.1881026327610016,
|
| 1554 |
+
"learning_rate": 0.0001597227316163029,
|
| 1555 |
+
"loss": 1.7974,
|
| 1556 |
+
"step": 221
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.3757934828607702,
|
| 1560 |
+
"grad_norm": 0.2134140431880951,
|
| 1561 |
+
"learning_rate": 0.00015907553045637116,
|
| 1562 |
+
"loss": 1.8425,
|
| 1563 |
+
"step": 222
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.37748624629708,
|
| 1567 |
+
"grad_norm": 0.2233268767595291,
|
| 1568 |
+
"learning_rate": 0.00015842474692416068,
|
| 1569 |
+
"loss": 1.8192,
|
| 1570 |
+
"step": 223
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.37917900973338975,
|
| 1574 |
+
"grad_norm": 0.19751399755477905,
|
| 1575 |
+
"learning_rate": 0.0001577704211630652,
|
| 1576 |
+
"loss": 1.7833,
|
| 1577 |
+
"step": 224
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.38087177316969956,
|
| 1581 |
+
"grad_norm": 0.218443363904953,
|
| 1582 |
+
"learning_rate": 0.00015711259353497981,
|
| 1583 |
+
"loss": 1.9236,
|
| 1584 |
+
"step": 225
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.3825645366060093,
|
| 1588 |
+
"grad_norm": 0.20756369829177856,
|
| 1589 |
+
"learning_rate": 0.0001564513046178113,
|
| 1590 |
+
"loss": 1.906,
|
| 1591 |
+
"step": 226
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.38425730004231906,
|
| 1595 |
+
"grad_norm": 0.19934311509132385,
|
| 1596 |
+
"learning_rate": 0.000155786595202975,
|
| 1597 |
+
"loss": 1.8093,
|
| 1598 |
+
"step": 227
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.38595006347862887,
|
| 1602 |
+
"grad_norm": 0.20041096210479736,
|
| 1603 |
+
"learning_rate": 0.00015511850629287865,
|
| 1604 |
+
"loss": 1.7607,
|
| 1605 |
+
"step": 228
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.3876428269149386,
|
| 1609 |
+
"grad_norm": 0.18540289998054504,
|
| 1610 |
+
"learning_rate": 0.00015444707909839325,
|
| 1611 |
+
"loss": 1.8091,
|
| 1612 |
+
"step": 229
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.38933559035124843,
|
| 1616 |
+
"grad_norm": 0.22061359882354736,
|
| 1617 |
+
"learning_rate": 0.00015377235503631083,
|
| 1618 |
+
"loss": 1.782,
|
| 1619 |
+
"step": 230
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.3910283537875582,
|
| 1623 |
+
"grad_norm": 0.22130614519119263,
|
| 1624 |
+
"learning_rate": 0.0001530943757267898,
|
| 1625 |
+
"loss": 1.8557,
|
| 1626 |
+
"step": 231
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.392721117223868,
|
| 1630 |
+
"grad_norm": 0.1992771476507187,
|
| 1631 |
+
"learning_rate": 0.00015241318299078751,
|
| 1632 |
+
"loss": 1.8052,
|
| 1633 |
+
"step": 232
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.39441388066017774,
|
| 1637 |
+
"grad_norm": 0.22611509263515472,
|
| 1638 |
+
"learning_rate": 0.00015172881884748063,
|
| 1639 |
+
"loss": 1.8771,
|
| 1640 |
+
"step": 233
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.3961066440964875,
|
| 1644 |
+
"grad_norm": 0.21634873747825623,
|
| 1645 |
+
"learning_rate": 0.00015104132551167318,
|
| 1646 |
+
"loss": 1.8709,
|
| 1647 |
+
"step": 234
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.3977994075327973,
|
| 1651 |
+
"grad_norm": 0.1996215432882309,
|
| 1652 |
+
"learning_rate": 0.00015035074539119248,
|
| 1653 |
+
"loss": 1.8022,
|
| 1654 |
+
"step": 235
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.39949217096910705,
|
| 1658 |
+
"grad_norm": 0.2338496297597885,
|
| 1659 |
+
"learning_rate": 0.00014965712108427323,
|
| 1660 |
+
"loss": 1.8723,
|
| 1661 |
+
"step": 236
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.40118493440541686,
|
| 1665 |
+
"grad_norm": 0.21306854486465454,
|
| 1666 |
+
"learning_rate": 0.00014896049537693005,
|
| 1667 |
+
"loss": 1.8632,
|
| 1668 |
+
"step": 237
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.4028776978417266,
|
| 1672 |
+
"grad_norm": 0.19065231084823608,
|
| 1673 |
+
"learning_rate": 0.00014826091124031792,
|
| 1674 |
+
"loss": 1.7692,
|
| 1675 |
+
"step": 238
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.4045704612780364,
|
| 1679 |
+
"grad_norm": 0.30616074800491333,
|
| 1680 |
+
"learning_rate": 0.0001475584118280817,
|
| 1681 |
+
"loss": 1.8729,
|
| 1682 |
+
"step": 239
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.40626322471434617,
|
| 1686 |
+
"grad_norm": 0.20752687752246857,
|
| 1687 |
+
"learning_rate": 0.00014685304047369423,
|
| 1688 |
+
"loss": 1.7964,
|
| 1689 |
+
"step": 240
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.4079559881506559,
|
| 1693 |
+
"grad_norm": 0.200820654630661,
|
| 1694 |
+
"learning_rate": 0.00014614484068778324,
|
| 1695 |
+
"loss": 1.7949,
|
| 1696 |
+
"step": 241
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.40964875158696573,
|
| 1700 |
+
"grad_norm": 0.21263371407985687,
|
| 1701 |
+
"learning_rate": 0.00014543385615544744,
|
| 1702 |
+
"loss": 1.866,
|
| 1703 |
+
"step": 242
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.4113415150232755,
|
| 1707 |
+
"grad_norm": 0.23685312271118164,
|
| 1708 |
+
"learning_rate": 0.00014472013073356184,
|
| 1709 |
+
"loss": 1.8304,
|
| 1710 |
+
"step": 243
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.4130342784595853,
|
| 1714 |
+
"grad_norm": 0.21853387355804443,
|
| 1715 |
+
"learning_rate": 0.00014400370844807234,
|
| 1716 |
+
"loss": 1.8574,
|
| 1717 |
+
"step": 244
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.41472704189589504,
|
| 1721 |
+
"grad_norm": 0.2155625820159912,
|
| 1722 |
+
"learning_rate": 0.00014328463349128025,
|
| 1723 |
+
"loss": 1.8748,
|
| 1724 |
+
"step": 245
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.41641980533220485,
|
| 1728 |
+
"grad_norm": 0.2086298018693924,
|
| 1729 |
+
"learning_rate": 0.000142562950219116,
|
| 1730 |
+
"loss": 1.9206,
|
| 1731 |
+
"step": 246
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.4181125687685146,
|
| 1735 |
+
"grad_norm": 0.20329339802265167,
|
| 1736 |
+
"learning_rate": 0.00014183870314840325,
|
| 1737 |
+
"loss": 1.8398,
|
| 1738 |
+
"step": 247
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.41980533220482436,
|
| 1742 |
+
"grad_norm": 0.196868896484375,
|
| 1743 |
+
"learning_rate": 0.00014111193695411285,
|
| 1744 |
+
"loss": 1.8197,
|
| 1745 |
+
"step": 248
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.42149809564113416,
|
| 1749 |
+
"grad_norm": 0.1998075544834137,
|
| 1750 |
+
"learning_rate": 0.00014038269646660703,
|
| 1751 |
+
"loss": 1.804,
|
| 1752 |
+
"step": 249
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.4231908590774439,
|
| 1756 |
+
"grad_norm": 0.2248334139585495,
|
| 1757 |
+
"learning_rate": 0.00013965102666887408,
|
| 1758 |
+
"loss": 1.8629,
|
| 1759 |
+
"step": 250
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.4248836225137537,
|
| 1763 |
+
"grad_norm": 0.21032220125198364,
|
| 1764 |
+
"learning_rate": 0.0001389169726937536,
|
| 1765 |
+
"loss": 1.7899,
|
| 1766 |
+
"step": 251
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.4265763859500635,
|
| 1770 |
+
"grad_norm": 0.21330855786800385,
|
| 1771 |
+
"learning_rate": 0.0001381805798211525,
|
| 1772 |
+
"loss": 1.8903,
|
| 1773 |
+
"step": 252
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.4282691493863732,
|
| 1777 |
+
"grad_norm": 0.1978665292263031,
|
| 1778 |
+
"learning_rate": 0.00013744189347525182,
|
| 1779 |
+
"loss": 1.8784,
|
| 1780 |
+
"step": 253
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.42996191282268303,
|
| 1784 |
+
"grad_norm": 0.2091052383184433,
|
| 1785 |
+
"learning_rate": 0.00013670095922170498,
|
| 1786 |
+
"loss": 1.7486,
|
| 1787 |
+
"step": 254
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.4316546762589928,
|
| 1791 |
+
"grad_norm": 0.20555751025676727,
|
| 1792 |
+
"learning_rate": 0.00013595782276482678,
|
| 1793 |
+
"loss": 1.8544,
|
| 1794 |
+
"step": 255
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.4333474396953026,
|
| 1798 |
+
"grad_norm": 0.18778344988822937,
|
| 1799 |
+
"learning_rate": 0.00013521252994477446,
|
| 1800 |
+
"loss": 1.8234,
|
| 1801 |
+
"step": 256
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.43504020313161235,
|
| 1805 |
+
"grad_norm": 0.1997567117214203,
|
| 1806 |
+
"learning_rate": 0.00013446512673471965,
|
| 1807 |
+
"loss": 1.8087,
|
| 1808 |
+
"step": 257
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.43673296656792215,
|
| 1812 |
+
"grad_norm": 0.23277805745601654,
|
| 1813 |
+
"learning_rate": 0.0001337156592380131,
|
| 1814 |
+
"loss": 1.8419,
|
| 1815 |
+
"step": 258
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.4384257300042319,
|
| 1819 |
+
"grad_norm": 0.22513163089752197,
|
| 1820 |
+
"learning_rate": 0.0001329641736853402,
|
| 1821 |
+
"loss": 1.8437,
|
| 1822 |
+
"step": 259
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.44011849344054166,
|
| 1826 |
+
"grad_norm": 0.2149161845445633,
|
| 1827 |
+
"learning_rate": 0.0001322107164318697,
|
| 1828 |
+
"loss": 1.8383,
|
| 1829 |
+
"step": 260
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.44181125687685147,
|
| 1833 |
+
"grad_norm": 0.21721015870571136,
|
| 1834 |
+
"learning_rate": 0.00013145533395439405,
|
| 1835 |
+
"loss": 1.7647,
|
| 1836 |
+
"step": 261
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.4435040203131612,
|
| 1840 |
+
"grad_norm": 0.209782674908638,
|
| 1841 |
+
"learning_rate": 0.0001306980728484627,
|
| 1842 |
+
"loss": 1.8086,
|
| 1843 |
+
"step": 262
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.445196783749471,
|
| 1847 |
+
"grad_norm": 0.21785935759544373,
|
| 1848 |
+
"learning_rate": 0.00012993897982550764,
|
| 1849 |
+
"loss": 1.8221,
|
| 1850 |
+
"step": 263
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.4468895471857808,
|
| 1854 |
+
"grad_norm": 0.19847460091114044,
|
| 1855 |
+
"learning_rate": 0.00012917810170996218,
|
| 1856 |
+
"loss": 1.7695,
|
| 1857 |
+
"step": 264
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.4485823106220906,
|
| 1861 |
+
"grad_norm": 0.24909834563732147,
|
| 1862 |
+
"learning_rate": 0.0001284154854363725,
|
| 1863 |
+
"loss": 1.9249,
|
| 1864 |
+
"step": 265
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.45027507405840034,
|
| 1868 |
+
"grad_norm": 0.20455898344516754,
|
| 1869 |
+
"learning_rate": 0.00012765117804650267,
|
| 1870 |
+
"loss": 1.736,
|
| 1871 |
+
"step": 266
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.4519678374947101,
|
| 1875 |
+
"grad_norm": 0.2129652500152588,
|
| 1876 |
+
"learning_rate": 0.00012688522668643268,
|
| 1877 |
+
"loss": 1.8665,
|
| 1878 |
+
"step": 267
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 0.4536606009310199,
|
| 1882 |
+
"grad_norm": 0.23460032045841217,
|
| 1883 |
+
"learning_rate": 0.00012611767860365038,
|
| 1884 |
+
"loss": 1.8598,
|
| 1885 |
+
"step": 268
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.45535336436732965,
|
| 1889 |
+
"grad_norm": 0.1984863132238388,
|
| 1890 |
+
"learning_rate": 0.00012534858114413692,
|
| 1891 |
+
"loss": 1.8512,
|
| 1892 |
+
"step": 269
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.45704612780363946,
|
| 1896 |
+
"grad_norm": 0.22249212861061096,
|
| 1897 |
+
"learning_rate": 0.00012457798174944645,
|
| 1898 |
+
"loss": 1.8617,
|
| 1899 |
+
"step": 270
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.4587388912399492,
|
| 1903 |
+
"grad_norm": 0.1910618543624878,
|
| 1904 |
+
"learning_rate": 0.0001238059279537795,
|
| 1905 |
+
"loss": 1.8236,
|
| 1906 |
+
"step": 271
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.460431654676259,
|
| 1910 |
+
"grad_norm": 0.1930653601884842,
|
| 1911 |
+
"learning_rate": 0.00012303246738105082,
|
| 1912 |
+
"loss": 1.7204,
|
| 1913 |
+
"step": 272
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.46212441811256877,
|
| 1917 |
+
"grad_norm": 0.21550333499908447,
|
| 1918 |
+
"learning_rate": 0.00012225764774195186,
|
| 1919 |
+
"loss": 1.8523,
|
| 1920 |
+
"step": 273
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.4638171815488785,
|
| 1924 |
+
"grad_norm": 0.22164791822433472,
|
| 1925 |
+
"learning_rate": 0.00012148151683100776,
|
| 1926 |
+
"loss": 1.8166,
|
| 1927 |
+
"step": 274
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.46550994498518833,
|
| 1931 |
+
"grad_norm": 0.19043266773223877,
|
| 1932 |
+
"learning_rate": 0.00012070412252362897,
|
| 1933 |
+
"loss": 1.7265,
|
| 1934 |
+
"step": 275
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.4672027084214981,
|
| 1938 |
+
"grad_norm": 0.21201427280902863,
|
| 1939 |
+
"learning_rate": 0.0001199255127731582,
|
| 1940 |
+
"loss": 1.8403,
|
| 1941 |
+
"step": 276
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.4688954718578079,
|
| 1945 |
+
"grad_norm": 0.1951863020658493,
|
| 1946 |
+
"learning_rate": 0.00011914573560791246,
|
| 1947 |
+
"loss": 1.8029,
|
| 1948 |
+
"step": 277
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 0.47058823529411764,
|
| 1952 |
+
"grad_norm": 0.19758546352386475,
|
| 1953 |
+
"learning_rate": 0.00011836483912822035,
|
| 1954 |
+
"loss": 1.7447,
|
| 1955 |
+
"step": 278
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.47228099873042745,
|
| 1959 |
+
"grad_norm": 0.1987844705581665,
|
| 1960 |
+
"learning_rate": 0.00011758287150345516,
|
| 1961 |
+
"loss": 1.8123,
|
| 1962 |
+
"step": 279
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.4739737621667372,
|
| 1966 |
+
"grad_norm": 0.20801664888858795,
|
| 1967 |
+
"learning_rate": 0.00011679988096906333,
|
| 1968 |
+
"loss": 1.8099,
|
| 1969 |
+
"step": 280
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.47566652560304695,
|
| 1973 |
+
"grad_norm": 0.20373427867889404,
|
| 1974 |
+
"learning_rate": 0.00011601591582358924,
|
| 1975 |
+
"loss": 1.8075,
|
| 1976 |
+
"step": 281
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.47735928903935676,
|
| 1980 |
+
"grad_norm": 0.18766620755195618,
|
| 1981 |
+
"learning_rate": 0.00011523102442569585,
|
| 1982 |
+
"loss": 1.8565,
|
| 1983 |
+
"step": 282
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.4790520524756665,
|
| 1987 |
+
"grad_norm": 0.20334315299987793,
|
| 1988 |
+
"learning_rate": 0.00011444525519118179,
|
| 1989 |
+
"loss": 1.7725,
|
| 1990 |
+
"step": 283
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.4807448159119763,
|
| 1994 |
+
"grad_norm": 0.23168785870075226,
|
| 1995 |
+
"learning_rate": 0.00011365865658999474,
|
| 1996 |
+
"loss": 1.8644,
|
| 1997 |
+
"step": 284
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.48243757934828607,
|
| 2001 |
+
"grad_norm": 0.21688470244407654,
|
| 2002 |
+
"learning_rate": 0.00011287127714324162,
|
| 2003 |
+
"loss": 1.8269,
|
| 2004 |
+
"step": 285
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.4841303427845959,
|
| 2008 |
+
"grad_norm": 0.1990613490343094,
|
| 2009 |
+
"learning_rate": 0.00011208316542019556,
|
| 2010 |
+
"loss": 1.8364,
|
| 2011 |
+
"step": 286
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.48582310622090563,
|
| 2015 |
+
"grad_norm": 0.2150726169347763,
|
| 2016 |
+
"learning_rate": 0.00011129437003530006,
|
| 2017 |
+
"loss": 1.7863,
|
| 2018 |
+
"step": 287
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.4875158696572154,
|
| 2022 |
+
"grad_norm": 0.21324212849140167,
|
| 2023 |
+
"learning_rate": 0.00011050493964516997,
|
| 2024 |
+
"loss": 1.8465,
|
| 2025 |
+
"step": 288
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.4892086330935252,
|
| 2029 |
+
"grad_norm": 0.22838270664215088,
|
| 2030 |
+
"learning_rate": 0.00010971492294559029,
|
| 2031 |
+
"loss": 1.7879,
|
| 2032 |
+
"step": 289
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.49090139652983494,
|
| 2036 |
+
"grad_norm": 0.2122029811143875,
|
| 2037 |
+
"learning_rate": 0.00010892436866851235,
|
| 2038 |
+
"loss": 1.8314,
|
| 2039 |
+
"step": 290
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.49259415996614475,
|
| 2043 |
+
"grad_norm": 0.20107725262641907,
|
| 2044 |
+
"learning_rate": 0.00010813332557904784,
|
| 2045 |
+
"loss": 1.8476,
|
| 2046 |
+
"step": 291
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.4942869234024545,
|
| 2050 |
+
"grad_norm": 0.20374621450901031,
|
| 2051 |
+
"learning_rate": 0.00010734184247246066,
|
| 2052 |
+
"loss": 1.7898,
|
| 2053 |
+
"step": 292
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.49597968683876426,
|
| 2057 |
+
"grad_norm": 0.2181493192911148,
|
| 2058 |
+
"learning_rate": 0.00010654996817115704,
|
| 2059 |
+
"loss": 1.8615,
|
| 2060 |
+
"step": 293
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.49767245027507406,
|
| 2064 |
+
"grad_norm": 0.2149876058101654,
|
| 2065 |
+
"learning_rate": 0.00010575775152167391,
|
| 2066 |
+
"loss": 1.8864,
|
| 2067 |
+
"step": 294
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.4993652137113838,
|
| 2071 |
+
"grad_norm": 0.2074560672044754,
|
| 2072 |
+
"learning_rate": 0.00010496524139166594,
|
| 2073 |
+
"loss": 1.8098,
|
| 2074 |
+
"step": 295
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.5010579771476936,
|
| 2078 |
+
"grad_norm": 0.21023057401180267,
|
| 2079 |
+
"learning_rate": 0.00010417248666689095,
|
| 2080 |
+
"loss": 1.8146,
|
| 2081 |
+
"step": 296
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.5027507405840034,
|
| 2085 |
+
"grad_norm": 0.22075513005256653,
|
| 2086 |
+
"learning_rate": 0.00010337953624819464,
|
| 2087 |
+
"loss": 1.7364,
|
| 2088 |
+
"step": 297
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.5044435040203131,
|
| 2092 |
+
"grad_norm": 0.20402000844478607,
|
| 2093 |
+
"learning_rate": 0.0001025864390484939,
|
| 2094 |
+
"loss": 1.8982,
|
| 2095 |
+
"step": 298
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.506136267456623,
|
| 2099 |
+
"grad_norm": 0.20802898705005646,
|
| 2100 |
+
"learning_rate": 0.00010179324398975984,
|
| 2101 |
+
"loss": 1.8944,
|
| 2102 |
+
"step": 299
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.5078290308929327,
|
| 2106 |
+
"grad_norm": 0.21477678418159485,
|
| 2107 |
+
"learning_rate": 0.000101,
|
| 2108 |
+
"loss": 1.739,
|
| 2109 |
+
"step": 300
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.5095217943292425,
|
| 2113 |
+
"grad_norm": 0.21539942920207977,
|
| 2114 |
+
"learning_rate": 0.00010020675601024019,
|
| 2115 |
+
"loss": 1.8687,
|
| 2116 |
+
"step": 301
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.5112145577655522,
|
| 2120 |
+
"grad_norm": 0.1995563805103302,
|
| 2121 |
+
"learning_rate": 9.941356095150613e-05,
|
| 2122 |
+
"loss": 1.7643,
|
| 2123 |
+
"step": 302
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.512907321201862,
|
| 2127 |
+
"grad_norm": 0.22377008199691772,
|
| 2128 |
+
"learning_rate": 9.862046375180539e-05,
|
| 2129 |
+
"loss": 1.858,
|
| 2130 |
+
"step": 303
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.5146000846381719,
|
| 2134 |
+
"grad_norm": 0.22329548001289368,
|
| 2135 |
+
"learning_rate": 9.782751333310905e-05,
|
| 2136 |
+
"loss": 1.8245,
|
| 2137 |
+
"step": 304
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.5162928480744816,
|
| 2141 |
+
"grad_norm": 0.20432743430137634,
|
| 2142 |
+
"learning_rate": 9.70347586083341e-05,
|
| 2143 |
+
"loss": 1.8553,
|
| 2144 |
+
"step": 305
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.5179856115107914,
|
| 2148 |
+
"grad_norm": 0.19676503539085388,
|
| 2149 |
+
"learning_rate": 9.62422484783261e-05,
|
| 2150 |
+
"loss": 1.9008,
|
| 2151 |
+
"step": 306
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.5196783749471011,
|
| 2155 |
+
"grad_norm": 0.201835498213768,
|
| 2156 |
+
"learning_rate": 9.5450031828843e-05,
|
| 2157 |
+
"loss": 1.8466,
|
| 2158 |
+
"step": 307
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.5213711383834109,
|
| 2162 |
+
"grad_norm": 0.2252872735261917,
|
| 2163 |
+
"learning_rate": 9.465815752753935e-05,
|
| 2164 |
+
"loss": 1.7508,
|
| 2165 |
+
"step": 308
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.5230639018197207,
|
| 2169 |
+
"grad_norm": 0.20253726840019226,
|
| 2170 |
+
"learning_rate": 9.386667442095219e-05,
|
| 2171 |
+
"loss": 1.7062,
|
| 2172 |
+
"step": 309
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.5247566652560305,
|
| 2176 |
+
"grad_norm": 0.18099112808704376,
|
| 2177 |
+
"learning_rate": 9.307563133148767e-05,
|
| 2178 |
+
"loss": 1.7196,
|
| 2179 |
+
"step": 310
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.5264494286923402,
|
| 2183 |
+
"grad_norm": 0.20946381986141205,
|
| 2184 |
+
"learning_rate": 9.228507705440976e-05,
|
| 2185 |
+
"loss": 1.6923,
|
| 2186 |
+
"step": 311
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.52814219212865,
|
| 2190 |
+
"grad_norm": 0.19370995461940765,
|
| 2191 |
+
"learning_rate": 9.149506035483005e-05,
|
| 2192 |
+
"loss": 1.767,
|
| 2193 |
+
"step": 312
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.5298349555649597,
|
| 2197 |
+
"grad_norm": 0.23071925342082977,
|
| 2198 |
+
"learning_rate": 9.070562996469997e-05,
|
| 2199 |
+
"loss": 1.9319,
|
| 2200 |
+
"step": 313
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 0.5315277190012696,
|
| 2204 |
+
"grad_norm": 0.209041029214859,
|
| 2205 |
+
"learning_rate": 8.991683457980443e-05,
|
| 2206 |
+
"loss": 1.8223,
|
| 2207 |
+
"step": 314
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.5332204824375794,
|
| 2211 |
+
"grad_norm": 0.21399877965450287,
|
| 2212 |
+
"learning_rate": 8.912872285675841e-05,
|
| 2213 |
+
"loss": 1.8666,
|
| 2214 |
+
"step": 315
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.5349132458738891,
|
| 2218 |
+
"grad_norm": 0.19409359991550446,
|
| 2219 |
+
"learning_rate": 8.834134341000527e-05,
|
| 2220 |
+
"loss": 1.7784,
|
| 2221 |
+
"step": 316
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.5366060093101989,
|
| 2225 |
+
"grad_norm": 0.204691082239151,
|
| 2226 |
+
"learning_rate": 8.755474480881823e-05,
|
| 2227 |
+
"loss": 1.719,
|
| 2228 |
+
"step": 317
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.5382987727465087,
|
| 2232 |
+
"grad_norm": 0.2197725772857666,
|
| 2233 |
+
"learning_rate": 8.676897557430415e-05,
|
| 2234 |
+
"loss": 1.8214,
|
| 2235 |
+
"step": 318
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.5399915361828185,
|
| 2239 |
+
"grad_norm": 0.20693747699260712,
|
| 2240 |
+
"learning_rate": 8.598408417641078e-05,
|
| 2241 |
+
"loss": 1.9092,
|
| 2242 |
+
"step": 319
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.5416842996191282,
|
| 2246 |
+
"grad_norm": 0.21056115627288818,
|
| 2247 |
+
"learning_rate": 8.520011903093666e-05,
|
| 2248 |
+
"loss": 1.7916,
|
| 2249 |
+
"step": 320
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.543377063055438,
|
| 2253 |
+
"grad_norm": 0.2322707176208496,
|
| 2254 |
+
"learning_rate": 8.441712849654485e-05,
|
| 2255 |
+
"loss": 1.7776,
|
| 2256 |
+
"step": 321
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.5450698264917477,
|
| 2260 |
+
"grad_norm": 0.22040331363677979,
|
| 2261 |
+
"learning_rate": 8.363516087177962e-05,
|
| 2262 |
+
"loss": 1.7787,
|
| 2263 |
+
"step": 322
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.5467625899280576,
|
| 2267 |
+
"grad_norm": 0.20133259892463684,
|
| 2268 |
+
"learning_rate": 8.285426439208755e-05,
|
| 2269 |
+
"loss": 1.8502,
|
| 2270 |
+
"step": 323
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.5484553533643673,
|
| 2274 |
+
"grad_norm": 0.21346233785152435,
|
| 2275 |
+
"learning_rate": 8.20744872268418e-05,
|
| 2276 |
+
"loss": 1.8366,
|
| 2277 |
+
"step": 324
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.5501481168006771,
|
| 2281 |
+
"grad_norm": 0.23861512541770935,
|
| 2282 |
+
"learning_rate": 8.129587747637105e-05,
|
| 2283 |
+
"loss": 1.8267,
|
| 2284 |
+
"step": 325
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.5518408802369869,
|
| 2288 |
+
"grad_norm": 0.2035307139158249,
|
| 2289 |
+
"learning_rate": 8.051848316899227e-05,
|
| 2290 |
+
"loss": 1.8537,
|
| 2291 |
+
"step": 326
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.5535336436732966,
|
| 2295 |
+
"grad_norm": 0.2048177719116211,
|
| 2296 |
+
"learning_rate": 7.974235225804814e-05,
|
| 2297 |
+
"loss": 1.7852,
|
| 2298 |
+
"step": 327
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.5552264071096065,
|
| 2302 |
+
"grad_norm": 0.20414908230304718,
|
| 2303 |
+
"learning_rate": 7.896753261894923e-05,
|
| 2304 |
+
"loss": 1.8421,
|
| 2305 |
+
"step": 328
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.5569191705459162,
|
| 2309 |
+
"grad_norm": 0.24092479050159454,
|
| 2310 |
+
"learning_rate": 7.819407204622054e-05,
|
| 2311 |
+
"loss": 1.854,
|
| 2312 |
+
"step": 329
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 0.558611933982226,
|
| 2316 |
+
"grad_norm": 0.18901631236076355,
|
| 2317 |
+
"learning_rate": 7.74220182505536e-05,
|
| 2318 |
+
"loss": 1.8054,
|
| 2319 |
+
"step": 330
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.5603046974185357,
|
| 2323 |
+
"grad_norm": 0.2006632387638092,
|
| 2324 |
+
"learning_rate": 7.665141885586312e-05,
|
| 2325 |
+
"loss": 1.8048,
|
| 2326 |
+
"step": 331
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.5619974608548456,
|
| 2330 |
+
"grad_norm": 0.24550236761569977,
|
| 2331 |
+
"learning_rate": 7.588232139634968e-05,
|
| 2332 |
+
"loss": 1.925,
|
| 2333 |
+
"step": 332
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.5636902242911553,
|
| 2337 |
+
"grad_norm": 0.2135893553495407,
|
| 2338 |
+
"learning_rate": 7.511477331356733e-05,
|
| 2339 |
+
"loss": 1.8726,
|
| 2340 |
+
"step": 333
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 0.5653829877274651,
|
| 2344 |
+
"grad_norm": 0.2010648548603058,
|
| 2345 |
+
"learning_rate": 7.434882195349736e-05,
|
| 2346 |
+
"loss": 1.8045,
|
| 2347 |
+
"step": 334
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.5670757511637748,
|
| 2351 |
+
"grad_norm": 0.21286746859550476,
|
| 2352 |
+
"learning_rate": 7.358451456362751e-05,
|
| 2353 |
+
"loss": 1.7486,
|
| 2354 |
+
"step": 335
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 0.5687685146000846,
|
| 2358 |
+
"grad_norm": 0.21406236290931702,
|
| 2359 |
+
"learning_rate": 7.282189829003785e-05,
|
| 2360 |
+
"loss": 1.7529,
|
| 2361 |
+
"step": 336
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.5704612780363945,
|
| 2365 |
+
"grad_norm": 0.22069211304187775,
|
| 2366 |
+
"learning_rate": 7.206102017449237e-05,
|
| 2367 |
+
"loss": 1.8614,
|
| 2368 |
+
"step": 337
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 0.5721540414727042,
|
| 2372 |
+
"grad_norm": 0.21297217905521393,
|
| 2373 |
+
"learning_rate": 7.130192715153731e-05,
|
| 2374 |
+
"loss": 1.8435,
|
| 2375 |
+
"step": 338
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.573846804909014,
|
| 2379 |
+
"grad_norm": 0.21049076318740845,
|
| 2380 |
+
"learning_rate": 7.054466604560595e-05,
|
| 2381 |
+
"loss": 1.7618,
|
| 2382 |
+
"step": 339
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 0.5755395683453237,
|
| 2386 |
+
"grad_norm": 0.21273387968540192,
|
| 2387 |
+
"learning_rate": 6.978928356813031e-05,
|
| 2388 |
+
"loss": 1.7966,
|
| 2389 |
+
"step": 340
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.5772323317816335,
|
| 2393 |
+
"grad_norm": 0.21543648838996887,
|
| 2394 |
+
"learning_rate": 6.90358263146598e-05,
|
| 2395 |
+
"loss": 1.7777,
|
| 2396 |
+
"step": 341
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 0.5789250952179433,
|
| 2400 |
+
"grad_norm": 0.21663051843643188,
|
| 2401 |
+
"learning_rate": 6.828434076198693e-05,
|
| 2402 |
+
"loss": 1.8662,
|
| 2403 |
+
"step": 342
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.5806178586542531,
|
| 2407 |
+
"grad_norm": 0.2097054123878479,
|
| 2408 |
+
"learning_rate": 6.753487326528033e-05,
|
| 2409 |
+
"loss": 1.7905,
|
| 2410 |
+
"step": 343
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 0.5823106220905628,
|
| 2414 |
+
"grad_norm": 0.21476370096206665,
|
| 2415 |
+
"learning_rate": 6.678747005522557e-05,
|
| 2416 |
+
"loss": 1.868,
|
| 2417 |
+
"step": 344
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.5840033855268726,
|
| 2421 |
+
"grad_norm": 0.21085023880004883,
|
| 2422 |
+
"learning_rate": 6.60421772351732e-05,
|
| 2423 |
+
"loss": 1.7485,
|
| 2424 |
+
"step": 345
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.5856961489631825,
|
| 2428 |
+
"grad_norm": 0.20236246287822723,
|
| 2429 |
+
"learning_rate": 6.529904077829505e-05,
|
| 2430 |
+
"loss": 1.8017,
|
| 2431 |
+
"step": 346
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.5873889123994922,
|
| 2435 |
+
"grad_norm": 0.20598532259464264,
|
| 2436 |
+
"learning_rate": 6.455810652474817e-05,
|
| 2437 |
+
"loss": 1.8247,
|
| 2438 |
+
"step": 347
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.589081675835802,
|
| 2442 |
+
"grad_norm": 0.21530595421791077,
|
| 2443 |
+
"learning_rate": 6.381942017884753e-05,
|
| 2444 |
+
"loss": 1.7806,
|
| 2445 |
+
"step": 348
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.5907744392721117,
|
| 2449 |
+
"grad_norm": 0.20915140211582184,
|
| 2450 |
+
"learning_rate": 6.30830273062464e-05,
|
| 2451 |
+
"loss": 1.6916,
|
| 2452 |
+
"step": 349
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 0.5924672027084215,
|
| 2456 |
+
"grad_norm": 0.2102150022983551,
|
| 2457 |
+
"learning_rate": 6.234897333112594e-05,
|
| 2458 |
+
"loss": 1.7322,
|
| 2459 |
+
"step": 350
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.5941599661447313,
|
| 2463 |
+
"grad_norm": 0.2074473649263382,
|
| 2464 |
+
"learning_rate": 6.161730353339302e-05,
|
| 2465 |
+
"loss": 1.8016,
|
| 2466 |
+
"step": 351
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 0.5958527295810411,
|
| 2470 |
+
"grad_norm": 0.20407773554325104,
|
| 2471 |
+
"learning_rate": 6.088806304588717e-05,
|
| 2472 |
+
"loss": 1.7577,
|
| 2473 |
+
"step": 352
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.5975454930173508,
|
| 2477 |
+
"grad_norm": 0.19759750366210938,
|
| 2478 |
+
"learning_rate": 6.0161296851596766e-05,
|
| 2479 |
+
"loss": 1.7865,
|
| 2480 |
+
"step": 353
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.5992382564536606,
|
| 2484 |
+
"grad_norm": 0.1897537112236023,
|
| 2485 |
+
"learning_rate": 5.943704978088402e-05,
|
| 2486 |
+
"loss": 1.7259,
|
| 2487 |
+
"step": 354
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.6009310198899703,
|
| 2491 |
+
"grad_norm": 0.21245813369750977,
|
| 2492 |
+
"learning_rate": 5.871536650871979e-05,
|
| 2493 |
+
"loss": 1.7443,
|
| 2494 |
+
"step": 355
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 0.6026237833262802,
|
| 2498 |
+
"grad_norm": 0.21807269752025604,
|
| 2499 |
+
"learning_rate": 5.7996291551927666e-05,
|
| 2500 |
+
"loss": 1.8325,
|
| 2501 |
+
"step": 356
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.60431654676259,
|
| 2505 |
+
"grad_norm": 0.20956049859523773,
|
| 2506 |
+
"learning_rate": 5.7279869266438234e-05,
|
| 2507 |
+
"loss": 1.7937,
|
| 2508 |
+
"step": 357
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 0.6060093101988997,
|
| 2512 |
+
"grad_norm": 0.20313173532485962,
|
| 2513 |
+
"learning_rate": 5.656614384455257e-05,
|
| 2514 |
+
"loss": 1.7876,
|
| 2515 |
+
"step": 358
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.6077020736352094,
|
| 2519 |
+
"grad_norm": 0.20536667108535767,
|
| 2520 |
+
"learning_rate": 5.585515931221677e-05,
|
| 2521 |
+
"loss": 1.8179,
|
| 2522 |
+
"step": 359
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 0.6093948370715192,
|
| 2526 |
+
"grad_norm": 0.21091505885124207,
|
| 2527 |
+
"learning_rate": 5.514695952630578e-05,
|
| 2528 |
+
"loss": 1.7008,
|
| 2529 |
+
"step": 360
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.6110876005078291,
|
| 2533 |
+
"grad_norm": 0.22748170793056488,
|
| 2534 |
+
"learning_rate": 5.444158817191832e-05,
|
| 2535 |
+
"loss": 1.8367,
|
| 2536 |
+
"step": 361
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 0.6127803639441388,
|
| 2540 |
+
"grad_norm": 0.22794023156166077,
|
| 2541 |
+
"learning_rate": 5.373908875968211e-05,
|
| 2542 |
+
"loss": 1.7491,
|
| 2543 |
+
"step": 362
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.6144731273804486,
|
| 2547 |
+
"grad_norm": 0.20269587635993958,
|
| 2548 |
+
"learning_rate": 5.3039504623069965e-05,
|
| 2549 |
+
"loss": 1.7936,
|
| 2550 |
+
"step": 363
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 0.6161658908167583,
|
| 2554 |
+
"grad_norm": 0.2314659059047699,
|
| 2555 |
+
"learning_rate": 5.234287891572674e-05,
|
| 2556 |
+
"loss": 1.8786,
|
| 2557 |
+
"step": 364
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.6178586542530682,
|
| 2561 |
+
"grad_norm": 0.21339716017246246,
|
| 2562 |
+
"learning_rate": 5.164925460880758e-05,
|
| 2563 |
+
"loss": 1.7822,
|
| 2564 |
+
"step": 365
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 0.6195514176893779,
|
| 2568 |
+
"grad_norm": 0.2351083606481552,
|
| 2569 |
+
"learning_rate": 5.095867448832683e-05,
|
| 2570 |
+
"loss": 1.8096,
|
| 2571 |
+
"step": 366
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.6212441811256877,
|
| 2575 |
+
"grad_norm": 0.2355419397354126,
|
| 2576 |
+
"learning_rate": 5.027118115251938e-05,
|
| 2577 |
+
"loss": 1.8608,
|
| 2578 |
+
"step": 367
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 0.6229369445619974,
|
| 2582 |
+
"grad_norm": 0.20024722814559937,
|
| 2583 |
+
"learning_rate": 4.95868170092125e-05,
|
| 2584 |
+
"loss": 1.7936,
|
| 2585 |
+
"step": 368
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.6246297079983072,
|
| 2589 |
+
"grad_norm": 0.20535969734191895,
|
| 2590 |
+
"learning_rate": 4.890562427321021e-05,
|
| 2591 |
+
"loss": 1.8049,
|
| 2592 |
+
"step": 369
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 0.6263224714346171,
|
| 2596 |
+
"grad_norm": 0.23352813720703125,
|
| 2597 |
+
"learning_rate": 4.822764496368917e-05,
|
| 2598 |
+
"loss": 1.765,
|
| 2599 |
+
"step": 370
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.6280152348709268,
|
| 2603 |
+
"grad_norm": 0.1979178786277771,
|
| 2604 |
+
"learning_rate": 4.755292090160676e-05,
|
| 2605 |
+
"loss": 1.7403,
|
| 2606 |
+
"step": 371
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 0.6297079983072366,
|
| 2610 |
+
"grad_norm": 0.20019833743572235,
|
| 2611 |
+
"learning_rate": 4.6881493707121315e-05,
|
| 2612 |
+
"loss": 1.8232,
|
| 2613 |
+
"step": 372
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.6314007617435463,
|
| 2617 |
+
"grad_norm": 0.2228015512228012,
|
| 2618 |
+
"learning_rate": 4.621340479702503e-05,
|
| 2619 |
+
"loss": 1.7402,
|
| 2620 |
+
"step": 373
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 0.6330935251798561,
|
| 2624 |
+
"grad_norm": 0.21357794106006622,
|
| 2625 |
+
"learning_rate": 4.554869538218868e-05,
|
| 2626 |
+
"loss": 1.8108,
|
| 2627 |
+
"step": 374
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 0.6347862886161659,
|
| 2631 |
+
"grad_norm": 0.21230149269104004,
|
| 2632 |
+
"learning_rate": 4.48874064650202e-05,
|
| 2633 |
+
"loss": 1.8489,
|
| 2634 |
+
"step": 375
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 0.6364790520524757,
|
| 2638 |
+
"grad_norm": 0.24094673991203308,
|
| 2639 |
+
"learning_rate": 4.422957883693483e-05,
|
| 2640 |
+
"loss": 1.8017,
|
| 2641 |
+
"step": 376
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 0.6381718154887854,
|
| 2645 |
+
"grad_norm": 0.22956468164920807,
|
| 2646 |
+
"learning_rate": 4.357525307583933e-05,
|
| 2647 |
+
"loss": 1.8582,
|
| 2648 |
+
"step": 377
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 0.6398645789250952,
|
| 2652 |
+
"grad_norm": 0.2082371562719345,
|
| 2653 |
+
"learning_rate": 4.29244695436289e-05,
|
| 2654 |
+
"loss": 1.7844,
|
| 2655 |
+
"step": 378
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 0.641557342361405,
|
| 2659 |
+
"grad_norm": 0.19524511694908142,
|
| 2660 |
+
"learning_rate": 4.227726838369711e-05,
|
| 2661 |
+
"loss": 1.8427,
|
| 2662 |
+
"step": 379
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 0.6432501057977148,
|
| 2666 |
+
"grad_norm": 0.21189072728157043,
|
| 2667 |
+
"learning_rate": 4.1633689518460225e-05,
|
| 2668 |
+
"loss": 1.7981,
|
| 2669 |
+
"step": 380
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 0.6449428692340246,
|
| 2673 |
+
"grad_norm": 0.2074735313653946,
|
| 2674 |
+
"learning_rate": 4.0993772646894116e-05,
|
| 2675 |
+
"loss": 1.7982,
|
| 2676 |
+
"step": 381
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 0.6466356326703343,
|
| 2680 |
+
"grad_norm": 0.20359306037425995,
|
| 2681 |
+
"learning_rate": 4.035755724208573e-05,
|
| 2682 |
+
"loss": 1.8001,
|
| 2683 |
+
"step": 382
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 0.6483283961066441,
|
| 2687 |
+
"grad_norm": 0.1999865025281906,
|
| 2688 |
+
"learning_rate": 3.972508254879805e-05,
|
| 2689 |
+
"loss": 1.8001,
|
| 2690 |
+
"step": 383
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 0.6500211595429539,
|
| 2694 |
+
"grad_norm": 0.21898256242275238,
|
| 2695 |
+
"learning_rate": 3.90963875810494e-05,
|
| 2696 |
+
"loss": 1.8164,
|
| 2697 |
+
"step": 384
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 0.6517139229792637,
|
| 2701 |
+
"grad_norm": 0.21683290600776672,
|
| 2702 |
+
"learning_rate": 3.847151111970676e-05,
|
| 2703 |
+
"loss": 1.8172,
|
| 2704 |
+
"step": 385
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 0.6534066864155734,
|
| 2708 |
+
"grad_norm": 0.20884141325950623,
|
| 2709 |
+
"learning_rate": 3.785049171009381e-05,
|
| 2710 |
+
"loss": 1.8675,
|
| 2711 |
+
"step": 386
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 0.6550994498518832,
|
| 2715 |
+
"grad_norm": 0.21106429398059845,
|
| 2716 |
+
"learning_rate": 3.723336765961285e-05,
|
| 2717 |
+
"loss": 1.7616,
|
| 2718 |
+
"step": 387
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 0.6567922132881929,
|
| 2722 |
+
"grad_norm": 0.23011848330497742,
|
| 2723 |
+
"learning_rate": 3.662017703538234e-05,
|
| 2724 |
+
"loss": 1.8289,
|
| 2725 |
+
"step": 388
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 0.6584849767245028,
|
| 2729 |
+
"grad_norm": 0.2037750780582428,
|
| 2730 |
+
"learning_rate": 3.601095766188833e-05,
|
| 2731 |
+
"loss": 1.8335,
|
| 2732 |
+
"step": 389
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 0.6601777401608125,
|
| 2736 |
+
"grad_norm": 0.2219899743795395,
|
| 2737 |
+
"learning_rate": 3.540574711865146e-05,
|
| 2738 |
+
"loss": 1.9411,
|
| 2739 |
+
"step": 390
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 0.6618705035971223,
|
| 2743 |
+
"grad_norm": 0.21334752440452576,
|
| 2744 |
+
"learning_rate": 3.4804582737908825e-05,
|
| 2745 |
+
"loss": 1.8087,
|
| 2746 |
+
"step": 391
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 0.663563267033432,
|
| 2750 |
+
"grad_norm": 0.189884215593338,
|
| 2751 |
+
"learning_rate": 3.420750160231118e-05,
|
| 2752 |
+
"loss": 1.7682,
|
| 2753 |
+
"step": 392
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 0.6652560304697418,
|
| 2757 |
+
"grad_norm": 0.19877025485038757,
|
| 2758 |
+
"learning_rate": 3.361454054263541e-05,
|
| 2759 |
+
"loss": 1.6733,
|
| 2760 |
+
"step": 393
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 0.6669487939060517,
|
| 2764 |
+
"grad_norm": 0.2145155668258667,
|
| 2765 |
+
"learning_rate": 3.302573613551292e-05,
|
| 2766 |
+
"loss": 1.8208,
|
| 2767 |
+
"step": 394
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 0.6686415573423614,
|
| 2771 |
+
"grad_norm": 0.20586173236370087,
|
| 2772 |
+
"learning_rate": 3.244112470117288e-05,
|
| 2773 |
+
"loss": 1.7466,
|
| 2774 |
+
"step": 395
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 0.6703343207786712,
|
| 2778 |
+
"grad_norm": 0.21139511466026306,
|
| 2779 |
+
"learning_rate": 3.186074230120244e-05,
|
| 2780 |
+
"loss": 1.7321,
|
| 2781 |
+
"step": 396
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 0.6720270842149809,
|
| 2785 |
+
"grad_norm": 0.21532289683818817,
|
| 2786 |
+
"learning_rate": 3.1284624736321846e-05,
|
| 2787 |
+
"loss": 1.8668,
|
| 2788 |
+
"step": 397
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 0.6737198476512908,
|
| 2792 |
+
"grad_norm": 0.20813466608524323,
|
| 2793 |
+
"learning_rate": 3.071280754417626e-05,
|
| 2794 |
+
"loss": 1.9226,
|
| 2795 |
+
"step": 398
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 0.6754126110876005,
|
| 2799 |
+
"grad_norm": 0.21900610625743866,
|
| 2800 |
+
"learning_rate": 3.0145325997143577e-05,
|
| 2801 |
+
"loss": 1.8024,
|
| 2802 |
+
"step": 399
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 0.6771053745239103,
|
| 2806 |
+
"grad_norm": 0.22422060370445251,
|
| 2807 |
+
"learning_rate": 2.9582215100158706e-05,
|
| 2808 |
+
"loss": 1.8334,
|
| 2809 |
+
"step": 400
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 0.67879813796022,
|
| 2813 |
+
"grad_norm": 0.23467899858951569,
|
| 2814 |
+
"learning_rate": 2.902350958855426e-05,
|
| 2815 |
+
"loss": 1.8694,
|
| 2816 |
+
"step": 401
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 0.6804909013965298,
|
| 2820 |
+
"grad_norm": 0.21651369333267212,
|
| 2821 |
+
"learning_rate": 2.846924392591794e-05,
|
| 2822 |
+
"loss": 1.8401,
|
| 2823 |
+
"step": 402
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 0.6821836648328397,
|
| 2827 |
+
"grad_norm": 0.19963063299655914,
|
| 2828 |
+
"learning_rate": 2.791945230196663e-05,
|
| 2829 |
+
"loss": 1.7546,
|
| 2830 |
+
"step": 403
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"epoch": 0.6838764282691494,
|
| 2834 |
+
"grad_norm": 0.19555777311325073,
|
| 2835 |
+
"learning_rate": 2.7374168630437456e-05,
|
| 2836 |
+
"loss": 1.7436,
|
| 2837 |
+
"step": 404
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 0.6855691917054592,
|
| 2841 |
+
"grad_norm": 0.22838395833969116,
|
| 2842 |
+
"learning_rate": 2.6833426546995782e-05,
|
| 2843 |
+
"loss": 1.7865,
|
| 2844 |
+
"step": 405
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 0.6872619551417689,
|
| 2848 |
+
"grad_norm": 0.21524296700954437,
|
| 2849 |
+
"learning_rate": 2.629725940716041e-05,
|
| 2850 |
+
"loss": 1.8273,
|
| 2851 |
+
"step": 406
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 0.6889547185780787,
|
| 2855 |
+
"grad_norm": 0.2013399302959442,
|
| 2856 |
+
"learning_rate": 2.57657002842462e-05,
|
| 2857 |
+
"loss": 1.8137,
|
| 2858 |
+
"step": 407
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 0.6906474820143885,
|
| 2862 |
+
"grad_norm": 0.21510232985019684,
|
| 2863 |
+
"learning_rate": 2.523878196732358e-05,
|
| 2864 |
+
"loss": 1.8143,
|
| 2865 |
+
"step": 408
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 0.6923402454506983,
|
| 2869 |
+
"grad_norm": 0.21713508665561676,
|
| 2870 |
+
"learning_rate": 2.4716536959196462e-05,
|
| 2871 |
+
"loss": 1.726,
|
| 2872 |
+
"step": 409
|
| 2873 |
+
},
|
| 2874 |
+
{
|
| 2875 |
+
"epoch": 0.694033008887008,
|
| 2876 |
+
"grad_norm": 0.21626891195774078,
|
| 2877 |
+
"learning_rate": 2.4198997474396877e-05,
|
| 2878 |
+
"loss": 1.8512,
|
| 2879 |
+
"step": 410
|
| 2880 |
+
},
|
| 2881 |
+
{
|
| 2882 |
+
"epoch": 0.6957257723233178,
|
| 2883 |
+
"grad_norm": 0.20656228065490723,
|
| 2884 |
+
"learning_rate": 2.3686195437198112e-05,
|
| 2885 |
+
"loss": 1.7622,
|
| 2886 |
+
"step": 411
|
| 2887 |
+
},
|
| 2888 |
+
{
|
| 2889 |
+
"epoch": 0.6974185357596276,
|
| 2890 |
+
"grad_norm": 0.20512975752353668,
|
| 2891 |
+
"learning_rate": 2.31781624796453e-05,
|
| 2892 |
+
"loss": 1.8007,
|
| 2893 |
+
"step": 412
|
| 2894 |
+
},
|
| 2895 |
+
{
|
| 2896 |
+
"epoch": 0.6991112991959374,
|
| 2897 |
+
"grad_norm": 0.211225688457489,
|
| 2898 |
+
"learning_rate": 2.2674929939604332e-05,
|
| 2899 |
+
"loss": 1.8128,
|
| 2900 |
+
"step": 413
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 0.7008040626322471,
|
| 2904 |
+
"grad_norm": 0.21974876523017883,
|
| 2905 |
+
"learning_rate": 2.217652885882869e-05,
|
| 2906 |
+
"loss": 1.883,
|
| 2907 |
+
"step": 414
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 0.7024968260685569,
|
| 2911 |
+
"grad_norm": 0.20600928366184235,
|
| 2912 |
+
"learning_rate": 2.1682989981044783e-05,
|
| 2913 |
+
"loss": 1.7697,
|
| 2914 |
+
"step": 415
|
| 2915 |
+
},
|
| 2916 |
+
{
|
| 2917 |
+
"epoch": 0.7041895895048667,
|
| 2918 |
+
"grad_norm": 0.22947439551353455,
|
| 2919 |
+
"learning_rate": 2.119434375005527e-05,
|
| 2920 |
+
"loss": 1.8393,
|
| 2921 |
+
"step": 416
|
| 2922 |
+
},
|
| 2923 |
+
{
|
| 2924 |
+
"epoch": 0.7058823529411765,
|
| 2925 |
+
"grad_norm": 0.20363295078277588,
|
| 2926 |
+
"learning_rate": 2.071062030786149e-05,
|
| 2927 |
+
"loss": 1.7937,
|
| 2928 |
+
"step": 417
|
| 2929 |
+
},
|
| 2930 |
+
{
|
| 2931 |
+
"epoch": 0.7075751163774863,
|
| 2932 |
+
"grad_norm": 0.21072493493556976,
|
| 2933 |
+
"learning_rate": 2.0231849492803852e-05,
|
| 2934 |
+
"loss": 1.84,
|
| 2935 |
+
"step": 418
|
| 2936 |
+
},
|
| 2937 |
+
{
|
| 2938 |
+
"epoch": 0.709267879813796,
|
| 2939 |
+
"grad_norm": 0.218157559633255,
|
| 2940 |
+
"learning_rate": 1.9758060837721467e-05,
|
| 2941 |
+
"loss": 1.8936,
|
| 2942 |
+
"step": 419
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 0.7109606432501058,
|
| 2946 |
+
"grad_norm": 0.22965873777866364,
|
| 2947 |
+
"learning_rate": 1.928928356813032e-05,
|
| 2948 |
+
"loss": 1.7123,
|
| 2949 |
+
"step": 420
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 0.7126534066864155,
|
| 2953 |
+
"grad_norm": 0.22897976636886597,
|
| 2954 |
+
"learning_rate": 1.882554660042052e-05,
|
| 2955 |
+
"loss": 1.78,
|
| 2956 |
+
"step": 421
|
| 2957 |
+
},
|
| 2958 |
+
{
|
| 2959 |
+
"epoch": 0.7143461701227254,
|
| 2960 |
+
"grad_norm": 0.22148145735263824,
|
| 2961 |
+
"learning_rate": 1.8366878540072614e-05,
|
| 2962 |
+
"loss": 1.7913,
|
| 2963 |
+
"step": 422
|
| 2964 |
+
},
|
| 2965 |
+
{
|
| 2966 |
+
"epoch": 0.7160389335590351,
|
| 2967 |
+
"grad_norm": 0.2105412781238556,
|
| 2968 |
+
"learning_rate": 1.7913307679893173e-05,
|
| 2969 |
+
"loss": 1.7588,
|
| 2970 |
+
"step": 423
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"epoch": 0.7177316969953449,
|
| 2974 |
+
"grad_norm": 0.19640448689460754,
|
| 2975 |
+
"learning_rate": 1.7464861998269243e-05,
|
| 2976 |
+
"loss": 1.8379,
|
| 2977 |
+
"step": 424
|
| 2978 |
+
},
|
| 2979 |
+
{
|
| 2980 |
+
"epoch": 0.7194244604316546,
|
| 2981 |
+
"grad_norm": 0.20884667336940765,
|
| 2982 |
+
"learning_rate": 1.702156915744292e-05,
|
| 2983 |
+
"loss": 1.8713,
|
| 2984 |
+
"step": 425
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 0.7211172238679645,
|
| 2988 |
+
"grad_norm": 0.20887801051139832,
|
| 2989 |
+
"learning_rate": 1.6583456501804725e-05,
|
| 2990 |
+
"loss": 1.7939,
|
| 2991 |
+
"step": 426
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 0.7228099873042743,
|
| 2995 |
+
"grad_norm": 0.21152956783771515,
|
| 2996 |
+
"learning_rate": 1.6150551056206867e-05,
|
| 2997 |
+
"loss": 1.7871,
|
| 2998 |
+
"step": 427
|
| 2999 |
+
},
|
| 3000 |
+
{
|
| 3001 |
+
"epoch": 0.724502750740584,
|
| 3002 |
+
"grad_norm": 0.18513014912605286,
|
| 3003 |
+
"learning_rate": 1.57228795242965e-05,
|
| 3004 |
+
"loss": 1.7296,
|
| 3005 |
+
"step": 428
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 0.7261955141768938,
|
| 3009 |
+
"grad_norm": 0.19580882787704468,
|
| 3010 |
+
"learning_rate": 1.5300468286868137e-05,
|
| 3011 |
+
"loss": 1.7489,
|
| 3012 |
+
"step": 429
|
| 3013 |
+
},
|
| 3014 |
+
{
|
| 3015 |
+
"epoch": 0.7278882776132035,
|
| 3016 |
+
"grad_norm": 0.21818384528160095,
|
| 3017 |
+
"learning_rate": 1.488334340023669e-05,
|
| 3018 |
+
"loss": 1.8618,
|
| 3019 |
+
"step": 430
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 0.7295810410495134,
|
| 3023 |
+
"grad_norm": 0.22403159737586975,
|
| 3024 |
+
"learning_rate": 1.4471530594629996e-05,
|
| 3025 |
+
"loss": 1.8694,
|
| 3026 |
+
"step": 431
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 0.7312738044858231,
|
| 3030 |
+
"grad_norm": 0.2089739292860031,
|
| 3031 |
+
"learning_rate": 1.4065055272601703e-05,
|
| 3032 |
+
"loss": 1.8291,
|
| 3033 |
+
"step": 432
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 0.7329665679221329,
|
| 3037 |
+
"grad_norm": 0.22134815156459808,
|
| 3038 |
+
"learning_rate": 1.3663942507464348e-05,
|
| 3039 |
+
"loss": 1.7524,
|
| 3040 |
+
"step": 433
|
| 3041 |
+
},
|
| 3042 |
+
{
|
| 3043 |
+
"epoch": 0.7346593313584426,
|
| 3044 |
+
"grad_norm": 0.21070238947868347,
|
| 3045 |
+
"learning_rate": 1.3268217041742701e-05,
|
| 3046 |
+
"loss": 1.7339,
|
| 3047 |
+
"step": 434
|
| 3048 |
+
},
|
| 3049 |
+
{
|
| 3050 |
+
"epoch": 0.7363520947947524,
|
| 3051 |
+
"grad_norm": 0.20640292763710022,
|
| 3052 |
+
"learning_rate": 1.2877903285647486e-05,
|
| 3053 |
+
"loss": 1.749,
|
| 3054 |
+
"step": 435
|
| 3055 |
+
},
|
| 3056 |
+
{
|
| 3057 |
+
"epoch": 0.7380448582310623,
|
| 3058 |
+
"grad_norm": 0.21918413043022156,
|
| 3059 |
+
"learning_rate": 1.2493025315569801e-05,
|
| 3060 |
+
"loss": 1.8355,
|
| 3061 |
+
"step": 436
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 0.739737621667372,
|
| 3065 |
+
"grad_norm": 0.22140200436115265,
|
| 3066 |
+
"learning_rate": 1.2113606872595673e-05,
|
| 3067 |
+
"loss": 1.7544,
|
| 3068 |
+
"step": 437
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 0.7414303851036818,
|
| 3072 |
+
"grad_norm": 0.2224489450454712,
|
| 3073 |
+
"learning_rate": 1.173967136104196e-05,
|
| 3074 |
+
"loss": 1.7686,
|
| 3075 |
+
"step": 438
|
| 3076 |
+
},
|
| 3077 |
+
{
|
| 3078 |
+
"epoch": 0.7431231485399915,
|
| 3079 |
+
"grad_norm": 0.21481674909591675,
|
| 3080 |
+
"learning_rate": 1.1371241847012401e-05,
|
| 3081 |
+
"loss": 1.7817,
|
| 3082 |
+
"step": 439
|
| 3083 |
+
},
|
| 3084 |
+
{
|
| 3085 |
+
"epoch": 0.7448159119763013,
|
| 3086 |
+
"grad_norm": 0.20408138632774353,
|
| 3087 |
+
"learning_rate": 1.1008341056974854e-05,
|
| 3088 |
+
"loss": 1.748,
|
| 3089 |
+
"step": 440
|
| 3090 |
+
},
|
| 3091 |
+
{
|
| 3092 |
+
"epoch": 0.7465086754126111,
|
| 3093 |
+
"grad_norm": 0.23499758541584015,
|
| 3094 |
+
"learning_rate": 1.0650991376359473e-05,
|
| 3095 |
+
"loss": 1.7775,
|
| 3096 |
+
"step": 441
|
| 3097 |
+
},
|
| 3098 |
+
{
|
| 3099 |
+
"epoch": 0.7482014388489209,
|
| 3100 |
+
"grad_norm": 0.21035221219062805,
|
| 3101 |
+
"learning_rate": 1.029921484817783e-05,
|
| 3102 |
+
"loss": 1.8775,
|
| 3103 |
+
"step": 442
|
| 3104 |
+
},
|
| 3105 |
+
{
|
| 3106 |
+
"epoch": 0.7498942022852306,
|
| 3107 |
+
"grad_norm": 0.20913664996623993,
|
| 3108 |
+
"learning_rate": 9.953033171663175e-06,
|
| 3109 |
+
"loss": 1.7602,
|
| 3110 |
+
"step": 443
|
| 3111 |
+
},
|
| 3112 |
+
{
|
| 3113 |
+
"epoch": 0.7515869657215404,
|
| 3114 |
+
"grad_norm": 0.20781245827674866,
|
| 3115 |
+
"learning_rate": 9.612467700932045e-06,
|
| 3116 |
+
"loss": 1.7158,
|
| 3117 |
+
"step": 444
|
| 3118 |
+
},
|
| 3119 |
+
{
|
| 3120 |
+
"epoch": 0.7532797291578502,
|
| 3121 |
+
"grad_norm": 0.20402781665325165,
|
| 3122 |
+
"learning_rate": 9.277539443666783e-06,
|
| 3123 |
+
"loss": 1.818,
|
| 3124 |
+
"step": 445
|
| 3125 |
+
},
|
| 3126 |
+
{
|
| 3127 |
+
"epoch": 0.75497249259416,
|
| 3128 |
+
"grad_norm": 0.21362698078155518,
|
| 3129 |
+
"learning_rate": 8.948269059820025e-06,
|
| 3130 |
+
"loss": 1.8516,
|
| 3131 |
+
"step": 446
|
| 3132 |
+
},
|
| 3133 |
+
{
|
| 3134 |
+
"epoch": 0.7566652560304697,
|
| 3135 |
+
"grad_norm": 0.2265281230211258,
|
| 3136 |
+
"learning_rate": 8.624676860340025e-06,
|
| 3137 |
+
"loss": 1.7944,
|
| 3138 |
+
"step": 447
|
| 3139 |
+
},
|
| 3140 |
+
{
|
| 3141 |
+
"epoch": 0.7583580194667795,
|
| 3142 |
+
"grad_norm": 0.21393375098705292,
|
| 3143 |
+
"learning_rate": 8.306782805917904e-06,
|
| 3144 |
+
"loss": 1.7829,
|
| 3145 |
+
"step": 448
|
| 3146 |
+
},
|
| 3147 |
+
{
|
| 3148 |
+
"epoch": 0.7600507829030893,
|
| 3149 |
+
"grad_norm": 0.20928075909614563,
|
| 3150 |
+
"learning_rate": 7.994606505756355e-06,
|
| 3151 |
+
"loss": 1.7777,
|
| 3152 |
+
"step": 449
|
| 3153 |
+
},
|
| 3154 |
+
{
|
| 3155 |
+
"epoch": 0.7617435463393991,
|
| 3156 |
+
"grad_norm": 0.2121303230524063,
|
| 3157 |
+
"learning_rate": 7.68816721636004e-06,
|
| 3158 |
+
"loss": 1.8348,
|
| 3159 |
+
"step": 450
|
| 3160 |
+
},
|
| 3161 |
+
{
|
| 3162 |
+
"epoch": 0.7634363097757089,
|
| 3163 |
+
"grad_norm": 0.21304333209991455,
|
| 3164 |
+
"learning_rate": 7.3874838403478e-06,
|
| 3165 |
+
"loss": 1.8322,
|
| 3166 |
+
"step": 451
|
| 3167 |
+
},
|
| 3168 |
+
{
|
| 3169 |
+
"epoch": 0.7651290732120186,
|
| 3170 |
+
"grad_norm": 0.19794292747974396,
|
| 3171 |
+
"learning_rate": 7.092574925286614e-06,
|
| 3172 |
+
"loss": 1.7484,
|
| 3173 |
+
"step": 452
|
| 3174 |
+
},
|
| 3175 |
+
{
|
| 3176 |
+
"epoch": 0.7668218366483284,
|
| 3177 |
+
"grad_norm": 0.23775118589401245,
|
| 3178 |
+
"learning_rate": 6.803458662547507e-06,
|
| 3179 |
+
"loss": 1.8244,
|
| 3180 |
+
"step": 453
|
| 3181 |
+
},
|
| 3182 |
+
{
|
| 3183 |
+
"epoch": 0.7685146000846381,
|
| 3184 |
+
"grad_norm": 0.21358804404735565,
|
| 3185 |
+
"learning_rate": 6.520152886183406e-06,
|
| 3186 |
+
"loss": 1.7668,
|
| 3187 |
+
"step": 454
|
| 3188 |
+
},
|
| 3189 |
+
{
|
| 3190 |
+
"epoch": 0.770207363520948,
|
| 3191 |
+
"grad_norm": 0.2213735729455948,
|
| 3192 |
+
"learning_rate": 6.242675071829111e-06,
|
| 3193 |
+
"loss": 1.8165,
|
| 3194 |
+
"step": 455
|
| 3195 |
+
},
|
| 3196 |
+
{
|
| 3197 |
+
"epoch": 0.7719001269572577,
|
| 3198 |
+
"grad_norm": 0.20860306918621063,
|
| 3199 |
+
"learning_rate": 5.971042335623229e-06,
|
| 3200 |
+
"loss": 1.7456,
|
| 3201 |
+
"step": 456
|
| 3202 |
+
},
|
| 3203 |
+
{
|
| 3204 |
+
"epoch": 0.7735928903935675,
|
| 3205 |
+
"grad_norm": 0.2030525654554367,
|
| 3206 |
+
"learning_rate": 5.705271433152458e-06,
|
| 3207 |
+
"loss": 1.7243,
|
| 3208 |
+
"step": 457
|
| 3209 |
+
},
|
| 3210 |
+
{
|
| 3211 |
+
"epoch": 0.7752856538298772,
|
| 3212 |
+
"grad_norm": 0.23554547131061554,
|
| 3213 |
+
"learning_rate": 5.445378758417925e-06,
|
| 3214 |
+
"loss": 1.8786,
|
| 3215 |
+
"step": 458
|
| 3216 |
+
},
|
| 3217 |
+
{
|
| 3218 |
+
"epoch": 0.7769784172661871,
|
| 3219 |
+
"grad_norm": 0.19026103615760803,
|
| 3220 |
+
"learning_rate": 5.191380342824035e-06,
|
| 3221 |
+
"loss": 1.7338,
|
| 3222 |
+
"step": 459
|
| 3223 |
+
},
|
| 3224 |
+
{
|
| 3225 |
+
"epoch": 0.7786711807024969,
|
| 3226 |
+
"grad_norm": 0.21249499917030334,
|
| 3227 |
+
"learning_rate": 4.943291854189493e-06,
|
| 3228 |
+
"loss": 1.8831,
|
| 3229 |
+
"step": 460
|
| 3230 |
+
},
|
| 3231 |
+
{
|
| 3232 |
+
"epoch": 0.7803639441388066,
|
| 3233 |
+
"grad_norm": 0.1983940303325653,
|
| 3234 |
+
"learning_rate": 4.701128595780878e-06,
|
| 3235 |
+
"loss": 1.8124,
|
| 3236 |
+
"step": 461
|
| 3237 |
+
},
|
| 3238 |
+
{
|
| 3239 |
+
"epoch": 0.7820567075751164,
|
| 3240 |
+
"grad_norm": 0.2183755785226822,
|
| 3241 |
+
"learning_rate": 4.464905505368658e-06,
|
| 3242 |
+
"loss": 1.8125,
|
| 3243 |
+
"step": 462
|
| 3244 |
+
},
|
| 3245 |
+
{
|
| 3246 |
+
"epoch": 0.7837494710114261,
|
| 3247 |
+
"grad_norm": 0.20469729602336884,
|
| 3248 |
+
"learning_rate": 4.23463715430577e-06,
|
| 3249 |
+
"loss": 1.7181,
|
| 3250 |
+
"step": 463
|
| 3251 |
+
},
|
| 3252 |
+
{
|
| 3253 |
+
"epoch": 0.785442234447736,
|
| 3254 |
+
"grad_norm": 0.21118509769439697,
|
| 3255 |
+
"learning_rate": 4.010337746628751e-06,
|
| 3256 |
+
"loss": 1.8343,
|
| 3257 |
+
"step": 464
|
| 3258 |
+
},
|
| 3259 |
+
{
|
| 3260 |
+
"epoch": 0.7871349978840457,
|
| 3261 |
+
"grad_norm": 0.20791935920715332,
|
| 3262 |
+
"learning_rate": 3.792021118181636e-06,
|
| 3263 |
+
"loss": 1.8717,
|
| 3264 |
+
"step": 465
|
| 3265 |
+
},
|
| 3266 |
+
{
|
| 3267 |
+
"epoch": 0.7888277613203555,
|
| 3268 |
+
"grad_norm": 0.21682444214820862,
|
| 3269 |
+
"learning_rate": 3.5797007357623945e-06,
|
| 3270 |
+
"loss": 1.9463,
|
| 3271 |
+
"step": 466
|
| 3272 |
+
},
|
| 3273 |
+
{
|
| 3274 |
+
"epoch": 0.7905205247566652,
|
| 3275 |
+
"grad_norm": 0.2028808295726776,
|
| 3276 |
+
"learning_rate": 3.3733896962923658e-06,
|
| 3277 |
+
"loss": 1.7656,
|
| 3278 |
+
"step": 467
|
| 3279 |
+
},
|
| 3280 |
+
{
|
| 3281 |
+
"epoch": 0.792213288192975,
|
| 3282 |
+
"grad_norm": 0.20768266916275024,
|
| 3283 |
+
"learning_rate": 3.1731007260082616e-06,
|
| 3284 |
+
"loss": 1.8322,
|
| 3285 |
+
"step": 468
|
| 3286 |
+
},
|
| 3287 |
+
{
|
| 3288 |
+
"epoch": 0.7939060516292848,
|
| 3289 |
+
"grad_norm": 0.22645053267478943,
|
| 3290 |
+
"learning_rate": 2.9788461796772114e-06,
|
| 3291 |
+
"loss": 1.7735,
|
| 3292 |
+
"step": 469
|
| 3293 |
+
},
|
| 3294 |
+
{
|
| 3295 |
+
"epoch": 0.7955988150655946,
|
| 3296 |
+
"grad_norm": 0.20245122909545898,
|
| 3297 |
+
"learning_rate": 2.790638039834668e-06,
|
| 3298 |
+
"loss": 1.7191,
|
| 3299 |
+
"step": 470
|
| 3300 |
+
},
|
| 3301 |
+
{
|
| 3302 |
+
"epoch": 0.7972915785019044,
|
| 3303 |
+
"grad_norm": 0.2117125540971756,
|
| 3304 |
+
"learning_rate": 2.6084879160452166e-06,
|
| 3305 |
+
"loss": 1.7797,
|
| 3306 |
+
"step": 471
|
| 3307 |
+
},
|
| 3308 |
+
{
|
| 3309 |
+
"epoch": 0.7989843419382141,
|
| 3310 |
+
"grad_norm": 0.2047407627105713,
|
| 3311 |
+
"learning_rate": 2.432407044186509e-06,
|
| 3312 |
+
"loss": 1.8037,
|
| 3313 |
+
"step": 472
|
| 3314 |
+
},
|
| 3315 |
+
{
|
| 3316 |
+
"epoch": 0.8006771053745239,
|
| 3317 |
+
"grad_norm": 0.19866344332695007,
|
| 3318 |
+
"learning_rate": 2.26240628575615e-06,
|
| 3319 |
+
"loss": 1.8208,
|
| 3320 |
+
"step": 473
|
| 3321 |
+
},
|
| 3322 |
+
{
|
| 3323 |
+
"epoch": 0.8023698688108337,
|
| 3324 |
+
"grad_norm": 0.21329368650913239,
|
| 3325 |
+
"learning_rate": 2.098496127201648e-06,
|
| 3326 |
+
"loss": 1.7743,
|
| 3327 |
+
"step": 474
|
| 3328 |
+
},
|
| 3329 |
+
{
|
| 3330 |
+
"epoch": 0.8040626322471435,
|
| 3331 |
+
"grad_norm": 0.2227088063955307,
|
| 3332 |
+
"learning_rate": 1.9406866792737267e-06,
|
| 3333 |
+
"loss": 1.802,
|
| 3334 |
+
"step": 475
|
| 3335 |
+
},
|
| 3336 |
+
{
|
| 3337 |
+
"epoch": 0.8057553956834532,
|
| 3338 |
+
"grad_norm": 0.23095914721488953,
|
| 3339 |
+
"learning_rate": 1.7889876764024505e-06,
|
| 3340 |
+
"loss": 1.7875,
|
| 3341 |
+
"step": 476
|
| 3342 |
+
},
|
| 3343 |
+
{
|
| 3344 |
+
"epoch": 0.807448159119763,
|
| 3345 |
+
"grad_norm": 0.19540473818778992,
|
| 3346 |
+
"learning_rate": 1.6434084760968697e-06,
|
| 3347 |
+
"loss": 1.7506,
|
| 3348 |
+
"step": 477
|
| 3349 |
+
},
|
| 3350 |
+
{
|
| 3351 |
+
"epoch": 0.8091409225560728,
|
| 3352 |
+
"grad_norm": 0.22987684607505798,
|
| 3353 |
+
"learning_rate": 1.5039580583678393e-06,
|
| 3354 |
+
"loss": 1.8692,
|
| 3355 |
+
"step": 478
|
| 3356 |
+
},
|
| 3357 |
+
{
|
| 3358 |
+
"epoch": 0.8108336859923826,
|
| 3359 |
+
"grad_norm": 0.21226081252098083,
|
| 3360 |
+
"learning_rate": 1.3706450251739613e-06,
|
| 3361 |
+
"loss": 1.8634,
|
| 3362 |
+
"step": 479
|
| 3363 |
+
},
|
| 3364 |
+
{
|
| 3365 |
+
"epoch": 0.8125264494286923,
|
| 3366 |
+
"grad_norm": 0.22443637251853943,
|
| 3367 |
+
"learning_rate": 1.2434775998910964e-06,
|
| 3368 |
+
"loss": 1.7992,
|
| 3369 |
+
"step": 480
|
| 3370 |
+
},
|
| 3371 |
+
{
|
| 3372 |
+
"epoch": 0.8142192128650021,
|
| 3373 |
+
"grad_norm": 0.2271965891122818,
|
| 3374 |
+
"learning_rate": 1.1224636268050439e-06,
|
| 3375 |
+
"loss": 1.8904,
|
| 3376 |
+
"step": 481
|
| 3377 |
+
},
|
| 3378 |
+
{
|
| 3379 |
+
"epoch": 0.8159119763013118,
|
| 3380 |
+
"grad_norm": 0.20612284541130066,
|
| 3381 |
+
"learning_rate": 1.0076105706276888e-06,
|
| 3382 |
+
"loss": 1.8025,
|
| 3383 |
+
"step": 482
|
| 3384 |
+
},
|
| 3385 |
+
{
|
| 3386 |
+
"epoch": 0.8176047397376217,
|
| 3387 |
+
"grad_norm": 0.2131970375776291,
|
| 3388 |
+
"learning_rate": 8.989255160365527e-07,
|
| 3389 |
+
"loss": 1.8113,
|
| 3390 |
+
"step": 483
|
| 3391 |
+
},
|
| 3392 |
+
{
|
| 3393 |
+
"epoch": 0.8192975031739315,
|
| 3394 |
+
"grad_norm": 0.20513294637203217,
|
| 3395 |
+
"learning_rate": 7.964151672377458e-07,
|
| 3396 |
+
"loss": 1.7326,
|
| 3397 |
+
"step": 484
|
| 3398 |
+
},
|
| 3399 |
+
{
|
| 3400 |
+
"epoch": 0.8209902666102412,
|
| 3401 |
+
"grad_norm": 0.19909213483333588,
|
| 3402 |
+
"learning_rate": 7.000858475524444e-07,
|
| 3403 |
+
"loss": 1.7877,
|
| 3404 |
+
"step": 485
|
| 3405 |
+
},
|
| 3406 |
+
{
|
| 3407 |
+
"epoch": 0.822683030046551,
|
| 3408 |
+
"grad_norm": 0.2285769283771515,
|
| 3409 |
+
"learning_rate": 6.099434990268609e-07,
|
| 3410 |
+
"loss": 1.7713,
|
| 3411 |
+
"step": 486
|
| 3412 |
+
},
|
| 3413 |
+
{
|
| 3414 |
+
"epoch": 0.8243757934828607,
|
| 3415 |
+
"grad_norm": 0.22476732730865479,
|
| 3416 |
+
"learning_rate": 5.259936820656257e-07,
|
| 3417 |
+
"loss": 1.8826,
|
| 3418 |
+
"step": 487
|
| 3419 |
+
},
|
| 3420 |
+
{
|
| 3421 |
+
"epoch": 0.8260685569191706,
|
| 3422 |
+
"grad_norm": 0.19041244685649872,
|
| 3423 |
+
"learning_rate": 4.482415750889204e-07,
|
| 3424 |
+
"loss": 1.7251,
|
| 3425 |
+
"step": 488
|
| 3426 |
+
},
|
| 3427 |
+
{
|
| 3428 |
+
"epoch": 0.8277613203554803,
|
| 3429 |
+
"grad_norm": 0.2075662761926651,
|
| 3430 |
+
"learning_rate": 3.766919742129331e-07,
|
| 3431 |
+
"loss": 1.7731,
|
| 3432 |
+
"step": 489
|
| 3433 |
+
},
|
| 3434 |
+
{
|
| 3435 |
+
"epoch": 0.8294540837917901,
|
| 3436 |
+
"grad_norm": 0.18497450649738312,
|
| 3437 |
+
"learning_rate": 3.1134929295407564e-07,
|
| 3438 |
+
"loss": 1.8623,
|
| 3439 |
+
"step": 490
|
| 3440 |
+
},
|
| 3441 |
+
{
|
| 3442 |
+
"epoch": 0.8311468472280998,
|
| 3443 |
+
"grad_norm": 0.219017893075943,
|
| 3444 |
+
"learning_rate": 2.5221756195672563e-07,
|
| 3445 |
+
"loss": 1.8737,
|
| 3446 |
+
"step": 491
|
| 3447 |
+
},
|
| 3448 |
+
{
|
| 3449 |
+
"epoch": 0.8328396106644097,
|
| 3450 |
+
"grad_norm": 0.19198881089687347,
|
| 3451 |
+
"learning_rate": 1.9930042874457254e-07,
|
| 3452 |
+
"loss": 1.6552,
|
| 3453 |
+
"step": 492
|
| 3454 |
+
},
|
| 3455 |
+
{
|
| 3456 |
+
"epoch": 0.8345323741007195,
|
| 3457 |
+
"grad_norm": 0.20981106162071228,
|
| 3458 |
+
"learning_rate": 1.5260115749566882e-07,
|
| 3459 |
+
"loss": 1.8265,
|
| 3460 |
+
"step": 493
|
| 3461 |
+
},
|
| 3462 |
+
{
|
| 3463 |
+
"epoch": 0.8362251375370292,
|
| 3464 |
+
"grad_norm": 0.2261609137058258,
|
| 3465 |
+
"learning_rate": 1.1212262884103974e-07,
|
| 3466 |
+
"loss": 1.8204,
|
| 3467 |
+
"step": 494
|
| 3468 |
+
},
|
| 3469 |
+
{
|
| 3470 |
+
"epoch": 0.837917900973339,
|
| 3471 |
+
"grad_norm": 0.2019382268190384,
|
| 3472 |
+
"learning_rate": 7.7867339686987e-08,
|
| 3473 |
+
"loss": 1.7678,
|
| 3474 |
+
"step": 495
|
| 3475 |
+
},
|
| 3476 |
+
{
|
| 3477 |
+
"epoch": 0.8396106644096487,
|
| 3478 |
+
"grad_norm": 0.2012385129928589,
|
| 3479 |
+
"learning_rate": 4.98374030611084e-08,
|
| 3480 |
+
"loss": 1.8016,
|
| 3481 |
+
"step": 496
|
| 3482 |
+
},
|
| 3483 |
+
{
|
| 3484 |
+
"epoch": 0.8413034278459586,
|
| 3485 |
+
"grad_norm": 0.21322940289974213,
|
| 3486 |
+
"learning_rate": 2.8034547981943713e-08,
|
| 3487 |
+
"loss": 1.8225,
|
| 3488 |
+
"step": 497
|
| 3489 |
+
},
|
| 3490 |
+
{
|
| 3491 |
+
"epoch": 0.8429961912822683,
|
| 3492 |
+
"grad_norm": 0.24298058450222015,
|
| 3493 |
+
"learning_rate": 1.246011935228064e-08,
|
| 3494 |
+
"loss": 1.8557,
|
| 3495 |
+
"step": 498
|
| 3496 |
+
},
|
| 3497 |
+
{
|
| 3498 |
+
"epoch": 0.8446889547185781,
|
| 3499 |
+
"grad_norm": 0.2144518941640854,
|
| 3500 |
+
"learning_rate": 3.115077876243988e-09,
|
| 3501 |
+
"loss": 1.795,
|
| 3502 |
+
"step": 499
|
| 3503 |
+
},
|
| 3504 |
+
{
|
| 3505 |
+
"epoch": 0.8463817181548878,
|
| 3506 |
+
"grad_norm": 0.19734685122966766,
|
| 3507 |
+
"learning_rate": 0.0,
|
| 3508 |
+
"loss": 1.7337,
|
| 3509 |
+
"step": 500
|
| 3510 |
+
}
|
| 3511 |
+
],
|
| 3512 |
+
"logging_steps": 1,
|
| 3513 |
+
"max_steps": 500,
|
| 3514 |
+
"num_input_tokens_seen": 0,
|
| 3515 |
+
"num_train_epochs": 1,
|
| 3516 |
+
"save_steps": 500,
|
| 3517 |
+
"stateful_callbacks": {
|
| 3518 |
+
"TrainerControl": {
|
| 3519 |
+
"args": {
|
| 3520 |
+
"should_epoch_stop": false,
|
| 3521 |
+
"should_evaluate": false,
|
| 3522 |
+
"should_log": false,
|
| 3523 |
+
"should_save": true,
|
| 3524 |
+
"should_training_stop": true
|
| 3525 |
+
},
|
| 3526 |
+
"attributes": {}
|
| 3527 |
+
}
|
| 3528 |
+
},
|
| 3529 |
+
"total_flos": 7.881222559251825e+17,
|
| 3530 |
+
"train_batch_size": 1,
|
| 3531 |
+
"trial_name": null,
|
| 3532 |
+
"trial_params": null
|
| 3533 |
+
}
|
last-checkpoint/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1374dc08f3b8ef62277e3ff9ab13fb0e17955003d7d7244ed20e7b3e268bfa7f
|
| 3 |
+
size 6264
|