Upload folder using huggingface_hub
Browse files- README.md +59 -0
- all_results.json +8 -0
- config.json +26 -0
- runs/Apr15_20-58-46_ggpu163/events.out.tfevents.1713207929.ggpu163.2276267.0 +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +43 -0
- train_results.json +8 -0
- trainer_state.json +1248 -0
README.md
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: mistralai/Mistral-7B-v0.1
|
| 3 |
+
tags:
|
| 4 |
+
- alignment-handbook
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- maxidl/instruct-en-de
|
| 8 |
+
model-index:
|
| 9 |
+
- name: Mistral-7B-v0.1-Instruct-sft-en-de
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# Mistral-7B-v0.1-Instruct-sft-en-de
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the maxidl/instruct-en-de dataset.
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 1e-05
|
| 38 |
+
- train_batch_size: 4
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- distributed_type: multi-GPU
|
| 42 |
+
- num_devices: 32
|
| 43 |
+
- total_train_batch_size: 128
|
| 44 |
+
- total_eval_batch_size: 256
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: cosine
|
| 47 |
+
- lr_scheduler_warmup_steps: 50
|
| 48 |
+
- num_epochs: 3
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
### Framework versions
|
| 55 |
+
|
| 56 |
+
- Transformers 4.39.3
|
| 57 |
+
- Pytorch 2.1.2
|
| 58 |
+
- Datasets 2.18.0
|
| 59 |
+
- Tokenizers 0.15.2
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.6828734450847135,
|
| 4 |
+
"train_runtime": 21591.6608,
|
| 5 |
+
"train_samples": 1226825,
|
| 6 |
+
"train_samples_per_second": 10.261,
|
| 7 |
+
"train_steps_per_second": 0.08
|
| 8 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "mistralai/Mistral-7B-v0.1",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MistralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 14336,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"model_type": "mistral",
|
| 15 |
+
"num_attention_heads": 32,
|
| 16 |
+
"num_hidden_layers": 32,
|
| 17 |
+
"num_key_value_heads": 8,
|
| 18 |
+
"rms_norm_eps": 1e-05,
|
| 19 |
+
"rope_theta": 10000.0,
|
| 20 |
+
"sliding_window": 4096,
|
| 21 |
+
"tie_word_embeddings": false,
|
| 22 |
+
"torch_dtype": "bfloat16",
|
| 23 |
+
"transformers_version": "4.39.3",
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 32000
|
| 26 |
+
}
|
runs/Apr15_20-58-46_ggpu163/events.out.tfevents.1713207929.ggpu163.2276267.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9821cd638666e0dc29c4c418463bd5222febf2d020b7450eb0a09bbf20670373
|
| 3 |
+
size 41835
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"additional_special_tokens": [],
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": true,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"sp_model_kwargs": {},
|
| 39 |
+
"spaces_between_special_tokens": false,
|
| 40 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 41 |
+
"unk_token": "<unk>",
|
| 42 |
+
"use_default_system_prompt": false
|
| 43 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.6828734450847135,
|
| 4 |
+
"train_runtime": 21591.6608,
|
| 5 |
+
"train_samples": 1226825,
|
| 6 |
+
"train_samples_per_second": 10.261,
|
| 7 |
+
"train_steps_per_second": 0.08
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1248 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1731,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"grad_norm": 35.0,
|
| 14 |
+
"learning_rate": 2.0000000000000002e-07,
|
| 15 |
+
"loss": 1.2265,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02,
|
| 20 |
+
"grad_norm": 15.875,
|
| 21 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 22 |
+
"loss": 1.2023,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03,
|
| 27 |
+
"grad_norm": 3.59375,
|
| 28 |
+
"learning_rate": 4.000000000000001e-06,
|
| 29 |
+
"loss": 1.0622,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.05,
|
| 34 |
+
"grad_norm": 1.734375,
|
| 35 |
+
"learning_rate": 6e-06,
|
| 36 |
+
"loss": 0.9902,
|
| 37 |
+
"step": 30
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.07,
|
| 41 |
+
"grad_norm": 1.8125,
|
| 42 |
+
"learning_rate": 8.000000000000001e-06,
|
| 43 |
+
"loss": 0.9469,
|
| 44 |
+
"step": 40
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.09,
|
| 48 |
+
"grad_norm": 1.8359375,
|
| 49 |
+
"learning_rate": 1e-05,
|
| 50 |
+
"loss": 0.9271,
|
| 51 |
+
"step": 50
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1,
|
| 55 |
+
"grad_norm": 1.3125,
|
| 56 |
+
"learning_rate": 9.999126844313853e-06,
|
| 57 |
+
"loss": 0.9067,
|
| 58 |
+
"step": 60
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.12,
|
| 62 |
+
"grad_norm": 1.328125,
|
| 63 |
+
"learning_rate": 9.996507682215754e-06,
|
| 64 |
+
"loss": 0.8857,
|
| 65 |
+
"step": 70
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.14,
|
| 69 |
+
"grad_norm": 1.265625,
|
| 70 |
+
"learning_rate": 9.992143428480215e-06,
|
| 71 |
+
"loss": 0.8738,
|
| 72 |
+
"step": 80
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.16,
|
| 76 |
+
"grad_norm": 1.265625,
|
| 77 |
+
"learning_rate": 9.986035607376421e-06,
|
| 78 |
+
"loss": 0.8758,
|
| 79 |
+
"step": 90
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.17,
|
| 83 |
+
"grad_norm": 1.3828125,
|
| 84 |
+
"learning_rate": 9.97818635213586e-06,
|
| 85 |
+
"loss": 0.8689,
|
| 86 |
+
"step": 100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.19,
|
| 90 |
+
"grad_norm": 1.15625,
|
| 91 |
+
"learning_rate": 9.968598404207276e-06,
|
| 92 |
+
"loss": 0.8657,
|
| 93 |
+
"step": 110
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.21,
|
| 97 |
+
"grad_norm": 1.1015625,
|
| 98 |
+
"learning_rate": 9.957275112299164e-06,
|
| 99 |
+
"loss": 0.8516,
|
| 100 |
+
"step": 120
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.23,
|
| 104 |
+
"grad_norm": 1.15625,
|
| 105 |
+
"learning_rate": 9.944220431210216e-06,
|
| 106 |
+
"loss": 0.8466,
|
| 107 |
+
"step": 130
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.24,
|
| 111 |
+
"grad_norm": 1.28125,
|
| 112 |
+
"learning_rate": 9.929438920448038e-06,
|
| 113 |
+
"loss": 0.8462,
|
| 114 |
+
"step": 140
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.26,
|
| 118 |
+
"grad_norm": 1.140625,
|
| 119 |
+
"learning_rate": 9.912935742636698e-06,
|
| 120 |
+
"loss": 0.8377,
|
| 121 |
+
"step": 150
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.28,
|
| 125 |
+
"grad_norm": 1.1953125,
|
| 126 |
+
"learning_rate": 9.894716661713616e-06,
|
| 127 |
+
"loss": 0.8335,
|
| 128 |
+
"step": 160
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.29,
|
| 132 |
+
"grad_norm": 1.046875,
|
| 133 |
+
"learning_rate": 9.874788040916433e-06,
|
| 134 |
+
"loss": 0.8363,
|
| 135 |
+
"step": 170
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.31,
|
| 139 |
+
"grad_norm": 1.125,
|
| 140 |
+
"learning_rate": 9.853156840560576e-06,
|
| 141 |
+
"loss": 0.8231,
|
| 142 |
+
"step": 180
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.33,
|
| 146 |
+
"grad_norm": 1.234375,
|
| 147 |
+
"learning_rate": 9.82983061560828e-06,
|
| 148 |
+
"loss": 0.8186,
|
| 149 |
+
"step": 190
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.35,
|
| 153 |
+
"grad_norm": 1.234375,
|
| 154 |
+
"learning_rate": 9.804817513029927e-06,
|
| 155 |
+
"loss": 0.8274,
|
| 156 |
+
"step": 200
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.36,
|
| 160 |
+
"grad_norm": 1.25,
|
| 161 |
+
"learning_rate": 9.778126268958614e-06,
|
| 162 |
+
"loss": 0.8121,
|
| 163 |
+
"step": 210
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.38,
|
| 167 |
+
"grad_norm": 1.109375,
|
| 168 |
+
"learning_rate": 9.749766205638954e-06,
|
| 169 |
+
"loss": 0.8086,
|
| 170 |
+
"step": 220
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.4,
|
| 174 |
+
"grad_norm": 1.0703125,
|
| 175 |
+
"learning_rate": 9.719747228171163e-06,
|
| 176 |
+
"loss": 0.8032,
|
| 177 |
+
"step": 230
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.42,
|
| 181 |
+
"grad_norm": 1.140625,
|
| 182 |
+
"learning_rate": 9.688079821051594e-06,
|
| 183 |
+
"loss": 0.8001,
|
| 184 |
+
"step": 240
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.43,
|
| 188 |
+
"grad_norm": 1.078125,
|
| 189 |
+
"learning_rate": 9.65477504451088e-06,
|
| 190 |
+
"loss": 0.7901,
|
| 191 |
+
"step": 250
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.45,
|
| 195 |
+
"grad_norm": 1.1796875,
|
| 196 |
+
"learning_rate": 9.619844530651026e-06,
|
| 197 |
+
"loss": 0.7966,
|
| 198 |
+
"step": 260
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.47,
|
| 202 |
+
"grad_norm": 1.0390625,
|
| 203 |
+
"learning_rate": 9.583300479382754e-06,
|
| 204 |
+
"loss": 0.7904,
|
| 205 |
+
"step": 270
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.49,
|
| 209 |
+
"grad_norm": 1.28125,
|
| 210 |
+
"learning_rate": 9.545155654164523e-06,
|
| 211 |
+
"loss": 0.7905,
|
| 212 |
+
"step": 280
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.5,
|
| 216 |
+
"grad_norm": 1.125,
|
| 217 |
+
"learning_rate": 9.50542337754475e-06,
|
| 218 |
+
"loss": 0.7979,
|
| 219 |
+
"step": 290
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.52,
|
| 223 |
+
"grad_norm": 1.109375,
|
| 224 |
+
"learning_rate": 9.464117526508736e-06,
|
| 225 |
+
"loss": 0.7846,
|
| 226 |
+
"step": 300
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.54,
|
| 230 |
+
"grad_norm": 1.2421875,
|
| 231 |
+
"learning_rate": 9.421252527631964e-06,
|
| 232 |
+
"loss": 0.7775,
|
| 233 |
+
"step": 310
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.55,
|
| 237 |
+
"grad_norm": 1.109375,
|
| 238 |
+
"learning_rate": 9.376843352041434e-06,
|
| 239 |
+
"loss": 0.785,
|
| 240 |
+
"step": 320
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.57,
|
| 244 |
+
"grad_norm": 1.09375,
|
| 245 |
+
"learning_rate": 9.33090551018682e-06,
|
| 246 |
+
"loss": 0.7771,
|
| 247 |
+
"step": 330
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.59,
|
| 251 |
+
"grad_norm": 1.09375,
|
| 252 |
+
"learning_rate": 9.283455046423254e-06,
|
| 253 |
+
"loss": 0.777,
|
| 254 |
+
"step": 340
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.61,
|
| 258 |
+
"grad_norm": 1.125,
|
| 259 |
+
"learning_rate": 9.234508533407633e-06,
|
| 260 |
+
"loss": 0.7779,
|
| 261 |
+
"step": 350
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.62,
|
| 265 |
+
"grad_norm": 1.1328125,
|
| 266 |
+
"learning_rate": 9.184083066310419e-06,
|
| 267 |
+
"loss": 0.7757,
|
| 268 |
+
"step": 360
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.64,
|
| 272 |
+
"grad_norm": 1.0703125,
|
| 273 |
+
"learning_rate": 9.132196256844941e-06,
|
| 274 |
+
"loss": 0.7634,
|
| 275 |
+
"step": 370
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.66,
|
| 279 |
+
"grad_norm": 1.09375,
|
| 280 |
+
"learning_rate": 9.078866227116288e-06,
|
| 281 |
+
"loss": 0.7634,
|
| 282 |
+
"step": 380
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.68,
|
| 286 |
+
"grad_norm": 1.1328125,
|
| 287 |
+
"learning_rate": 9.02411160329194e-06,
|
| 288 |
+
"loss": 0.7658,
|
| 289 |
+
"step": 390
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.69,
|
| 293 |
+
"grad_norm": 1.09375,
|
| 294 |
+
"learning_rate": 8.96795150909635e-06,
|
| 295 |
+
"loss": 0.7578,
|
| 296 |
+
"step": 400
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.71,
|
| 300 |
+
"grad_norm": 1.21875,
|
| 301 |
+
"learning_rate": 8.910405559131752e-06,
|
| 302 |
+
"loss": 0.7598,
|
| 303 |
+
"step": 410
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.73,
|
| 307 |
+
"grad_norm": 1.0859375,
|
| 308 |
+
"learning_rate": 8.851493852027515e-06,
|
| 309 |
+
"loss": 0.7596,
|
| 310 |
+
"step": 420
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.75,
|
| 314 |
+
"grad_norm": 1.265625,
|
| 315 |
+
"learning_rate": 8.791236963420458e-06,
|
| 316 |
+
"loss": 0.7555,
|
| 317 |
+
"step": 430
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.76,
|
| 321 |
+
"grad_norm": 1.109375,
|
| 322 |
+
"learning_rate": 8.729655938768542e-06,
|
| 323 |
+
"loss": 0.7569,
|
| 324 |
+
"step": 440
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.78,
|
| 328 |
+
"grad_norm": 1.109375,
|
| 329 |
+
"learning_rate": 8.666772286000505e-06,
|
| 330 |
+
"loss": 0.7618,
|
| 331 |
+
"step": 450
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.8,
|
| 335 |
+
"grad_norm": 34.5,
|
| 336 |
+
"learning_rate": 8.602607968003935e-06,
|
| 337 |
+
"loss": 0.754,
|
| 338 |
+
"step": 460
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.81,
|
| 342 |
+
"grad_norm": 1.4140625,
|
| 343 |
+
"learning_rate": 8.53718539495448e-06,
|
| 344 |
+
"loss": 0.7425,
|
| 345 |
+
"step": 470
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.83,
|
| 349 |
+
"grad_norm": 1.1875,
|
| 350 |
+
"learning_rate": 8.470527416488799e-06,
|
| 351 |
+
"loss": 0.7554,
|
| 352 |
+
"step": 480
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.85,
|
| 356 |
+
"grad_norm": 1.140625,
|
| 357 |
+
"learning_rate": 8.402657313724065e-06,
|
| 358 |
+
"loss": 0.7517,
|
| 359 |
+
"step": 490
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.87,
|
| 363 |
+
"grad_norm": 1.421875,
|
| 364 |
+
"learning_rate": 8.333598791126737e-06,
|
| 365 |
+
"loss": 0.7453,
|
| 366 |
+
"step": 500
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.88,
|
| 370 |
+
"grad_norm": 1.1875,
|
| 371 |
+
"learning_rate": 8.263375968233487e-06,
|
| 372 |
+
"loss": 0.7395,
|
| 373 |
+
"step": 510
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.9,
|
| 377 |
+
"grad_norm": 1.1171875,
|
| 378 |
+
"learning_rate": 8.192013371227157e-06,
|
| 379 |
+
"loss": 0.7501,
|
| 380 |
+
"step": 520
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.92,
|
| 384 |
+
"grad_norm": 1.1796875,
|
| 385 |
+
"learning_rate": 8.119535924370692e-06,
|
| 386 |
+
"loss": 0.7473,
|
| 387 |
+
"step": 530
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.94,
|
| 391 |
+
"grad_norm": 1.1640625,
|
| 392 |
+
"learning_rate": 8.045968941302024e-06,
|
| 393 |
+
"loss": 0.7407,
|
| 394 |
+
"step": 540
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.95,
|
| 398 |
+
"grad_norm": 1.1484375,
|
| 399 |
+
"learning_rate": 7.971338116192986e-06,
|
| 400 |
+
"loss": 0.7425,
|
| 401 |
+
"step": 550
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.97,
|
| 405 |
+
"grad_norm": 1.09375,
|
| 406 |
+
"learning_rate": 7.895669514775302e-06,
|
| 407 |
+
"loss": 0.7432,
|
| 408 |
+
"step": 560
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.99,
|
| 412 |
+
"grad_norm": 1.0859375,
|
| 413 |
+
"learning_rate": 7.818989565236806e-06,
|
| 414 |
+
"loss": 0.7342,
|
| 415 |
+
"step": 570
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.01,
|
| 419 |
+
"grad_norm": 1.5859375,
|
| 420 |
+
"learning_rate": 7.74132504899108e-06,
|
| 421 |
+
"loss": 0.7181,
|
| 422 |
+
"step": 580
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.02,
|
| 426 |
+
"grad_norm": 1.3203125,
|
| 427 |
+
"learning_rate": 7.662703091323713e-06,
|
| 428 |
+
"loss": 0.6629,
|
| 429 |
+
"step": 590
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.04,
|
| 433 |
+
"grad_norm": 1.1875,
|
| 434 |
+
"learning_rate": 7.583151151918464e-06,
|
| 435 |
+
"loss": 0.6644,
|
| 436 |
+
"step": 600
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.06,
|
| 440 |
+
"grad_norm": 1.1875,
|
| 441 |
+
"learning_rate": 7.502697015266623e-06,
|
| 442 |
+
"loss": 0.6537,
|
| 443 |
+
"step": 610
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.07,
|
| 447 |
+
"grad_norm": 1.1484375,
|
| 448 |
+
"learning_rate": 7.421368780962951e-06,
|
| 449 |
+
"loss": 0.659,
|
| 450 |
+
"step": 620
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.09,
|
| 454 |
+
"grad_norm": 1.1953125,
|
| 455 |
+
"learning_rate": 7.339194853891536e-06,
|
| 456 |
+
"loss": 0.6518,
|
| 457 |
+
"step": 630
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.11,
|
| 461 |
+
"grad_norm": 1.34375,
|
| 462 |
+
"learning_rate": 7.256203934305047e-06,
|
| 463 |
+
"loss": 0.653,
|
| 464 |
+
"step": 640
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.13,
|
| 468 |
+
"grad_norm": 1.3671875,
|
| 469 |
+
"learning_rate": 7.172425007800822e-06,
|
| 470 |
+
"loss": 0.6566,
|
| 471 |
+
"step": 650
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.14,
|
| 475 |
+
"grad_norm": 1.3046875,
|
| 476 |
+
"learning_rate": 7.087887335197281e-06,
|
| 477 |
+
"loss": 0.6528,
|
| 478 |
+
"step": 660
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.16,
|
| 482 |
+
"grad_norm": 1.15625,
|
| 483 |
+
"learning_rate": 7.0026204423142364e-06,
|
| 484 |
+
"loss": 0.6547,
|
| 485 |
+
"step": 670
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.18,
|
| 489 |
+
"grad_norm": 1.125,
|
| 490 |
+
"learning_rate": 6.91665410966063e-06,
|
| 491 |
+
"loss": 0.6503,
|
| 492 |
+
"step": 680
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.2,
|
| 496 |
+
"grad_norm": 1.125,
|
| 497 |
+
"learning_rate": 6.830018362033335e-06,
|
| 498 |
+
"loss": 0.6486,
|
| 499 |
+
"step": 690
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.21,
|
| 503 |
+
"grad_norm": 1.46875,
|
| 504 |
+
"learning_rate": 6.742743458030614e-06,
|
| 505 |
+
"loss": 0.6496,
|
| 506 |
+
"step": 700
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.23,
|
| 510 |
+
"grad_norm": 1.109375,
|
| 511 |
+
"learning_rate": 6.654859879483942e-06,
|
| 512 |
+
"loss": 0.6485,
|
| 513 |
+
"step": 710
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.25,
|
| 517 |
+
"grad_norm": 1.1484375,
|
| 518 |
+
"learning_rate": 6.566398320811852e-06,
|
| 519 |
+
"loss": 0.6534,
|
| 520 |
+
"step": 720
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.27,
|
| 524 |
+
"grad_norm": 1.0703125,
|
| 525 |
+
"learning_rate": 6.477389678299528e-06,
|
| 526 |
+
"loss": 0.6473,
|
| 527 |
+
"step": 730
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.28,
|
| 531 |
+
"grad_norm": 1.1640625,
|
| 532 |
+
"learning_rate": 6.387865039307899e-06,
|
| 533 |
+
"loss": 0.6503,
|
| 534 |
+
"step": 740
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.3,
|
| 538 |
+
"grad_norm": 1.140625,
|
| 539 |
+
"learning_rate": 6.297855671415999e-06,
|
| 540 |
+
"loss": 0.6537,
|
| 541 |
+
"step": 750
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.32,
|
| 545 |
+
"grad_norm": 1.203125,
|
| 546 |
+
"learning_rate": 6.207393011500382e-06,
|
| 547 |
+
"loss": 0.6483,
|
| 548 |
+
"step": 760
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.33,
|
| 552 |
+
"grad_norm": 1.09375,
|
| 553 |
+
"learning_rate": 6.116508654755402e-06,
|
| 554 |
+
"loss": 0.648,
|
| 555 |
+
"step": 770
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.35,
|
| 559 |
+
"grad_norm": 1.1171875,
|
| 560 |
+
"learning_rate": 6.025234343658209e-06,
|
| 561 |
+
"loss": 0.6456,
|
| 562 |
+
"step": 780
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.37,
|
| 566 |
+
"grad_norm": 1.1328125,
|
| 567 |
+
"learning_rate": 5.933601956882299e-06,
|
| 568 |
+
"loss": 0.6459,
|
| 569 |
+
"step": 790
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.39,
|
| 573 |
+
"grad_norm": 1.171875,
|
| 574 |
+
"learning_rate": 5.841643498163488e-06,
|
| 575 |
+
"loss": 0.6543,
|
| 576 |
+
"step": 800
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.4,
|
| 580 |
+
"grad_norm": 1.203125,
|
| 581 |
+
"learning_rate": 5.7493910851222244e-06,
|
| 582 |
+
"loss": 0.6438,
|
| 583 |
+
"step": 810
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.42,
|
| 587 |
+
"grad_norm": 1.3828125,
|
| 588 |
+
"learning_rate": 5.656876938046112e-06,
|
| 589 |
+
"loss": 0.6428,
|
| 590 |
+
"step": 820
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.44,
|
| 594 |
+
"grad_norm": 1.1015625,
|
| 595 |
+
"learning_rate": 5.56413336863658e-06,
|
| 596 |
+
"loss": 0.6442,
|
| 597 |
+
"step": 830
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.46,
|
| 601 |
+
"grad_norm": 1.1796875,
|
| 602 |
+
"learning_rate": 5.471192768723618e-06,
|
| 603 |
+
"loss": 0.6428,
|
| 604 |
+
"step": 840
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.47,
|
| 608 |
+
"grad_norm": 1.1328125,
|
| 609 |
+
"learning_rate": 5.378087598952543e-06,
|
| 610 |
+
"loss": 0.648,
|
| 611 |
+
"step": 850
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.49,
|
| 615 |
+
"grad_norm": 1.1015625,
|
| 616 |
+
"learning_rate": 5.284850377446715e-06,
|
| 617 |
+
"loss": 0.6411,
|
| 618 |
+
"step": 860
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.51,
|
| 622 |
+
"grad_norm": 1.09375,
|
| 623 |
+
"learning_rate": 5.191513668450178e-06,
|
| 624 |
+
"loss": 0.647,
|
| 625 |
+
"step": 870
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.53,
|
| 629 |
+
"grad_norm": 1.1640625,
|
| 630 |
+
"learning_rate": 5.098110070954209e-06,
|
| 631 |
+
"loss": 0.6477,
|
| 632 |
+
"step": 880
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.54,
|
| 636 |
+
"grad_norm": 1.1328125,
|
| 637 |
+
"learning_rate": 5.004672207311709e-06,
|
| 638 |
+
"loss": 0.6457,
|
| 639 |
+
"step": 890
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.56,
|
| 643 |
+
"grad_norm": 1.140625,
|
| 644 |
+
"learning_rate": 4.911232711843459e-06,
|
| 645 |
+
"loss": 0.6399,
|
| 646 |
+
"step": 900
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.58,
|
| 650 |
+
"grad_norm": 1.140625,
|
| 651 |
+
"learning_rate": 4.817824219440167e-06,
|
| 652 |
+
"loss": 0.6414,
|
| 653 |
+
"step": 910
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.59,
|
| 657 |
+
"grad_norm": 1.1484375,
|
| 658 |
+
"learning_rate": 4.724479354164347e-06,
|
| 659 |
+
"loss": 0.6378,
|
| 660 |
+
"step": 920
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.61,
|
| 664 |
+
"grad_norm": 1.1015625,
|
| 665 |
+
"learning_rate": 4.631230717855949e-06,
|
| 666 |
+
"loss": 0.6437,
|
| 667 |
+
"step": 930
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.63,
|
| 671 |
+
"grad_norm": 1.1484375,
|
| 672 |
+
"learning_rate": 4.538110878745784e-06,
|
| 673 |
+
"loss": 0.6439,
|
| 674 |
+
"step": 940
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.65,
|
| 678 |
+
"grad_norm": 1.2265625,
|
| 679 |
+
"learning_rate": 4.4451523600806555e-06,
|
| 680 |
+
"loss": 0.6394,
|
| 681 |
+
"step": 950
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.66,
|
| 685 |
+
"grad_norm": 1.1328125,
|
| 686 |
+
"learning_rate": 4.352387628764223e-06,
|
| 687 |
+
"loss": 0.638,
|
| 688 |
+
"step": 960
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.68,
|
| 692 |
+
"grad_norm": 1.1015625,
|
| 693 |
+
"learning_rate": 4.259849084017537e-06,
|
| 694 |
+
"loss": 0.6361,
|
| 695 |
+
"step": 970
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.7,
|
| 699 |
+
"grad_norm": 1.109375,
|
| 700 |
+
"learning_rate": 4.16756904606321e-06,
|
| 701 |
+
"loss": 0.626,
|
| 702 |
+
"step": 980
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.72,
|
| 706 |
+
"grad_norm": 1.109375,
|
| 707 |
+
"learning_rate": 4.075579744837185e-06,
|
| 708 |
+
"loss": 0.6424,
|
| 709 |
+
"step": 990
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.73,
|
| 713 |
+
"grad_norm": 1.2265625,
|
| 714 |
+
"learning_rate": 3.983913308732033e-06,
|
| 715 |
+
"loss": 0.6348,
|
| 716 |
+
"step": 1000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.75,
|
| 720 |
+
"grad_norm": 1.1328125,
|
| 721 |
+
"learning_rate": 3.89260175337572e-06,
|
| 722 |
+
"loss": 0.6433,
|
| 723 |
+
"step": 1010
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.77,
|
| 727 |
+
"grad_norm": 1.1328125,
|
| 728 |
+
"learning_rate": 3.801676970449755e-06,
|
| 729 |
+
"loss": 0.6352,
|
| 730 |
+
"step": 1020
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.79,
|
| 734 |
+
"grad_norm": 1.0859375,
|
| 735 |
+
"learning_rate": 3.711170716550627e-06,
|
| 736 |
+
"loss": 0.6308,
|
| 737 |
+
"step": 1030
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.8,
|
| 741 |
+
"grad_norm": 1.1015625,
|
| 742 |
+
"learning_rate": 3.6211146020984246e-06,
|
| 743 |
+
"loss": 0.636,
|
| 744 |
+
"step": 1040
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.82,
|
| 748 |
+
"grad_norm": 1.109375,
|
| 749 |
+
"learning_rate": 3.531540080296513e-06,
|
| 750 |
+
"loss": 0.6352,
|
| 751 |
+
"step": 1050
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.84,
|
| 755 |
+
"grad_norm": 1.125,
|
| 756 |
+
"learning_rate": 3.442478436146108e-06,
|
| 757 |
+
"loss": 0.6368,
|
| 758 |
+
"step": 1060
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.85,
|
| 762 |
+
"grad_norm": 1.1171875,
|
| 763 |
+
"learning_rate": 3.353960775519612e-06,
|
| 764 |
+
"loss": 0.6386,
|
| 765 |
+
"step": 1070
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.87,
|
| 769 |
+
"grad_norm": 1.09375,
|
| 770 |
+
"learning_rate": 3.266018014296506e-06,
|
| 771 |
+
"loss": 0.6371,
|
| 772 |
+
"step": 1080
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.89,
|
| 776 |
+
"grad_norm": 1.109375,
|
| 777 |
+
"learning_rate": 3.1786808675655973e-06,
|
| 778 |
+
"loss": 0.6308,
|
| 779 |
+
"step": 1090
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.91,
|
| 783 |
+
"grad_norm": 1.1015625,
|
| 784 |
+
"learning_rate": 3.0919798388973977e-06,
|
| 785 |
+
"loss": 0.6394,
|
| 786 |
+
"step": 1100
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.92,
|
| 790 |
+
"grad_norm": 1.09375,
|
| 791 |
+
"learning_rate": 3.005945209690378e-06,
|
| 792 |
+
"loss": 0.6318,
|
| 793 |
+
"step": 1110
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.94,
|
| 797 |
+
"grad_norm": 1.0859375,
|
| 798 |
+
"learning_rate": 2.920607028594819e-06,
|
| 799 |
+
"loss": 0.6281,
|
| 800 |
+
"step": 1120
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.96,
|
| 804 |
+
"grad_norm": 1.0859375,
|
| 805 |
+
"learning_rate": 2.835995101017943e-06,
|
| 806 |
+
"loss": 0.6366,
|
| 807 |
+
"step": 1130
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.98,
|
| 811 |
+
"grad_norm": 1.1171875,
|
| 812 |
+
"learning_rate": 2.7521389787140264e-06,
|
| 813 |
+
"loss": 0.6326,
|
| 814 |
+
"step": 1140
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.99,
|
| 818 |
+
"grad_norm": 1.1015625,
|
| 819 |
+
"learning_rate": 2.6690679494630734e-06,
|
| 820 |
+
"loss": 0.6318,
|
| 821 |
+
"step": 1150
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 2.01,
|
| 825 |
+
"grad_norm": 1.7265625,
|
| 826 |
+
"learning_rate": 2.5868110268416974e-06,
|
| 827 |
+
"loss": 0.603,
|
| 828 |
+
"step": 1160
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 2.03,
|
| 832 |
+
"grad_norm": 1.328125,
|
| 833 |
+
"learning_rate": 2.5053969400897847e-06,
|
| 834 |
+
"loss": 0.5946,
|
| 835 |
+
"step": 1170
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 2.05,
|
| 839 |
+
"grad_norm": 1.1015625,
|
| 840 |
+
"learning_rate": 2.4248541240764484e-06,
|
| 841 |
+
"loss": 0.5963,
|
| 842 |
+
"step": 1180
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 2.06,
|
| 846 |
+
"grad_norm": 1.1015625,
|
| 847 |
+
"learning_rate": 2.345210709368802e-06,
|
| 848 |
+
"loss": 0.5989,
|
| 849 |
+
"step": 1190
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.08,
|
| 853 |
+
"grad_norm": 1.125,
|
| 854 |
+
"learning_rate": 2.2664945124070076e-06,
|
| 855 |
+
"loss": 0.5926,
|
| 856 |
+
"step": 1200
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 2.1,
|
| 860 |
+
"grad_norm": 1.109375,
|
| 861 |
+
"learning_rate": 2.1887330257890554e-06,
|
| 862 |
+
"loss": 0.5868,
|
| 863 |
+
"step": 1210
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 2.11,
|
| 867 |
+
"grad_norm": 1.09375,
|
| 868 |
+
"learning_rate": 2.1119534086686265e-06,
|
| 869 |
+
"loss": 0.5908,
|
| 870 |
+
"step": 1220
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 2.13,
|
| 874 |
+
"grad_norm": 1.109375,
|
| 875 |
+
"learning_rate": 2.036182477269429e-06,
|
| 876 |
+
"loss": 0.5918,
|
| 877 |
+
"step": 1230
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 2.15,
|
| 881 |
+
"grad_norm": 1.0859375,
|
| 882 |
+
"learning_rate": 1.9614466955193007e-06,
|
| 883 |
+
"loss": 0.5982,
|
| 884 |
+
"step": 1240
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.17,
|
| 888 |
+
"grad_norm": 1.1015625,
|
| 889 |
+
"learning_rate": 1.8877721658073589e-06,
|
| 890 |
+
"loss": 0.5901,
|
| 891 |
+
"step": 1250
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.18,
|
| 895 |
+
"grad_norm": 1.09375,
|
| 896 |
+
"learning_rate": 1.8151846198674227e-06,
|
| 897 |
+
"loss": 0.5967,
|
| 898 |
+
"step": 1260
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 2.2,
|
| 902 |
+
"grad_norm": 1.0703125,
|
| 903 |
+
"learning_rate": 1.7437094097908813e-06,
|
| 904 |
+
"loss": 0.5953,
|
| 905 |
+
"step": 1270
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 2.22,
|
| 909 |
+
"grad_norm": 1.1328125,
|
| 910 |
+
"learning_rate": 1.6733714991721738e-06,
|
| 911 |
+
"loss": 0.5902,
|
| 912 |
+
"step": 1280
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.24,
|
| 916 |
+
"grad_norm": 1.078125,
|
| 917 |
+
"learning_rate": 1.6041954543899452e-06,
|
| 918 |
+
"loss": 0.5891,
|
| 919 |
+
"step": 1290
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 2.25,
|
| 923 |
+
"grad_norm": 1.125,
|
| 924 |
+
"learning_rate": 1.5362054360269336e-06,
|
| 925 |
+
"loss": 0.5912,
|
| 926 |
+
"step": 1300
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 2.27,
|
| 930 |
+
"grad_norm": 1.0703125,
|
| 931 |
+
"learning_rate": 1.469425190431592e-06,
|
| 932 |
+
"loss": 0.595,
|
| 933 |
+
"step": 1310
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.29,
|
| 937 |
+
"grad_norm": 1.1015625,
|
| 938 |
+
"learning_rate": 1.4038780414243875e-06,
|
| 939 |
+
"loss": 0.5978,
|
| 940 |
+
"step": 1320
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 2.31,
|
| 944 |
+
"grad_norm": 1.09375,
|
| 945 |
+
"learning_rate": 1.3395868821516667e-06,
|
| 946 |
+
"loss": 0.5871,
|
| 947 |
+
"step": 1330
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 2.32,
|
| 951 |
+
"grad_norm": 1.078125,
|
| 952 |
+
"learning_rate": 1.2765741670899428e-06,
|
| 953 |
+
"loss": 0.5934,
|
| 954 |
+
"step": 1340
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.34,
|
| 958 |
+
"grad_norm": 1.0625,
|
| 959 |
+
"learning_rate": 1.2148619042033994e-06,
|
| 960 |
+
"loss": 0.5928,
|
| 961 |
+
"step": 1350
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 2.36,
|
| 965 |
+
"grad_norm": 1.0859375,
|
| 966 |
+
"learning_rate": 1.1544716472573336e-06,
|
| 967 |
+
"loss": 0.5853,
|
| 968 |
+
"step": 1360
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 2.37,
|
| 972 |
+
"grad_norm": 1.109375,
|
| 973 |
+
"learning_rate": 1.0954244882902426e-06,
|
| 974 |
+
"loss": 0.5905,
|
| 975 |
+
"step": 1370
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 2.39,
|
| 979 |
+
"grad_norm": 1.109375,
|
| 980 |
+
"learning_rate": 1.0377410502471668e-06,
|
| 981 |
+
"loss": 0.5859,
|
| 982 |
+
"step": 1380
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 2.41,
|
| 986 |
+
"grad_norm": 1.09375,
|
| 987 |
+
"learning_rate": 9.814414797768756e-07,
|
| 988 |
+
"loss": 0.5956,
|
| 989 |
+
"step": 1390
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 2.43,
|
| 993 |
+
"grad_norm": 1.09375,
|
| 994 |
+
"learning_rate": 9.265454401954044e-07,
|
| 995 |
+
"loss": 0.5911,
|
| 996 |
+
"step": 1400
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 2.44,
|
| 1000 |
+
"grad_norm": 1.0859375,
|
| 1001 |
+
"learning_rate": 8.730721046183932e-07,
|
| 1002 |
+
"loss": 0.5868,
|
| 1003 |
+
"step": 1410
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 2.46,
|
| 1007 |
+
"grad_norm": 1.09375,
|
| 1008 |
+
"learning_rate": 8.210401492646497e-07,
|
| 1009 |
+
"loss": 0.5946,
|
| 1010 |
+
"step": 1420
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 2.48,
|
| 1014 |
+
"grad_norm": 1.0703125,
|
| 1015 |
+
"learning_rate": 7.704677469332455e-07,
|
| 1016 |
+
"loss": 0.5925,
|
| 1017 |
+
"step": 1430
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 2.5,
|
| 1021 |
+
"grad_norm": 1.125,
|
| 1022 |
+
"learning_rate": 7.213725606564436e-07,
|
| 1023 |
+
"loss": 0.5947,
|
| 1024 |
+
"step": 1440
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 2.51,
|
| 1028 |
+
"grad_norm": 1.1015625,
|
| 1029 |
+
"learning_rate": 6.737717375306684e-07,
|
| 1030 |
+
"loss": 0.5923,
|
| 1031 |
+
"step": 1450
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 2.53,
|
| 1035 |
+
"grad_norm": 1.09375,
|
| 1036 |
+
"learning_rate": 6.276819027276709e-07,
|
| 1037 |
+
"loss": 0.5861,
|
| 1038 |
+
"step": 1460
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 2.55,
|
| 1042 |
+
"grad_norm": 1.0625,
|
| 1043 |
+
"learning_rate": 5.831191536879843e-07,
|
| 1044 |
+
"loss": 0.5956,
|
| 1045 |
+
"step": 1470
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 2.56,
|
| 1049 |
+
"grad_norm": 1.0859375,
|
| 1050 |
+
"learning_rate": 5.400990544986922e-07,
|
| 1051 |
+
"loss": 0.5896,
|
| 1052 |
+
"step": 1480
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 2.58,
|
| 1056 |
+
"grad_norm": 1.1015625,
|
| 1057 |
+
"learning_rate": 4.986366304574869e-07,
|
| 1058 |
+
"loss": 0.5951,
|
| 1059 |
+
"step": 1490
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 2.6,
|
| 1063 |
+
"grad_norm": 1.1015625,
|
| 1064 |
+
"learning_rate": 4.587463628248923e-07,
|
| 1065 |
+
"loss": 0.5884,
|
| 1066 |
+
"step": 1500
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.62,
|
| 1070 |
+
"grad_norm": 1.0859375,
|
| 1071 |
+
"learning_rate": 4.2044218376651124e-07,
|
| 1072 |
+
"loss": 0.5919,
|
| 1073 |
+
"step": 1510
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 2.63,
|
| 1077 |
+
"grad_norm": 1.109375,
|
| 1078 |
+
"learning_rate": 3.837374714870434e-07,
|
| 1079 |
+
"loss": 0.6024,
|
| 1080 |
+
"step": 1520
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 2.65,
|
| 1084 |
+
"grad_norm": 1.109375,
|
| 1085 |
+
"learning_rate": 3.486450455577828e-07,
|
| 1086 |
+
"loss": 0.5936,
|
| 1087 |
+
"step": 1530
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 2.67,
|
| 1091 |
+
"grad_norm": 1.3515625,
|
| 1092 |
+
"learning_rate": 3.1517716243922414e-07,
|
| 1093 |
+
"loss": 0.5921,
|
| 1094 |
+
"step": 1540
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 2.69,
|
| 1098 |
+
"grad_norm": 1.0859375,
|
| 1099 |
+
"learning_rate": 2.8334551120034857e-07,
|
| 1100 |
+
"loss": 0.5965,
|
| 1101 |
+
"step": 1550
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 2.7,
|
| 1105 |
+
"grad_norm": 1.1015625,
|
| 1106 |
+
"learning_rate": 2.5316120943606634e-07,
|
| 1107 |
+
"loss": 0.5922,
|
| 1108 |
+
"step": 1560
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 2.72,
|
| 1112 |
+
"grad_norm": 1.125,
|
| 1113 |
+
"learning_rate": 2.246347993842657e-07,
|
| 1114 |
+
"loss": 0.5878,
|
| 1115 |
+
"step": 1570
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 2.74,
|
| 1119 |
+
"grad_norm": 1.1015625,
|
| 1120 |
+
"learning_rate": 1.977762442438025e-07,
|
| 1121 |
+
"loss": 0.5946,
|
| 1122 |
+
"step": 1580
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 2.76,
|
| 1126 |
+
"grad_norm": 1.0703125,
|
| 1127 |
+
"learning_rate": 1.725949246947345e-07,
|
| 1128 |
+
"loss": 0.5888,
|
| 1129 |
+
"step": 1590
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 2.77,
|
| 1133 |
+
"grad_norm": 1.1328125,
|
| 1134 |
+
"learning_rate": 1.4909963562200036e-07,
|
| 1135 |
+
"loss": 0.593,
|
| 1136 |
+
"step": 1600
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 2.79,
|
| 1140 |
+
"grad_norm": 1.0859375,
|
| 1141 |
+
"learning_rate": 1.272985830437018e-07,
|
| 1142 |
+
"loss": 0.5916,
|
| 1143 |
+
"step": 1610
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 2.81,
|
| 1147 |
+
"grad_norm": 1.1015625,
|
| 1148 |
+
"learning_rate": 1.0719938124504725e-07,
|
| 1149 |
+
"loss": 0.5984,
|
| 1150 |
+
"step": 1620
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 2.82,
|
| 1154 |
+
"grad_norm": 1.140625,
|
| 1155 |
+
"learning_rate": 8.880905011897145e-08,
|
| 1156 |
+
"loss": 0.5938,
|
| 1157 |
+
"step": 1630
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 2.84,
|
| 1161 |
+
"grad_norm": 1.0703125,
|
| 1162 |
+
"learning_rate": 7.213401271435216e-08,
|
| 1163 |
+
"loss": 0.5911,
|
| 1164 |
+
"step": 1640
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 2.86,
|
| 1168 |
+
"grad_norm": 1.1171875,
|
| 1169 |
+
"learning_rate": 5.718009299267968e-08,
|
| 1170 |
+
"loss": 0.5826,
|
| 1171 |
+
"step": 1650
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 2.88,
|
| 1175 |
+
"grad_norm": 1.09375,
|
| 1176 |
+
"learning_rate": 4.395251379396781e-08,
|
| 1177 |
+
"loss": 0.5969,
|
| 1178 |
+
"step": 1660
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 2.89,
|
| 1182 |
+
"grad_norm": 1.09375,
|
| 1183 |
+
"learning_rate": 3.2455895012614146e-08,
|
| 1184 |
+
"loss": 0.5877,
|
| 1185 |
+
"step": 1670
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 2.91,
|
| 1189 |
+
"grad_norm": 1.0546875,
|
| 1190 |
+
"learning_rate": 2.2694251983841896e-08,
|
| 1191 |
+
"loss": 0.5877,
|
| 1192 |
+
"step": 1680
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 2.93,
|
| 1196 |
+
"grad_norm": 1.1015625,
|
| 1197 |
+
"learning_rate": 1.4670994081297796e-08,
|
| 1198 |
+
"loss": 0.5914,
|
| 1199 |
+
"step": 1690
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 2.95,
|
| 1203 |
+
"grad_norm": 1.0859375,
|
| 1204 |
+
"learning_rate": 8.38892352628573e-09,
|
| 1205 |
+
"loss": 0.5922,
|
| 1206 |
+
"step": 1700
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 2.96,
|
| 1210 |
+
"grad_norm": 1.1171875,
|
| 1211 |
+
"learning_rate": 3.850234409055742e-09,
|
| 1212 |
+
"loss": 0.5935,
|
| 1213 |
+
"step": 1710
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.98,
|
| 1217 |
+
"grad_norm": 1.1015625,
|
| 1218 |
+
"learning_rate": 1.0565119224925646e-09,
|
| 1219 |
+
"loss": 0.5911,
|
| 1220 |
+
"step": 1720
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 3.0,
|
| 1224 |
+
"grad_norm": 1.109375,
|
| 1225 |
+
"learning_rate": 8.731808465167746e-12,
|
| 1226 |
+
"loss": 0.5943,
|
| 1227 |
+
"step": 1730
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 3.0,
|
| 1231 |
+
"step": 1731,
|
| 1232 |
+
"total_flos": 2.4199600073374433e+18,
|
| 1233 |
+
"train_loss": 0.6828734450847135,
|
| 1234 |
+
"train_runtime": 21591.6608,
|
| 1235 |
+
"train_samples_per_second": 10.261,
|
| 1236 |
+
"train_steps_per_second": 0.08
|
| 1237 |
+
}
|
| 1238 |
+
],
|
| 1239 |
+
"logging_steps": 10,
|
| 1240 |
+
"max_steps": 1731,
|
| 1241 |
+
"num_input_tokens_seen": 0,
|
| 1242 |
+
"num_train_epochs": 3,
|
| 1243 |
+
"save_steps": 500,
|
| 1244 |
+
"total_flos": 2.4199600073374433e+18,
|
| 1245 |
+
"train_batch_size": 4,
|
| 1246 |
+
"trial_name": null,
|
| 1247 |
+
"trial_params": null
|
| 1248 |
+
}
|