End of training
Browse files- README.md +3 -2
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +524 -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/Qwen2.5-32B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: pretrain
|
|
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# pretrain
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 1.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen2.5-32B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- lora
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: pretrain
|
|
|
|
| 16 |
|
| 17 |
# pretrain
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) on the openreview dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.1076
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9995988768551946,
|
| 3 |
+
"eval_loss": 1.1075533628463745,
|
| 4 |
+
"eval_runtime": 37.4732,
|
| 5 |
+
"eval_samples_per_second": 5.391,
|
| 6 |
+
"eval_steps_per_second": 1.361,
|
| 7 |
+
"perplexity": 3.026943494933559,
|
| 8 |
+
"total_flos": 6308174864842752.0,
|
| 9 |
+
"train_loss": 1.1638640125146074,
|
| 10 |
+
"train_runtime": 6246.6188,
|
| 11 |
+
"train_samples_per_second": 3.192,
|
| 12 |
+
"train_steps_per_second": 0.1
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9995988768551946,
|
| 3 |
+
"eval_loss": 1.1075533628463745,
|
| 4 |
+
"eval_runtime": 37.4732,
|
| 5 |
+
"eval_samples_per_second": 5.391,
|
| 6 |
+
"eval_steps_per_second": 1.361,
|
| 7 |
+
"perplexity": 3.026943494933559
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9995988768551946,
|
| 3 |
+
"total_flos": 6308174864842752.0,
|
| 4 |
+
"train_loss": 1.1638640125146074,
|
| 5 |
+
"train_runtime": 6246.6188,
|
| 6 |
+
"train_samples_per_second": 3.192,
|
| 7 |
+
"train_steps_per_second": 0.1
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,524 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9995988768551946,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 623,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.016044925792218213,
|
| 13 |
+
"grad_norm": 0.07964161388964953,
|
| 14 |
+
"learning_rate": 1.5873015873015873e-06,
|
| 15 |
+
"loss": 1.478,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.032089851584436425,
|
| 20 |
+
"grad_norm": 0.08446800204864474,
|
| 21 |
+
"learning_rate": 3.1746031746031746e-06,
|
| 22 |
+
"loss": 1.4734,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.048134777376654635,
|
| 27 |
+
"grad_norm": 0.0880665470615365,
|
| 28 |
+
"learning_rate": 4.761904761904762e-06,
|
| 29 |
+
"loss": 1.4686,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06417970316887285,
|
| 34 |
+
"grad_norm": 0.11036773606126081,
|
| 35 |
+
"learning_rate": 6.349206349206349e-06,
|
| 36 |
+
"loss": 1.4799,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08022462896109106,
|
| 41 |
+
"grad_norm": 0.1984820440725813,
|
| 42 |
+
"learning_rate": 7.936507936507936e-06,
|
| 43 |
+
"loss": 1.4712,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.09626955475330927,
|
| 48 |
+
"grad_norm": 0.3636876671405763,
|
| 49 |
+
"learning_rate": 9.523809523809525e-06,
|
| 50 |
+
"loss": 1.4479,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.11231448054552748,
|
| 55 |
+
"grad_norm": 0.33961243491902277,
|
| 56 |
+
"learning_rate": 9.996145181203616e-06,
|
| 57 |
+
"loss": 1.3449,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.1283594063377457,
|
| 62 |
+
"grad_norm": 0.11623936014320749,
|
| 63 |
+
"learning_rate": 9.977278743495434e-06,
|
| 64 |
+
"loss": 1.3048,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.1444043321299639,
|
| 69 |
+
"grad_norm": 0.09934569363354419,
|
| 70 |
+
"learning_rate": 9.942751945444437e-06,
|
| 71 |
+
"loss": 1.2392,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.16044925792218212,
|
| 76 |
+
"grad_norm": 0.0749779795039777,
|
| 77 |
+
"learning_rate": 9.892673421130979e-06,
|
| 78 |
+
"loss": 1.2155,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.16044925792218212,
|
| 83 |
+
"eval_loss": 1.2045714855194092,
|
| 84 |
+
"eval_runtime": 36.9278,
|
| 85 |
+
"eval_samples_per_second": 5.47,
|
| 86 |
+
"eval_steps_per_second": 1.381,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.17649418371440032,
|
| 91 |
+
"grad_norm": 0.06497134561472019,
|
| 92 |
+
"learning_rate": 9.827200736119815e-06,
|
| 93 |
+
"loss": 1.2129,
|
| 94 |
+
"step": 110
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.19253910950661854,
|
| 98 |
+
"grad_norm": 0.06149214025937759,
|
| 99 |
+
"learning_rate": 9.746539891700558e-06,
|
| 100 |
+
"loss": 1.1695,
|
| 101 |
+
"step": 120
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.20858403529883673,
|
| 105 |
+
"grad_norm": 0.05334876254417194,
|
| 106 |
+
"learning_rate": 9.650944676731383e-06,
|
| 107 |
+
"loss": 1.162,
|
| 108 |
+
"step": 130
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.22462896109105496,
|
| 112 |
+
"grad_norm": 0.04556668435804944,
|
| 113 |
+
"learning_rate": 9.540715869125407e-06,
|
| 114 |
+
"loss": 1.1491,
|
| 115 |
+
"step": 140
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.24067388688327315,
|
| 119 |
+
"grad_norm": 0.04356126220951498,
|
| 120 |
+
"learning_rate": 9.416200289492092e-06,
|
| 121 |
+
"loss": 1.1358,
|
| 122 |
+
"step": 150
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.2567188126754914,
|
| 126 |
+
"grad_norm": 0.03723127058817997,
|
| 127 |
+
"learning_rate": 9.27778970991129e-06,
|
| 128 |
+
"loss": 1.1338,
|
| 129 |
+
"step": 160
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.27276373846770957,
|
| 133 |
+
"grad_norm": 0.03598344746987169,
|
| 134 |
+
"learning_rate": 9.125919621273348e-06,
|
| 135 |
+
"loss": 1.1333,
|
| 136 |
+
"step": 170
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.2888086642599278,
|
| 140 |
+
"grad_norm": 0.03958997125425865,
|
| 141 |
+
"learning_rate": 8.961067863063638e-06,
|
| 142 |
+
"loss": 1.1382,
|
| 143 |
+
"step": 180
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.304853590052146,
|
| 147 |
+
"grad_norm": 0.033584445768925664,
|
| 148 |
+
"learning_rate": 8.783753119902766e-06,
|
| 149 |
+
"loss": 1.1329,
|
| 150 |
+
"step": 190
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.32089851584436424,
|
| 154 |
+
"grad_norm": 0.0370694089463755,
|
| 155 |
+
"learning_rate": 8.594533289572852e-06,
|
| 156 |
+
"loss": 1.1392,
|
| 157 |
+
"step": 200
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.32089851584436424,
|
| 161 |
+
"eval_loss": 1.1237837076187134,
|
| 162 |
+
"eval_runtime": 36.9468,
|
| 163 |
+
"eval_samples_per_second": 5.467,
|
| 164 |
+
"eval_steps_per_second": 1.38,
|
| 165 |
+
"step": 200
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.3369434416365824,
|
| 169 |
+
"grad_norm": 0.031404112904854176,
|
| 170 |
+
"learning_rate": 8.39400372766471e-06,
|
| 171 |
+
"loss": 1.1338,
|
| 172 |
+
"step": 210
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.35298836742880063,
|
| 176 |
+
"grad_norm": 0.03068751780314738,
|
| 177 |
+
"learning_rate": 8.182795374368893e-06,
|
| 178 |
+
"loss": 1.1313,
|
| 179 |
+
"step": 220
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.36903329322101885,
|
| 183 |
+
"grad_norm": 0.030467037926615172,
|
| 184 |
+
"learning_rate": 7.961572769304437e-06,
|
| 185 |
+
"loss": 1.1247,
|
| 186 |
+
"step": 230
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.3850782190132371,
|
| 190 |
+
"grad_norm": 0.030773507709064975,
|
| 191 |
+
"learning_rate": 7.731031960631354e-06,
|
| 192 |
+
"loss": 1.1318,
|
| 193 |
+
"step": 240
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.4011231448054553,
|
| 197 |
+
"grad_norm": 0.033328095202181884,
|
| 198 |
+
"learning_rate": 7.491898315025615e-06,
|
| 199 |
+
"loss": 1.1249,
|
| 200 |
+
"step": 250
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.41716807059767347,
|
| 204 |
+
"grad_norm": 0.03128616232047187,
|
| 205 |
+
"learning_rate": 7.244924235407224e-06,
|
| 206 |
+
"loss": 1.1162,
|
| 207 |
+
"step": 260
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.4332129963898917,
|
| 211 |
+
"grad_norm": 0.031188168038119562,
|
| 212 |
+
"learning_rate": 6.990886793602268e-06,
|
| 213 |
+
"loss": 1.1133,
|
| 214 |
+
"step": 270
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.4492579221821099,
|
| 218 |
+
"grad_norm": 0.03333159876932075,
|
| 219 |
+
"learning_rate": 6.730585285387465e-06,
|
| 220 |
+
"loss": 1.1056,
|
| 221 |
+
"step": 280
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.46530284797432814,
|
| 225 |
+
"grad_norm": 0.0316593444984735,
|
| 226 |
+
"learning_rate": 6.464838715609945e-06,
|
| 227 |
+
"loss": 1.1266,
|
| 228 |
+
"step": 290
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.4813477737665463,
|
| 232 |
+
"grad_norm": 0.03167501381379994,
|
| 233 |
+
"learning_rate": 6.194483221294989e-06,
|
| 234 |
+
"loss": 1.1181,
|
| 235 |
+
"step": 300
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.4813477737665463,
|
| 239 |
+
"eval_loss": 1.1140353679656982,
|
| 240 |
+
"eval_runtime": 36.7217,
|
| 241 |
+
"eval_samples_per_second": 5.501,
|
| 242 |
+
"eval_steps_per_second": 1.389,
|
| 243 |
+
"step": 300
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.49739269955876453,
|
| 247 |
+
"grad_norm": 0.03328370476401871,
|
| 248 |
+
"learning_rate": 5.920369440849609e-06,
|
| 249 |
+
"loss": 1.0962,
|
| 250 |
+
"step": 310
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.5134376253509828,
|
| 254 |
+
"grad_norm": 0.03447585267125308,
|
| 255 |
+
"learning_rate": 5.643359837639419e-06,
|
| 256 |
+
"loss": 1.1171,
|
| 257 |
+
"step": 320
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.529482551143201,
|
| 261 |
+
"grad_norm": 0.03781496580664963,
|
| 262 |
+
"learning_rate": 5.3643259863598015e-06,
|
| 263 |
+
"loss": 1.1091,
|
| 264 |
+
"step": 330
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.5455274769354191,
|
| 268 |
+
"grad_norm": 0.03172320948571133,
|
| 269 |
+
"learning_rate": 5.084145830739462e-06,
|
| 270 |
+
"loss": 1.1017,
|
| 271 |
+
"step": 340
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.5615724027276374,
|
| 275 |
+
"grad_norm": 0.03412876166847143,
|
| 276 |
+
"learning_rate": 4.803700921204659e-06,
|
| 277 |
+
"loss": 1.1169,
|
| 278 |
+
"step": 350
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.5776173285198556,
|
| 282 |
+
"grad_norm": 0.03375281781263732,
|
| 283 |
+
"learning_rate": 4.5238736411954075e-06,
|
| 284 |
+
"loss": 1.0998,
|
| 285 |
+
"step": 360
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.5936622543120738,
|
| 289 |
+
"grad_norm": 0.03717435838572482,
|
| 290 |
+
"learning_rate": 4.245544430860743e-06,
|
| 291 |
+
"loss": 1.1117,
|
| 292 |
+
"step": 370
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.609707180104292,
|
| 296 |
+
"grad_norm": 0.029559551388140908,
|
| 297 |
+
"learning_rate": 3.969589016868269e-06,
|
| 298 |
+
"loss": 1.1283,
|
| 299 |
+
"step": 380
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.6257521058965102,
|
| 303 |
+
"grad_norm": 0.04200189123455742,
|
| 304 |
+
"learning_rate": 3.6968756570440735e-06,
|
| 305 |
+
"loss": 1.1228,
|
| 306 |
+
"step": 390
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.6417970316887285,
|
| 310 |
+
"grad_norm": 0.03378722314455019,
|
| 311 |
+
"learning_rate": 3.42826240851239e-06,
|
| 312 |
+
"loss": 1.1252,
|
| 313 |
+
"step": 400
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.6417970316887285,
|
| 317 |
+
"eval_loss": 1.1096988916397095,
|
| 318 |
+
"eval_runtime": 36.792,
|
| 319 |
+
"eval_samples_per_second": 5.49,
|
| 320 |
+
"eval_steps_per_second": 1.386,
|
| 321 |
+
"step": 400
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.6578419574809466,
|
| 325 |
+
"grad_norm": 0.03734682816128997,
|
| 326 |
+
"learning_rate": 3.1645944279304296e-06,
|
| 327 |
+
"loss": 1.1085,
|
| 328 |
+
"step": 410
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.6738868832731648,
|
| 332 |
+
"grad_norm": 0.06074049582614517,
|
| 333 |
+
"learning_rate": 2.906701312312861e-06,
|
| 334 |
+
"loss": 1.0973,
|
| 335 |
+
"step": 420
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.6899318090653831,
|
| 339 |
+
"grad_norm": 0.03310219959096242,
|
| 340 |
+
"learning_rate": 2.6553944888126772e-06,
|
| 341 |
+
"loss": 1.0965,
|
| 342 |
+
"step": 430
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.7059767348576013,
|
| 346 |
+
"grad_norm": 0.036021492275449166,
|
| 347 |
+
"learning_rate": 2.4114646616711844e-06,
|
| 348 |
+
"loss": 1.1028,
|
| 349 |
+
"step": 440
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.7220216606498195,
|
| 353 |
+
"grad_norm": 0.03370764681001696,
|
| 354 |
+
"learning_rate": 2.175679324369913e-06,
|
| 355 |
+
"loss": 1.1094,
|
| 356 |
+
"step": 450
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.7380665864420377,
|
| 360 |
+
"grad_norm": 0.032620569117429374,
|
| 361 |
+
"learning_rate": 1.948780344812181e-06,
|
| 362 |
+
"loss": 1.103,
|
| 363 |
+
"step": 460
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.7541115122342559,
|
| 367 |
+
"grad_norm": 0.03518623684780172,
|
| 368 |
+
"learning_rate": 1.7314816311322219e-06,
|
| 369 |
+
"loss": 1.1019,
|
| 370 |
+
"step": 470
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.7701564380264742,
|
| 374 |
+
"grad_norm": 0.033154472751256124,
|
| 375 |
+
"learning_rate": 1.5244668854760459e-06,
|
| 376 |
+
"loss": 1.1025,
|
| 377 |
+
"step": 480
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.7862013638186923,
|
| 381 |
+
"grad_norm": 0.03282196969531501,
|
| 382 |
+
"learning_rate": 1.3283874528215735e-06,
|
| 383 |
+
"loss": 1.0912,
|
| 384 |
+
"step": 490
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.8022462896109106,
|
| 388 |
+
"grad_norm": 0.03261545464797978,
|
| 389 |
+
"learning_rate": 1.143860271606333e-06,
|
| 390 |
+
"loss": 1.1199,
|
| 391 |
+
"step": 500
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.8022462896109106,
|
| 395 |
+
"eval_loss": 1.1079450845718384,
|
| 396 |
+
"eval_runtime": 37.0687,
|
| 397 |
+
"eval_samples_per_second": 5.449,
|
| 398 |
+
"eval_steps_per_second": 1.376,
|
| 399 |
+
"step": 500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.8182912154031288,
|
| 403 |
+
"grad_norm": 0.03521866325178647,
|
| 404 |
+
"learning_rate": 9.714659326109138e-07,
|
| 405 |
+
"loss": 1.1117,
|
| 406 |
+
"step": 510
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.8343361411953469,
|
| 410 |
+
"grad_norm": 0.03534230366225303,
|
| 411 |
+
"learning_rate": 8.117468522055578e-07,
|
| 412 |
+
"loss": 1.1197,
|
| 413 |
+
"step": 520
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.8503810669875652,
|
| 417 |
+
"grad_norm": 0.03192663388371955,
|
| 418 |
+
"learning_rate": 6.652055657075845e-07,
|
| 419 |
+
"loss": 1.1212,
|
| 420 |
+
"step": 530
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.8664259927797834,
|
| 424 |
+
"grad_norm": 0.03381094832008424,
|
| 425 |
+
"learning_rate": 5.323031462193757e-07,
|
| 426 |
+
"loss": 1.1147,
|
| 427 |
+
"step": 540
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 0.8824709185720016,
|
| 431 |
+
"grad_norm": 0.0312520726762653,
|
| 432 |
+
"learning_rate": 4.134577539217965e-07,
|
| 433 |
+
"loss": 1.1094,
|
| 434 |
+
"step": 550
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.8985158443642198,
|
| 438 |
+
"grad_norm": 0.031196657419516906,
|
| 439 |
+
"learning_rate": 3.0904332038757977e-07,
|
| 440 |
+
"loss": 1.1008,
|
| 441 |
+
"step": 560
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.914560770156438,
|
| 445 |
+
"grad_norm": 0.03159621090668423,
|
| 446 |
+
"learning_rate": 2.1938837205424002e-07,
|
| 447 |
+
"loss": 1.1146,
|
| 448 |
+
"step": 570
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 0.9306056959486563,
|
| 452 |
+
"grad_norm": 0.03478277084648844,
|
| 453 |
+
"learning_rate": 1.4477499655837278e-07,
|
| 454 |
+
"loss": 1.1122,
|
| 455 |
+
"step": 580
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 0.9466506217408744,
|
| 459 |
+
"grad_norm": 0.03684852374687432,
|
| 460 |
+
"learning_rate": 8.543795518357767e-08,
|
| 461 |
+
"loss": 1.1185,
|
| 462 |
+
"step": 590
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.9626955475330926,
|
| 466 |
+
"grad_norm": 0.03649848908454171,
|
| 467 |
+
"learning_rate": 4.15639442146093e-08,
|
| 468 |
+
"loss": 1.1104,
|
| 469 |
+
"step": 600
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 0.9626955475330926,
|
| 473 |
+
"eval_loss": 1.107527494430542,
|
| 474 |
+
"eval_runtime": 36.8485,
|
| 475 |
+
"eval_samples_per_second": 5.482,
|
| 476 |
+
"eval_steps_per_second": 1.384,
|
| 477 |
+
"step": 600
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.9787404733253109,
|
| 481 |
+
"grad_norm": 0.032198270473962474,
|
| 482 |
+
"learning_rate": 1.3291007521799015e-08,
|
| 483 |
+
"loss": 1.1028,
|
| 484 |
+
"step": 610
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.9947853991175291,
|
| 488 |
+
"grad_norm": 0.0365869343105355,
|
| 489 |
+
"learning_rate": 7.081022239591173e-10,
|
| 490 |
+
"loss": 1.1179,
|
| 491 |
+
"step": 620
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.9995988768551946,
|
| 495 |
+
"step": 623,
|
| 496 |
+
"total_flos": 6308174864842752.0,
|
| 497 |
+
"train_loss": 1.1638640125146074,
|
| 498 |
+
"train_runtime": 6246.6188,
|
| 499 |
+
"train_samples_per_second": 3.192,
|
| 500 |
+
"train_steps_per_second": 0.1
|
| 501 |
+
}
|
| 502 |
+
],
|
| 503 |
+
"logging_steps": 10,
|
| 504 |
+
"max_steps": 623,
|
| 505 |
+
"num_input_tokens_seen": 0,
|
| 506 |
+
"num_train_epochs": 1,
|
| 507 |
+
"save_steps": 500,
|
| 508 |
+
"stateful_callbacks": {
|
| 509 |
+
"TrainerControl": {
|
| 510 |
+
"args": {
|
| 511 |
+
"should_epoch_stop": false,
|
| 512 |
+
"should_evaluate": false,
|
| 513 |
+
"should_log": false,
|
| 514 |
+
"should_save": true,
|
| 515 |
+
"should_training_stop": true
|
| 516 |
+
},
|
| 517 |
+
"attributes": {}
|
| 518 |
+
}
|
| 519 |
+
},
|
| 520 |
+
"total_flos": 6308174864842752.0,
|
| 521 |
+
"train_batch_size": 2,
|
| 522 |
+
"trial_name": null,
|
| 523 |
+
"trial_params": null
|
| 524 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|