End of training
Browse files- README.md +3 -2
- all_results.json +12 -0
- eval_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +517 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: Qwen/Qwen2.5-1.5B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: models1
|
|
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# models1
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen2.5-1.5B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- lora
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: models1
|
|
|
|
| 16 |
|
| 17 |
# models1
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the comment_finetune_train dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.1252
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 0.12520842254161835,
|
| 4 |
+
"eval_runtime": 62.8478,
|
| 5 |
+
"eval_samples_per_second": 1.082,
|
| 6 |
+
"eval_steps_per_second": 1.082,
|
| 7 |
+
"total_flos": 1.134915283869696e+16,
|
| 8 |
+
"train_loss": 0.04400509732668517,
|
| 9 |
+
"train_runtime": 2473.793,
|
| 10 |
+
"train_samples_per_second": 0.986,
|
| 11 |
+
"train_steps_per_second": 0.247
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 0.12520842254161835,
|
| 4 |
+
"eval_runtime": 62.8478,
|
| 5 |
+
"eval_samples_per_second": 1.082,
|
| 6 |
+
"eval_steps_per_second": 1.082
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 1.134915283869696e+16,
|
| 4 |
+
"train_loss": 0.04400509732668517,
|
| 5 |
+
"train_runtime": 2473.793,
|
| 6 |
+
"train_samples_per_second": 0.986,
|
| 7 |
+
"train_steps_per_second": 0.247
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,517 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 610,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01639344262295082,
|
| 13 |
+
"grad_norm": 1.9867063760757446,
|
| 14 |
+
"learning_rate": 1.6393442622950818e-05,
|
| 15 |
+
"loss": 0.3745,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03278688524590164,
|
| 20 |
+
"grad_norm": 1.508779525756836,
|
| 21 |
+
"learning_rate": 3.2786885245901635e-05,
|
| 22 |
+
"loss": 0.2514,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.04918032786885246,
|
| 27 |
+
"grad_norm": 0.43040570616722107,
|
| 28 |
+
"learning_rate": 4.918032786885246e-05,
|
| 29 |
+
"loss": 0.1555,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06557377049180328,
|
| 34 |
+
"grad_norm": 1.1166633367538452,
|
| 35 |
+
"learning_rate": 6.557377049180327e-05,
|
| 36 |
+
"loss": 0.1932,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08196721311475409,
|
| 41 |
+
"grad_norm": 0.4990024268627167,
|
| 42 |
+
"learning_rate": 8.19672131147541e-05,
|
| 43 |
+
"loss": 0.1536,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.09836065573770492,
|
| 48 |
+
"grad_norm": 1.1272306442260742,
|
| 49 |
+
"learning_rate": 9.836065573770493e-05,
|
| 50 |
+
"loss": 0.1524,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.11475409836065574,
|
| 55 |
+
"grad_norm": 0.4084867238998413,
|
| 56 |
+
"learning_rate": 9.993370449424153e-05,
|
| 57 |
+
"loss": 0.1391,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.13114754098360656,
|
| 62 |
+
"grad_norm": 0.6679890751838684,
|
| 63 |
+
"learning_rate": 9.970476054107763e-05,
|
| 64 |
+
"loss": 0.1274,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.14754098360655737,
|
| 69 |
+
"grad_norm": 1.0677056312561035,
|
| 70 |
+
"learning_rate": 9.931309898856423e-05,
|
| 71 |
+
"loss": 0.1283,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.16393442622950818,
|
| 76 |
+
"grad_norm": 1.0797268152236938,
|
| 77 |
+
"learning_rate": 9.876000201222912e-05,
|
| 78 |
+
"loss": 0.1317,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.16393442622950818,
|
| 83 |
+
"eval_loss": 0.16001197695732117,
|
| 84 |
+
"eval_runtime": 62.2223,
|
| 85 |
+
"eval_samples_per_second": 1.093,
|
| 86 |
+
"eval_steps_per_second": 1.093,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.18032786885245902,
|
| 91 |
+
"grad_norm": 0.9521363973617554,
|
| 92 |
+
"learning_rate": 9.804728027590449e-05,
|
| 93 |
+
"loss": 0.1882,
|
| 94 |
+
"step": 110
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.19672131147540983,
|
| 98 |
+
"grad_norm": 0.835111141204834,
|
| 99 |
+
"learning_rate": 9.717726700418842e-05,
|
| 100 |
+
"loss": 0.1557,
|
| 101 |
+
"step": 120
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.21311475409836064,
|
| 105 |
+
"grad_norm": 0.6795278787612915,
|
| 106 |
+
"learning_rate": 9.61528103442088e-05,
|
| 107 |
+
"loss": 0.161,
|
| 108 |
+
"step": 130
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.22950819672131148,
|
| 112 |
+
"grad_norm": 0.9582076072692871,
|
| 113 |
+
"learning_rate": 9.497726404169412e-05,
|
| 114 |
+
"loss": 0.1615,
|
| 115 |
+
"step": 140
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.2459016393442623,
|
| 119 |
+
"grad_norm": 0.9718400239944458,
|
| 120 |
+
"learning_rate": 9.365447646187509e-05,
|
| 121 |
+
"loss": 0.1473,
|
| 122 |
+
"step": 150
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.26229508196721313,
|
| 126 |
+
"grad_norm": 0.881258487701416,
|
| 127 |
+
"learning_rate": 9.218877799115928e-05,
|
| 128 |
+
"loss": 0.125,
|
| 129 |
+
"step": 160
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.2786885245901639,
|
| 133 |
+
"grad_norm": 0.9122475385665894,
|
| 134 |
+
"learning_rate": 9.058496686082132e-05,
|
| 135 |
+
"loss": 0.1401,
|
| 136 |
+
"step": 170
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.29508196721311475,
|
| 140 |
+
"grad_norm": 1.2337970733642578,
|
| 141 |
+
"learning_rate": 8.884829343911762e-05,
|
| 142 |
+
"loss": 0.145,
|
| 143 |
+
"step": 180
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.3114754098360656,
|
| 147 |
+
"grad_norm": 0.3640283942222595,
|
| 148 |
+
"learning_rate": 8.698444304324835e-05,
|
| 149 |
+
"loss": 0.1411,
|
| 150 |
+
"step": 190
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.32786885245901637,
|
| 154 |
+
"grad_norm": 0.9699270129203796,
|
| 155 |
+
"learning_rate": 8.499951732743457e-05,
|
| 156 |
+
"loss": 0.1605,
|
| 157 |
+
"step": 200
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.32786885245901637,
|
| 161 |
+
"eval_loss": 0.15475818514823914,
|
| 162 |
+
"eval_runtime": 62.2552,
|
| 163 |
+
"eval_samples_per_second": 1.092,
|
| 164 |
+
"eval_steps_per_second": 1.092,
|
| 165 |
+
"step": 200
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.3442622950819672,
|
| 169 |
+
"grad_norm": 1.2340621948242188,
|
| 170 |
+
"learning_rate": 8.290001430804025e-05,
|
| 171 |
+
"loss": 0.1302,
|
| 172 |
+
"step": 210
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.36065573770491804,
|
| 176 |
+
"grad_norm": 0.7683020234107971,
|
| 177 |
+
"learning_rate": 8.06928070911306e-05,
|
| 178 |
+
"loss": 0.1771,
|
| 179 |
+
"step": 220
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.3770491803278688,
|
| 183 |
+
"grad_norm": 1.2670581340789795,
|
| 184 |
+
"learning_rate": 7.838512137210565e-05,
|
| 185 |
+
"loss": 0.1442,
|
| 186 |
+
"step": 230
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.39344262295081966,
|
| 190 |
+
"grad_norm": 0.6768158078193665,
|
| 191 |
+
"learning_rate": 7.598451178106857e-05,
|
| 192 |
+
"loss": 0.1389,
|
| 193 |
+
"step": 240
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.4098360655737705,
|
| 197 |
+
"grad_norm": 1.129391074180603,
|
| 198 |
+
"learning_rate": 7.3498837151366e-05,
|
| 199 |
+
"loss": 0.1385,
|
| 200 |
+
"step": 250
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.4262295081967213,
|
| 204 |
+
"grad_norm": 1.101136326789856,
|
| 205 |
+
"learning_rate": 7.093623479226385e-05,
|
| 206 |
+
"loss": 0.1564,
|
| 207 |
+
"step": 260
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.4426229508196721,
|
| 211 |
+
"grad_norm": 0.2261950969696045,
|
| 212 |
+
"learning_rate": 6.830509384998114e-05,
|
| 213 |
+
"loss": 0.1431,
|
| 214 |
+
"step": 270
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.45901639344262296,
|
| 218 |
+
"grad_norm": 0.3458766043186188,
|
| 219 |
+
"learning_rate": 6.561402784428974e-05,
|
| 220 |
+
"loss": 0.1206,
|
| 221 |
+
"step": 280
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.47540983606557374,
|
| 225 |
+
"grad_norm": 1.1199126243591309,
|
| 226 |
+
"learning_rate": 6.287184647058648e-05,
|
| 227 |
+
"loss": 0.11,
|
| 228 |
+
"step": 290
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.4918032786885246,
|
| 232 |
+
"grad_norm": 0.45597025752067566,
|
| 233 |
+
"learning_rate": 6.0087526759748304e-05,
|
| 234 |
+
"loss": 0.1191,
|
| 235 |
+
"step": 300
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.4918032786885246,
|
| 239 |
+
"eval_loss": 0.1460057497024536,
|
| 240 |
+
"eval_runtime": 62.2673,
|
| 241 |
+
"eval_samples_per_second": 1.092,
|
| 242 |
+
"eval_steps_per_second": 1.092,
|
| 243 |
+
"step": 300
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.5081967213114754,
|
| 247 |
+
"grad_norm": 0.734933614730835,
|
| 248 |
+
"learning_rate": 5.7270183690184495e-05,
|
| 249 |
+
"loss": 0.1585,
|
| 250 |
+
"step": 310
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.5245901639344263,
|
| 254 |
+
"grad_norm": 0.8497341275215149,
|
| 255 |
+
"learning_rate": 5.4429040348292256e-05,
|
| 256 |
+
"loss": 0.1406,
|
| 257 |
+
"step": 320
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.5409836065573771,
|
| 261 |
+
"grad_norm": 0.8217471241950989,
|
| 262 |
+
"learning_rate": 5.157339773500125e-05,
|
| 263 |
+
"loss": 0.1388,
|
| 264 |
+
"step": 330
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.5573770491803278,
|
| 268 |
+
"grad_norm": 0.3617191016674042,
|
| 269 |
+
"learning_rate": 4.8712604317250576e-05,
|
| 270 |
+
"loss": 0.1493,
|
| 271 |
+
"step": 340
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.5737704918032787,
|
| 275 |
+
"grad_norm": 0.9715378880500793,
|
| 276 |
+
"learning_rate": 4.585602542407722e-05,
|
| 277 |
+
"loss": 0.1446,
|
| 278 |
+
"step": 350
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.5901639344262295,
|
| 282 |
+
"grad_norm": 0.8967556953430176,
|
| 283 |
+
"learning_rate": 4.3013012587503254e-05,
|
| 284 |
+
"loss": 0.1134,
|
| 285 |
+
"step": 360
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.6065573770491803,
|
| 289 |
+
"grad_norm": 1.1487077474594116,
|
| 290 |
+
"learning_rate": 4.019287292859016e-05,
|
| 291 |
+
"loss": 0.1419,
|
| 292 |
+
"step": 370
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.6229508196721312,
|
| 296 |
+
"grad_norm": 0.8955410718917847,
|
| 297 |
+
"learning_rate": 3.7404838688880446e-05,
|
| 298 |
+
"loss": 0.1339,
|
| 299 |
+
"step": 380
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.639344262295082,
|
| 303 |
+
"grad_norm": 0.7369993925094604,
|
| 304 |
+
"learning_rate": 3.465803700697114e-05,
|
| 305 |
+
"loss": 0.1435,
|
| 306 |
+
"step": 390
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.6557377049180327,
|
| 310 |
+
"grad_norm": 0.4338698089122772,
|
| 311 |
+
"learning_rate": 3.196146003916084e-05,
|
| 312 |
+
"loss": 0.1423,
|
| 313 |
+
"step": 400
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.6557377049180327,
|
| 317 |
+
"eval_loss": 0.13493812084197998,
|
| 318 |
+
"eval_runtime": 62.3222,
|
| 319 |
+
"eval_samples_per_second": 1.091,
|
| 320 |
+
"eval_steps_per_second": 1.091,
|
| 321 |
+
"step": 400
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.6721311475409836,
|
| 325 |
+
"grad_norm": 1.00863516330719,
|
| 326 |
+
"learning_rate": 2.932393552198597e-05,
|
| 327 |
+
"loss": 0.1575,
|
| 328 |
+
"step": 410
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.6885245901639344,
|
| 332 |
+
"grad_norm": 1.1648294925689697,
|
| 333 |
+
"learning_rate": 2.6754097873015148e-05,
|
| 334 |
+
"loss": 0.1372,
|
| 335 |
+
"step": 420
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.7049180327868853,
|
| 339 |
+
"grad_norm": 0.5712903141975403,
|
| 340 |
+
"learning_rate": 2.426035992450848e-05,
|
| 341 |
+
"loss": 0.1293,
|
| 342 |
+
"step": 430
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.7213114754098361,
|
| 346 |
+
"grad_norm": 0.6494749188423157,
|
| 347 |
+
"learning_rate": 2.1850885382476562e-05,
|
| 348 |
+
"loss": 0.1347,
|
| 349 |
+
"step": 440
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.7377049180327869,
|
| 353 |
+
"grad_norm": 0.7962918281555176,
|
| 354 |
+
"learning_rate": 1.9533562101300097e-05,
|
| 355 |
+
"loss": 0.1157,
|
| 356 |
+
"step": 450
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.7540983606557377,
|
| 360 |
+
"grad_norm": 0.7322007417678833,
|
| 361 |
+
"learning_rate": 1.7315976261399696e-05,
|
| 362 |
+
"loss": 0.1339,
|
| 363 |
+
"step": 460
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.7704918032786885,
|
| 367 |
+
"grad_norm": 1.0486736297607422,
|
| 368 |
+
"learning_rate": 1.5205387534490806e-05,
|
| 369 |
+
"loss": 0.1327,
|
| 370 |
+
"step": 470
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.7868852459016393,
|
| 374 |
+
"grad_norm": 0.28778010606765747,
|
| 375 |
+
"learning_rate": 1.3208705317724006e-05,
|
| 376 |
+
"loss": 0.0872,
|
| 377 |
+
"step": 480
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.8032786885245902,
|
| 381 |
+
"grad_norm": 1.064375638961792,
|
| 382 |
+
"learning_rate": 1.1332466114513512e-05,
|
| 383 |
+
"loss": 0.1348,
|
| 384 |
+
"step": 490
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.819672131147541,
|
| 388 |
+
"grad_norm": 0.7255303263664246,
|
| 389 |
+
"learning_rate": 9.582812136100783e-06,
|
| 390 |
+
"loss": 0.1065,
|
| 391 |
+
"step": 500
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.819672131147541,
|
| 395 |
+
"eval_loss": 0.1266276091337204,
|
| 396 |
+
"eval_runtime": 62.2443,
|
| 397 |
+
"eval_samples_per_second": 1.092,
|
| 398 |
+
"eval_steps_per_second": 1.092,
|
| 399 |
+
"step": 500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.8360655737704918,
|
| 403 |
+
"grad_norm": 0.8413804173469543,
|
| 404 |
+
"learning_rate": 7.965471193905954e-06,
|
| 405 |
+
"loss": 0.114,
|
| 406 |
+
"step": 510
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.8524590163934426,
|
| 410 |
+
"grad_norm": 0.9656268954277039,
|
| 411 |
+
"learning_rate": 6.4857379484922375e-06,
|
| 412 |
+
"loss": 0.1114,
|
| 413 |
+
"step": 520
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.8688524590163934,
|
| 417 |
+
"grad_norm": 0.6842993497848511,
|
| 418 |
+
"learning_rate": 5.148456576529081e-06,
|
| 419 |
+
"loss": 0.1265,
|
| 420 |
+
"step": 530
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.8852459016393442,
|
| 424 |
+
"grad_norm": 1.1006067991256714,
|
| 425 |
+
"learning_rate": 3.958004912496127e-06,
|
| 426 |
+
"loss": 0.1418,
|
| 427 |
+
"step": 540
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 0.9016393442622951,
|
| 431 |
+
"grad_norm": 0.8723937273025513,
|
| 432 |
+
"learning_rate": 2.918280117043709e-06,
|
| 433 |
+
"loss": 0.1555,
|
| 434 |
+
"step": 550
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.9180327868852459,
|
| 438 |
+
"grad_norm": 0.810757577419281,
|
| 439 |
+
"learning_rate": 2.032685918926508e-06,
|
| 440 |
+
"loss": 0.1195,
|
| 441 |
+
"step": 560
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.9344262295081968,
|
| 445 |
+
"grad_norm": 1.3418116569519043,
|
| 446 |
+
"learning_rate": 1.3041214722768035e-06,
|
| 447 |
+
"loss": 0.1395,
|
| 448 |
+
"step": 570
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 0.9508196721311475,
|
| 452 |
+
"grad_norm": 0.7165635228157043,
|
| 453 |
+
"learning_rate": 7.349718656945504e-07,
|
| 454 |
+
"loss": 0.1296,
|
| 455 |
+
"step": 580
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 0.9672131147540983,
|
| 459 |
+
"grad_norm": 0.7757364511489868,
|
| 460 |
+
"learning_rate": 3.271003142248652e-07,
|
| 461 |
+
"loss": 0.1411,
|
| 462 |
+
"step": 590
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.9836065573770492,
|
| 466 |
+
"grad_norm": 0.8983824253082275,
|
| 467 |
+
"learning_rate": 8.184205978370996e-08,
|
| 468 |
+
"loss": 0.1174,
|
| 469 |
+
"step": 600
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 0.9836065573770492,
|
| 473 |
+
"eval_loss": 0.12527307868003845,
|
| 474 |
+
"eval_runtime": 62.1952,
|
| 475 |
+
"eval_samples_per_second": 1.093,
|
| 476 |
+
"eval_steps_per_second": 1.093,
|
| 477 |
+
"step": 600
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.0,
|
| 481 |
+
"grad_norm": 0.8321591019630432,
|
| 482 |
+
"learning_rate": 0.0,
|
| 483 |
+
"loss": 0.1184,
|
| 484 |
+
"step": 610
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 1.0,
|
| 488 |
+
"step": 610,
|
| 489 |
+
"total_flos": 1.134915283869696e+16,
|
| 490 |
+
"train_loss": 0.04400509732668517,
|
| 491 |
+
"train_runtime": 2473.793,
|
| 492 |
+
"train_samples_per_second": 0.986,
|
| 493 |
+
"train_steps_per_second": 0.247
|
| 494 |
+
}
|
| 495 |
+
],
|
| 496 |
+
"logging_steps": 10,
|
| 497 |
+
"max_steps": 610,
|
| 498 |
+
"num_input_tokens_seen": 0,
|
| 499 |
+
"num_train_epochs": 1,
|
| 500 |
+
"save_steps": 100,
|
| 501 |
+
"stateful_callbacks": {
|
| 502 |
+
"TrainerControl": {
|
| 503 |
+
"args": {
|
| 504 |
+
"should_epoch_stop": false,
|
| 505 |
+
"should_evaluate": false,
|
| 506 |
+
"should_log": false,
|
| 507 |
+
"should_save": true,
|
| 508 |
+
"should_training_stop": true
|
| 509 |
+
},
|
| 510 |
+
"attributes": {}
|
| 511 |
+
}
|
| 512 |
+
},
|
| 513 |
+
"total_flos": 1.134915283869696e+16,
|
| 514 |
+
"train_batch_size": 1,
|
| 515 |
+
"trial_name": null,
|
| 516 |
+
"trial_params": null
|
| 517 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|