Model save
Browse files- README.md +18 -24
- adapter_config.json +4 -4
- all_results.json +6 -11
- runs/Jun10_11-43-03_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1717987400.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.73754.0 +2 -2
- runs/Jun10_14-00-49_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1717995664.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.77116.0 +3 -0
- train_results.json +6 -6
- trainer_state.json +648 -1654
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -2,13 +2,12 @@
|
|
| 2 |
license: gemma
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
| 5 |
-
- alignment-handbook
|
| 6 |
- trl
|
| 7 |
- sft
|
| 8 |
- generated_from_trainer
|
| 9 |
base_model: google/gemma-2b
|
| 10 |
datasets:
|
| 11 |
-
-
|
| 12 |
model-index:
|
| 13 |
- name: gemma2b-summarize-gpt4o-64k
|
| 14 |
results: []
|
|
@@ -19,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
|
| 20 |
# gemma2b-summarize-gpt4o-64k
|
| 21 |
|
| 22 |
-
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
-
- Loss: 2.
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -41,38 +40,33 @@ More information needed
|
|
| 41 |
|
| 42 |
The following hyperparameters were used during training:
|
| 43 |
- learning_rate: 0.0002
|
| 44 |
-
- train_batch_size:
|
| 45 |
-
- eval_batch_size:
|
| 46 |
- seed: 42
|
| 47 |
- distributed_type: multi-GPU
|
| 48 |
- num_devices: 3
|
| 49 |
- gradient_accumulation_steps: 2
|
| 50 |
-
- total_train_batch_size:
|
| 51 |
-
- total_eval_batch_size:
|
| 52 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 53 |
- lr_scheduler_type: cosine
|
| 54 |
- lr_scheduler_warmup_ratio: 0.1
|
| 55 |
-
- num_epochs:
|
| 56 |
|
| 57 |
### Training results
|
| 58 |
|
| 59 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 60 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 61 |
-
| 1.
|
| 62 |
-
| 1.
|
| 63 |
-
| 1.
|
| 64 |
-
| 1.
|
| 65 |
-
| 1.
|
| 66 |
-
|
|
| 67 |
-
|
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.952 | 11.0 | 1606 | 2.5889 |
|
| 72 |
-
| 0.97 | 12.0 | 1752 | 2.5957 |
|
| 73 |
-
| 0.9514 | 13.0 | 1898 | 2.5988 |
|
| 74 |
-
| 0.9469 | 14.0 | 2044 | 2.5997 |
|
| 75 |
-
| 0.9469 | 15.0 | 2190 | 2.5990 |
|
| 76 |
|
| 77 |
|
| 78 |
### Framework versions
|
|
|
|
| 2 |
license: gemma
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
|
|
|
| 5 |
- trl
|
| 6 |
- sft
|
| 7 |
- generated_from_trainer
|
| 8 |
base_model: google/gemma-2b
|
| 9 |
datasets:
|
| 10 |
+
- generator
|
| 11 |
model-index:
|
| 12 |
- name: gemma2b-summarize-gpt4o-64k
|
| 13 |
results: []
|
|
|
|
| 18 |
|
| 19 |
# gemma2b-summarize-gpt4o-64k
|
| 20 |
|
| 21 |
+
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the generator dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 2.6852
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 40 |
|
| 41 |
The following hyperparameters were used during training:
|
| 42 |
- learning_rate: 0.0002
|
| 43 |
+
- train_batch_size: 16
|
| 44 |
+
- eval_batch_size: 16
|
| 45 |
- seed: 42
|
| 46 |
- distributed_type: multi-GPU
|
| 47 |
- num_devices: 3
|
| 48 |
- gradient_accumulation_steps: 2
|
| 49 |
+
- total_train_batch_size: 96
|
| 50 |
+
- total_eval_batch_size: 48
|
| 51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
- lr_scheduler_type: cosine
|
| 53 |
- lr_scheduler_warmup_ratio: 0.1
|
| 54 |
+
- num_epochs: 10
|
| 55 |
|
| 56 |
### Training results
|
| 57 |
|
| 58 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 59 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 60 |
+
| 1.2474 | 1.0 | 146 | 2.5237 |
|
| 61 |
+
| 1.1269 | 2.0 | 292 | 2.4805 |
|
| 62 |
+
| 1.0909 | 3.0 | 438 | 2.4893 |
|
| 63 |
+
| 1.0354 | 4.0 | 584 | 2.5017 |
|
| 64 |
+
| 1.0016 | 5.0 | 730 | 2.5295 |
|
| 65 |
+
| 0.9823 | 6.0 | 876 | 2.5500 |
|
| 66 |
+
| 0.955 | 7.0 | 1022 | 2.5866 |
|
| 67 |
+
| 0.9214 | 8.0 | 1168 | 2.6224 |
|
| 68 |
+
| 0.913 | 9.0 | 1314 | 2.6512 |
|
| 69 |
+
| 0.889 | 10.0 | 1460 | 2.6852 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
|
| 71 |
|
| 72 |
### Framework versions
|
adapter_config.json
CHANGED
|
@@ -20,13 +20,13 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"up_proj",
|
| 24 |
-
"q_proj",
|
| 25 |
"down_proj",
|
|
|
|
| 26 |
"v_proj",
|
| 27 |
"gate_proj",
|
| 28 |
-
"
|
| 29 |
-
"
|
|
|
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
|
|
|
| 23 |
"down_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
"v_proj",
|
| 26 |
"gate_proj",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"up_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
all_results.json
CHANGED
|
@@ -1,14 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"eval_samples_per_second": 18.818,
|
| 7 |
-
"eval_steps_per_second": 1.882,
|
| 8 |
-
"total_flos": 1.2863476116823736e+18,
|
| 9 |
-
"train_loss": 1.080002195214572,
|
| 10 |
-
"train_runtime": 11705.6736,
|
| 11 |
"train_samples": 64610,
|
| 12 |
-
"train_samples_per_second":
|
| 13 |
-
"train_steps_per_second":
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.273972602739725,
|
| 3 |
+
"total_flos": 8.853977907740017e+17,
|
| 4 |
+
"train_loss": 0.0,
|
| 5 |
+
"train_runtime": 2.8738,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"train_samples": 64610,
|
| 7 |
+
"train_samples_per_second": 24365.255,
|
| 8 |
+
"train_steps_per_second": 508.044
|
| 9 |
}
|
runs/Jun10_11-43-03_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1717987400.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.73754.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1586b8aacbaee33c4b5a35a3ebcad1ef834b46c289f437e3d88dc880170926c
|
| 3 |
+
size 72136
|
runs/Jun10_14-00-49_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1717995664.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.77116.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eca5cc643fd868cfbd2abee5fdc3b9696c593af3b2e02ff5bd0c6c2f8aeae47a
|
| 3 |
+
size 5953
|
train_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss":
|
| 5 |
-
"train_runtime":
|
| 6 |
"train_samples": 64610,
|
| 7 |
-
"train_samples_per_second":
|
| 8 |
-
"train_steps_per_second":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.273972602739725,
|
| 3 |
+
"total_flos": 8.853977907740017e+17,
|
| 4 |
+
"train_loss": 0.0,
|
| 5 |
+
"train_runtime": 2.8738,
|
| 6 |
"train_samples": 64610,
|
| 7 |
+
"train_samples_per_second": 24365.255,
|
| 8 |
+
"train_steps_per_second": 508.044
|
| 9 |
}
|
trainer_state.json
CHANGED
|
@@ -1,3220 +1,2214 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.00684931506849315,
|
| 13 |
-
"grad_norm":
|
| 14 |
"learning_rate": 9.132420091324201e-07,
|
| 15 |
"loss": 3.0017,
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.03424657534246575,
|
| 20 |
-
"grad_norm":
|
| 21 |
"learning_rate": 4.566210045662101e-06,
|
| 22 |
-
"loss": 3.
|
| 23 |
"step": 5
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.0684931506849315,
|
| 27 |
-
"grad_norm":
|
| 28 |
"learning_rate": 9.132420091324201e-06,
|
| 29 |
-
"loss": 3.
|
| 30 |
"step": 10
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.10273972602739725,
|
| 34 |
-
"grad_norm":
|
| 35 |
"learning_rate": 1.3698630136986302e-05,
|
| 36 |
-
"loss": 3.
|
| 37 |
"step": 15
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.136986301369863,
|
| 41 |
-
"grad_norm": 2.
|
| 42 |
"learning_rate": 1.8264840182648402e-05,
|
| 43 |
-
"loss":
|
| 44 |
"step": 20
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.17123287671232876,
|
| 48 |
-
"grad_norm":
|
| 49 |
"learning_rate": 2.2831050228310503e-05,
|
| 50 |
-
"loss": 2.
|
| 51 |
"step": 25
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.2054794520547945,
|
| 55 |
-
"grad_norm":
|
| 56 |
"learning_rate": 2.7397260273972603e-05,
|
| 57 |
-
"loss": 2.
|
| 58 |
"step": 30
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.23972602739726026,
|
| 62 |
-
"grad_norm": 1.
|
| 63 |
"learning_rate": 3.1963470319634704e-05,
|
| 64 |
-
"loss": 2.
|
| 65 |
"step": 35
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.273972602739726,
|
| 69 |
-
"grad_norm": 1.
|
| 70 |
"learning_rate": 3.6529680365296805e-05,
|
| 71 |
-
"loss": 2.
|
| 72 |
"step": 40
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.3082191780821918,
|
| 76 |
-
"grad_norm":
|
| 77 |
"learning_rate": 4.1095890410958905e-05,
|
| 78 |
-
"loss": 2.
|
| 79 |
"step": 45
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.3424657534246575,
|
| 83 |
-
"grad_norm": 1.
|
| 84 |
"learning_rate": 4.5662100456621006e-05,
|
| 85 |
-
"loss": 2.
|
| 86 |
"step": 50
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.3767123287671233,
|
| 90 |
-
"grad_norm": 1.
|
| 91 |
"learning_rate": 5.0228310502283106e-05,
|
| 92 |
-
"loss":
|
| 93 |
"step": 55
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.410958904109589,
|
| 97 |
-
"grad_norm":
|
| 98 |
"learning_rate": 5.479452054794521e-05,
|
| 99 |
-
"loss":
|
| 100 |
"step": 60
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.4452054794520548,
|
| 104 |
-
"grad_norm":
|
| 105 |
"learning_rate": 5.936073059360731e-05,
|
| 106 |
-
"loss": 1.
|
| 107 |
"step": 65
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.4794520547945205,
|
| 111 |
-
"grad_norm": 0.
|
| 112 |
"learning_rate": 6.392694063926941e-05,
|
| 113 |
-
"loss": 1.
|
| 114 |
"step": 70
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.5136986301369864,
|
| 118 |
-
"grad_norm":
|
| 119 |
"learning_rate": 6.84931506849315e-05,
|
| 120 |
-
"loss": 1.
|
| 121 |
"step": 75
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.547945205479452,
|
| 125 |
-
"grad_norm": 0.
|
| 126 |
"learning_rate": 7.305936073059361e-05,
|
| 127 |
-
"loss": 1.
|
| 128 |
"step": 80
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.5821917808219178,
|
| 132 |
-
"grad_norm": 0.
|
| 133 |
"learning_rate": 7.76255707762557e-05,
|
| 134 |
-
"loss": 1.
|
| 135 |
"step": 85
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.6164383561643836,
|
| 139 |
-
"grad_norm": 0.
|
| 140 |
"learning_rate": 8.219178082191781e-05,
|
| 141 |
-
"loss": 1.
|
| 142 |
"step": 90
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.6506849315068494,
|
| 146 |
-
"grad_norm": 0.
|
| 147 |
"learning_rate": 8.67579908675799e-05,
|
| 148 |
-
"loss": 1.
|
| 149 |
"step": 95
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.684931506849315,
|
| 153 |
-
"grad_norm": 0.
|
| 154 |
"learning_rate": 9.132420091324201e-05,
|
| 155 |
-
"loss": 1.
|
| 156 |
"step": 100
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 0.7191780821917808,
|
| 160 |
-
"grad_norm": 0.
|
| 161 |
"learning_rate": 9.58904109589041e-05,
|
| 162 |
-
"loss": 1.
|
| 163 |
"step": 105
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 0.7534246575342466,
|
| 167 |
-
"grad_norm": 0.
|
| 168 |
"learning_rate": 0.00010045662100456621,
|
| 169 |
-
"loss": 1.
|
| 170 |
"step": 110
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.7876712328767124,
|
| 174 |
-
"grad_norm": 0.
|
| 175 |
"learning_rate": 0.00010502283105022832,
|
| 176 |
-
"loss": 1.
|
| 177 |
"step": 115
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.821917808219178,
|
| 181 |
-
"grad_norm": 0.
|
| 182 |
"learning_rate": 0.00010958904109589041,
|
| 183 |
-
"loss": 1.
|
| 184 |
"step": 120
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 0.8561643835616438,
|
| 188 |
-
"grad_norm": 0.
|
| 189 |
"learning_rate": 0.00011415525114155252,
|
| 190 |
-
"loss": 1.
|
| 191 |
"step": 125
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 0.8904109589041096,
|
| 195 |
-
"grad_norm": 0.
|
| 196 |
"learning_rate": 0.00011872146118721462,
|
| 197 |
-
"loss": 1.
|
| 198 |
"step": 130
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 0.9246575342465754,
|
| 202 |
-
"grad_norm": 0.
|
| 203 |
"learning_rate": 0.0001232876712328767,
|
| 204 |
-
"loss": 1.
|
| 205 |
"step": 135
|
| 206 |
},
|
| 207 |
{
|
| 208 |
"epoch": 0.958904109589041,
|
| 209 |
-
"grad_norm": 0.
|
| 210 |
"learning_rate": 0.00012785388127853882,
|
| 211 |
-
"loss": 1.
|
| 212 |
"step": 140
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 0.9931506849315068,
|
| 216 |
-
"grad_norm": 0.
|
| 217 |
"learning_rate": 0.00013242009132420092,
|
| 218 |
-
"loss": 1.
|
| 219 |
"step": 145
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 1.0,
|
| 223 |
-
"eval_loss": 2.
|
| 224 |
-
"eval_runtime": 0.
|
| 225 |
-
"eval_samples_per_second":
|
| 226 |
-
"eval_steps_per_second": 1.
|
| 227 |
"step": 146
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 1.0273972602739727,
|
| 231 |
-
"grad_norm": 0.
|
| 232 |
"learning_rate": 0.000136986301369863,
|
| 233 |
-
"loss": 1.
|
| 234 |
"step": 150
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 1.0616438356164384,
|
| 238 |
-
"grad_norm": 0.
|
| 239 |
"learning_rate": 0.0001415525114155251,
|
| 240 |
-
"loss": 1.
|
| 241 |
"step": 155
|
| 242 |
},
|
| 243 |
{
|
| 244 |
"epoch": 1.095890410958904,
|
| 245 |
-
"grad_norm": 0.
|
| 246 |
"learning_rate": 0.00014611872146118722,
|
| 247 |
-
"loss": 1.
|
| 248 |
"step": 160
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 1.13013698630137,
|
| 252 |
-
"grad_norm": 0.
|
| 253 |
"learning_rate": 0.00015068493150684933,
|
| 254 |
-
"loss": 1.
|
| 255 |
"step": 165
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 1.1643835616438356,
|
| 259 |
-
"grad_norm": 0.
|
| 260 |
"learning_rate": 0.0001552511415525114,
|
| 261 |
-
"loss": 1.
|
| 262 |
"step": 170
|
| 263 |
},
|
| 264 |
{
|
| 265 |
"epoch": 1.1986301369863013,
|
| 266 |
-
"grad_norm": 0.
|
| 267 |
"learning_rate": 0.00015981735159817351,
|
| 268 |
-
"loss": 1.
|
| 269 |
"step": 175
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 1.2328767123287672,
|
| 273 |
-
"grad_norm": 0.
|
| 274 |
"learning_rate": 0.00016438356164383562,
|
| 275 |
-
"loss": 1.
|
| 276 |
"step": 180
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 1.2671232876712328,
|
| 280 |
-
"grad_norm": 0.
|
| 281 |
"learning_rate": 0.00016894977168949773,
|
| 282 |
-
"loss": 1.
|
| 283 |
"step": 185
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"epoch": 1.3013698630136985,
|
| 287 |
-
"grad_norm": 0.
|
| 288 |
"learning_rate": 0.0001735159817351598,
|
| 289 |
-
"loss": 1.
|
| 290 |
"step": 190
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 1.3356164383561644,
|
| 294 |
-
"grad_norm": 0.
|
| 295 |
"learning_rate": 0.00017808219178082192,
|
| 296 |
-
"loss": 1.
|
| 297 |
"step": 195
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 1.36986301369863,
|
| 301 |
-
"grad_norm":
|
| 302 |
"learning_rate": 0.00018264840182648402,
|
| 303 |
-
"loss": 1.
|
| 304 |
"step": 200
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 1.404109589041096,
|
| 308 |
-
"grad_norm":
|
| 309 |
"learning_rate": 0.00018721461187214613,
|
| 310 |
-
"loss": 1.
|
| 311 |
"step": 205
|
| 312 |
},
|
| 313 |
{
|
| 314 |
"epoch": 1.4383561643835616,
|
| 315 |
-
"grad_norm": 0.
|
| 316 |
"learning_rate": 0.0001917808219178082,
|
| 317 |
-
"loss": 1.
|
| 318 |
"step": 210
|
| 319 |
},
|
| 320 |
{
|
| 321 |
"epoch": 1.4726027397260273,
|
| 322 |
-
"grad_norm": 0.
|
| 323 |
"learning_rate": 0.00019634703196347032,
|
| 324 |
-
"loss": 1.
|
| 325 |
"step": 215
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 1.5068493150684932,
|
| 329 |
-
"grad_norm": 0.
|
| 330 |
"learning_rate": 0.00019999987297289245,
|
| 331 |
-
"loss": 1.
|
| 332 |
"step": 220
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 1.541095890410959,
|
| 336 |
-
"grad_norm": 0.
|
| 337 |
"learning_rate": 0.00019999542705801296,
|
| 338 |
-
"loss": 1.
|
| 339 |
"step": 225
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 1.5753424657534247,
|
| 343 |
-
"grad_norm": 0.
|
| 344 |
"learning_rate": 0.00019998463011046926,
|
| 345 |
-
"loss": 1.
|
| 346 |
"step": 230
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 1.6095890410958904,
|
| 350 |
-
"grad_norm":
|
| 351 |
"learning_rate": 0.00019996748281601038,
|
| 352 |
-
"loss": 1.
|
| 353 |
"step": 235
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 1.643835616438356,
|
| 357 |
-
"grad_norm":
|
| 358 |
"learning_rate": 0.00019994398626371643,
|
| 359 |
-
"loss": 1.
|
| 360 |
"step": 240
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 1.678082191780822,
|
| 364 |
-
"grad_norm": 0.
|
| 365 |
"learning_rate": 0.0001999141419459293,
|
| 366 |
-
"loss": 1.
|
| 367 |
"step": 245
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"epoch": 1.7123287671232876,
|
| 371 |
-
"grad_norm": 0.
|
| 372 |
"learning_rate": 0.00019987795175815807,
|
| 373 |
-
"loss": 1.
|
| 374 |
"step": 250
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 1.7465753424657535,
|
| 378 |
-
"grad_norm": 0.
|
| 379 |
"learning_rate": 0.0001998354179989585,
|
| 380 |
-
"loss": 1.
|
| 381 |
"step": 255
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 1.7808219178082192,
|
| 385 |
-
"grad_norm": 0.
|
| 386 |
"learning_rate": 0.0001997865433697871,
|
| 387 |
-
"loss": 1.
|
| 388 |
"step": 260
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 1.8150684931506849,
|
| 392 |
-
"grad_norm": 0.
|
| 393 |
"learning_rate": 0.00019973133097482947,
|
| 394 |
-
"loss": 1.
|
| 395 |
"step": 265
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 1.8493150684931505,
|
| 399 |
-
"grad_norm": 0.
|
| 400 |
"learning_rate": 0.00019966978432080316,
|
| 401 |
-
"loss": 1.
|
| 402 |
"step": 270
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 1.8835616438356164,
|
| 406 |
-
"grad_norm": 0.
|
| 407 |
"learning_rate": 0.00019960190731673505,
|
| 408 |
-
"loss": 1.
|
| 409 |
"step": 275
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"epoch": 1.9178082191780823,
|
| 413 |
-
"grad_norm": 0.
|
| 414 |
"learning_rate": 0.00019952770427371304,
|
| 415 |
-
"loss": 1.
|
| 416 |
"step": 280
|
| 417 |
},
|
| 418 |
{
|
| 419 |
"epoch": 1.952054794520548,
|
| 420 |
-
"grad_norm": 0.
|
| 421 |
"learning_rate": 0.00019944717990461207,
|
| 422 |
-
"loss": 1.
|
| 423 |
"step": 285
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 1.9863013698630136,
|
| 427 |
-
"grad_norm": 0.
|
| 428 |
"learning_rate": 0.00019936033932379504,
|
| 429 |
-
"loss": 1.
|
| 430 |
"step": 290
|
| 431 |
},
|
| 432 |
{
|
| 433 |
"epoch": 2.0,
|
| 434 |
-
"eval_loss": 2.
|
| 435 |
-
"eval_runtime": 0.
|
| 436 |
-
"eval_samples_per_second":
|
| 437 |
-
"eval_steps_per_second": 1.
|
| 438 |
"step": 292
|
| 439 |
},
|
| 440 |
{
|
| 441 |
"epoch": 2.0205479452054793,
|
| 442 |
-
"grad_norm": 0.
|
| 443 |
"learning_rate": 0.00019926718804678785,
|
| 444 |
-
"loss": 1.
|
| 445 |
"step": 295
|
| 446 |
},
|
| 447 |
{
|
| 448 |
"epoch": 2.0547945205479454,
|
| 449 |
-
"grad_norm": 0.
|
| 450 |
"learning_rate": 0.000199167731989929,
|
| 451 |
-
"loss": 1.
|
| 452 |
"step": 300
|
| 453 |
},
|
| 454 |
{
|
| 455 |
"epoch": 2.089041095890411,
|
| 456 |
-
"grad_norm": 0.
|
| 457 |
"learning_rate": 0.00019906197746999408,
|
| 458 |
-
"loss": 1.
|
| 459 |
"step": 305
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 2.1232876712328768,
|
| 463 |
-
"grad_norm": 0.
|
| 464 |
"learning_rate": 0.00019894993120379435,
|
| 465 |
-
"loss": 1.
|
| 466 |
"step": 310
|
| 467 |
},
|
| 468 |
{
|
| 469 |
"epoch": 2.1575342465753424,
|
| 470 |
-
"grad_norm": 0.
|
| 471 |
"learning_rate": 0.00019883160030775016,
|
| 472 |
-
"loss": 1.
|
| 473 |
"step": 315
|
| 474 |
},
|
| 475 |
{
|
| 476 |
"epoch": 2.191780821917808,
|
| 477 |
-
"grad_norm": 0.
|
| 478 |
"learning_rate": 0.00019870699229743911,
|
| 479 |
-
"loss": 1.
|
| 480 |
"step": 320
|
| 481 |
},
|
| 482 |
{
|
| 483 |
"epoch": 2.2260273972602738,
|
| 484 |
-
"grad_norm": 0.
|
| 485 |
"learning_rate": 0.0001985761150871185,
|
| 486 |
-
"loss": 1.
|
| 487 |
"step": 325
|
| 488 |
},
|
| 489 |
{
|
| 490 |
"epoch": 2.26027397260274,
|
| 491 |
-
"grad_norm": 0.
|
| 492 |
"learning_rate": 0.00019843897698922284,
|
| 493 |
-
"loss": 1.
|
| 494 |
"step": 330
|
| 495 |
},
|
| 496 |
{
|
| 497 |
"epoch": 2.2945205479452055,
|
| 498 |
-
"grad_norm": 0.
|
| 499 |
"learning_rate": 0.00019829558671383585,
|
| 500 |
-
"loss": 1.
|
| 501 |
"step": 335
|
| 502 |
},
|
| 503 |
{
|
| 504 |
"epoch": 2.328767123287671,
|
| 505 |
-
"grad_norm": 0.
|
| 506 |
"learning_rate": 0.00019814595336813725,
|
| 507 |
-
"loss": 1.
|
| 508 |
"step": 340
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"epoch": 2.363013698630137,
|
| 512 |
-
"grad_norm": 0.
|
| 513 |
"learning_rate": 0.0001979900864558242,
|
| 514 |
-
"loss": 1.
|
| 515 |
"step": 345
|
| 516 |
},
|
| 517 |
{
|
| 518 |
"epoch": 2.3972602739726026,
|
| 519 |
-
"grad_norm": 0.
|
| 520 |
"learning_rate": 0.00019782799587650805,
|
| 521 |
-
"loss": 1.
|
| 522 |
"step": 350
|
| 523 |
},
|
| 524 |
{
|
| 525 |
"epoch": 2.4315068493150687,
|
| 526 |
-
"grad_norm": 0.
|
| 527 |
"learning_rate": 0.00019765969192508508,
|
| 528 |
-
"loss": 1.
|
| 529 |
"step": 355
|
| 530 |
},
|
| 531 |
{
|
| 532 |
"epoch": 2.4657534246575343,
|
| 533 |
-
"grad_norm": 0.
|
| 534 |
"learning_rate": 0.00019748518529108316,
|
| 535 |
-
"loss": 1.
|
| 536 |
"step": 360
|
| 537 |
},
|
| 538 |
{
|
| 539 |
"epoch": 2.5,
|
| 540 |
-
"grad_norm": 0.
|
| 541 |
"learning_rate": 0.00019730448705798239,
|
| 542 |
-
"loss": 1.
|
| 543 |
"step": 365
|
| 544 |
},
|
| 545 |
{
|
| 546 |
"epoch": 2.5342465753424657,
|
| 547 |
-
"grad_norm": 0.
|
| 548 |
"learning_rate": 0.00019711760870251143,
|
| 549 |
-
"loss": 1.
|
| 550 |
"step": 370
|
| 551 |
},
|
| 552 |
{
|
| 553 |
"epoch": 2.5684931506849313,
|
| 554 |
-
"grad_norm": 0.
|
| 555 |
"learning_rate": 0.00019692456209391846,
|
| 556 |
-
"loss": 1.
|
| 557 |
"step": 375
|
| 558 |
},
|
| 559 |
{
|
| 560 |
"epoch": 2.602739726027397,
|
| 561 |
-
"grad_norm": 0.
|
| 562 |
"learning_rate": 0.0001967253594932173,
|
| 563 |
-
"loss": 1.
|
| 564 |
"step": 380
|
| 565 |
},
|
| 566 |
{
|
| 567 |
"epoch": 2.636986301369863,
|
| 568 |
-
"grad_norm": 0.
|
| 569 |
"learning_rate": 0.00019652001355240878,
|
| 570 |
-
"loss": 1.
|
| 571 |
"step": 385
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"epoch": 2.671232876712329,
|
| 575 |
-
"grad_norm": 0.
|
| 576 |
"learning_rate": 0.00019630853731367713,
|
| 577 |
-
"loss": 1.
|
| 578 |
"step": 390
|
| 579 |
},
|
| 580 |
{
|
| 581 |
"epoch": 2.7054794520547945,
|
| 582 |
-
"grad_norm": 0.
|
| 583 |
"learning_rate": 0.0001960909442085615,
|
| 584 |
-
"loss": 1.
|
| 585 |
"step": 395
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"epoch": 2.73972602739726,
|
| 589 |
-
"grad_norm": 0.
|
| 590 |
"learning_rate": 0.00019586724805710306,
|
| 591 |
-
"loss": 1.
|
| 592 |
"step": 400
|
| 593 |
},
|
| 594 |
{
|
| 595 |
"epoch": 2.7739726027397262,
|
| 596 |
-
"grad_norm": 0.
|
| 597 |
"learning_rate": 0.0001956374630669672,
|
| 598 |
-
"loss": 1.
|
| 599 |
"step": 405
|
| 600 |
},
|
| 601 |
{
|
| 602 |
"epoch": 2.808219178082192,
|
| 603 |
-
"grad_norm": 0.
|
| 604 |
"learning_rate": 0.00019540160383254107,
|
| 605 |
-
"loss": 1.
|
| 606 |
"step": 410
|
| 607 |
},
|
| 608 |
{
|
| 609 |
"epoch": 2.8424657534246576,
|
| 610 |
-
"grad_norm": 0.
|
| 611 |
"learning_rate": 0.00019515968533400673,
|
| 612 |
-
"loss": 1.
|
| 613 |
"step": 415
|
| 614 |
},
|
| 615 |
{
|
| 616 |
"epoch": 2.8767123287671232,
|
| 617 |
-
"grad_norm": 0.
|
| 618 |
"learning_rate": 0.00019491172293638968,
|
| 619 |
-
"loss": 1.
|
| 620 |
"step": 420
|
| 621 |
},
|
| 622 |
{
|
| 623 |
"epoch": 2.910958904109589,
|
| 624 |
-
"grad_norm": 0.
|
| 625 |
"learning_rate": 0.00019465773238858298,
|
| 626 |
-
"loss": 1.
|
| 627 |
"step": 425
|
| 628 |
},
|
| 629 |
{
|
| 630 |
"epoch": 2.9452054794520546,
|
| 631 |
-
"grad_norm": 0.
|
| 632 |
"learning_rate": 0.00019439772982234697,
|
| 633 |
-
"loss": 1.
|
| 634 |
"step": 430
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"epoch": 2.9794520547945207,
|
| 638 |
-
"grad_norm":
|
| 639 |
"learning_rate": 0.00019413173175128473,
|
| 640 |
-
"loss": 1.
|
| 641 |
"step": 435
|
| 642 |
},
|
| 643 |
{
|
| 644 |
"epoch": 3.0,
|
| 645 |
-
"eval_loss": 2.
|
| 646 |
-
"eval_runtime": 0.
|
| 647 |
-
"eval_samples_per_second": 18.
|
| 648 |
-
"eval_steps_per_second": 1.
|
| 649 |
"step": 438
|
| 650 |
},
|
| 651 |
{
|
| 652 |
"epoch": 3.0136986301369864,
|
| 653 |
-
"grad_norm":
|
| 654 |
"learning_rate": 0.0001938597550697932,
|
| 655 |
-
"loss": 1.
|
| 656 |
"step": 440
|
| 657 |
},
|
| 658 |
{
|
| 659 |
"epoch": 3.047945205479452,
|
| 660 |
-
"grad_norm": 0.
|
| 661 |
"learning_rate": 0.00019358181705199015,
|
| 662 |
-
"loss": 1.
|
| 663 |
"step": 445
|
| 664 |
},
|
| 665 |
{
|
| 666 |
"epoch": 3.0821917808219177,
|
| 667 |
-
"grad_norm": 0.
|
| 668 |
"learning_rate": 0.00019329793535061723,
|
| 669 |
-
"loss": 1.
|
| 670 |
"step": 450
|
| 671 |
},
|
| 672 |
{
|
| 673 |
"epoch": 3.1164383561643834,
|
| 674 |
-
"grad_norm": 0.
|
| 675 |
"learning_rate": 0.00019300812799591846,
|
| 676 |
-
"loss": 1.
|
| 677 |
"step": 455
|
| 678 |
},
|
| 679 |
{
|
| 680 |
"epoch": 3.1506849315068495,
|
| 681 |
-
"grad_norm": 0.
|
| 682 |
"learning_rate": 0.00019271241339449536,
|
| 683 |
-
"loss": 1.
|
| 684 |
"step": 460
|
| 685 |
},
|
| 686 |
{
|
| 687 |
"epoch": 3.184931506849315,
|
| 688 |
-
"grad_norm": 0.
|
| 689 |
"learning_rate": 0.00019241081032813772,
|
| 690 |
-
"loss": 1.
|
| 691 |
"step": 465
|
| 692 |
},
|
| 693 |
{
|
| 694 |
"epoch": 3.219178082191781,
|
| 695 |
-
"grad_norm": 0.
|
| 696 |
"learning_rate": 0.00019210333795263075,
|
| 697 |
-
"loss": 1.
|
| 698 |
"step": 470
|
| 699 |
},
|
| 700 |
{
|
| 701 |
"epoch": 3.2534246575342465,
|
| 702 |
-
"grad_norm":
|
| 703 |
"learning_rate": 0.00019179001579653853,
|
| 704 |
-
"loss": 1.
|
| 705 |
"step": 475
|
| 706 |
},
|
| 707 |
{
|
| 708 |
"epoch": 3.287671232876712,
|
| 709 |
-
"grad_norm":
|
| 710 |
"learning_rate": 0.0001914708637599636,
|
| 711 |
-
"loss": 1.
|
| 712 |
"step": 480
|
| 713 |
},
|
| 714 |
{
|
| 715 |
"epoch": 3.3219178082191783,
|
| 716 |
-
"grad_norm": 0.
|
| 717 |
"learning_rate": 0.00019114590211328288,
|
| 718 |
-
"loss": 1.
|
| 719 |
"step": 485
|
| 720 |
},
|
| 721 |
{
|
| 722 |
"epoch": 3.356164383561644,
|
| 723 |
-
"grad_norm": 0.
|
| 724 |
"learning_rate": 0.0001908151514958606,
|
| 725 |
-
"loss": 1.
|
| 726 |
"step": 490
|
| 727 |
},
|
| 728 |
{
|
| 729 |
"epoch": 3.3904109589041096,
|
| 730 |
-
"grad_norm": 0.
|
| 731 |
"learning_rate": 0.00019047863291473717,
|
| 732 |
-
"loss": 1.
|
| 733 |
"step": 495
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"epoch": 3.4246575342465753,
|
| 737 |
-
"grad_norm": 0.
|
| 738 |
"learning_rate": 0.00019013636774329495,
|
| 739 |
-
"loss": 1.
|
| 740 |
"step": 500
|
| 741 |
},
|
| 742 |
{
|
| 743 |
"epoch": 3.458904109589041,
|
| 744 |
-
"grad_norm": 0.
|
| 745 |
"learning_rate": 0.00018978837771990085,
|
| 746 |
-
"loss": 1.
|
| 747 |
"step": 505
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 3.493150684931507,
|
| 751 |
-
"grad_norm": 0.
|
| 752 |
"learning_rate": 0.0001894346849465257,
|
| 753 |
-
"loss": 1.
|
| 754 |
"step": 510
|
| 755 |
},
|
| 756 |
{
|
| 757 |
"epoch": 3.5273972602739727,
|
| 758 |
-
"grad_norm": 0.
|
| 759 |
"learning_rate": 0.00018907531188734026,
|
| 760 |
-
"loss": 1.
|
| 761 |
"step": 515
|
| 762 |
},
|
| 763 |
{
|
| 764 |
"epoch": 3.5616438356164384,
|
| 765 |
-
"grad_norm": 0.
|
| 766 |
"learning_rate": 0.00018871028136728874,
|
| 767 |
-
"loss": 1.
|
| 768 |
"step": 520
|
| 769 |
},
|
| 770 |
{
|
| 771 |
"epoch": 3.595890410958904,
|
| 772 |
-
"grad_norm": 0.
|
| 773 |
"learning_rate": 0.00018833961657063885,
|
| 774 |
-
"loss": 1.
|
| 775 |
"step": 525
|
| 776 |
},
|
| 777 |
{
|
| 778 |
"epoch": 3.6301369863013697,
|
| 779 |
-
"grad_norm": 0.
|
| 780 |
"learning_rate": 0.0001879633410395095,
|
| 781 |
-
"loss": 1.
|
| 782 |
"step": 530
|
| 783 |
},
|
| 784 |
{
|
| 785 |
"epoch": 3.6643835616438354,
|
| 786 |
-
"grad_norm": 0.
|
| 787 |
"learning_rate": 0.00018758147867237548,
|
| 788 |
-
"loss": 1.
|
| 789 |
"step": 535
|
| 790 |
},
|
| 791 |
{
|
| 792 |
"epoch": 3.6986301369863015,
|
| 793 |
-
"grad_norm": 0.
|
| 794 |
"learning_rate": 0.00018719405372254948,
|
| 795 |
-
"loss": 1.
|
| 796 |
"step": 540
|
| 797 |
},
|
| 798 |
{
|
| 799 |
"epoch": 3.732876712328767,
|
| 800 |
-
"grad_norm": 0.
|
| 801 |
"learning_rate": 0.00018680109079664188,
|
| 802 |
-
"loss": 1.
|
| 803 |
"step": 545
|
| 804 |
},
|
| 805 |
{
|
| 806 |
"epoch": 3.767123287671233,
|
| 807 |
-
"grad_norm": 0.
|
| 808 |
"learning_rate": 0.0001864026148529978,
|
| 809 |
-
"loss": 1.
|
| 810 |
"step": 550
|
| 811 |
},
|
| 812 |
{
|
| 813 |
"epoch": 3.8013698630136985,
|
| 814 |
-
"grad_norm": 0.
|
| 815 |
"learning_rate": 0.00018599865120011192,
|
| 816 |
-
"loss": 1.
|
| 817 |
"step": 555
|
| 818 |
},
|
| 819 |
{
|
| 820 |
"epoch": 3.8356164383561646,
|
| 821 |
-
"grad_norm": 0.
|
| 822 |
"learning_rate": 0.00018558922549502107,
|
| 823 |
-
"loss": 1.
|
| 824 |
"step": 560
|
| 825 |
},
|
| 826 |
{
|
| 827 |
"epoch": 3.8698630136986303,
|
| 828 |
-
"grad_norm": 0.
|
| 829 |
"learning_rate": 0.0001851743637416747,
|
| 830 |
-
"loss": 1.
|
| 831 |
"step": 565
|
| 832 |
},
|
| 833 |
{
|
| 834 |
"epoch": 3.904109589041096,
|
| 835 |
-
"grad_norm": 0.
|
| 836 |
"learning_rate": 0.00018475409228928312,
|
| 837 |
-
"loss": 1.
|
| 838 |
"step": 570
|
| 839 |
},
|
| 840 |
{
|
| 841 |
"epoch": 3.9383561643835616,
|
| 842 |
-
"grad_norm": 0.
|
| 843 |
"learning_rate": 0.00018432843783064429,
|
| 844 |
-
"loss": 1.
|
| 845 |
"step": 575
|
| 846 |
},
|
| 847 |
{
|
| 848 |
"epoch": 3.9726027397260273,
|
| 849 |
-
"grad_norm": 0.
|
| 850 |
"learning_rate": 0.00018389742740044813,
|
| 851 |
-
"loss": 1.
|
| 852 |
"step": 580
|
| 853 |
},
|
| 854 |
{
|
| 855 |
"epoch": 4.0,
|
| 856 |
-
"eval_loss": 2.
|
| 857 |
-
"eval_runtime": 0.
|
| 858 |
-
"eval_samples_per_second":
|
| 859 |
-
"eval_steps_per_second": 1.
|
| 860 |
"step": 584
|
| 861 |
},
|
| 862 |
{
|
| 863 |
"epoch": 4.006849315068493,
|
| 864 |
-
"grad_norm": 0.
|
| 865 |
"learning_rate": 0.00018346108837355972,
|
| 866 |
-
"loss": 1.
|
| 867 |
"step": 585
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 4.041095890410959,
|
| 871 |
-
"grad_norm": 0.
|
| 872 |
"learning_rate": 0.00018301944846328049,
|
| 873 |
-
"loss":
|
| 874 |
"step": 590
|
| 875 |
},
|
| 876 |
{
|
| 877 |
"epoch": 4.075342465753424,
|
| 878 |
-
"grad_norm": 0.
|
| 879 |
"learning_rate": 0.0001825725357195881,
|
| 880 |
-
"loss": 1.
|
| 881 |
"step": 595
|
| 882 |
},
|
| 883 |
{
|
| 884 |
"epoch": 4.109589041095891,
|
| 885 |
-
"grad_norm": 0.
|
| 886 |
"learning_rate": 0.00018212037852735486,
|
| 887 |
-
"loss": 1.
|
| 888 |
"step": 600
|
| 889 |
},
|
| 890 |
{
|
| 891 |
"epoch": 4.1438356164383565,
|
| 892 |
-
"grad_norm": 0.
|
| 893 |
"learning_rate": 0.0001816630056045451,
|
| 894 |
-
"loss": 1.
|
| 895 |
"step": 605
|
| 896 |
},
|
| 897 |
{
|
| 898 |
"epoch": 4.178082191780822,
|
| 899 |
-
"grad_norm": 0.
|
| 900 |
"learning_rate": 0.0001812004460003909,
|
| 901 |
-
"loss":
|
| 902 |
"step": 610
|
| 903 |
},
|
| 904 |
{
|
| 905 |
"epoch": 4.212328767123288,
|
| 906 |
-
"grad_norm": 0.
|
| 907 |
"learning_rate": 0.00018073272909354727,
|
| 908 |
-
"loss": 1.
|
| 909 |
"step": 615
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 4.2465753424657535,
|
| 913 |
-
"grad_norm": 0.
|
| 914 |
"learning_rate": 0.0001802598845902262,
|
| 915 |
-
"loss":
|
| 916 |
"step": 620
|
| 917 |
},
|
| 918 |
{
|
| 919 |
"epoch": 4.280821917808219,
|
| 920 |
-
"grad_norm": 0.
|
| 921 |
"learning_rate": 0.00017978194252230985,
|
| 922 |
-
"loss": 1.
|
| 923 |
"step": 625
|
| 924 |
},
|
| 925 |
{
|
| 926 |
"epoch": 4.315068493150685,
|
| 927 |
-
"grad_norm": 0.
|
| 928 |
"learning_rate": 0.00017929893324544332,
|
| 929 |
-
"loss":
|
| 930 |
"step": 630
|
| 931 |
},
|
| 932 |
{
|
| 933 |
"epoch": 4.3493150684931505,
|
| 934 |
-
"grad_norm": 0.
|
| 935 |
"learning_rate": 0.0001788108874371063,
|
| 936 |
-
"loss": 1.
|
| 937 |
"step": 635
|
| 938 |
},
|
| 939 |
{
|
| 940 |
"epoch": 4.383561643835616,
|
| 941 |
-
"grad_norm": 0.
|
| 942 |
"learning_rate": 0.00017831783609466504,
|
| 943 |
-
"loss": 1.
|
| 944 |
"step": 640
|
| 945 |
},
|
| 946 |
{
|
| 947 |
"epoch": 4.417808219178082,
|
| 948 |
-
"grad_norm": 0.
|
| 949 |
"learning_rate": 0.00017781981053340337,
|
| 950 |
-
"loss": 1.
|
| 951 |
"step": 645
|
| 952 |
},
|
| 953 |
{
|
| 954 |
"epoch": 4.4520547945205475,
|
| 955 |
-
"grad_norm": 0.
|
| 956 |
"learning_rate": 0.00017731684238453385,
|
| 957 |
-
"loss": 1.
|
| 958 |
"step": 650
|
| 959 |
},
|
| 960 |
{
|
| 961 |
"epoch": 4.486301369863014,
|
| 962 |
-
"grad_norm": 0.
|
| 963 |
"learning_rate": 0.0001768089635931887,
|
| 964 |
-
"loss": 1.
|
| 965 |
"step": 655
|
| 966 |
},
|
| 967 |
{
|
| 968 |
"epoch": 4.52054794520548,
|
| 969 |
-
"grad_norm": 0.
|
| 970 |
"learning_rate": 0.00017629620641639103,
|
| 971 |
-
"loss": 1.
|
| 972 |
"step": 660
|
| 973 |
},
|
| 974 |
{
|
| 975 |
"epoch": 4.554794520547945,
|
| 976 |
-
"grad_norm": 0.
|
| 977 |
"learning_rate": 0.00017577860342100579,
|
| 978 |
-
"loss": 1.
|
| 979 |
"step": 665
|
| 980 |
},
|
| 981 |
{
|
| 982 |
"epoch": 4.589041095890411,
|
| 983 |
-
"grad_norm": 0.
|
| 984 |
"learning_rate": 0.0001752561874816717,
|
| 985 |
-
"loss": 1.
|
| 986 |
"step": 670
|
| 987 |
},
|
| 988 |
{
|
| 989 |
"epoch": 4.623287671232877,
|
| 990 |
-
"grad_norm": 0.
|
| 991 |
"learning_rate": 0.00017472899177871297,
|
| 992 |
-
"loss": 1.
|
| 993 |
"step": 675
|
| 994 |
},
|
| 995 |
{
|
| 996 |
"epoch": 4.657534246575342,
|
| 997 |
-
"grad_norm": 0.
|
| 998 |
"learning_rate": 0.00017419704979603214,
|
| 999 |
-
"loss": 1.
|
| 1000 |
"step": 680
|
| 1001 |
},
|
| 1002 |
{
|
| 1003 |
"epoch": 4.691780821917808,
|
| 1004 |
-
"grad_norm": 0.
|
| 1005 |
"learning_rate": 0.00017366039531898326,
|
| 1006 |
-
"loss": 1.
|
| 1007 |
"step": 685
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
"epoch": 4.726027397260274,
|
| 1011 |
-
"grad_norm": 0.
|
| 1012 |
"learning_rate": 0.00017311906243222614,
|
| 1013 |
-
"loss": 1.
|
| 1014 |
"step": 690
|
| 1015 |
},
|
| 1016 |
{
|
| 1017 |
"epoch": 4.760273972602739,
|
| 1018 |
-
"grad_norm": 0.
|
| 1019 |
"learning_rate": 0.0001725730855175615,
|
| 1020 |
-
"loss": 1.
|
| 1021 |
"step": 695
|
| 1022 |
},
|
| 1023 |
{
|
| 1024 |
"epoch": 4.794520547945205,
|
| 1025 |
-
"grad_norm": 0.
|
| 1026 |
"learning_rate": 0.00017202249925174723,
|
| 1027 |
-
"loss": 1.
|
| 1028 |
"step": 700
|
| 1029 |
},
|
| 1030 |
{
|
| 1031 |
"epoch": 4.828767123287671,
|
| 1032 |
-
"grad_norm": 0.
|
| 1033 |
"learning_rate": 0.00017146733860429612,
|
| 1034 |
-
"loss": 1.
|
| 1035 |
"step": 705
|
| 1036 |
},
|
| 1037 |
{
|
| 1038 |
"epoch": 4.863013698630137,
|
| 1039 |
-
"grad_norm": 0.
|
| 1040 |
"learning_rate": 0.0001709076388352546,
|
| 1041 |
-
"loss": 1.
|
| 1042 |
"step": 710
|
| 1043 |
},
|
| 1044 |
{
|
| 1045 |
"epoch": 4.897260273972603,
|
| 1046 |
-
"grad_norm": 0.
|
| 1047 |
"learning_rate": 0.00017034343549296346,
|
| 1048 |
-
"loss": 1.
|
| 1049 |
"step": 715
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
"epoch": 4.931506849315069,
|
| 1053 |
-
"grad_norm": 0.
|
| 1054 |
"learning_rate": 0.00016977476441179992,
|
| 1055 |
-
"loss": 1.
|
| 1056 |
"step": 720
|
| 1057 |
},
|
| 1058 |
{
|
| 1059 |
"epoch": 4.965753424657534,
|
| 1060 |
-
"grad_norm": 0.
|
| 1061 |
"learning_rate": 0.0001692016617099018,
|
| 1062 |
-
"loss": 1.
|
| 1063 |
"step": 725
|
| 1064 |
},
|
| 1065 |
{
|
| 1066 |
"epoch": 5.0,
|
| 1067 |
-
"grad_norm": 0.
|
| 1068 |
"learning_rate": 0.0001686241637868734,
|
| 1069 |
-
"loss": 1.
|
| 1070 |
"step": 730
|
| 1071 |
},
|
| 1072 |
{
|
| 1073 |
"epoch": 5.0,
|
| 1074 |
-
"eval_loss": 2.
|
| 1075 |
-
"eval_runtime": 0.
|
| 1076 |
-
"eval_samples_per_second": 18.
|
| 1077 |
-
"eval_steps_per_second": 1.
|
| 1078 |
"step": 730
|
| 1079 |
},
|
| 1080 |
{
|
| 1081 |
"epoch": 5.034246575342466,
|
| 1082 |
-
"grad_norm": 0.
|
| 1083 |
"learning_rate": 0.0001680423073214737,
|
| 1084 |
-
"loss":
|
| 1085 |
"step": 735
|
| 1086 |
},
|
| 1087 |
{
|
| 1088 |
"epoch": 5.068493150684931,
|
| 1089 |
-
"grad_norm": 0.
|
| 1090 |
"learning_rate": 0.00016745612926928694,
|
| 1091 |
-
"loss":
|
| 1092 |
"step": 740
|
| 1093 |
},
|
| 1094 |
{
|
| 1095 |
"epoch": 5.102739726027397,
|
| 1096 |
-
"grad_norm": 0.
|
| 1097 |
"learning_rate": 0.0001668656668603751,
|
| 1098 |
-
"loss":
|
| 1099 |
"step": 745
|
| 1100 |
},
|
| 1101 |
{
|
| 1102 |
"epoch": 5.136986301369863,
|
| 1103 |
-
"grad_norm": 0.
|
| 1104 |
"learning_rate": 0.00016627095759691362,
|
| 1105 |
-
"loss":
|
| 1106 |
"step": 750
|
| 1107 |
},
|
| 1108 |
{
|
| 1109 |
"epoch": 5.171232876712328,
|
| 1110 |
-
"grad_norm": 0.
|
| 1111 |
"learning_rate": 0.0001656720392508094,
|
| 1112 |
-
"loss":
|
| 1113 |
"step": 755
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
"epoch": 5.205479452054795,
|
| 1117 |
"grad_norm": 0.376953125,
|
| 1118 |
"learning_rate": 0.00016506894986130171,
|
| 1119 |
-
"loss":
|
| 1120 |
"step": 760
|
| 1121 |
},
|
| 1122 |
{
|
| 1123 |
"epoch": 5.239726027397261,
|
| 1124 |
-
"grad_norm": 0.
|
| 1125 |
"learning_rate": 0.00016446172773254629,
|
| 1126 |
-
"loss":
|
| 1127 |
"step": 765
|
| 1128 |
},
|
| 1129 |
{
|
| 1130 |
"epoch": 5.273972602739726,
|
| 1131 |
-
"grad_norm": 0.
|
| 1132 |
"learning_rate": 0.00016385041143118255,
|
| 1133 |
-
"loss":
|
| 1134 |
"step": 770
|
| 1135 |
},
|
| 1136 |
{
|
| 1137 |
"epoch": 5.308219178082192,
|
| 1138 |
-
"grad_norm": 0.
|
| 1139 |
"learning_rate": 0.000163235039783884,
|
| 1140 |
-
"loss":
|
| 1141 |
"step": 775
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
"epoch": 5.342465753424658,
|
| 1145 |
-
"grad_norm": 0.
|
| 1146 |
"learning_rate": 0.0001626156518748922,
|
| 1147 |
-
"loss":
|
| 1148 |
"step": 780
|
| 1149 |
},
|
| 1150 |
{
|
| 1151 |
"epoch": 5.376712328767123,
|
| 1152 |
-
"grad_norm": 0.
|
| 1153 |
"learning_rate": 0.00016199228704353455,
|
| 1154 |
-
"loss":
|
| 1155 |
"step": 785
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
"epoch": 5.410958904109589,
|
| 1159 |
-
"grad_norm": 0.
|
| 1160 |
"learning_rate": 0.00016136498488172568,
|
| 1161 |
-
"loss":
|
| 1162 |
"step": 790
|
| 1163 |
},
|
| 1164 |
{
|
| 1165 |
"epoch": 5.445205479452055,
|
| 1166 |
-
"grad_norm": 0.
|
| 1167 |
"learning_rate": 0.0001607337852314527,
|
| 1168 |
-
"loss":
|
| 1169 |
"step": 795
|
| 1170 |
},
|
| 1171 |
{
|
| 1172 |
"epoch": 5.47945205479452,
|
| 1173 |
-
"grad_norm": 0.
|
| 1174 |
"learning_rate": 0.00016009872818224485,
|
| 1175 |
-
"loss":
|
| 1176 |
"step": 800
|
| 1177 |
},
|
| 1178 |
{
|
| 1179 |
"epoch": 5.513698630136986,
|
| 1180 |
-
"grad_norm": 0.
|
| 1181 |
"learning_rate": 0.00015945985406862721,
|
| 1182 |
-
"loss":
|
| 1183 |
"step": 805
|
| 1184 |
},
|
| 1185 |
{
|
| 1186 |
"epoch": 5.5479452054794525,
|
| 1187 |
-
"grad_norm": 0.
|
| 1188 |
"learning_rate": 0.00015881720346755905,
|
| 1189 |
-
"loss":
|
| 1190 |
"step": 810
|
| 1191 |
},
|
| 1192 |
{
|
| 1193 |
"epoch": 5.582191780821918,
|
| 1194 |
-
"grad_norm": 0.
|
| 1195 |
"learning_rate": 0.00015817081719585643,
|
| 1196 |
-
"loss":
|
| 1197 |
"step": 815
|
| 1198 |
},
|
| 1199 |
{
|
| 1200 |
"epoch": 5.616438356164384,
|
| 1201 |
-
"grad_norm": 0.
|
| 1202 |
"learning_rate": 0.00015752073630759998,
|
| 1203 |
-
"loss":
|
| 1204 |
"step": 820
|
| 1205 |
},
|
| 1206 |
{
|
| 1207 |
"epoch": 5.6506849315068495,
|
| 1208 |
-
"grad_norm": 0.
|
| 1209 |
"learning_rate": 0.00015686700209152738,
|
| 1210 |
-
"loss":
|
| 1211 |
"step": 825
|
| 1212 |
},
|
| 1213 |
{
|
| 1214 |
"epoch": 5.684931506849315,
|
| 1215 |
-
"grad_norm": 0.
|
| 1216 |
"learning_rate": 0.00015620965606841098,
|
| 1217 |
-
"loss":
|
| 1218 |
"step": 830
|
| 1219 |
},
|
| 1220 |
{
|
| 1221 |
"epoch": 5.719178082191781,
|
| 1222 |
-
"grad_norm": 0.
|
| 1223 |
"learning_rate": 0.0001555487399884206,
|
| 1224 |
-
"loss":
|
| 1225 |
"step": 835
|
| 1226 |
},
|
| 1227 |
{
|
| 1228 |
"epoch": 5.7534246575342465,
|
| 1229 |
-
"grad_norm": 0.
|
| 1230 |
"learning_rate": 0.00015488429582847192,
|
| 1231 |
-
"loss":
|
| 1232 |
"step": 840
|
| 1233 |
},
|
| 1234 |
{
|
| 1235 |
"epoch": 5.787671232876712,
|
| 1236 |
-
"grad_norm": 0.
|
| 1237 |
"learning_rate": 0.0001542163657895605,
|
| 1238 |
-
"loss":
|
| 1239 |
"step": 845
|
| 1240 |
},
|
| 1241 |
{
|
| 1242 |
"epoch": 5.821917808219178,
|
| 1243 |
-
"grad_norm": 0.
|
| 1244 |
"learning_rate": 0.00015354499229408114,
|
| 1245 |
-
"loss":
|
| 1246 |
"step": 850
|
| 1247 |
},
|
| 1248 |
{
|
| 1249 |
"epoch": 5.8561643835616435,
|
| 1250 |
-
"grad_norm": 0.
|
| 1251 |
"learning_rate": 0.0001528702179831338,
|
| 1252 |
-
"loss":
|
| 1253 |
"step": 855
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
"epoch": 5.890410958904109,
|
| 1257 |
-
"grad_norm": 0.
|
| 1258 |
"learning_rate": 0.00015219208571381525,
|
| 1259 |
-
"loss":
|
| 1260 |
"step": 860
|
| 1261 |
},
|
| 1262 |
{
|
| 1263 |
"epoch": 5.924657534246576,
|
| 1264 |
-
"grad_norm": 0.
|
| 1265 |
"learning_rate": 0.00015151063855649698,
|
| 1266 |
-
"loss":
|
| 1267 |
"step": 865
|
| 1268 |
},
|
| 1269 |
{
|
| 1270 |
"epoch": 5.958904109589041,
|
| 1271 |
-
"grad_norm": 0.
|
| 1272 |
"learning_rate": 0.00015082591979208976,
|
| 1273 |
-
"loss":
|
| 1274 |
"step": 870
|
| 1275 |
},
|
| 1276 |
{
|
| 1277 |
"epoch": 5.993150684931507,
|
| 1278 |
-
"grad_norm": 0.
|
| 1279 |
"learning_rate": 0.00015013797290929466,
|
| 1280 |
-
"loss":
|
| 1281 |
"step": 875
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
"epoch": 6.0,
|
| 1285 |
-
"eval_loss": 2.
|
| 1286 |
-
"eval_runtime": 0.
|
| 1287 |
-
"eval_samples_per_second": 18.
|
| 1288 |
-
"eval_steps_per_second": 1.
|
| 1289 |
"step": 876
|
| 1290 |
},
|
| 1291 |
{
|
| 1292 |
"epoch": 6.027397260273973,
|
| 1293 |
-
"grad_norm": 0.
|
| 1294 |
"learning_rate": 0.00014944684160184108,
|
| 1295 |
-
"loss":
|
| 1296 |
"step": 880
|
| 1297 |
},
|
| 1298 |
{
|
| 1299 |
"epoch": 6.061643835616438,
|
| 1300 |
-
"grad_norm": 0.
|
| 1301 |
"learning_rate": 0.00014875256976571135,
|
| 1302 |
-
"loss":
|
| 1303 |
"step": 885
|
| 1304 |
},
|
| 1305 |
{
|
| 1306 |
"epoch": 6.095890410958904,
|
| 1307 |
-
"grad_norm": 0.
|
| 1308 |
"learning_rate": 0.00014805520149635307,
|
| 1309 |
-
"loss": 0.
|
| 1310 |
"step": 890
|
| 1311 |
},
|
| 1312 |
{
|
| 1313 |
"epoch": 6.13013698630137,
|
| 1314 |
-
"grad_norm": 0.
|
| 1315 |
"learning_rate": 0.00014735478108587828,
|
| 1316 |
-
"loss":
|
| 1317 |
"step": 895
|
| 1318 |
},
|
| 1319 |
{
|
| 1320 |
"epoch": 6.164383561643835,
|
| 1321 |
-
"grad_norm": 0.
|
| 1322 |
"learning_rate": 0.00014665135302025035,
|
| 1323 |
-
"loss":
|
| 1324 |
"step": 900
|
| 1325 |
},
|
| 1326 |
{
|
| 1327 |
"epoch": 6.198630136986301,
|
| 1328 |
-
"grad_norm": 0.
|
| 1329 |
"learning_rate": 0.00014594496197645852,
|
| 1330 |
-
"loss":
|
| 1331 |
"step": 905
|
| 1332 |
},
|
| 1333 |
{
|
| 1334 |
"epoch": 6.232876712328767,
|
| 1335 |
-
"grad_norm": 0.
|
| 1336 |
"learning_rate": 0.0001452356528196804,
|
| 1337 |
-
"loss":
|
| 1338 |
"step": 910
|
| 1339 |
},
|
| 1340 |
{
|
| 1341 |
"epoch": 6.267123287671233,
|
| 1342 |
-
"grad_norm": 0.
|
| 1343 |
"learning_rate": 0.00014452347060043237,
|
| 1344 |
-
"loss":
|
| 1345 |
"step": 915
|
| 1346 |
},
|
| 1347 |
{
|
| 1348 |
"epoch": 6.301369863013699,
|
| 1349 |
-
"grad_norm": 0.
|
| 1350 |
"learning_rate": 0.00014380846055170828,
|
| 1351 |
-
"loss":
|
| 1352 |
"step": 920
|
| 1353 |
},
|
| 1354 |
{
|
| 1355 |
"epoch": 6.335616438356165,
|
| 1356 |
-
"grad_norm": 0.
|
| 1357 |
"learning_rate": 0.00014309066808610655,
|
| 1358 |
-
"loss":
|
| 1359 |
"step": 925
|
| 1360 |
},
|
| 1361 |
{
|
| 1362 |
"epoch": 6.36986301369863,
|
| 1363 |
-
"grad_norm": 0.
|
| 1364 |
"learning_rate": 0.0001423701387929459,
|
| 1365 |
-
"loss":
|
| 1366 |
"step": 930
|
| 1367 |
},
|
| 1368 |
{
|
| 1369 |
"epoch": 6.404109589041096,
|
| 1370 |
-
"grad_norm": 0.
|
| 1371 |
"learning_rate": 0.00014164691843536982,
|
| 1372 |
-
"loss":
|
| 1373 |
"step": 935
|
| 1374 |
},
|
| 1375 |
{
|
| 1376 |
"epoch": 6.438356164383562,
|
| 1377 |
-
"grad_norm": 0.
|
| 1378 |
"learning_rate": 0.00014092105294744,
|
| 1379 |
-
"loss":
|
| 1380 |
"step": 940
|
| 1381 |
},
|
| 1382 |
{
|
| 1383 |
"epoch": 6.472602739726027,
|
| 1384 |
-
"grad_norm": 0.
|
| 1385 |
"learning_rate": 0.00014019258843121893,
|
| 1386 |
-
"loss":
|
| 1387 |
"step": 945
|
| 1388 |
},
|
| 1389 |
{
|
| 1390 |
"epoch": 6.506849315068493,
|
| 1391 |
-
"grad_norm": 0.
|
| 1392 |
"learning_rate": 0.0001394615711538417,
|
| 1393 |
-
"loss":
|
| 1394 |
"step": 950
|
| 1395 |
},
|
| 1396 |
{
|
| 1397 |
"epoch": 6.541095890410959,
|
| 1398 |
-
"grad_norm": 0.
|
| 1399 |
"learning_rate": 0.00013872804754457759,
|
| 1400 |
-
"loss":
|
| 1401 |
"step": 955
|
| 1402 |
},
|
| 1403 |
{
|
| 1404 |
"epoch": 6.575342465753424,
|
| 1405 |
-
"grad_norm": 0.
|
| 1406 |
"learning_rate": 0.00013799206419188103,
|
| 1407 |
-
"loss":
|
| 1408 |
"step": 960
|
| 1409 |
},
|
| 1410 |
{
|
| 1411 |
"epoch": 6.609589041095891,
|
| 1412 |
-
"grad_norm": 0.
|
| 1413 |
"learning_rate": 0.00013725366784043288,
|
| 1414 |
-
"loss":
|
| 1415 |
"step": 965
|
| 1416 |
},
|
| 1417 |
{
|
| 1418 |
"epoch": 6.6438356164383565,
|
| 1419 |
-
"grad_norm": 0.
|
| 1420 |
"learning_rate": 0.00013651290538817113,
|
| 1421 |
-
"loss":
|
| 1422 |
"step": 970
|
| 1423 |
},
|
| 1424 |
{
|
| 1425 |
"epoch": 6.678082191780822,
|
| 1426 |
-
"grad_norm": 0.
|
| 1427 |
"learning_rate": 0.0001357698238833126,
|
| 1428 |
-
"loss":
|
| 1429 |
"step": 975
|
| 1430 |
},
|
| 1431 |
{
|
| 1432 |
"epoch": 6.712328767123288,
|
| 1433 |
-
"grad_norm": 0.
|
| 1434 |
"learning_rate": 0.00013502447052136455,
|
| 1435 |
-
"loss":
|
| 1436 |
"step": 980
|
| 1437 |
},
|
| 1438 |
{
|
| 1439 |
"epoch": 6.7465753424657535,
|
| 1440 |
-
"grad_norm": 0.
|
| 1441 |
"learning_rate": 0.00013427689264212738,
|
| 1442 |
-
"loss":
|
| 1443 |
"step": 985
|
| 1444 |
},
|
| 1445 |
{
|
| 1446 |
"epoch": 6.780821917808219,
|
| 1447 |
-
"grad_norm": 0.
|
| 1448 |
"learning_rate": 0.00013352713772668765,
|
| 1449 |
-
"loss":
|
| 1450 |
"step": 990
|
| 1451 |
},
|
| 1452 |
{
|
| 1453 |
"epoch": 6.815068493150685,
|
| 1454 |
-
"grad_norm": 0.
|
| 1455 |
"learning_rate": 0.0001327752533944025,
|
| 1456 |
-
"loss":
|
| 1457 |
"step": 995
|
| 1458 |
},
|
| 1459 |
{
|
| 1460 |
"epoch": 6.8493150684931505,
|
| 1461 |
-
"grad_norm": 0.
|
| 1462 |
"learning_rate": 0.00013202128739987532,
|
| 1463 |
-
"loss":
|
| 1464 |
"step": 1000
|
| 1465 |
},
|
| 1466 |
{
|
| 1467 |
"epoch": 6.883561643835616,
|
| 1468 |
-
"grad_norm": 0.
|
| 1469 |
"learning_rate": 0.00013126528762992247,
|
| 1470 |
-
"loss":
|
| 1471 |
"step": 1005
|
| 1472 |
},
|
| 1473 |
{
|
| 1474 |
"epoch": 6.917808219178082,
|
| 1475 |
-
"grad_norm": 0.
|
| 1476 |
"learning_rate": 0.0001305073021005321,
|
| 1477 |
-
"loss":
|
| 1478 |
"step": 1010
|
| 1479 |
},
|
| 1480 |
{
|
| 1481 |
"epoch": 6.9520547945205475,
|
| 1482 |
-
"grad_norm": 0.
|
| 1483 |
"learning_rate": 0.0001297473789538142,
|
| 1484 |
-
"loss":
|
| 1485 |
"step": 1015
|
| 1486 |
},
|
| 1487 |
{
|
| 1488 |
"epoch": 6.986301369863014,
|
| 1489 |
-
"grad_norm": 0.
|
| 1490 |
"learning_rate": 0.00012898556645494325,
|
| 1491 |
-
"loss":
|
| 1492 |
"step": 1020
|
| 1493 |
},
|
| 1494 |
{
|
| 1495 |
"epoch": 7.0,
|
| 1496 |
-
"eval_loss": 2.
|
| 1497 |
-
"eval_runtime": 0.
|
| 1498 |
-
"eval_samples_per_second":
|
| 1499 |
-
"eval_steps_per_second": 1.
|
| 1500 |
"step": 1022
|
| 1501 |
},
|
| 1502 |
{
|
| 1503 |
"epoch": 7.02054794520548,
|
| 1504 |
-
"grad_norm": 0.
|
| 1505 |
"learning_rate": 0.0001282219129890925,
|
| 1506 |
-
"loss": 0.
|
| 1507 |
"step": 1025
|
| 1508 |
},
|
| 1509 |
{
|
| 1510 |
"epoch": 7.054794520547945,
|
| 1511 |
-
"grad_norm": 0.
|
| 1512 |
"learning_rate": 0.00012745646705836097,
|
| 1513 |
-
"loss": 0.
|
| 1514 |
"step": 1030
|
| 1515 |
},
|
| 1516 |
{
|
| 1517 |
"epoch": 7.089041095890411,
|
| 1518 |
-
"grad_norm": 0.
|
| 1519 |
"learning_rate": 0.0001266892772786929,
|
| 1520 |
-
"loss": 0.
|
| 1521 |
"step": 1035
|
| 1522 |
},
|
| 1523 |
{
|
| 1524 |
"epoch": 7.123287671232877,
|
| 1525 |
-
"grad_norm": 0.
|
| 1526 |
"learning_rate": 0.0001259203923767901,
|
| 1527 |
-
"loss": 0.
|
| 1528 |
"step": 1040
|
| 1529 |
},
|
| 1530 |
{
|
| 1531 |
"epoch": 7.157534246575342,
|
| 1532 |
-
"grad_norm": 0.
|
| 1533 |
"learning_rate": 0.00012514986118701695,
|
| 1534 |
-
"loss": 0.
|
| 1535 |
"step": 1045
|
| 1536 |
},
|
| 1537 |
{
|
| 1538 |
"epoch": 7.191780821917808,
|
| 1539 |
-
"grad_norm": 0.
|
| 1540 |
"learning_rate": 0.00012437773264829897,
|
| 1541 |
-
"loss": 0.
|
| 1542 |
"step": 1050
|
| 1543 |
},
|
| 1544 |
{
|
| 1545 |
"epoch": 7.226027397260274,
|
| 1546 |
-
"grad_norm": 0.
|
| 1547 |
"learning_rate": 0.00012360405580101448,
|
| 1548 |
-
"loss": 0.
|
| 1549 |
"step": 1055
|
| 1550 |
},
|
| 1551 |
{
|
| 1552 |
"epoch": 7.260273972602739,
|
| 1553 |
-
"grad_norm": 0.
|
| 1554 |
"learning_rate": 0.00012282887978387976,
|
| 1555 |
-
"loss":
|
| 1556 |
"step": 1060
|
| 1557 |
},
|
| 1558 |
{
|
| 1559 |
"epoch": 7.294520547945205,
|
| 1560 |
-
"grad_norm": 0.
|
| 1561 |
"learning_rate": 0.00012205225383082843,
|
| 1562 |
-
"loss": 0.
|
| 1563 |
"step": 1065
|
| 1564 |
},
|
| 1565 |
{
|
| 1566 |
"epoch": 7.328767123287671,
|
| 1567 |
-
"grad_norm": 0.
|
| 1568 |
"learning_rate": 0.000121274227267884,
|
| 1569 |
-
"loss": 0.
|
| 1570 |
"step": 1070
|
| 1571 |
},
|
| 1572 |
{
|
| 1573 |
"epoch": 7.363013698630137,
|
| 1574 |
-
"grad_norm": 0.
|
| 1575 |
"learning_rate": 0.00012049484951002739,
|
| 1576 |
-
"loss":
|
| 1577 |
"step": 1075
|
| 1578 |
},
|
| 1579 |
{
|
| 1580 |
"epoch": 7.397260273972603,
|
| 1581 |
-
"grad_norm": 0.
|
| 1582 |
"learning_rate": 0.00011971417005805818,
|
| 1583 |
-
"loss": 0.
|
| 1584 |
"step": 1080
|
| 1585 |
},
|
| 1586 |
{
|
| 1587 |
"epoch": 7.431506849315069,
|
| 1588 |
-
"grad_norm": 0.
|
| 1589 |
"learning_rate": 0.00011893223849545084,
|
| 1590 |
-
"loss": 0.
|
| 1591 |
"step": 1085
|
| 1592 |
},
|
| 1593 |
{
|
| 1594 |
"epoch": 7.465753424657534,
|
| 1595 |
-
"grad_norm": 0.
|
| 1596 |
"learning_rate": 0.00011814910448520536,
|
| 1597 |
-
"loss": 0.
|
| 1598 |
"step": 1090
|
| 1599 |
},
|
| 1600 |
{
|
| 1601 |
"epoch": 7.5,
|
| 1602 |
"grad_norm": 0.404296875,
|
| 1603 |
"learning_rate": 0.00011736481776669306,
|
| 1604 |
-
"loss": 0.
|
| 1605 |
"step": 1095
|
| 1606 |
},
|
| 1607 |
{
|
| 1608 |
"epoch": 7.534246575342466,
|
| 1609 |
-
"grad_norm": 0.
|
| 1610 |
"learning_rate": 0.00011657942815249754,
|
| 1611 |
-
"loss": 0.
|
| 1612 |
"step": 1100
|
| 1613 |
},
|
| 1614 |
{
|
| 1615 |
"epoch": 7.568493150684931,
|
| 1616 |
-
"grad_norm": 0.
|
| 1617 |
"learning_rate": 0.00011579298552525084,
|
| 1618 |
-
"loss": 0.
|
| 1619 |
"step": 1105
|
| 1620 |
},
|
| 1621 |
{
|
| 1622 |
"epoch": 7.602739726027397,
|
| 1623 |
-
"grad_norm": 0.
|
| 1624 |
"learning_rate": 0.00011500553983446527,
|
| 1625 |
-
"loss": 0.
|
| 1626 |
"step": 1110
|
| 1627 |
},
|
| 1628 |
{
|
| 1629 |
"epoch": 7.636986301369863,
|
| 1630 |
-
"grad_norm": 0.
|
| 1631 |
"learning_rate": 0.00011421714109336097,
|
| 1632 |
-
"loss": 0.
|
| 1633 |
"step": 1115
|
| 1634 |
},
|
| 1635 |
{
|
| 1636 |
"epoch": 7.671232876712329,
|
| 1637 |
-
"grad_norm": 0.
|
| 1638 |
"learning_rate": 0.00011342783937568926,
|
| 1639 |
-
"loss":
|
| 1640 |
"step": 1120
|
| 1641 |
},
|
| 1642 |
{
|
| 1643 |
"epoch": 7.705479452054795,
|
| 1644 |
-
"grad_norm": 0.
|
| 1645 |
"learning_rate": 0.00011263768481255264,
|
| 1646 |
-
"loss": 0.
|
| 1647 |
"step": 1125
|
| 1648 |
},
|
| 1649 |
{
|
| 1650 |
"epoch": 7.739726027397261,
|
| 1651 |
-
"grad_norm": 0.
|
| 1652 |
"learning_rate": 0.00011184672758922034,
|
| 1653 |
-
"loss":
|
| 1654 |
"step": 1130
|
| 1655 |
},
|
| 1656 |
{
|
| 1657 |
"epoch": 7.773972602739726,
|
| 1658 |
-
"grad_norm": 0.
|
| 1659 |
"learning_rate": 0.00011105501794194131,
|
| 1660 |
-
"loss": 0.
|
| 1661 |
"step": 1135
|
| 1662 |
},
|
| 1663 |
{
|
| 1664 |
"epoch": 7.808219178082192,
|
| 1665 |
-
"grad_norm": 0.
|
| 1666 |
"learning_rate": 0.00011026260615475333,
|
| 1667 |
-
"loss":
|
| 1668 |
"step": 1140
|
| 1669 |
},
|
| 1670 |
{
|
| 1671 |
"epoch": 7.842465753424658,
|
| 1672 |
-
"grad_norm": 0.
|
| 1673 |
"learning_rate": 0.00010946954255628928,
|
| 1674 |
-
"loss": 0.
|
| 1675 |
"step": 1145
|
| 1676 |
},
|
| 1677 |
{
|
| 1678 |
"epoch": 7.876712328767123,
|
| 1679 |
-
"grad_norm": 0.
|
| 1680 |
"learning_rate": 0.00010867587751658079,
|
| 1681 |
-
"loss": 0.
|
| 1682 |
"step": 1150
|
| 1683 |
},
|
| 1684 |
{
|
| 1685 |
"epoch": 7.910958904109589,
|
| 1686 |
-
"grad_norm": 0.
|
| 1687 |
"learning_rate": 0.00010788166144385888,
|
| 1688 |
-
"loss": 0.
|
| 1689 |
"step": 1155
|
| 1690 |
},
|
| 1691 |
{
|
| 1692 |
"epoch": 7.945205479452055,
|
| 1693 |
-
"grad_norm": 0.
|
| 1694 |
"learning_rate": 0.0001070869447813525,
|
| 1695 |
-
"loss": 0.
|
| 1696 |
"step": 1160
|
| 1697 |
},
|
| 1698 |
{
|
| 1699 |
"epoch": 7.97945205479452,
|
| 1700 |
-
"grad_norm": 0.
|
| 1701 |
"learning_rate": 0.0001062917780040847,
|
| 1702 |
-
"loss": 0.
|
| 1703 |
"step": 1165
|
| 1704 |
},
|
| 1705 |
{
|
| 1706 |
"epoch": 8.0,
|
| 1707 |
-
"eval_loss": 2.
|
| 1708 |
-
"eval_runtime": 0.
|
| 1709 |
-
"eval_samples_per_second":
|
| 1710 |
-
"eval_steps_per_second": 1.
|
| 1711 |
"step": 1168
|
| 1712 |
},
|
| 1713 |
{
|
| 1714 |
"epoch": 8.013698630136986,
|
| 1715 |
-
"grad_norm": 0.
|
| 1716 |
"learning_rate": 0.0001054962116156667,
|
| 1717 |
-
"loss": 0.
|
| 1718 |
"step": 1170
|
| 1719 |
},
|
| 1720 |
{
|
| 1721 |
"epoch": 8.047945205479452,
|
| 1722 |
"grad_norm": 0.41796875,
|
| 1723 |
"learning_rate": 0.00010470029614509041,
|
| 1724 |
-
"loss": 0.
|
| 1725 |
"step": 1175
|
| 1726 |
},
|
| 1727 |
{
|
| 1728 |
"epoch": 8.082191780821917,
|
| 1729 |
-
"grad_norm": 0.
|
| 1730 |
"learning_rate": 0.00010390408214351892,
|
| 1731 |
-
"loss": 0.
|
| 1732 |
"step": 1180
|
| 1733 |
},
|
| 1734 |
{
|
| 1735 |
"epoch": 8.116438356164384,
|
| 1736 |
-
"grad_norm": 0.
|
| 1737 |
"learning_rate": 0.0001031076201810762,
|
| 1738 |
-
"loss": 0.
|
| 1739 |
"step": 1185
|
| 1740 |
},
|
| 1741 |
{
|
| 1742 |
"epoch": 8.150684931506849,
|
| 1743 |
-
"grad_norm": 0.
|
| 1744 |
"learning_rate": 0.00010231096084363483,
|
| 1745 |
-
"loss": 0.
|
| 1746 |
"step": 1190
|
| 1747 |
},
|
| 1748 |
{
|
| 1749 |
"epoch": 8.184931506849315,
|
| 1750 |
-
"grad_norm": 0.
|
| 1751 |
"learning_rate": 0.00010151415472960342,
|
| 1752 |
-
"loss": 0.
|
| 1753 |
"step": 1195
|
| 1754 |
},
|
| 1755 |
{
|
| 1756 |
"epoch": 8.219178082191782,
|
| 1757 |
-
"grad_norm": 0.
|
| 1758 |
"learning_rate": 0.00010071725244671282,
|
| 1759 |
-
"loss": 0.
|
| 1760 |
"step": 1200
|
| 1761 |
},
|
| 1762 |
{
|
| 1763 |
"epoch": 8.253424657534246,
|
| 1764 |
-
"grad_norm": 0.
|
| 1765 |
"learning_rate": 9.992030460880181e-05,
|
| 1766 |
-
"loss": 0.
|
| 1767 |
"step": 1205
|
| 1768 |
},
|
| 1769 |
{
|
| 1770 |
"epoch": 8.287671232876713,
|
| 1771 |
-
"grad_norm": 0.
|
| 1772 |
"learning_rate": 9.91233618326026e-05,
|
| 1773 |
-
"loss": 0.
|
| 1774 |
"step": 1210
|
| 1775 |
},
|
| 1776 |
{
|
| 1777 |
"epoch": 8.321917808219178,
|
| 1778 |
-
"grad_norm": 0.
|
| 1779 |
"learning_rate": 9.83264747345259e-05,
|
| 1780 |
-
"loss": 0.
|
| 1781 |
"step": 1215
|
| 1782 |
},
|
| 1783 |
{
|
| 1784 |
"epoch": 8.356164383561644,
|
| 1785 |
-
"grad_norm": 0.
|
| 1786 |
"learning_rate": 9.752969392744606e-05,
|
| 1787 |
-
"loss": 0.
|
| 1788 |
"step": 1220
|
| 1789 |
},
|
| 1790 |
{
|
| 1791 |
"epoch": 8.39041095890411,
|
| 1792 |
-
"grad_norm": 0.
|
| 1793 |
"learning_rate": 9.673307001748661e-05,
|
| 1794 |
-
"loss": 0.
|
| 1795 |
"step": 1225
|
| 1796 |
},
|
| 1797 |
{
|
| 1798 |
"epoch": 8.424657534246576,
|
| 1799 |
-
"grad_norm": 0.
|
| 1800 |
"learning_rate": 9.593665360080599e-05,
|
| 1801 |
-
"loss": 0.
|
| 1802 |
"step": 1230
|
| 1803 |
},
|
| 1804 |
{
|
| 1805 |
"epoch": 8.45890410958904,
|
| 1806 |
-
"grad_norm": 0.
|
| 1807 |
"learning_rate": 9.514049526038418e-05,
|
| 1808 |
-
"loss": 0.
|
| 1809 |
"step": 1235
|
| 1810 |
},
|
| 1811 |
{
|
| 1812 |
"epoch": 8.493150684931507,
|
| 1813 |
-
"grad_norm": 0.
|
| 1814 |
"learning_rate": 9.43446455628097e-05,
|
| 1815 |
-
"loss": 0.
|
| 1816 |
"step": 1240
|
| 1817 |
},
|
| 1818 |
{
|
| 1819 |
"epoch": 8.527397260273972,
|
| 1820 |
-
"grad_norm": 0.
|
| 1821 |
"learning_rate": 9.354915505506839e-05,
|
| 1822 |
-
"loss": 0.
|
| 1823 |
"step": 1245
|
| 1824 |
},
|
| 1825 |
{
|
| 1826 |
"epoch": 8.561643835616438,
|
| 1827 |
-
"grad_norm": 0.
|
| 1828 |
"learning_rate": 9.27540742613326e-05,
|
| 1829 |
-
"loss": 0.
|
| 1830 |
"step": 1250
|
| 1831 |
},
|
| 1832 |
{
|
| 1833 |
"epoch": 8.595890410958905,
|
| 1834 |
-
"grad_norm": 0.
|
| 1835 |
"learning_rate": 9.195945367975256e-05,
|
| 1836 |
-
"loss": 0.
|
| 1837 |
"step": 1255
|
| 1838 |
},
|
| 1839 |
{
|
| 1840 |
"epoch": 8.63013698630137,
|
| 1841 |
-
"grad_norm": 0.
|
| 1842 |
"learning_rate": 9.116534377924883e-05,
|
| 1843 |
-
"loss": 0.
|
| 1844 |
"step": 1260
|
| 1845 |
},
|
| 1846 |
{
|
| 1847 |
"epoch": 8.664383561643836,
|
| 1848 |
-
"grad_norm": 0.
|
| 1849 |
"learning_rate": 9.037179499630703e-05,
|
| 1850 |
-
"loss": 0.
|
| 1851 |
"step": 1265
|
| 1852 |
},
|
| 1853 |
{
|
| 1854 |
"epoch": 8.698630136986301,
|
| 1855 |
-
"grad_norm": 0.
|
| 1856 |
"learning_rate": 8.957885773177438e-05,
|
| 1857 |
-
"loss": 0.
|
| 1858 |
"step": 1270
|
| 1859 |
},
|
| 1860 |
{
|
| 1861 |
"epoch": 8.732876712328768,
|
| 1862 |
-
"grad_norm": 0.
|
| 1863 |
"learning_rate": 8.878658234765858e-05,
|
| 1864 |
-
"loss": 0.
|
| 1865 |
"step": 1275
|
| 1866 |
},
|
| 1867 |
{
|
| 1868 |
"epoch": 8.767123287671232,
|
| 1869 |
-
"grad_norm": 0.
|
| 1870 |
"learning_rate": 8.799501916392912e-05,
|
| 1871 |
-
"loss": 0.
|
| 1872 |
"step": 1280
|
| 1873 |
},
|
| 1874 |
{
|
| 1875 |
"epoch": 8.801369863013699,
|
| 1876 |
-
"grad_norm": 0.
|
| 1877 |
"learning_rate": 8.720421845532151e-05,
|
| 1878 |
-
"loss": 0.
|
| 1879 |
"step": 1285
|
| 1880 |
},
|
| 1881 |
{
|
| 1882 |
"epoch": 8.835616438356164,
|
| 1883 |
-
"grad_norm": 0.
|
| 1884 |
"learning_rate": 8.641423044814374e-05,
|
| 1885 |
-
"loss": 0.
|
| 1886 |
"step": 1290
|
| 1887 |
},
|
| 1888 |
{
|
| 1889 |
"epoch": 8.86986301369863,
|
| 1890 |
-
"grad_norm": 0.
|
| 1891 |
"learning_rate": 8.562510531708677e-05,
|
| 1892 |
-
"loss": 0.
|
| 1893 |
"step": 1295
|
| 1894 |
},
|
| 1895 |
{
|
| 1896 |
"epoch": 8.904109589041095,
|
| 1897 |
-
"grad_norm": 0.
|
| 1898 |
"learning_rate": 8.48368931820373e-05,
|
| 1899 |
-
"loss": 0.
|
| 1900 |
"step": 1300
|
| 1901 |
},
|
| 1902 |
{
|
| 1903 |
"epoch": 8.938356164383562,
|
| 1904 |
-
"grad_norm": 0.
|
| 1905 |
"learning_rate": 8.404964410489485e-05,
|
| 1906 |
-
"loss": 0.
|
| 1907 |
"step": 1305
|
| 1908 |
},
|
| 1909 |
{
|
| 1910 |
"epoch": 8.972602739726028,
|
| 1911 |
-
"grad_norm": 0.
|
| 1912 |
"learning_rate": 8.32634080863919e-05,
|
| 1913 |
-
"loss": 0.
|
| 1914 |
"step": 1310
|
| 1915 |
},
|
| 1916 |
{
|
| 1917 |
"epoch": 9.0,
|
| 1918 |
-
"eval_loss": 2.
|
| 1919 |
-
"eval_runtime": 0.
|
| 1920 |
-
"eval_samples_per_second": 18.
|
| 1921 |
-
"eval_steps_per_second": 1.
|
| 1922 |
"step": 1314
|
| 1923 |
},
|
| 1924 |
{
|
| 1925 |
"epoch": 9.006849315068493,
|
| 1926 |
-
"grad_norm": 0.
|
| 1927 |
"learning_rate": 8.247823506291844e-05,
|
| 1928 |
-
"loss": 0.
|
| 1929 |
"step": 1315
|
| 1930 |
},
|
| 1931 |
{
|
| 1932 |
"epoch": 9.04109589041096,
|
| 1933 |
-
"grad_norm": 0.
|
| 1934 |
"learning_rate": 8.169417490335007e-05,
|
| 1935 |
-
"loss": 0.
|
| 1936 |
"step": 1320
|
| 1937 |
},
|
| 1938 |
{
|
| 1939 |
"epoch": 9.075342465753424,
|
| 1940 |
-
"grad_norm": 0.
|
| 1941 |
"learning_rate": 8.091127740588094e-05,
|
| 1942 |
-
"loss": 0.
|
| 1943 |
"step": 1325
|
| 1944 |
},
|
| 1945 |
{
|
| 1946 |
"epoch": 9.10958904109589,
|
| 1947 |
-
"grad_norm": 0.
|
| 1948 |
"learning_rate": 8.012959229486061e-05,
|
| 1949 |
-
"loss": 0.
|
| 1950 |
"step": 1330
|
| 1951 |
},
|
| 1952 |
{
|
| 1953 |
"epoch": 9.143835616438356,
|
| 1954 |
-
"grad_norm": 0.
|
| 1955 |
"learning_rate": 7.934916921763628e-05,
|
| 1956 |
-
"loss": 0.
|
| 1957 |
"step": 1335
|
| 1958 |
},
|
| 1959 |
{
|
| 1960 |
"epoch": 9.178082191780822,
|
| 1961 |
-
"grad_norm": 0.
|
| 1962 |
"learning_rate": 7.857005774139907e-05,
|
| 1963 |
-
"loss": 0.
|
| 1964 |
"step": 1340
|
| 1965 |
},
|
| 1966 |
{
|
| 1967 |
"epoch": 9.212328767123287,
|
| 1968 |
-
"grad_norm": 0.
|
| 1969 |
"learning_rate": 7.779230735003628e-05,
|
| 1970 |
-
"loss": 0.
|
| 1971 |
"step": 1345
|
| 1972 |
},
|
| 1973 |
{
|
| 1974 |
"epoch": 9.246575342465754,
|
| 1975 |
-
"grad_norm": 0.
|
| 1976 |
"learning_rate": 7.701596744098818e-05,
|
| 1977 |
-
"loss": 0.
|
| 1978 |
"step": 1350
|
| 1979 |
},
|
| 1980 |
{
|
| 1981 |
"epoch": 9.280821917808218,
|
| 1982 |
-
"grad_norm": 0.
|
| 1983 |
"learning_rate": 7.624108732211081e-05,
|
| 1984 |
-
"loss": 0.
|
| 1985 |
"step": 1355
|
| 1986 |
},
|
| 1987 |
{
|
| 1988 |
"epoch": 9.315068493150685,
|
| 1989 |
-
"grad_norm": 0.
|
| 1990 |
"learning_rate": 7.54677162085442e-05,
|
| 1991 |
-
"loss": 0.
|
| 1992 |
"step": 1360
|
| 1993 |
},
|
| 1994 |
{
|
| 1995 |
"epoch": 9.349315068493151,
|
| 1996 |
-
"grad_norm": 0.
|
| 1997 |
"learning_rate": 7.469590321958662e-05,
|
| 1998 |
-
"loss": 0.
|
| 1999 |
"step": 1365
|
| 2000 |
},
|
| 2001 |
{
|
| 2002 |
"epoch": 9.383561643835616,
|
| 2003 |
"grad_norm": 0.43359375,
|
| 2004 |
"learning_rate": 7.392569737557474e-05,
|
| 2005 |
-
"loss": 0.
|
| 2006 |
"step": 1370
|
| 2007 |
},
|
| 2008 |
{
|
| 2009 |
"epoch": 9.417808219178083,
|
| 2010 |
-
"grad_norm": 0.
|
| 2011 |
"learning_rate": 7.31571475947703e-05,
|
| 2012 |
-
"loss": 0.
|
| 2013 |
"step": 1375
|
| 2014 |
},
|
| 2015 |
{
|
| 2016 |
"epoch": 9.452054794520548,
|
| 2017 |
-
"grad_norm": 0.
|
| 2018 |
"learning_rate": 7.239030269025311e-05,
|
| 2019 |
-
"loss": 0.
|
| 2020 |
"step": 1380
|
| 2021 |
},
|
| 2022 |
{
|
| 2023 |
"epoch": 9.486301369863014,
|
| 2024 |
-
"grad_norm": 0.
|
| 2025 |
"learning_rate": 7.162521136682085e-05,
|
| 2026 |
-
"loss": 0.
|
| 2027 |
"step": 1385
|
| 2028 |
},
|
| 2029 |
{
|
| 2030 |
"epoch": 9.520547945205479,
|
| 2031 |
-
"grad_norm": 0.
|
| 2032 |
"learning_rate": 7.08619222178954e-05,
|
| 2033 |
-
"loss": 0.
|
| 2034 |
"step": 1390
|
| 2035 |
},
|
| 2036 |
{
|
| 2037 |
"epoch": 9.554794520547945,
|
| 2038 |
-
"grad_norm": 0.
|
| 2039 |
"learning_rate": 7.010048372243698e-05,
|
| 2040 |
-
"loss": 0.
|
| 2041 |
"step": 1395
|
| 2042 |
},
|
| 2043 |
{
|
| 2044 |
"epoch": 9.58904109589041,
|
| 2045 |
-
"grad_norm": 0.
|
| 2046 |
"learning_rate": 6.934094424186459e-05,
|
| 2047 |
-
"loss": 0.
|
| 2048 |
"step": 1400
|
| 2049 |
},
|
| 2050 |
{
|
| 2051 |
"epoch": 9.623287671232877,
|
| 2052 |
-
"grad_norm": 0.
|
| 2053 |
"learning_rate": 6.858335201698485e-05,
|
| 2054 |
-
"loss": 0.
|
| 2055 |
"step": 1405
|
| 2056 |
},
|
| 2057 |
{
|
| 2058 |
"epoch": 9.657534246575342,
|
| 2059 |
-
"grad_norm": 0.
|
| 2060 |
"learning_rate": 6.782775516492771e-05,
|
| 2061 |
-
"loss": 0.
|
| 2062 |
"step": 1410
|
| 2063 |
},
|
| 2064 |
{
|
| 2065 |
"epoch": 9.691780821917808,
|
| 2066 |
-
"grad_norm": 0.
|
| 2067 |
"learning_rate": 6.70742016760907e-05,
|
| 2068 |
-
"loss": 0.
|
| 2069 |
"step": 1415
|
| 2070 |
},
|
| 2071 |
{
|
| 2072 |
"epoch": 9.726027397260275,
|
| 2073 |
-
"grad_norm": 0.
|
| 2074 |
"learning_rate": 6.632273941109064e-05,
|
| 2075 |
-
"loss": 0.
|
| 2076 |
"step": 1420
|
| 2077 |
},
|
| 2078 |
{
|
| 2079 |
"epoch": 9.76027397260274,
|
| 2080 |
-
"grad_norm": 0.
|
| 2081 |
"learning_rate": 6.5573416097724e-05,
|
| 2082 |
-
"loss": 0.
|
| 2083 |
"step": 1425
|
| 2084 |
},
|
| 2085 |
{
|
| 2086 |
"epoch": 9.794520547945206,
|
| 2087 |
-
"grad_norm": 0.
|
| 2088 |
"learning_rate": 6.482627932793553e-05,
|
| 2089 |
-
"loss": 0.
|
| 2090 |
"step": 1430
|
| 2091 |
},
|
| 2092 |
{
|
| 2093 |
"epoch": 9.82876712328767,
|
| 2094 |
-
"grad_norm": 0.
|
| 2095 |
"learning_rate": 6.408137655479554e-05,
|
| 2096 |
-
"loss": 0.
|
| 2097 |
"step": 1435
|
| 2098 |
},
|
| 2099 |
{
|
| 2100 |
"epoch": 9.863013698630137,
|
| 2101 |
-
"grad_norm": 0.
|
| 2102 |
"learning_rate": 6.333875508948593e-05,
|
| 2103 |
-
"loss": 0.
|
| 2104 |
"step": 1440
|
| 2105 |
},
|
| 2106 |
{
|
| 2107 |
"epoch": 9.897260273972602,
|
| 2108 |
-
"grad_norm": 0.
|
| 2109 |
"learning_rate": 6.259846209829551e-05,
|
| 2110 |
-
"loss": 0.
|
| 2111 |
"step": 1445
|
| 2112 |
},
|
| 2113 |
{
|
| 2114 |
"epoch": 9.931506849315069,
|
| 2115 |
-
"grad_norm": 0.
|
| 2116 |
"learning_rate": 6.186054459962399e-05,
|
| 2117 |
-
"loss": 0.
|
| 2118 |
"step": 1450
|
| 2119 |
},
|
| 2120 |
{
|
| 2121 |
"epoch": 9.965753424657533,
|
| 2122 |
-
"grad_norm": 0.
|
| 2123 |
"learning_rate": 6.112504946099604e-05,
|
| 2124 |
-
"loss": 0.
|
| 2125 |
"step": 1455
|
| 2126 |
},
|
| 2127 |
{
|
| 2128 |
"epoch": 10.0,
|
| 2129 |
-
"grad_norm": 0.
|
| 2130 |
"learning_rate": 6.039202339608432e-05,
|
| 2131 |
-
"loss": 0.
|
| 2132 |
"step": 1460
|
| 2133 |
},
|
| 2134 |
{
|
| 2135 |
"epoch": 10.0,
|
| 2136 |
-
"eval_loss": 2.
|
| 2137 |
-
"eval_runtime": 0.
|
| 2138 |
-
"eval_samples_per_second": 18.
|
| 2139 |
-
"eval_steps_per_second": 1.
|
| 2140 |
"step": 1460
|
| 2141 |
},
|
| 2142 |
{
|
| 2143 |
"epoch": 10.034246575342467,
|
| 2144 |
-
"grad_norm": 0.
|
| 2145 |
"learning_rate": 5.966151296174268e-05,
|
| 2146 |
-
"loss": 0.
|
| 2147 |
"step": 1465
|
| 2148 |
},
|
| 2149 |
{
|
| 2150 |
"epoch": 10.068493150684931,
|
| 2151 |
-
"grad_norm": 0.
|
| 2152 |
"learning_rate": 5.8933564555049105e-05,
|
| 2153 |
-
"loss": 0.
|
| 2154 |
"step": 1470
|
| 2155 |
},
|
| 2156 |
{
|
| 2157 |
"epoch": 10.102739726027398,
|
| 2158 |
-
"grad_norm": 0.
|
| 2159 |
"learning_rate": 5.820822441035899e-05,
|
| 2160 |
-
"loss": 0.
|
| 2161 |
"step": 1475
|
| 2162 |
},
|
| 2163 |
{
|
| 2164 |
"epoch": 10.136986301369863,
|
| 2165 |
-
"grad_norm": 0.
|
| 2166 |
"learning_rate": 5.7485538596368496e-05,
|
| 2167 |
-
"loss": 0.
|
| 2168 |
"step": 1480
|
| 2169 |
},
|
| 2170 |
{
|
| 2171 |
"epoch": 10.17123287671233,
|
| 2172 |
"grad_norm": 0.41015625,
|
| 2173 |
"learning_rate": 5.6765553013188766e-05,
|
| 2174 |
-
"loss": 0.
|
| 2175 |
"step": 1485
|
| 2176 |
},
|
| 2177 |
{
|
| 2178 |
"epoch": 10.205479452054794,
|
| 2179 |
-
"grad_norm": 0.
|
| 2180 |
"learning_rate": 5.6048313389430484e-05,
|
| 2181 |
-
"loss": 0.
|
| 2182 |
"step": 1490
|
| 2183 |
},
|
| 2184 |
{
|
| 2185 |
"epoch": 10.23972602739726,
|
| 2186 |
-
"grad_norm": 0.
|
| 2187 |
"learning_rate": 5.533386527929962e-05,
|
| 2188 |
-
"loss": 0.
|
| 2189 |
"step": 1495
|
| 2190 |
},
|
| 2191 |
{
|
| 2192 |
"epoch": 10.273972602739725,
|
| 2193 |
-
"grad_norm": 0.
|
| 2194 |
"learning_rate": 5.462225405970401e-05,
|
| 2195 |
-
"loss": 0.
|
| 2196 |
"step": 1500
|
| 2197 |
},
|
| 2198 |
{
|
| 2199 |
-
"epoch": 10.
|
| 2200 |
-
"
|
| 2201 |
-
"
|
| 2202 |
-
"
|
| 2203 |
-
"
|
| 2204 |
-
|
| 2205 |
-
|
| 2206 |
-
"epoch": 10.342465753424657,
|
| 2207 |
-
"grad_norm": 0.412109375,
|
| 2208 |
-
"learning_rate": 5.3207722895979406e-05,
|
| 2209 |
-
"loss": 0.9602,
|
| 2210 |
-
"step": 1510
|
| 2211 |
-
},
|
| 2212 |
-
{
|
| 2213 |
-
"epoch": 10.376712328767123,
|
| 2214 |
-
"grad_norm": 0.41015625,
|
| 2215 |
-
"learning_rate": 5.2504892793295e-05,
|
| 2216 |
-
"loss": 0.9607,
|
| 2217 |
-
"step": 1515
|
| 2218 |
-
},
|
| 2219 |
-
{
|
| 2220 |
-
"epoch": 10.41095890410959,
|
| 2221 |
-
"grad_norm": 0.5,
|
| 2222 |
-
"learning_rate": 5.1805079258329056e-05,
|
| 2223 |
-
"loss": 0.9658,
|
| 2224 |
-
"step": 1520
|
| 2225 |
-
},
|
| 2226 |
-
{
|
| 2227 |
-
"epoch": 10.445205479452055,
|
| 2228 |
-
"grad_norm": 0.5078125,
|
| 2229 |
-
"learning_rate": 5.110832673850039e-05,
|
| 2230 |
-
"loss": 0.9648,
|
| 2231 |
-
"step": 1525
|
| 2232 |
-
},
|
| 2233 |
-
{
|
| 2234 |
-
"epoch": 10.479452054794521,
|
| 2235 |
-
"grad_norm": 0.451171875,
|
| 2236 |
-
"learning_rate": 5.041467948681269e-05,
|
| 2237 |
-
"loss": 0.9732,
|
| 2238 |
-
"step": 1530
|
| 2239 |
-
},
|
| 2240 |
-
{
|
| 2241 |
-
"epoch": 10.513698630136986,
|
| 2242 |
-
"grad_norm": 0.439453125,
|
| 2243 |
-
"learning_rate": 4.9724181559044234e-05,
|
| 2244 |
-
"loss": 0.9681,
|
| 2245 |
-
"step": 1535
|
| 2246 |
-
},
|
| 2247 |
-
{
|
| 2248 |
-
"epoch": 10.547945205479452,
|
| 2249 |
-
"grad_norm": 0.404296875,
|
| 2250 |
-
"learning_rate": 4.903687681094942e-05,
|
| 2251 |
-
"loss": 0.9639,
|
| 2252 |
-
"step": 1540
|
| 2253 |
-
},
|
| 2254 |
-
{
|
| 2255 |
-
"epoch": 10.582191780821917,
|
| 2256 |
-
"grad_norm": 0.412109375,
|
| 2257 |
-
"learning_rate": 4.835280889547351e-05,
|
| 2258 |
-
"loss": 0.9579,
|
| 2259 |
-
"step": 1545
|
| 2260 |
-
},
|
| 2261 |
-
{
|
| 2262 |
-
"epoch": 10.616438356164384,
|
| 2263 |
-
"grad_norm": 0.41015625,
|
| 2264 |
-
"learning_rate": 4.767202125998005e-05,
|
| 2265 |
-
"loss": 0.9553,
|
| 2266 |
-
"step": 1550
|
| 2267 |
-
},
|
| 2268 |
-
{
|
| 2269 |
-
"epoch": 10.650684931506849,
|
| 2270 |
-
"grad_norm": 0.41796875,
|
| 2271 |
-
"learning_rate": 4.699455714349152e-05,
|
| 2272 |
-
"loss": 0.9512,
|
| 2273 |
-
"step": 1555
|
| 2274 |
-
},
|
| 2275 |
-
{
|
| 2276 |
-
"epoch": 10.684931506849315,
|
| 2277 |
-
"grad_norm": 0.416015625,
|
| 2278 |
-
"learning_rate": 4.6320459573942856e-05,
|
| 2279 |
-
"loss": 0.968,
|
| 2280 |
-
"step": 1560
|
| 2281 |
-
},
|
| 2282 |
-
{
|
| 2283 |
-
"epoch": 10.719178082191782,
|
| 2284 |
-
"grad_norm": 0.416015625,
|
| 2285 |
-
"learning_rate": 4.564977136544873e-05,
|
| 2286 |
-
"loss": 0.9617,
|
| 2287 |
-
"step": 1565
|
| 2288 |
-
},
|
| 2289 |
-
{
|
| 2290 |
-
"epoch": 10.753424657534246,
|
| 2291 |
-
"grad_norm": 0.421875,
|
| 2292 |
-
"learning_rate": 4.49825351155843e-05,
|
| 2293 |
-
"loss": 0.9749,
|
| 2294 |
-
"step": 1570
|
| 2295 |
-
},
|
| 2296 |
-
{
|
| 2297 |
-
"epoch": 10.787671232876713,
|
| 2298 |
-
"grad_norm": 0.44140625,
|
| 2299 |
-
"learning_rate": 4.431879320267972e-05,
|
| 2300 |
-
"loss": 0.9662,
|
| 2301 |
-
"step": 1575
|
| 2302 |
-
},
|
| 2303 |
-
{
|
| 2304 |
-
"epoch": 10.821917808219178,
|
| 2305 |
-
"grad_norm": 0.412109375,
|
| 2306 |
-
"learning_rate": 4.3658587783128425e-05,
|
| 2307 |
-
"loss": 0.9661,
|
| 2308 |
-
"step": 1580
|
| 2309 |
-
},
|
| 2310 |
-
{
|
| 2311 |
-
"epoch": 10.856164383561644,
|
| 2312 |
-
"grad_norm": 0.4609375,
|
| 2313 |
-
"learning_rate": 4.300196078870982e-05,
|
| 2314 |
-
"loss": 0.9571,
|
| 2315 |
-
"step": 1585
|
| 2316 |
-
},
|
| 2317 |
-
{
|
| 2318 |
-
"epoch": 10.89041095890411,
|
| 2319 |
-
"grad_norm": 0.41015625,
|
| 2320 |
-
"learning_rate": 4.2348953923925916e-05,
|
| 2321 |
-
"loss": 0.9657,
|
| 2322 |
-
"step": 1590
|
| 2323 |
-
},
|
| 2324 |
-
{
|
| 2325 |
-
"epoch": 10.924657534246576,
|
| 2326 |
-
"grad_norm": 0.43359375,
|
| 2327 |
-
"learning_rate": 4.16996086633526e-05,
|
| 2328 |
-
"loss": 0.9587,
|
| 2329 |
-
"step": 1595
|
| 2330 |
-
},
|
| 2331 |
-
{
|
| 2332 |
-
"epoch": 10.95890410958904,
|
| 2333 |
-
"grad_norm": 0.390625,
|
| 2334 |
-
"learning_rate": 4.105396624900538e-05,
|
| 2335 |
-
"loss": 0.9548,
|
| 2336 |
-
"step": 1600
|
| 2337 |
-
},
|
| 2338 |
-
{
|
| 2339 |
-
"epoch": 10.993150684931507,
|
| 2340 |
-
"grad_norm": 0.427734375,
|
| 2341 |
-
"learning_rate": 4.041206768772022e-05,
|
| 2342 |
-
"loss": 0.952,
|
| 2343 |
-
"step": 1605
|
| 2344 |
-
},
|
| 2345 |
-
{
|
| 2346 |
-
"epoch": 11.0,
|
| 2347 |
-
"eval_loss": 2.5889077186584473,
|
| 2348 |
-
"eval_runtime": 0.5538,
|
| 2349 |
-
"eval_samples_per_second": 18.057,
|
| 2350 |
-
"eval_steps_per_second": 1.806,
|
| 2351 |
-
"step": 1606
|
| 2352 |
-
},
|
| 2353 |
-
{
|
| 2354 |
-
"epoch": 11.027397260273972,
|
| 2355 |
-
"grad_norm": 0.416015625,
|
| 2356 |
-
"learning_rate": 3.977395374854871e-05,
|
| 2357 |
-
"loss": 0.9434,
|
| 2358 |
-
"step": 1610
|
| 2359 |
-
},
|
| 2360 |
-
{
|
| 2361 |
-
"epoch": 11.061643835616438,
|
| 2362 |
-
"grad_norm": 0.419921875,
|
| 2363 |
-
"learning_rate": 3.913966496016891e-05,
|
| 2364 |
-
"loss": 0.9579,
|
| 2365 |
-
"step": 1615
|
| 2366 |
-
},
|
| 2367 |
-
{
|
| 2368 |
-
"epoch": 11.095890410958905,
|
| 2369 |
-
"grad_norm": 0.453125,
|
| 2370 |
-
"learning_rate": 3.850924160831115e-05,
|
| 2371 |
-
"loss": 0.9524,
|
| 2372 |
-
"step": 1620
|
| 2373 |
-
},
|
| 2374 |
-
{
|
| 2375 |
-
"epoch": 11.13013698630137,
|
| 2376 |
-
"grad_norm": 0.42578125,
|
| 2377 |
-
"learning_rate": 3.788272373319955e-05,
|
| 2378 |
-
"loss": 0.9618,
|
| 2379 |
-
"step": 1625
|
| 2380 |
-
},
|
| 2381 |
-
{
|
| 2382 |
-
"epoch": 11.164383561643836,
|
| 2383 |
-
"grad_norm": 0.40625,
|
| 2384 |
-
"learning_rate": 3.726015112700859e-05,
|
| 2385 |
-
"loss": 0.9503,
|
| 2386 |
-
"step": 1630
|
| 2387 |
-
},
|
| 2388 |
-
{
|
| 2389 |
-
"epoch": 11.198630136986301,
|
| 2390 |
-
"grad_norm": 0.41796875,
|
| 2391 |
-
"learning_rate": 3.6641563331336125e-05,
|
| 2392 |
-
"loss": 0.9475,
|
| 2393 |
-
"step": 1635
|
| 2394 |
-
},
|
| 2395 |
-
{
|
| 2396 |
-
"epoch": 11.232876712328768,
|
| 2397 |
-
"grad_norm": 0.41796875,
|
| 2398 |
-
"learning_rate": 3.6026999634691725e-05,
|
| 2399 |
-
"loss": 0.945,
|
| 2400 |
-
"step": 1640
|
| 2401 |
-
},
|
| 2402 |
-
{
|
| 2403 |
-
"epoch": 11.267123287671232,
|
| 2404 |
-
"grad_norm": 0.40234375,
|
| 2405 |
-
"learning_rate": 3.541649907000147e-05,
|
| 2406 |
-
"loss": 0.9528,
|
| 2407 |
-
"step": 1645
|
| 2408 |
-
},
|
| 2409 |
-
{
|
| 2410 |
-
"epoch": 11.301369863013699,
|
| 2411 |
-
"grad_norm": 0.423828125,
|
| 2412 |
-
"learning_rate": 3.4810100412128747e-05,
|
| 2413 |
-
"loss": 0.946,
|
| 2414 |
-
"step": 1650
|
| 2415 |
-
},
|
| 2416 |
-
{
|
| 2417 |
-
"epoch": 11.335616438356164,
|
| 2418 |
-
"grad_norm": 0.404296875,
|
| 2419 |
-
"learning_rate": 3.42078421754117e-05,
|
| 2420 |
-
"loss": 0.9535,
|
| 2421 |
-
"step": 1655
|
| 2422 |
-
},
|
| 2423 |
-
{
|
| 2424 |
-
"epoch": 11.36986301369863,
|
| 2425 |
-
"grad_norm": 0.41015625,
|
| 2426 |
-
"learning_rate": 3.360976261121684e-05,
|
| 2427 |
-
"loss": 0.962,
|
| 2428 |
-
"step": 1660
|
| 2429 |
-
},
|
| 2430 |
-
{
|
| 2431 |
-
"epoch": 11.404109589041095,
|
| 2432 |
-
"grad_norm": 0.412109375,
|
| 2433 |
-
"learning_rate": 3.3015899705509734e-05,
|
| 2434 |
-
"loss": 0.9503,
|
| 2435 |
-
"step": 1665
|
| 2436 |
-
},
|
| 2437 |
-
{
|
| 2438 |
-
"epoch": 11.438356164383562,
|
| 2439 |
-
"grad_norm": 0.423828125,
|
| 2440 |
-
"learning_rate": 3.242629117644229e-05,
|
| 2441 |
-
"loss": 0.9564,
|
| 2442 |
-
"step": 1670
|
| 2443 |
-
},
|
| 2444 |
-
{
|
| 2445 |
-
"epoch": 11.472602739726028,
|
| 2446 |
-
"grad_norm": 0.41796875,
|
| 2447 |
-
"learning_rate": 3.184097447195732e-05,
|
| 2448 |
-
"loss": 0.9714,
|
| 2449 |
-
"step": 1675
|
| 2450 |
-
},
|
| 2451 |
-
{
|
| 2452 |
-
"epoch": 11.506849315068493,
|
| 2453 |
-
"grad_norm": 0.404296875,
|
| 2454 |
-
"learning_rate": 3.125998676740987e-05,
|
| 2455 |
-
"loss": 0.9516,
|
| 2456 |
-
"step": 1680
|
| 2457 |
-
},
|
| 2458 |
-
{
|
| 2459 |
-
"epoch": 11.54109589041096,
|
| 2460 |
-
"grad_norm": 0.416015625,
|
| 2461 |
-
"learning_rate": 3.068336496320631e-05,
|
| 2462 |
-
"loss": 0.9634,
|
| 2463 |
-
"step": 1685
|
| 2464 |
-
},
|
| 2465 |
-
{
|
| 2466 |
-
"epoch": 11.575342465753424,
|
| 2467 |
-
"grad_norm": 0.419921875,
|
| 2468 |
-
"learning_rate": 3.0111145682460507e-05,
|
| 2469 |
-
"loss": 0.9578,
|
| 2470 |
-
"step": 1690
|
| 2471 |
-
},
|
| 2472 |
-
{
|
| 2473 |
-
"epoch": 11.60958904109589,
|
| 2474 |
-
"grad_norm": 0.412109375,
|
| 2475 |
-
"learning_rate": 2.9543365268667867e-05,
|
| 2476 |
-
"loss": 0.9551,
|
| 2477 |
-
"step": 1695
|
| 2478 |
-
},
|
| 2479 |
-
{
|
| 2480 |
-
"epoch": 11.643835616438356,
|
| 2481 |
-
"grad_norm": 0.404296875,
|
| 2482 |
-
"learning_rate": 2.8980059783396953e-05,
|
| 2483 |
-
"loss": 0.9585,
|
| 2484 |
-
"step": 1700
|
| 2485 |
-
},
|
| 2486 |
-
{
|
| 2487 |
-
"epoch": 11.678082191780822,
|
| 2488 |
-
"grad_norm": 0.390625,
|
| 2489 |
-
"learning_rate": 2.8421265003999286e-05,
|
| 2490 |
-
"loss": 0.9573,
|
| 2491 |
-
"step": 1705
|
| 2492 |
-
},
|
| 2493 |
-
{
|
| 2494 |
-
"epoch": 11.712328767123287,
|
| 2495 |
-
"grad_norm": 0.4140625,
|
| 2496 |
-
"learning_rate": 2.7867016421336776e-05,
|
| 2497 |
-
"loss": 0.9544,
|
| 2498 |
-
"step": 1710
|
| 2499 |
-
},
|
| 2500 |
-
{
|
| 2501 |
-
"epoch": 11.746575342465754,
|
| 2502 |
-
"grad_norm": 0.396484375,
|
| 2503 |
-
"learning_rate": 2.7317349237527724e-05,
|
| 2504 |
-
"loss": 0.9432,
|
| 2505 |
-
"step": 1715
|
| 2506 |
-
},
|
| 2507 |
-
{
|
| 2508 |
-
"epoch": 11.780821917808218,
|
| 2509 |
-
"grad_norm": 0.41015625,
|
| 2510 |
-
"learning_rate": 2.6772298363710956e-05,
|
| 2511 |
-
"loss": 0.9567,
|
| 2512 |
-
"step": 1720
|
| 2513 |
-
},
|
| 2514 |
-
{
|
| 2515 |
-
"epoch": 11.815068493150685,
|
| 2516 |
-
"grad_norm": 0.431640625,
|
| 2517 |
-
"learning_rate": 2.6231898417828603e-05,
|
| 2518 |
-
"loss": 0.9667,
|
| 2519 |
-
"step": 1725
|
| 2520 |
-
},
|
| 2521 |
-
{
|
| 2522 |
-
"epoch": 11.849315068493151,
|
| 2523 |
-
"grad_norm": 0.421875,
|
| 2524 |
-
"learning_rate": 2.569618372242727e-05,
|
| 2525 |
-
"loss": 0.962,
|
| 2526 |
-
"step": 1730
|
| 2527 |
-
},
|
| 2528 |
-
{
|
| 2529 |
-
"epoch": 11.883561643835616,
|
| 2530 |
-
"grad_norm": 0.427734375,
|
| 2531 |
-
"learning_rate": 2.5165188302478215e-05,
|
| 2532 |
-
"loss": 0.9514,
|
| 2533 |
-
"step": 1735
|
| 2534 |
-
},
|
| 2535 |
-
{
|
| 2536 |
-
"epoch": 11.917808219178083,
|
| 2537 |
-
"grad_norm": 0.435546875,
|
| 2538 |
-
"learning_rate": 2.4638945883216235e-05,
|
| 2539 |
-
"loss": 0.9446,
|
| 2540 |
-
"step": 1740
|
| 2541 |
-
},
|
| 2542 |
-
{
|
| 2543 |
-
"epoch": 11.952054794520548,
|
| 2544 |
-
"grad_norm": 0.412109375,
|
| 2545 |
-
"learning_rate": 2.411748988799769e-05,
|
| 2546 |
-
"loss": 0.9473,
|
| 2547 |
-
"step": 1745
|
| 2548 |
-
},
|
| 2549 |
-
{
|
| 2550 |
-
"epoch": 11.986301369863014,
|
| 2551 |
-
"grad_norm": 0.4375,
|
| 2552 |
-
"learning_rate": 2.3600853436177672e-05,
|
| 2553 |
-
"loss": 0.97,
|
| 2554 |
-
"step": 1750
|
| 2555 |
-
},
|
| 2556 |
-
{
|
| 2557 |
-
"epoch": 12.0,
|
| 2558 |
-
"eval_loss": 2.5957212448120117,
|
| 2559 |
-
"eval_runtime": 0.5471,
|
| 2560 |
-
"eval_samples_per_second": 18.279,
|
| 2561 |
-
"eval_steps_per_second": 1.828,
|
| 2562 |
-
"step": 1752
|
| 2563 |
-
},
|
| 2564 |
-
{
|
| 2565 |
-
"epoch": 12.020547945205479,
|
| 2566 |
-
"grad_norm": 0.388671875,
|
| 2567 |
-
"learning_rate": 2.3089069341006565e-05,
|
| 2568 |
-
"loss": 0.9617,
|
| 2569 |
-
"step": 1755
|
| 2570 |
-
},
|
| 2571 |
-
{
|
| 2572 |
-
"epoch": 12.054794520547945,
|
| 2573 |
-
"grad_norm": 0.447265625,
|
| 2574 |
-
"learning_rate": 2.2582170107545852e-05,
|
| 2575 |
-
"loss": 0.9448,
|
| 2576 |
-
"step": 1760
|
| 2577 |
-
},
|
| 2578 |
-
{
|
| 2579 |
-
"epoch": 12.08904109589041,
|
| 2580 |
-
"grad_norm": 0.41015625,
|
| 2581 |
-
"learning_rate": 2.2080187930603668e-05,
|
| 2582 |
-
"loss": 0.9451,
|
| 2583 |
-
"step": 1765
|
| 2584 |
-
},
|
| 2585 |
-
{
|
| 2586 |
-
"epoch": 12.123287671232877,
|
| 2587 |
-
"grad_norm": 0.41796875,
|
| 2588 |
-
"learning_rate": 2.1583154692689976e-05,
|
| 2589 |
-
"loss": 0.9472,
|
| 2590 |
-
"step": 1770
|
| 2591 |
-
},
|
| 2592 |
-
{
|
| 2593 |
-
"epoch": 12.157534246575343,
|
| 2594 |
-
"grad_norm": 0.412109375,
|
| 2595 |
-
"learning_rate": 2.109110196199171e-05,
|
| 2596 |
-
"loss": 0.9536,
|
| 2597 |
-
"step": 1775
|
| 2598 |
-
},
|
| 2599 |
-
{
|
| 2600 |
-
"epoch": 12.191780821917808,
|
| 2601 |
-
"grad_norm": 0.3984375,
|
| 2602 |
-
"learning_rate": 2.0604060990367624e-05,
|
| 2603 |
-
"loss": 0.9578,
|
| 2604 |
-
"step": 1780
|
| 2605 |
-
},
|
| 2606 |
-
{
|
| 2607 |
-
"epoch": 12.226027397260275,
|
| 2608 |
-
"grad_norm": 0.412109375,
|
| 2609 |
-
"learning_rate": 2.0122062711363532e-05,
|
| 2610 |
-
"loss": 0.9515,
|
| 2611 |
-
"step": 1785
|
| 2612 |
-
},
|
| 2613 |
-
{
|
| 2614 |
-
"epoch": 12.26027397260274,
|
| 2615 |
-
"grad_norm": 0.423828125,
|
| 2616 |
-
"learning_rate": 1.9645137738247422e-05,
|
| 2617 |
-
"loss": 0.9438,
|
| 2618 |
-
"step": 1790
|
| 2619 |
-
},
|
| 2620 |
-
{
|
| 2621 |
-
"epoch": 12.294520547945206,
|
| 2622 |
-
"grad_norm": 0.40625,
|
| 2623 |
-
"learning_rate": 1.9173316362065384e-05,
|
| 2624 |
-
"loss": 0.9516,
|
| 2625 |
-
"step": 1795
|
| 2626 |
-
},
|
| 2627 |
-
{
|
| 2628 |
-
"epoch": 12.32876712328767,
|
| 2629 |
-
"grad_norm": 0.41796875,
|
| 2630 |
-
"learning_rate": 1.8706628549717452e-05,
|
| 2631 |
-
"loss": 0.9517,
|
| 2632 |
-
"step": 1800
|
| 2633 |
-
},
|
| 2634 |
-
{
|
| 2635 |
-
"epoch": 12.363013698630137,
|
| 2636 |
-
"grad_norm": 0.41015625,
|
| 2637 |
-
"learning_rate": 1.824510394205453e-05,
|
| 2638 |
-
"loss": 0.9475,
|
| 2639 |
-
"step": 1805
|
| 2640 |
-
},
|
| 2641 |
-
{
|
| 2642 |
-
"epoch": 12.397260273972602,
|
| 2643 |
-
"grad_norm": 0.412109375,
|
| 2644 |
-
"learning_rate": 1.7788771851995655e-05,
|
| 2645 |
-
"loss": 0.9536,
|
| 2646 |
-
"step": 1810
|
| 2647 |
-
},
|
| 2648 |
-
{
|
| 2649 |
-
"epoch": 12.431506849315069,
|
| 2650 |
-
"grad_norm": 0.421875,
|
| 2651 |
-
"learning_rate": 1.7337661262666294e-05,
|
| 2652 |
-
"loss": 0.9551,
|
| 2653 |
-
"step": 1815
|
| 2654 |
-
},
|
| 2655 |
-
{
|
| 2656 |
-
"epoch": 12.465753424657533,
|
| 2657 |
-
"grad_norm": 0.40625,
|
| 2658 |
-
"learning_rate": 1.6891800825557535e-05,
|
| 2659 |
-
"loss": 0.9537,
|
| 2660 |
-
"step": 1820
|
| 2661 |
-
},
|
| 2662 |
-
{
|
| 2663 |
-
"epoch": 12.5,
|
| 2664 |
-
"grad_norm": 0.419921875,
|
| 2665 |
-
"learning_rate": 1.6451218858706374e-05,
|
| 2666 |
-
"loss": 0.9516,
|
| 2667 |
-
"step": 1825
|
| 2668 |
-
},
|
| 2669 |
-
{
|
| 2670 |
-
"epoch": 12.534246575342467,
|
| 2671 |
-
"grad_norm": 0.408203125,
|
| 2672 |
-
"learning_rate": 1.601594334489702e-05,
|
| 2673 |
-
"loss": 0.9535,
|
| 2674 |
-
"step": 1830
|
| 2675 |
-
},
|
| 2676 |
-
{
|
| 2677 |
-
"epoch": 12.568493150684931,
|
| 2678 |
-
"grad_norm": 0.4375,
|
| 2679 |
-
"learning_rate": 1.5586001929883865e-05,
|
| 2680 |
-
"loss": 0.9489,
|
| 2681 |
-
"step": 1835
|
| 2682 |
-
},
|
| 2683 |
-
{
|
| 2684 |
-
"epoch": 12.602739726027398,
|
| 2685 |
-
"grad_norm": 0.41015625,
|
| 2686 |
-
"learning_rate": 1.516142192063521e-05,
|
| 2687 |
-
"loss": 0.9554,
|
| 2688 |
-
"step": 1840
|
| 2689 |
-
},
|
| 2690 |
-
{
|
| 2691 |
-
"epoch": 12.636986301369863,
|
| 2692 |
-
"grad_norm": 0.41015625,
|
| 2693 |
-
"learning_rate": 1.474223028359939e-05,
|
| 2694 |
-
"loss": 0.9518,
|
| 2695 |
-
"step": 1845
|
| 2696 |
-
},
|
| 2697 |
-
{
|
| 2698 |
-
"epoch": 12.67123287671233,
|
| 2699 |
-
"grad_norm": 0.41015625,
|
| 2700 |
-
"learning_rate": 1.4328453642991646e-05,
|
| 2701 |
-
"loss": 0.9565,
|
| 2702 |
-
"step": 1850
|
| 2703 |
-
},
|
| 2704 |
-
{
|
| 2705 |
-
"epoch": 12.705479452054794,
|
| 2706 |
-
"grad_norm": 0.396484375,
|
| 2707 |
-
"learning_rate": 1.392011827910341e-05,
|
| 2708 |
-
"loss": 0.9538,
|
| 2709 |
-
"step": 1855
|
| 2710 |
-
},
|
| 2711 |
-
{
|
| 2712 |
-
"epoch": 12.73972602739726,
|
| 2713 |
-
"grad_norm": 0.416015625,
|
| 2714 |
-
"learning_rate": 1.3517250126632986e-05,
|
| 2715 |
-
"loss": 0.9498,
|
| 2716 |
-
"step": 1860
|
| 2717 |
-
},
|
| 2718 |
-
{
|
| 2719 |
-
"epoch": 12.773972602739725,
|
| 2720 |
-
"grad_norm": 0.39453125,
|
| 2721 |
-
"learning_rate": 1.311987477303842e-05,
|
| 2722 |
-
"loss": 0.9468,
|
| 2723 |
-
"step": 1865
|
| 2724 |
-
},
|
| 2725 |
-
{
|
| 2726 |
-
"epoch": 12.808219178082192,
|
| 2727 |
-
"grad_norm": 0.40234375,
|
| 2728 |
-
"learning_rate": 1.2728017456912344e-05,
|
| 2729 |
-
"loss": 0.9587,
|
| 2730 |
-
"step": 1870
|
| 2731 |
-
},
|
| 2732 |
-
{
|
| 2733 |
-
"epoch": 12.842465753424658,
|
| 2734 |
-
"grad_norm": 0.419921875,
|
| 2735 |
-
"learning_rate": 1.2341703066379074e-05,
|
| 2736 |
-
"loss": 0.9463,
|
| 2737 |
-
"step": 1875
|
| 2738 |
-
},
|
| 2739 |
-
{
|
| 2740 |
-
"epoch": 12.876712328767123,
|
| 2741 |
-
"grad_norm": 0.3984375,
|
| 2742 |
-
"learning_rate": 1.1960956137513701e-05,
|
| 2743 |
-
"loss": 0.9506,
|
| 2744 |
-
"step": 1880
|
| 2745 |
-
},
|
| 2746 |
-
{
|
| 2747 |
-
"epoch": 12.91095890410959,
|
| 2748 |
-
"grad_norm": 0.408203125,
|
| 2749 |
-
"learning_rate": 1.158580085278398e-05,
|
| 2750 |
-
"loss": 0.9492,
|
| 2751 |
-
"step": 1885
|
| 2752 |
-
},
|
| 2753 |
-
{
|
| 2754 |
-
"epoch": 12.945205479452055,
|
| 2755 |
-
"grad_norm": 0.416015625,
|
| 2756 |
-
"learning_rate": 1.1216261039514087e-05,
|
| 2757 |
-
"loss": 0.9569,
|
| 2758 |
-
"step": 1890
|
| 2759 |
-
},
|
| 2760 |
-
{
|
| 2761 |
-
"epoch": 12.979452054794521,
|
| 2762 |
-
"grad_norm": 0.408203125,
|
| 2763 |
-
"learning_rate": 1.0852360168371656e-05,
|
| 2764 |
-
"loss": 0.9514,
|
| 2765 |
-
"step": 1895
|
| 2766 |
-
},
|
| 2767 |
-
{
|
| 2768 |
-
"epoch": 13.0,
|
| 2769 |
-
"eval_loss": 2.598764181137085,
|
| 2770 |
-
"eval_runtime": 0.5483,
|
| 2771 |
-
"eval_samples_per_second": 18.237,
|
| 2772 |
-
"eval_steps_per_second": 1.824,
|
| 2773 |
-
"step": 1898
|
| 2774 |
-
},
|
| 2775 |
-
{
|
| 2776 |
-
"epoch": 13.013698630136986,
|
| 2777 |
-
"grad_norm": 0.412109375,
|
| 2778 |
-
"learning_rate": 1.049412135187675e-05,
|
| 2779 |
-
"loss": 0.9556,
|
| 2780 |
-
"step": 1900
|
| 2781 |
-
},
|
| 2782 |
-
{
|
| 2783 |
-
"epoch": 13.047945205479452,
|
| 2784 |
-
"grad_norm": 0.40234375,
|
| 2785 |
-
"learning_rate": 1.0141567342934132e-05,
|
| 2786 |
-
"loss": 0.9543,
|
| 2787 |
-
"step": 1905
|
| 2788 |
-
},
|
| 2789 |
-
{
|
| 2790 |
-
"epoch": 13.082191780821917,
|
| 2791 |
-
"grad_norm": 0.423828125,
|
| 2792 |
-
"learning_rate": 9.794720533388024e-06,
|
| 2793 |
-
"loss": 0.947,
|
| 2794 |
-
"step": 1910
|
| 2795 |
-
},
|
| 2796 |
-
{
|
| 2797 |
-
"epoch": 13.116438356164384,
|
| 2798 |
-
"grad_norm": 0.408203125,
|
| 2799 |
-
"learning_rate": 9.453602952599982e-06,
|
| 2800 |
-
"loss": 0.9567,
|
| 2801 |
-
"step": 1915
|
| 2802 |
-
},
|
| 2803 |
-
{
|
| 2804 |
-
"epoch": 13.150684931506849,
|
| 2805 |
-
"grad_norm": 0.408203125,
|
| 2806 |
-
"learning_rate": 9.118236266049707e-06,
|
| 2807 |
-
"loss": 0.956,
|
| 2808 |
-
"step": 1920
|
| 2809 |
-
},
|
| 2810 |
-
{
|
| 2811 |
-
"epoch": 13.184931506849315,
|
| 2812 |
-
"grad_norm": 0.41015625,
|
| 2813 |
-
"learning_rate": 8.788641773959105e-06,
|
| 2814 |
-
"loss": 0.9508,
|
| 2815 |
-
"step": 1925
|
| 2816 |
-
},
|
| 2817 |
-
{
|
| 2818 |
-
"epoch": 13.219178082191782,
|
| 2819 |
-
"grad_norm": 0.419921875,
|
| 2820 |
-
"learning_rate": 8.464840409939267e-06,
|
| 2821 |
-
"loss": 0.9556,
|
| 2822 |
-
"step": 1930
|
| 2823 |
-
},
|
| 2824 |
-
{
|
| 2825 |
-
"epoch": 13.253424657534246,
|
| 2826 |
-
"grad_norm": 0.41015625,
|
| 2827 |
-
"learning_rate": 8.146852739661105e-06,
|
| 2828 |
-
"loss": 0.9577,
|
| 2829 |
-
"step": 1935
|
| 2830 |
-
},
|
| 2831 |
-
{
|
| 2832 |
-
"epoch": 13.287671232876713,
|
| 2833 |
-
"grad_norm": 0.400390625,
|
| 2834 |
-
"learning_rate": 7.834698959548914e-06,
|
| 2835 |
-
"loss": 0.9505,
|
| 2836 |
-
"step": 1940
|
| 2837 |
-
},
|
| 2838 |
-
{
|
| 2839 |
-
"epoch": 13.321917808219178,
|
| 2840 |
-
"grad_norm": 0.404296875,
|
| 2841 |
-
"learning_rate": 7.528398895497924e-06,
|
| 2842 |
-
"loss": 0.9556,
|
| 2843 |
-
"step": 1945
|
| 2844 |
-
},
|
| 2845 |
-
{
|
| 2846 |
-
"epoch": 13.356164383561644,
|
| 2847 |
-
"grad_norm": 0.400390625,
|
| 2848 |
-
"learning_rate": 7.2279720016148244e-06,
|
| 2849 |
-
"loss": 0.9445,
|
| 2850 |
-
"step": 1950
|
| 2851 |
-
},
|
| 2852 |
-
{
|
| 2853 |
-
"epoch": 13.39041095890411,
|
| 2854 |
-
"grad_norm": 0.40625,
|
| 2855 |
-
"learning_rate": 6.933437358982409e-06,
|
| 2856 |
-
"loss": 0.9491,
|
| 2857 |
-
"step": 1955
|
| 2858 |
-
},
|
| 2859 |
-
{
|
| 2860 |
-
"epoch": 13.424657534246576,
|
| 2861 |
-
"grad_norm": 0.3984375,
|
| 2862 |
-
"learning_rate": 6.6448136744474474e-06,
|
| 2863 |
-
"loss": 0.9528,
|
| 2864 |
-
"step": 1960
|
| 2865 |
-
},
|
| 2866 |
-
{
|
| 2867 |
-
"epoch": 13.45890410958904,
|
| 2868 |
-
"grad_norm": 0.40234375,
|
| 2869 |
-
"learning_rate": 6.36211927943271e-06,
|
| 2870 |
-
"loss": 0.9531,
|
| 2871 |
-
"step": 1965
|
| 2872 |
-
},
|
| 2873 |
-
{
|
| 2874 |
-
"epoch": 13.493150684931507,
|
| 2875 |
-
"grad_norm": 0.43359375,
|
| 2876 |
-
"learning_rate": 6.085372128772637e-06,
|
| 2877 |
-
"loss": 0.949,
|
| 2878 |
-
"step": 1970
|
| 2879 |
-
},
|
| 2880 |
-
{
|
| 2881 |
-
"epoch": 13.527397260273972,
|
| 2882 |
-
"grad_norm": 0.408203125,
|
| 2883 |
-
"learning_rate": 5.814589799572956e-06,
|
| 2884 |
-
"loss": 0.9538,
|
| 2885 |
-
"step": 1975
|
| 2886 |
-
},
|
| 2887 |
-
{
|
| 2888 |
-
"epoch": 13.561643835616438,
|
| 2889 |
-
"grad_norm": 0.40625,
|
| 2890 |
-
"learning_rate": 5.549789490094304e-06,
|
| 2891 |
-
"loss": 0.9481,
|
| 2892 |
-
"step": 1980
|
| 2893 |
-
},
|
| 2894 |
-
{
|
| 2895 |
-
"epoch": 13.595890410958905,
|
| 2896 |
-
"grad_norm": 0.412109375,
|
| 2897 |
-
"learning_rate": 5.290988018659937e-06,
|
| 2898 |
-
"loss": 0.9523,
|
| 2899 |
-
"step": 1985
|
| 2900 |
-
},
|
| 2901 |
-
{
|
| 2902 |
-
"epoch": 13.63013698630137,
|
| 2903 |
-
"grad_norm": 0.390625,
|
| 2904 |
-
"learning_rate": 5.038201822587474e-06,
|
| 2905 |
-
"loss": 0.9483,
|
| 2906 |
-
"step": 1990
|
| 2907 |
-
},
|
| 2908 |
-
{
|
| 2909 |
-
"epoch": 13.664383561643836,
|
| 2910 |
-
"grad_norm": 0.416015625,
|
| 2911 |
-
"learning_rate": 4.79144695714504e-06,
|
| 2912 |
-
"loss": 0.9478,
|
| 2913 |
-
"step": 1995
|
| 2914 |
-
},
|
| 2915 |
-
{
|
| 2916 |
-
"epoch": 13.698630136986301,
|
| 2917 |
-
"grad_norm": 0.404296875,
|
| 2918 |
-
"learning_rate": 4.550739094531386e-06,
|
| 2919 |
-
"loss": 0.9459,
|
| 2920 |
-
"step": 2000
|
| 2921 |
-
},
|
| 2922 |
-
{
|
| 2923 |
-
"epoch": 13.732876712328768,
|
| 2924 |
-
"grad_norm": 0.38671875,
|
| 2925 |
-
"learning_rate": 4.316093522880648e-06,
|
| 2926 |
-
"loss": 0.9474,
|
| 2927 |
-
"step": 2005
|
| 2928 |
-
},
|
| 2929 |
-
{
|
| 2930 |
-
"epoch": 13.767123287671232,
|
| 2931 |
-
"grad_norm": 0.392578125,
|
| 2932 |
-
"learning_rate": 4.087525145291204e-06,
|
| 2933 |
-
"loss": 0.9457,
|
| 2934 |
-
"step": 2010
|
| 2935 |
-
},
|
| 2936 |
-
{
|
| 2937 |
-
"epoch": 13.801369863013699,
|
| 2938 |
-
"grad_norm": 0.408203125,
|
| 2939 |
-
"learning_rate": 3.865048478879241e-06,
|
| 2940 |
-
"loss": 0.9483,
|
| 2941 |
-
"step": 2015
|
| 2942 |
-
},
|
| 2943 |
-
{
|
| 2944 |
-
"epoch": 13.835616438356164,
|
| 2945 |
-
"grad_norm": 0.404296875,
|
| 2946 |
-
"learning_rate": 3.6486776538566803e-06,
|
| 2947 |
-
"loss": 0.9491,
|
| 2948 |
-
"step": 2020
|
| 2949 |
-
},
|
| 2950 |
-
{
|
| 2951 |
-
"epoch": 13.86986301369863,
|
| 2952 |
-
"grad_norm": 0.41796875,
|
| 2953 |
-
"learning_rate": 3.4384264126337328e-06,
|
| 2954 |
-
"loss": 0.9497,
|
| 2955 |
-
"step": 2025
|
| 2956 |
-
},
|
| 2957 |
-
{
|
| 2958 |
-
"epoch": 13.904109589041095,
|
| 2959 |
-
"grad_norm": 0.396484375,
|
| 2960 |
-
"learning_rate": 3.2343081089460603e-06,
|
| 2961 |
-
"loss": 0.9514,
|
| 2962 |
-
"step": 2030
|
| 2963 |
-
},
|
| 2964 |
-
{
|
| 2965 |
-
"epoch": 13.938356164383562,
|
| 2966 |
-
"grad_norm": 0.40234375,
|
| 2967 |
-
"learning_rate": 3.0363357070066544e-06,
|
| 2968 |
-
"loss": 0.9484,
|
| 2969 |
-
"step": 2035
|
| 2970 |
-
},
|
| 2971 |
-
{
|
| 2972 |
-
"epoch": 13.972602739726028,
|
| 2973 |
-
"grad_norm": 0.431640625,
|
| 2974 |
-
"learning_rate": 2.8445217806824077e-06,
|
| 2975 |
-
"loss": 0.9469,
|
| 2976 |
-
"step": 2040
|
| 2977 |
-
},
|
| 2978 |
-
{
|
| 2979 |
-
"epoch": 14.0,
|
| 2980 |
-
"eval_loss": 2.599691867828369,
|
| 2981 |
-
"eval_runtime": 0.5385,
|
| 2982 |
-
"eval_samples_per_second": 18.57,
|
| 2983 |
-
"eval_steps_per_second": 1.857,
|
| 2984 |
-
"step": 2044
|
| 2985 |
-
},
|
| 2986 |
-
{
|
| 2987 |
-
"epoch": 14.006849315068493,
|
| 2988 |
-
"grad_norm": 0.4296875,
|
| 2989 |
-
"learning_rate": 2.658878512695562e-06,
|
| 2990 |
-
"loss": 0.9462,
|
| 2991 |
-
"step": 2045
|
| 2992 |
-
},
|
| 2993 |
-
{
|
| 2994 |
-
"epoch": 14.04109589041096,
|
| 2995 |
-
"grad_norm": 0.41015625,
|
| 2996 |
-
"learning_rate": 2.4794176938498837e-06,
|
| 2997 |
-
"loss": 0.9509,
|
| 2998 |
-
"step": 2050
|
| 2999 |
-
},
|
| 3000 |
-
{
|
| 3001 |
-
"epoch": 14.075342465753424,
|
| 3002 |
-
"grad_norm": 0.39453125,
|
| 3003 |
-
"learning_rate": 2.30615072228183e-06,
|
| 3004 |
-
"loss": 0.9438,
|
| 3005 |
-
"step": 2055
|
| 3006 |
-
},
|
| 3007 |
-
{
|
| 3008 |
-
"epoch": 14.10958904109589,
|
| 3009 |
-
"grad_norm": 0.400390625,
|
| 3010 |
-
"learning_rate": 2.139088602736616e-06,
|
| 3011 |
-
"loss": 0.9567,
|
| 3012 |
-
"step": 2060
|
| 3013 |
-
},
|
| 3014 |
-
{
|
| 3015 |
-
"epoch": 14.143835616438356,
|
| 3016 |
-
"grad_norm": 0.404296875,
|
| 3017 |
-
"learning_rate": 1.9782419458692193e-06,
|
| 3018 |
-
"loss": 0.9454,
|
| 3019 |
-
"step": 2065
|
| 3020 |
-
},
|
| 3021 |
-
{
|
| 3022 |
-
"epoch": 14.178082191780822,
|
| 3023 |
-
"grad_norm": 0.404296875,
|
| 3024 |
-
"learning_rate": 1.8236209675705274e-06,
|
| 3025 |
-
"loss": 0.9486,
|
| 3026 |
-
"step": 2070
|
| 3027 |
-
},
|
| 3028 |
-
{
|
| 3029 |
-
"epoch": 14.212328767123287,
|
| 3030 |
-
"grad_norm": 0.408203125,
|
| 3031 |
-
"learning_rate": 1.6752354883184717e-06,
|
| 3032 |
-
"loss": 0.9521,
|
| 3033 |
-
"step": 2075
|
| 3034 |
-
},
|
| 3035 |
-
{
|
| 3036 |
-
"epoch": 14.246575342465754,
|
| 3037 |
-
"grad_norm": 0.40625,
|
| 3038 |
-
"learning_rate": 1.5330949325542797e-06,
|
| 3039 |
-
"loss": 0.9556,
|
| 3040 |
-
"step": 2080
|
| 3041 |
-
},
|
| 3042 |
-
{
|
| 3043 |
-
"epoch": 14.280821917808218,
|
| 3044 |
-
"grad_norm": 0.408203125,
|
| 3045 |
-
"learning_rate": 1.397208328083921e-06,
|
| 3046 |
-
"loss": 0.9574,
|
| 3047 |
-
"step": 2085
|
| 3048 |
-
},
|
| 3049 |
-
{
|
| 3050 |
-
"epoch": 14.315068493150685,
|
| 3051 |
-
"grad_norm": 0.427734375,
|
| 3052 |
-
"learning_rate": 1.2675843055046765e-06,
|
| 3053 |
-
"loss": 0.9557,
|
| 3054 |
-
"step": 2090
|
| 3055 |
-
},
|
| 3056 |
-
{
|
| 3057 |
-
"epoch": 14.349315068493151,
|
| 3058 |
-
"grad_norm": 0.41015625,
|
| 3059 |
-
"learning_rate": 1.144231097657078e-06,
|
| 3060 |
-
"loss": 0.952,
|
| 3061 |
-
"step": 2095
|
| 3062 |
-
},
|
| 3063 |
-
{
|
| 3064 |
-
"epoch": 14.383561643835616,
|
| 3065 |
-
"grad_norm": 0.404296875,
|
| 3066 |
-
"learning_rate": 1.0271565391018922e-06,
|
| 3067 |
-
"loss": 0.9475,
|
| 3068 |
-
"step": 2100
|
| 3069 |
-
},
|
| 3070 |
-
{
|
| 3071 |
-
"epoch": 14.417808219178083,
|
| 3072 |
-
"grad_norm": 0.41796875,
|
| 3073 |
-
"learning_rate": 9.163680656226303e-07,
|
| 3074 |
-
"loss": 0.9548,
|
| 3075 |
-
"step": 2105
|
| 3076 |
-
},
|
| 3077 |
-
{
|
| 3078 |
-
"epoch": 14.452054794520548,
|
| 3079 |
-
"grad_norm": 0.404296875,
|
| 3080 |
-
"learning_rate": 8.118727137532034e-07,
|
| 3081 |
-
"loss": 0.9473,
|
| 3082 |
-
"step": 2110
|
| 3083 |
-
},
|
| 3084 |
-
{
|
| 3085 |
-
"epoch": 14.486301369863014,
|
| 3086 |
-
"grad_norm": 0.396484375,
|
| 3087 |
-
"learning_rate": 7.136771203310245e-07,
|
| 3088 |
-
"loss": 0.9593,
|
| 3089 |
-
"step": 2115
|
| 3090 |
-
},
|
| 3091 |
-
{
|
| 3092 |
-
"epoch": 14.520547945205479,
|
| 3093 |
-
"grad_norm": 0.404296875,
|
| 3094 |
-
"learning_rate": 6.21787522075512e-07,
|
| 3095 |
-
"loss": 0.9442,
|
| 3096 |
-
"step": 2120
|
| 3097 |
-
},
|
| 3098 |
-
{
|
| 3099 |
-
"epoch": 14.554794520547945,
|
| 3100 |
-
"grad_norm": 0.396484375,
|
| 3101 |
-
"learning_rate": 5.362097551919631e-07,
|
| 3102 |
-
"loss": 0.9509,
|
| 3103 |
-
"step": 2125
|
| 3104 |
-
},
|
| 3105 |
-
{
|
| 3106 |
-
"epoch": 14.58904109589041,
|
| 3107 |
-
"grad_norm": 0.408203125,
|
| 3108 |
-
"learning_rate": 4.569492550008603e-07,
|
| 3109 |
-
"loss": 0.943,
|
| 3110 |
-
"step": 2130
|
| 3111 |
-
},
|
| 3112 |
-
{
|
| 3113 |
-
"epoch": 14.623287671232877,
|
| 3114 |
-
"grad_norm": 0.408203125,
|
| 3115 |
-
"learning_rate": 3.84011055592659e-07,
|
| 3116 |
-
"loss": 0.9539,
|
| 3117 |
-
"step": 2135
|
| 3118 |
-
},
|
| 3119 |
-
{
|
| 3120 |
-
"epoch": 14.657534246575342,
|
| 3121 |
-
"grad_norm": 0.4140625,
|
| 3122 |
-
"learning_rate": 3.1739978950806603e-07,
|
| 3123 |
-
"loss": 0.9477,
|
| 3124 |
-
"step": 2140
|
| 3125 |
-
},
|
| 3126 |
-
{
|
| 3127 |
-
"epoch": 14.691780821917808,
|
| 3128 |
-
"grad_norm": 0.404296875,
|
| 3129 |
-
"learning_rate": 2.5711968744382974e-07,
|
| 3130 |
-
"loss": 0.9532,
|
| 3131 |
-
"step": 2145
|
| 3132 |
-
},
|
| 3133 |
-
{
|
| 3134 |
-
"epoch": 14.726027397260275,
|
| 3135 |
-
"grad_norm": 0.404296875,
|
| 3136 |
-
"learning_rate": 2.0317457798398888e-07,
|
| 3137 |
-
"loss": 0.9453,
|
| 3138 |
-
"step": 2150
|
| 3139 |
-
},
|
| 3140 |
-
{
|
| 3141 |
-
"epoch": 14.76027397260274,
|
| 3142 |
-
"grad_norm": 0.392578125,
|
| 3143 |
-
"learning_rate": 1.5556788735676675e-07,
|
| 3144 |
-
"loss": 0.9501,
|
| 3145 |
-
"step": 2155
|
| 3146 |
-
},
|
| 3147 |
-
{
|
| 3148 |
-
"epoch": 14.794520547945206,
|
| 3149 |
-
"grad_norm": 0.423828125,
|
| 3150 |
-
"learning_rate": 1.143026392168789e-07,
|
| 3151 |
-
"loss": 0.9372,
|
| 3152 |
-
"step": 2160
|
| 3153 |
-
},
|
| 3154 |
-
{
|
| 3155 |
-
"epoch": 14.82876712328767,
|
| 3156 |
-
"grad_norm": 0.39453125,
|
| 3157 |
-
"learning_rate": 7.938145445357536e-08,
|
| 3158 |
-
"loss": 0.9602,
|
| 3159 |
-
"step": 2165
|
| 3160 |
-
},
|
| 3161 |
-
{
|
| 3162 |
-
"epoch": 14.863013698630137,
|
| 3163 |
-
"grad_norm": 0.41015625,
|
| 3164 |
-
"learning_rate": 5.0806551024129565e-08,
|
| 3165 |
-
"loss": 0.9451,
|
| 3166 |
-
"step": 2170
|
| 3167 |
-
},
|
| 3168 |
-
{
|
| 3169 |
-
"epoch": 14.897260273972602,
|
| 3170 |
-
"grad_norm": 0.412109375,
|
| 3171 |
-
"learning_rate": 2.8579743813006432e-08,
|
| 3172 |
-
"loss": 0.9433,
|
| 3173 |
-
"step": 2175
|
| 3174 |
-
},
|
| 3175 |
-
{
|
| 3176 |
-
"epoch": 14.931506849315069,
|
| 3177 |
-
"grad_norm": 0.408203125,
|
| 3178 |
-
"learning_rate": 1.270244451652136e-08,
|
| 3179 |
-
"loss": 0.9548,
|
| 3180 |
-
"step": 2180
|
| 3181 |
-
},
|
| 3182 |
-
{
|
| 3183 |
-
"epoch": 14.965753424657533,
|
| 3184 |
-
"grad_norm": 0.408203125,
|
| 3185 |
-
"learning_rate": 3.175661553256326e-09,
|
| 3186 |
-
"loss": 0.9541,
|
| 3187 |
-
"step": 2185
|
| 3188 |
-
},
|
| 3189 |
-
{
|
| 3190 |
-
"epoch": 15.0,
|
| 3191 |
-
"grad_norm": 0.408203125,
|
| 3192 |
-
"learning_rate": 0.0,
|
| 3193 |
-
"loss": 0.9469,
|
| 3194 |
-
"step": 2190
|
| 3195 |
-
},
|
| 3196 |
-
{
|
| 3197 |
-
"epoch": 15.0,
|
| 3198 |
-
"eval_loss": 2.5990421772003174,
|
| 3199 |
-
"eval_runtime": 0.5553,
|
| 3200 |
-
"eval_samples_per_second": 18.009,
|
| 3201 |
-
"eval_steps_per_second": 1.801,
|
| 3202 |
-
"step": 2190
|
| 3203 |
-
},
|
| 3204 |
-
{
|
| 3205 |
-
"epoch": 15.0,
|
| 3206 |
-
"step": 2190,
|
| 3207 |
-
"total_flos": 1.2863476116823736e+18,
|
| 3208 |
-
"train_loss": 1.080002195214572,
|
| 3209 |
-
"train_runtime": 11705.6736,
|
| 3210 |
-
"train_samples_per_second": 8.973,
|
| 3211 |
-
"train_steps_per_second": 0.187
|
| 3212 |
}
|
| 3213 |
],
|
| 3214 |
"logging_steps": 5,
|
| 3215 |
-
"max_steps":
|
| 3216 |
"num_input_tokens_seen": 0,
|
| 3217 |
-
"num_train_epochs":
|
| 3218 |
"save_steps": 100,
|
| 3219 |
"stateful_callbacks": {
|
| 3220 |
"TrainerControl": {
|
|
@@ -3228,7 +2222,7 @@
|
|
| 3228 |
"attributes": {}
|
| 3229 |
}
|
| 3230 |
},
|
| 3231 |
-
"total_flos":
|
| 3232 |
"train_batch_size": 8,
|
| 3233 |
"trial_name": null,
|
| 3234 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.273972602739725,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1500,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.00684931506849315,
|
| 13 |
+
"grad_norm": 3.5625,
|
| 14 |
"learning_rate": 9.132420091324201e-07,
|
| 15 |
"loss": 3.0017,
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.03424657534246575,
|
| 20 |
+
"grad_norm": 2.9375,
|
| 21 |
"learning_rate": 4.566210045662101e-06,
|
| 22 |
+
"loss": 3.0725,
|
| 23 |
"step": 5
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.0684931506849315,
|
| 27 |
+
"grad_norm": 3.078125,
|
| 28 |
"learning_rate": 9.132420091324201e-06,
|
| 29 |
+
"loss": 3.0374,
|
| 30 |
"step": 10
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.10273972602739725,
|
| 34 |
+
"grad_norm": 2.515625,
|
| 35 |
"learning_rate": 1.3698630136986302e-05,
|
| 36 |
+
"loss": 3.0044,
|
| 37 |
"step": 15
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.136986301369863,
|
| 41 |
+
"grad_norm": 2.3125,
|
| 42 |
"learning_rate": 1.8264840182648402e-05,
|
| 43 |
+
"loss": 2.9373,
|
| 44 |
"step": 20
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.17123287671232876,
|
| 48 |
+
"grad_norm": 4.90625,
|
| 49 |
"learning_rate": 2.2831050228310503e-05,
|
| 50 |
+
"loss": 2.7849,
|
| 51 |
"step": 25
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.2054794520547945,
|
| 55 |
+
"grad_norm": 17.0,
|
| 56 |
"learning_rate": 2.7397260273972603e-05,
|
| 57 |
+
"loss": 2.6263,
|
| 58 |
"step": 30
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.23972602739726026,
|
| 62 |
+
"grad_norm": 1.0859375,
|
| 63 |
"learning_rate": 3.1963470319634704e-05,
|
| 64 |
+
"loss": 2.4603,
|
| 65 |
"step": 35
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.273972602739726,
|
| 69 |
+
"grad_norm": 1.75,
|
| 70 |
"learning_rate": 3.6529680365296805e-05,
|
| 71 |
+
"loss": 2.3423,
|
| 72 |
"step": 40
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.3082191780821918,
|
| 76 |
+
"grad_norm": 3.0,
|
| 77 |
"learning_rate": 4.1095890410958905e-05,
|
| 78 |
+
"loss": 2.2364,
|
| 79 |
"step": 45
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.3424657534246575,
|
| 83 |
+
"grad_norm": 1.0546875,
|
| 84 |
"learning_rate": 4.5662100456621006e-05,
|
| 85 |
+
"loss": 2.0795,
|
| 86 |
"step": 50
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.3767123287671233,
|
| 90 |
+
"grad_norm": 1.734375,
|
| 91 |
"learning_rate": 5.0228310502283106e-05,
|
| 92 |
+
"loss": 1.9497,
|
| 93 |
"step": 55
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.410958904109589,
|
| 97 |
+
"grad_norm": 1.25,
|
| 98 |
"learning_rate": 5.479452054794521e-05,
|
| 99 |
+
"loss": 1.8556,
|
| 100 |
"step": 60
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.4452054794520548,
|
| 104 |
+
"grad_norm": 0.640625,
|
| 105 |
"learning_rate": 5.936073059360731e-05,
|
| 106 |
+
"loss": 1.759,
|
| 107 |
"step": 65
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.4794520547945205,
|
| 111 |
+
"grad_norm": 0.97265625,
|
| 112 |
"learning_rate": 6.392694063926941e-05,
|
| 113 |
+
"loss": 1.6773,
|
| 114 |
"step": 70
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.5136986301369864,
|
| 118 |
+
"grad_norm": 1.9296875,
|
| 119 |
"learning_rate": 6.84931506849315e-05,
|
| 120 |
+
"loss": 1.6105,
|
| 121 |
"step": 75
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.547945205479452,
|
| 125 |
+
"grad_norm": 0.51171875,
|
| 126 |
"learning_rate": 7.305936073059361e-05,
|
| 127 |
+
"loss": 1.5517,
|
| 128 |
"step": 80
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.5821917808219178,
|
| 132 |
+
"grad_norm": 0.45703125,
|
| 133 |
"learning_rate": 7.76255707762557e-05,
|
| 134 |
+
"loss": 1.4895,
|
| 135 |
"step": 85
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.6164383561643836,
|
| 139 |
+
"grad_norm": 0.326171875,
|
| 140 |
"learning_rate": 8.219178082191781e-05,
|
| 141 |
+
"loss": 1.466,
|
| 142 |
"step": 90
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.6506849315068494,
|
| 146 |
+
"grad_norm": 0.283203125,
|
| 147 |
"learning_rate": 8.67579908675799e-05,
|
| 148 |
+
"loss": 1.4237,
|
| 149 |
"step": 95
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.684931506849315,
|
| 153 |
+
"grad_norm": 0.333984375,
|
| 154 |
"learning_rate": 9.132420091324201e-05,
|
| 155 |
+
"loss": 1.3836,
|
| 156 |
"step": 100
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 0.7191780821917808,
|
| 160 |
+
"grad_norm": 0.578125,
|
| 161 |
"learning_rate": 9.58904109589041e-05,
|
| 162 |
+
"loss": 1.3655,
|
| 163 |
"step": 105
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 0.7534246575342466,
|
| 167 |
+
"grad_norm": 0.484375,
|
| 168 |
"learning_rate": 0.00010045662100456621,
|
| 169 |
+
"loss": 1.3369,
|
| 170 |
"step": 110
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.7876712328767124,
|
| 174 |
+
"grad_norm": 0.3671875,
|
| 175 |
"learning_rate": 0.00010502283105022832,
|
| 176 |
+
"loss": 1.3149,
|
| 177 |
"step": 115
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.821917808219178,
|
| 181 |
+
"grad_norm": 0.9765625,
|
| 182 |
"learning_rate": 0.00010958904109589041,
|
| 183 |
+
"loss": 1.3051,
|
| 184 |
"step": 120
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 0.8561643835616438,
|
| 188 |
+
"grad_norm": 0.74609375,
|
| 189 |
"learning_rate": 0.00011415525114155252,
|
| 190 |
+
"loss": 1.2835,
|
| 191 |
"step": 125
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 0.8904109589041096,
|
| 195 |
+
"grad_norm": 0.271484375,
|
| 196 |
"learning_rate": 0.00011872146118721462,
|
| 197 |
+
"loss": 1.2805,
|
| 198 |
"step": 130
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 0.9246575342465754,
|
| 202 |
+
"grad_norm": 0.82421875,
|
| 203 |
"learning_rate": 0.0001232876712328767,
|
| 204 |
+
"loss": 1.2617,
|
| 205 |
"step": 135
|
| 206 |
},
|
| 207 |
{
|
| 208 |
"epoch": 0.958904109589041,
|
| 209 |
+
"grad_norm": 0.498046875,
|
| 210 |
"learning_rate": 0.00012785388127853882,
|
| 211 |
+
"loss": 1.2659,
|
| 212 |
"step": 140
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 0.9931506849315068,
|
| 216 |
+
"grad_norm": 0.28125,
|
| 217 |
"learning_rate": 0.00013242009132420092,
|
| 218 |
+
"loss": 1.2474,
|
| 219 |
"step": 145
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 1.0,
|
| 223 |
+
"eval_loss": 2.523677110671997,
|
| 224 |
+
"eval_runtime": 0.5573,
|
| 225 |
+
"eval_samples_per_second": 17.944,
|
| 226 |
+
"eval_steps_per_second": 1.794,
|
| 227 |
"step": 146
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 1.0273972602739727,
|
| 231 |
+
"grad_norm": 0.58984375,
|
| 232 |
"learning_rate": 0.000136986301369863,
|
| 233 |
+
"loss": 1.2351,
|
| 234 |
"step": 150
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 1.0616438356164384,
|
| 238 |
+
"grad_norm": 0.5234375,
|
| 239 |
"learning_rate": 0.0001415525114155251,
|
| 240 |
+
"loss": 1.2256,
|
| 241 |
"step": 155
|
| 242 |
},
|
| 243 |
{
|
| 244 |
"epoch": 1.095890410958904,
|
| 245 |
+
"grad_norm": 0.55859375,
|
| 246 |
"learning_rate": 0.00014611872146118722,
|
| 247 |
+
"loss": 1.2203,
|
| 248 |
"step": 160
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 1.13013698630137,
|
| 252 |
+
"grad_norm": 0.35546875,
|
| 253 |
"learning_rate": 0.00015068493150684933,
|
| 254 |
+
"loss": 1.1994,
|
| 255 |
"step": 165
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 1.1643835616438356,
|
| 259 |
+
"grad_norm": 0.345703125,
|
| 260 |
"learning_rate": 0.0001552511415525114,
|
| 261 |
+
"loss": 1.2069,
|
| 262 |
"step": 170
|
| 263 |
},
|
| 264 |
{
|
| 265 |
"epoch": 1.1986301369863013,
|
| 266 |
+
"grad_norm": 0.412109375,
|
| 267 |
"learning_rate": 0.00015981735159817351,
|
| 268 |
+
"loss": 1.1912,
|
| 269 |
"step": 175
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 1.2328767123287672,
|
| 273 |
+
"grad_norm": 0.365234375,
|
| 274 |
"learning_rate": 0.00016438356164383562,
|
| 275 |
+
"loss": 1.1879,
|
| 276 |
"step": 180
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 1.2671232876712328,
|
| 280 |
+
"grad_norm": 0.42578125,
|
| 281 |
"learning_rate": 0.00016894977168949773,
|
| 282 |
+
"loss": 1.1983,
|
| 283 |
"step": 185
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"epoch": 1.3013698630136985,
|
| 287 |
+
"grad_norm": 0.63671875,
|
| 288 |
"learning_rate": 0.0001735159817351598,
|
| 289 |
+
"loss": 1.1872,
|
| 290 |
"step": 190
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 1.3356164383561644,
|
| 294 |
+
"grad_norm": 0.376953125,
|
| 295 |
"learning_rate": 0.00017808219178082192,
|
| 296 |
+
"loss": 1.1806,
|
| 297 |
"step": 195
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 1.36986301369863,
|
| 301 |
+
"grad_norm": 1.1640625,
|
| 302 |
"learning_rate": 0.00018264840182648402,
|
| 303 |
+
"loss": 1.1849,
|
| 304 |
"step": 200
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 1.404109589041096,
|
| 308 |
+
"grad_norm": 1.046875,
|
| 309 |
"learning_rate": 0.00018721461187214613,
|
| 310 |
+
"loss": 1.1782,
|
| 311 |
"step": 205
|
| 312 |
},
|
| 313 |
{
|
| 314 |
"epoch": 1.4383561643835616,
|
| 315 |
+
"grad_norm": 0.373046875,
|
| 316 |
"learning_rate": 0.0001917808219178082,
|
| 317 |
+
"loss": 1.1727,
|
| 318 |
"step": 210
|
| 319 |
},
|
| 320 |
{
|
| 321 |
"epoch": 1.4726027397260273,
|
| 322 |
+
"grad_norm": 0.482421875,
|
| 323 |
"learning_rate": 0.00019634703196347032,
|
| 324 |
+
"loss": 1.1725,
|
| 325 |
"step": 215
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 1.5068493150684932,
|
| 329 |
+
"grad_norm": 0.80859375,
|
| 330 |
"learning_rate": 0.00019999987297289245,
|
| 331 |
+
"loss": 1.1611,
|
| 332 |
"step": 220
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 1.541095890410959,
|
| 336 |
+
"grad_norm": 0.56640625,
|
| 337 |
"learning_rate": 0.00019999542705801296,
|
| 338 |
+
"loss": 1.1642,
|
| 339 |
"step": 225
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 1.5753424657534247,
|
| 343 |
+
"grad_norm": 0.361328125,
|
| 344 |
"learning_rate": 0.00019998463011046926,
|
| 345 |
+
"loss": 1.1608,
|
| 346 |
"step": 230
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 1.6095890410958904,
|
| 350 |
+
"grad_norm": 0.76953125,
|
| 351 |
"learning_rate": 0.00019996748281601038,
|
| 352 |
+
"loss": 1.1563,
|
| 353 |
"step": 235
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 1.643835616438356,
|
| 357 |
+
"grad_norm": 0.388671875,
|
| 358 |
"learning_rate": 0.00019994398626371643,
|
| 359 |
+
"loss": 1.1457,
|
| 360 |
"step": 240
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 1.678082191780822,
|
| 364 |
+
"grad_norm": 0.45703125,
|
| 365 |
"learning_rate": 0.0001999141419459293,
|
| 366 |
+
"loss": 1.1609,
|
| 367 |
"step": 245
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"epoch": 1.7123287671232876,
|
| 371 |
+
"grad_norm": 0.70703125,
|
| 372 |
"learning_rate": 0.00019987795175815807,
|
| 373 |
+
"loss": 1.1479,
|
| 374 |
"step": 250
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 1.7465753424657535,
|
| 378 |
+
"grad_norm": 0.451171875,
|
| 379 |
"learning_rate": 0.0001998354179989585,
|
| 380 |
+
"loss": 1.148,
|
| 381 |
"step": 255
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 1.7808219178082192,
|
| 385 |
+
"grad_norm": 0.421875,
|
| 386 |
"learning_rate": 0.0001997865433697871,
|
| 387 |
+
"loss": 1.1513,
|
| 388 |
"step": 260
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 1.8150684931506849,
|
| 392 |
+
"grad_norm": 0.64453125,
|
| 393 |
"learning_rate": 0.00019973133097482947,
|
| 394 |
+
"loss": 1.1327,
|
| 395 |
"step": 265
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 1.8493150684931505,
|
| 399 |
+
"grad_norm": 0.326171875,
|
| 400 |
"learning_rate": 0.00019966978432080316,
|
| 401 |
+
"loss": 1.1424,
|
| 402 |
"step": 270
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 1.8835616438356164,
|
| 406 |
+
"grad_norm": 0.4375,
|
| 407 |
"learning_rate": 0.00019960190731673505,
|
| 408 |
+
"loss": 1.1387,
|
| 409 |
"step": 275
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"epoch": 1.9178082191780823,
|
| 413 |
+
"grad_norm": 0.34765625,
|
| 414 |
"learning_rate": 0.00019952770427371304,
|
| 415 |
+
"loss": 1.1258,
|
| 416 |
"step": 280
|
| 417 |
},
|
| 418 |
{
|
| 419 |
"epoch": 1.952054794520548,
|
| 420 |
+
"grad_norm": 0.447265625,
|
| 421 |
"learning_rate": 0.00019944717990461207,
|
| 422 |
+
"loss": 1.1226,
|
| 423 |
"step": 285
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 1.9863013698630136,
|
| 427 |
+
"grad_norm": 0.427734375,
|
| 428 |
"learning_rate": 0.00019936033932379504,
|
| 429 |
+
"loss": 1.1269,
|
| 430 |
"step": 290
|
| 431 |
},
|
| 432 |
{
|
| 433 |
"epoch": 2.0,
|
| 434 |
+
"eval_loss": 2.4804677963256836,
|
| 435 |
+
"eval_runtime": 0.5614,
|
| 436 |
+
"eval_samples_per_second": 17.814,
|
| 437 |
+
"eval_steps_per_second": 1.781,
|
| 438 |
"step": 292
|
| 439 |
},
|
| 440 |
{
|
| 441 |
"epoch": 2.0205479452054793,
|
| 442 |
+
"grad_norm": 0.4609375,
|
| 443 |
"learning_rate": 0.00019926718804678785,
|
| 444 |
+
"loss": 1.1225,
|
| 445 |
"step": 295
|
| 446 |
},
|
| 447 |
{
|
| 448 |
"epoch": 2.0547945205479454,
|
| 449 |
+
"grad_norm": 0.435546875,
|
| 450 |
"learning_rate": 0.000199167731989929,
|
| 451 |
+
"loss": 1.1022,
|
| 452 |
"step": 300
|
| 453 |
},
|
| 454 |
{
|
| 455 |
"epoch": 2.089041095890411,
|
| 456 |
+
"grad_norm": 0.4140625,
|
| 457 |
"learning_rate": 0.00019906197746999408,
|
| 458 |
+
"loss": 1.1012,
|
| 459 |
"step": 305
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 2.1232876712328768,
|
| 463 |
+
"grad_norm": 0.3515625,
|
| 464 |
"learning_rate": 0.00019894993120379435,
|
| 465 |
+
"loss": 1.0928,
|
| 466 |
"step": 310
|
| 467 |
},
|
| 468 |
{
|
| 469 |
"epoch": 2.1575342465753424,
|
| 470 |
+
"grad_norm": 0.43359375,
|
| 471 |
"learning_rate": 0.00019883160030775016,
|
| 472 |
+
"loss": 1.1032,
|
| 473 |
"step": 315
|
| 474 |
},
|
| 475 |
{
|
| 476 |
"epoch": 2.191780821917808,
|
| 477 |
+
"grad_norm": 0.96484375,
|
| 478 |
"learning_rate": 0.00019870699229743911,
|
| 479 |
+
"loss": 1.0966,
|
| 480 |
"step": 320
|
| 481 |
},
|
| 482 |
{
|
| 483 |
"epoch": 2.2260273972602738,
|
| 484 |
+
"grad_norm": 0.81640625,
|
| 485 |
"learning_rate": 0.0001985761150871185,
|
| 486 |
+
"loss": 1.0952,
|
| 487 |
"step": 325
|
| 488 |
},
|
| 489 |
{
|
| 490 |
"epoch": 2.26027397260274,
|
| 491 |
+
"grad_norm": 0.462890625,
|
| 492 |
"learning_rate": 0.00019843897698922284,
|
| 493 |
+
"loss": 1.0936,
|
| 494 |
"step": 330
|
| 495 |
},
|
| 496 |
{
|
| 497 |
"epoch": 2.2945205479452055,
|
| 498 |
+
"grad_norm": 0.3203125,
|
| 499 |
"learning_rate": 0.00019829558671383585,
|
| 500 |
+
"loss": 1.0938,
|
| 501 |
"step": 335
|
| 502 |
},
|
| 503 |
{
|
| 504 |
"epoch": 2.328767123287671,
|
| 505 |
+
"grad_norm": 0.494140625,
|
| 506 |
"learning_rate": 0.00019814595336813725,
|
| 507 |
+
"loss": 1.0856,
|
| 508 |
"step": 340
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"epoch": 2.363013698630137,
|
| 512 |
+
"grad_norm": 0.353515625,
|
| 513 |
"learning_rate": 0.0001979900864558242,
|
| 514 |
+
"loss": 1.0851,
|
| 515 |
"step": 345
|
| 516 |
},
|
| 517 |
{
|
| 518 |
"epoch": 2.3972602739726026,
|
| 519 |
+
"grad_norm": 0.3359375,
|
| 520 |
"learning_rate": 0.00019782799587650805,
|
| 521 |
+
"loss": 1.1018,
|
| 522 |
"step": 350
|
| 523 |
},
|
| 524 |
{
|
| 525 |
"epoch": 2.4315068493150687,
|
| 526 |
+
"grad_norm": 0.39453125,
|
| 527 |
"learning_rate": 0.00019765969192508508,
|
| 528 |
+
"loss": 1.0882,
|
| 529 |
"step": 355
|
| 530 |
},
|
| 531 |
{
|
| 532 |
"epoch": 2.4657534246575343,
|
| 533 |
+
"grad_norm": 0.341796875,
|
| 534 |
"learning_rate": 0.00019748518529108316,
|
| 535 |
+
"loss": 1.0932,
|
| 536 |
"step": 360
|
| 537 |
},
|
| 538 |
{
|
| 539 |
"epoch": 2.5,
|
| 540 |
+
"grad_norm": 0.404296875,
|
| 541 |
"learning_rate": 0.00019730448705798239,
|
| 542 |
+
"loss": 1.0945,
|
| 543 |
"step": 365
|
| 544 |
},
|
| 545 |
{
|
| 546 |
"epoch": 2.5342465753424657,
|
| 547 |
+
"grad_norm": 0.35546875,
|
| 548 |
"learning_rate": 0.00019711760870251143,
|
| 549 |
+
"loss": 1.0881,
|
| 550 |
"step": 370
|
| 551 |
},
|
| 552 |
{
|
| 553 |
"epoch": 2.5684931506849313,
|
| 554 |
+
"grad_norm": 0.40234375,
|
| 555 |
"learning_rate": 0.00019692456209391846,
|
| 556 |
+
"loss": 1.0802,
|
| 557 |
"step": 375
|
| 558 |
},
|
| 559 |
{
|
| 560 |
"epoch": 2.602739726027397,
|
| 561 |
+
"grad_norm": 0.52734375,
|
| 562 |
"learning_rate": 0.0001967253594932173,
|
| 563 |
+
"loss": 1.0822,
|
| 564 |
"step": 380
|
| 565 |
},
|
| 566 |
{
|
| 567 |
"epoch": 2.636986301369863,
|
| 568 |
+
"grad_norm": 0.337890625,
|
| 569 |
"learning_rate": 0.00019652001355240878,
|
| 570 |
+
"loss": 1.0907,
|
| 571 |
"step": 385
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"epoch": 2.671232876712329,
|
| 575 |
+
"grad_norm": 0.373046875,
|
| 576 |
"learning_rate": 0.00019630853731367713,
|
| 577 |
+
"loss": 1.0868,
|
| 578 |
"step": 390
|
| 579 |
},
|
| 580 |
{
|
| 581 |
"epoch": 2.7054794520547945,
|
| 582 |
+
"grad_norm": 0.40234375,
|
| 583 |
"learning_rate": 0.0001960909442085615,
|
| 584 |
+
"loss": 1.086,
|
| 585 |
"step": 395
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"epoch": 2.73972602739726,
|
| 589 |
+
"grad_norm": 0.384765625,
|
| 590 |
"learning_rate": 0.00019586724805710306,
|
| 591 |
+
"loss": 1.0746,
|
| 592 |
"step": 400
|
| 593 |
},
|
| 594 |
{
|
| 595 |
"epoch": 2.7739726027397262,
|
| 596 |
+
"grad_norm": 0.353515625,
|
| 597 |
"learning_rate": 0.0001956374630669672,
|
| 598 |
+
"loss": 1.0832,
|
| 599 |
"step": 405
|
| 600 |
},
|
| 601 |
{
|
| 602 |
"epoch": 2.808219178082192,
|
| 603 |
+
"grad_norm": 0.34765625,
|
| 604 |
"learning_rate": 0.00019540160383254107,
|
| 605 |
+
"loss": 1.0753,
|
| 606 |
"step": 410
|
| 607 |
},
|
| 608 |
{
|
| 609 |
"epoch": 2.8424657534246576,
|
| 610 |
+
"grad_norm": 0.328125,
|
| 611 |
"learning_rate": 0.00019515968533400673,
|
| 612 |
+
"loss": 1.0844,
|
| 613 |
"step": 415
|
| 614 |
},
|
| 615 |
{
|
| 616 |
"epoch": 2.8767123287671232,
|
| 617 |
+
"grad_norm": 0.34765625,
|
| 618 |
"learning_rate": 0.00019491172293638968,
|
| 619 |
+
"loss": 1.083,
|
| 620 |
"step": 420
|
| 621 |
},
|
| 622 |
{
|
| 623 |
"epoch": 2.910958904109589,
|
| 624 |
+
"grad_norm": 0.369140625,
|
| 625 |
"learning_rate": 0.00019465773238858298,
|
| 626 |
+
"loss": 1.0757,
|
| 627 |
"step": 425
|
| 628 |
},
|
| 629 |
{
|
| 630 |
"epoch": 2.9452054794520546,
|
| 631 |
+
"grad_norm": 0.56640625,
|
| 632 |
"learning_rate": 0.00019439772982234697,
|
| 633 |
+
"loss": 1.075,
|
| 634 |
"step": 430
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"epoch": 2.9794520547945207,
|
| 638 |
+
"grad_norm": 3.71875,
|
| 639 |
"learning_rate": 0.00019413173175128473,
|
| 640 |
+
"loss": 1.0909,
|
| 641 |
"step": 435
|
| 642 |
},
|
| 643 |
{
|
| 644 |
"epoch": 3.0,
|
| 645 |
+
"eval_loss": 2.4892916679382324,
|
| 646 |
+
"eval_runtime": 0.5522,
|
| 647 |
+
"eval_samples_per_second": 18.108,
|
| 648 |
+
"eval_steps_per_second": 1.811,
|
| 649 |
"step": 438
|
| 650 |
},
|
| 651 |
{
|
| 652 |
"epoch": 3.0136986301369864,
|
| 653 |
+
"grad_norm": 1.3046875,
|
| 654 |
"learning_rate": 0.0001938597550697932,
|
| 655 |
+
"loss": 1.0635,
|
| 656 |
"step": 440
|
| 657 |
},
|
| 658 |
{
|
| 659 |
"epoch": 3.047945205479452,
|
| 660 |
+
"grad_norm": 0.3984375,
|
| 661 |
"learning_rate": 0.00019358181705199015,
|
| 662 |
+
"loss": 1.0518,
|
| 663 |
"step": 445
|
| 664 |
},
|
| 665 |
{
|
| 666 |
"epoch": 3.0821917808219177,
|
| 667 |
+
"grad_norm": 0.369140625,
|
| 668 |
"learning_rate": 0.00019329793535061723,
|
| 669 |
+
"loss": 1.0509,
|
| 670 |
"step": 450
|
| 671 |
},
|
| 672 |
{
|
| 673 |
"epoch": 3.1164383561643834,
|
| 674 |
+
"grad_norm": 0.412109375,
|
| 675 |
"learning_rate": 0.00019300812799591846,
|
| 676 |
+
"loss": 1.0529,
|
| 677 |
"step": 455
|
| 678 |
},
|
| 679 |
{
|
| 680 |
"epoch": 3.1506849315068495,
|
| 681 |
+
"grad_norm": 0.66015625,
|
| 682 |
"learning_rate": 0.00019271241339449536,
|
| 683 |
+
"loss": 1.0416,
|
| 684 |
"step": 460
|
| 685 |
},
|
| 686 |
{
|
| 687 |
"epoch": 3.184931506849315,
|
| 688 |
+
"grad_norm": 0.89453125,
|
| 689 |
"learning_rate": 0.00019241081032813772,
|
| 690 |
+
"loss": 1.0488,
|
| 691 |
"step": 465
|
| 692 |
},
|
| 693 |
{
|
| 694 |
"epoch": 3.219178082191781,
|
| 695 |
+
"grad_norm": 0.55078125,
|
| 696 |
"learning_rate": 0.00019210333795263075,
|
| 697 |
+
"loss": 1.0402,
|
| 698 |
"step": 470
|
| 699 |
},
|
| 700 |
{
|
| 701 |
"epoch": 3.2534246575342465,
|
| 702 |
+
"grad_norm": 0.73046875,
|
| 703 |
"learning_rate": 0.00019179001579653853,
|
| 704 |
+
"loss": 1.0568,
|
| 705 |
"step": 475
|
| 706 |
},
|
| 707 |
{
|
| 708 |
"epoch": 3.287671232876712,
|
| 709 |
+
"grad_norm": 1.0390625,
|
| 710 |
"learning_rate": 0.0001914708637599636,
|
| 711 |
+
"loss": 1.0487,
|
| 712 |
"step": 480
|
| 713 |
},
|
| 714 |
{
|
| 715 |
"epoch": 3.3219178082191783,
|
| 716 |
+
"grad_norm": 0.400390625,
|
| 717 |
"learning_rate": 0.00019114590211328288,
|
| 718 |
+
"loss": 1.0468,
|
| 719 |
"step": 485
|
| 720 |
},
|
| 721 |
{
|
| 722 |
"epoch": 3.356164383561644,
|
| 723 |
+
"grad_norm": 0.439453125,
|
| 724 |
"learning_rate": 0.0001908151514958606,
|
| 725 |
+
"loss": 1.0538,
|
| 726 |
"step": 490
|
| 727 |
},
|
| 728 |
{
|
| 729 |
"epoch": 3.3904109589041096,
|
| 730 |
+
"grad_norm": 0.37109375,
|
| 731 |
"learning_rate": 0.00019047863291473717,
|
| 732 |
+
"loss": 1.0441,
|
| 733 |
"step": 495
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"epoch": 3.4246575342465753,
|
| 737 |
+
"grad_norm": 0.34765625,
|
| 738 |
"learning_rate": 0.00019013636774329495,
|
| 739 |
+
"loss": 1.0521,
|
| 740 |
"step": 500
|
| 741 |
},
|
| 742 |
{
|
| 743 |
"epoch": 3.458904109589041,
|
| 744 |
+
"grad_norm": 0.4140625,
|
| 745 |
"learning_rate": 0.00018978837771990085,
|
| 746 |
+
"loss": 1.0405,
|
| 747 |
"step": 505
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 3.493150684931507,
|
| 751 |
+
"grad_norm": 0.4375,
|
| 752 |
"learning_rate": 0.0001894346849465257,
|
| 753 |
+
"loss": 1.0439,
|
| 754 |
"step": 510
|
| 755 |
},
|
| 756 |
{
|
| 757 |
"epoch": 3.5273972602739727,
|
| 758 |
+
"grad_norm": 0.349609375,
|
| 759 |
"learning_rate": 0.00018907531188734026,
|
| 760 |
+
"loss": 1.0525,
|
| 761 |
"step": 515
|
| 762 |
},
|
| 763 |
{
|
| 764 |
"epoch": 3.5616438356164384,
|
| 765 |
+
"grad_norm": 0.47265625,
|
| 766 |
"learning_rate": 0.00018871028136728874,
|
| 767 |
+
"loss": 1.0493,
|
| 768 |
"step": 520
|
| 769 |
},
|
| 770 |
{
|
| 771 |
"epoch": 3.595890410958904,
|
| 772 |
+
"grad_norm": 0.35546875,
|
| 773 |
"learning_rate": 0.00018833961657063885,
|
| 774 |
+
"loss": 1.0405,
|
| 775 |
"step": 525
|
| 776 |
},
|
| 777 |
{
|
| 778 |
"epoch": 3.6301369863013697,
|
| 779 |
+
"grad_norm": 0.50390625,
|
| 780 |
"learning_rate": 0.0001879633410395095,
|
| 781 |
+
"loss": 1.0452,
|
| 782 |
"step": 530
|
| 783 |
},
|
| 784 |
{
|
| 785 |
"epoch": 3.6643835616438354,
|
| 786 |
+
"grad_norm": 0.34765625,
|
| 787 |
"learning_rate": 0.00018758147867237548,
|
| 788 |
+
"loss": 1.0515,
|
| 789 |
"step": 535
|
| 790 |
},
|
| 791 |
{
|
| 792 |
"epoch": 3.6986301369863015,
|
| 793 |
+
"grad_norm": 0.421875,
|
| 794 |
"learning_rate": 0.00018719405372254948,
|
| 795 |
+
"loss": 1.0453,
|
| 796 |
"step": 540
|
| 797 |
},
|
| 798 |
{
|
| 799 |
"epoch": 3.732876712328767,
|
| 800 |
+
"grad_norm": 0.3359375,
|
| 801 |
"learning_rate": 0.00018680109079664188,
|
| 802 |
+
"loss": 1.0356,
|
| 803 |
"step": 545
|
| 804 |
},
|
| 805 |
{
|
| 806 |
"epoch": 3.767123287671233,
|
| 807 |
+
"grad_norm": 0.333984375,
|
| 808 |
"learning_rate": 0.0001864026148529978,
|
| 809 |
+
"loss": 1.0355,
|
| 810 |
"step": 550
|
| 811 |
},
|
| 812 |
{
|
| 813 |
"epoch": 3.8013698630136985,
|
| 814 |
+
"grad_norm": 0.427734375,
|
| 815 |
"learning_rate": 0.00018599865120011192,
|
| 816 |
+
"loss": 1.0452,
|
| 817 |
"step": 555
|
| 818 |
},
|
| 819 |
{
|
| 820 |
"epoch": 3.8356164383561646,
|
| 821 |
+
"grad_norm": 0.34375,
|
| 822 |
"learning_rate": 0.00018558922549502107,
|
| 823 |
+
"loss": 1.0258,
|
| 824 |
"step": 560
|
| 825 |
},
|
| 826 |
{
|
| 827 |
"epoch": 3.8698630136986303,
|
| 828 |
+
"grad_norm": 0.412109375,
|
| 829 |
"learning_rate": 0.0001851743637416747,
|
| 830 |
+
"loss": 1.0423,
|
| 831 |
"step": 565
|
| 832 |
},
|
| 833 |
{
|
| 834 |
"epoch": 3.904109589041096,
|
| 835 |
+
"grad_norm": 0.31640625,
|
| 836 |
"learning_rate": 0.00018475409228928312,
|
| 837 |
+
"loss": 1.0238,
|
| 838 |
"step": 570
|
| 839 |
},
|
| 840 |
{
|
| 841 |
"epoch": 3.9383561643835616,
|
| 842 |
+
"grad_norm": 0.400390625,
|
| 843 |
"learning_rate": 0.00018432843783064429,
|
| 844 |
+
"loss": 1.041,
|
| 845 |
"step": 575
|
| 846 |
},
|
| 847 |
{
|
| 848 |
"epoch": 3.9726027397260273,
|
| 849 |
+
"grad_norm": 0.412109375,
|
| 850 |
"learning_rate": 0.00018389742740044813,
|
| 851 |
+
"loss": 1.0354,
|
| 852 |
"step": 580
|
| 853 |
},
|
| 854 |
{
|
| 855 |
"epoch": 4.0,
|
| 856 |
+
"eval_loss": 2.5017333030700684,
|
| 857 |
+
"eval_runtime": 0.5568,
|
| 858 |
+
"eval_samples_per_second": 17.961,
|
| 859 |
+
"eval_steps_per_second": 1.796,
|
| 860 |
"step": 584
|
| 861 |
},
|
| 862 |
{
|
| 863 |
"epoch": 4.006849315068493,
|
| 864 |
+
"grad_norm": 0.52734375,
|
| 865 |
"learning_rate": 0.00018346108837355972,
|
| 866 |
+
"loss": 1.0411,
|
| 867 |
"step": 585
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 4.041095890410959,
|
| 871 |
+
"grad_norm": 0.41796875,
|
| 872 |
"learning_rate": 0.00018301944846328049,
|
| 873 |
+
"loss": 0.9963,
|
| 874 |
"step": 590
|
| 875 |
},
|
| 876 |
{
|
| 877 |
"epoch": 4.075342465753424,
|
| 878 |
+
"grad_norm": 0.36328125,
|
| 879 |
"learning_rate": 0.0001825725357195881,
|
| 880 |
+
"loss": 1.0137,
|
| 881 |
"step": 595
|
| 882 |
},
|
| 883 |
{
|
| 884 |
"epoch": 4.109589041095891,
|
| 885 |
+
"grad_norm": 0.48046875,
|
| 886 |
"learning_rate": 0.00018212037852735486,
|
| 887 |
+
"loss": 1.006,
|
| 888 |
"step": 600
|
| 889 |
},
|
| 890 |
{
|
| 891 |
"epoch": 4.1438356164383565,
|
| 892 |
+
"grad_norm": 0.4140625,
|
| 893 |
"learning_rate": 0.0001816630056045451,
|
| 894 |
+
"loss": 1.0075,
|
| 895 |
"step": 605
|
| 896 |
},
|
| 897 |
{
|
| 898 |
"epoch": 4.178082191780822,
|
| 899 |
+
"grad_norm": 0.353515625,
|
| 900 |
"learning_rate": 0.0001812004460003909,
|
| 901 |
+
"loss": 0.9975,
|
| 902 |
"step": 610
|
| 903 |
},
|
| 904 |
{
|
| 905 |
"epoch": 4.212328767123288,
|
| 906 |
+
"grad_norm": 0.365234375,
|
| 907 |
"learning_rate": 0.00018073272909354727,
|
| 908 |
+
"loss": 1.0171,
|
| 909 |
"step": 615
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 4.2465753424657535,
|
| 913 |
+
"grad_norm": 0.51171875,
|
| 914 |
"learning_rate": 0.0001802598845902262,
|
| 915 |
+
"loss": 0.9953,
|
| 916 |
"step": 620
|
| 917 |
},
|
| 918 |
{
|
| 919 |
"epoch": 4.280821917808219,
|
| 920 |
+
"grad_norm": 0.38671875,
|
| 921 |
"learning_rate": 0.00017978194252230985,
|
| 922 |
+
"loss": 1.008,
|
| 923 |
"step": 625
|
| 924 |
},
|
| 925 |
{
|
| 926 |
"epoch": 4.315068493150685,
|
| 927 |
+
"grad_norm": 0.359375,
|
| 928 |
"learning_rate": 0.00017929893324544332,
|
| 929 |
+
"loss": 0.9993,
|
| 930 |
"step": 630
|
| 931 |
},
|
| 932 |
{
|
| 933 |
"epoch": 4.3493150684931505,
|
| 934 |
+
"grad_norm": 0.56640625,
|
| 935 |
"learning_rate": 0.0001788108874371063,
|
| 936 |
+
"loss": 1.0119,
|
| 937 |
"step": 635
|
| 938 |
},
|
| 939 |
{
|
| 940 |
"epoch": 4.383561643835616,
|
| 941 |
+
"grad_norm": 0.33203125,
|
| 942 |
"learning_rate": 0.00017831783609466504,
|
| 943 |
+
"loss": 1.0047,
|
| 944 |
"step": 640
|
| 945 |
},
|
| 946 |
{
|
| 947 |
"epoch": 4.417808219178082,
|
| 948 |
+
"grad_norm": 0.341796875,
|
| 949 |
"learning_rate": 0.00017781981053340337,
|
| 950 |
+
"loss": 1.0143,
|
| 951 |
"step": 645
|
| 952 |
},
|
| 953 |
{
|
| 954 |
"epoch": 4.4520547945205475,
|
| 955 |
+
"grad_norm": 0.345703125,
|
| 956 |
"learning_rate": 0.00017731684238453385,
|
| 957 |
+
"loss": 1.0023,
|
| 958 |
"step": 650
|
| 959 |
},
|
| 960 |
{
|
| 961 |
"epoch": 4.486301369863014,
|
| 962 |
+
"grad_norm": 0.37890625,
|
| 963 |
"learning_rate": 0.0001768089635931887,
|
| 964 |
+
"loss": 1.0125,
|
| 965 |
"step": 655
|
| 966 |
},
|
| 967 |
{
|
| 968 |
"epoch": 4.52054794520548,
|
| 969 |
+
"grad_norm": 0.609375,
|
| 970 |
"learning_rate": 0.00017629620641639103,
|
| 971 |
+
"loss": 1.0074,
|
| 972 |
"step": 660
|
| 973 |
},
|
| 974 |
{
|
| 975 |
"epoch": 4.554794520547945,
|
| 976 |
+
"grad_norm": 0.36328125,
|
| 977 |
"learning_rate": 0.00017577860342100579,
|
| 978 |
+
"loss": 1.0124,
|
| 979 |
"step": 665
|
| 980 |
},
|
| 981 |
{
|
| 982 |
"epoch": 4.589041095890411,
|
| 983 |
+
"grad_norm": 0.65625,
|
| 984 |
"learning_rate": 0.0001752561874816717,
|
| 985 |
+
"loss": 1.015,
|
| 986 |
"step": 670
|
| 987 |
},
|
| 988 |
{
|
| 989 |
"epoch": 4.623287671232877,
|
| 990 |
+
"grad_norm": 0.38671875,
|
| 991 |
"learning_rate": 0.00017472899177871297,
|
| 992 |
+
"loss": 1.0066,
|
| 993 |
"step": 675
|
| 994 |
},
|
| 995 |
{
|
| 996 |
"epoch": 4.657534246575342,
|
| 997 |
+
"grad_norm": 0.32421875,
|
| 998 |
"learning_rate": 0.00017419704979603214,
|
| 999 |
+
"loss": 1.0182,
|
| 1000 |
"step": 680
|
| 1001 |
},
|
| 1002 |
{
|
| 1003 |
"epoch": 4.691780821917808,
|
| 1004 |
+
"grad_norm": 0.34375,
|
| 1005 |
"learning_rate": 0.00017366039531898326,
|
| 1006 |
+
"loss": 1.0139,
|
| 1007 |
"step": 685
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
"epoch": 4.726027397260274,
|
| 1011 |
+
"grad_norm": 0.349609375,
|
| 1012 |
"learning_rate": 0.00017311906243222614,
|
| 1013 |
+
"loss": 1.0162,
|
| 1014 |
"step": 690
|
| 1015 |
},
|
| 1016 |
{
|
| 1017 |
"epoch": 4.760273972602739,
|
| 1018 |
+
"grad_norm": 0.3359375,
|
| 1019 |
"learning_rate": 0.0001725730855175615,
|
| 1020 |
+
"loss": 1.019,
|
| 1021 |
"step": 695
|
| 1022 |
},
|
| 1023 |
{
|
| 1024 |
"epoch": 4.794520547945205,
|
| 1025 |
+
"grad_norm": 0.431640625,
|
| 1026 |
"learning_rate": 0.00017202249925174723,
|
| 1027 |
+
"loss": 1.0051,
|
| 1028 |
"step": 700
|
| 1029 |
},
|
| 1030 |
{
|
| 1031 |
"epoch": 4.828767123287671,
|
| 1032 |
+
"grad_norm": 0.4140625,
|
| 1033 |
"learning_rate": 0.00017146733860429612,
|
| 1034 |
+
"loss": 1.0174,
|
| 1035 |
"step": 705
|
| 1036 |
},
|
| 1037 |
{
|
| 1038 |
"epoch": 4.863013698630137,
|
| 1039 |
+
"grad_norm": 0.408203125,
|
| 1040 |
"learning_rate": 0.0001709076388352546,
|
| 1041 |
+
"loss": 1.0065,
|
| 1042 |
"step": 710
|
| 1043 |
},
|
| 1044 |
{
|
| 1045 |
"epoch": 4.897260273972603,
|
| 1046 |
+
"grad_norm": 0.359375,
|
| 1047 |
"learning_rate": 0.00017034343549296346,
|
| 1048 |
+
"loss": 1.0262,
|
| 1049 |
"step": 715
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
"epoch": 4.931506849315069,
|
| 1053 |
+
"grad_norm": 0.44140625,
|
| 1054 |
"learning_rate": 0.00016977476441179992,
|
| 1055 |
+
"loss": 1.0023,
|
| 1056 |
"step": 720
|
| 1057 |
},
|
| 1058 |
{
|
| 1059 |
"epoch": 4.965753424657534,
|
| 1060 |
+
"grad_norm": 0.357421875,
|
| 1061 |
"learning_rate": 0.0001692016617099018,
|
| 1062 |
+
"loss": 1.0048,
|
| 1063 |
"step": 725
|
| 1064 |
},
|
| 1065 |
{
|
| 1066 |
"epoch": 5.0,
|
| 1067 |
+
"grad_norm": 0.431640625,
|
| 1068 |
"learning_rate": 0.0001686241637868734,
|
| 1069 |
+
"loss": 1.0016,
|
| 1070 |
"step": 730
|
| 1071 |
},
|
| 1072 |
{
|
| 1073 |
"epoch": 5.0,
|
| 1074 |
+
"eval_loss": 2.5294971466064453,
|
| 1075 |
+
"eval_runtime": 0.5501,
|
| 1076 |
+
"eval_samples_per_second": 18.178,
|
| 1077 |
+
"eval_steps_per_second": 1.818,
|
| 1078 |
"step": 730
|
| 1079 |
},
|
| 1080 |
{
|
| 1081 |
"epoch": 5.034246575342466,
|
| 1082 |
+
"grad_norm": 0.380859375,
|
| 1083 |
"learning_rate": 0.0001680423073214737,
|
| 1084 |
+
"loss": 0.9822,
|
| 1085 |
"step": 735
|
| 1086 |
},
|
| 1087 |
{
|
| 1088 |
"epoch": 5.068493150684931,
|
| 1089 |
+
"grad_norm": 0.369140625,
|
| 1090 |
"learning_rate": 0.00016745612926928694,
|
| 1091 |
+
"loss": 0.9842,
|
| 1092 |
"step": 740
|
| 1093 |
},
|
| 1094 |
{
|
| 1095 |
"epoch": 5.102739726027397,
|
| 1096 |
+
"grad_norm": 0.38671875,
|
| 1097 |
"learning_rate": 0.0001668656668603751,
|
| 1098 |
+
"loss": 0.9717,
|
| 1099 |
"step": 745
|
| 1100 |
},
|
| 1101 |
{
|
| 1102 |
"epoch": 5.136986301369863,
|
| 1103 |
+
"grad_norm": 0.375,
|
| 1104 |
"learning_rate": 0.00016627095759691362,
|
| 1105 |
+
"loss": 0.9685,
|
| 1106 |
"step": 750
|
| 1107 |
},
|
| 1108 |
{
|
| 1109 |
"epoch": 5.171232876712328,
|
| 1110 |
+
"grad_norm": 0.353515625,
|
| 1111 |
"learning_rate": 0.0001656720392508094,
|
| 1112 |
+
"loss": 0.9744,
|
| 1113 |
"step": 755
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
"epoch": 5.205479452054795,
|
| 1117 |
"grad_norm": 0.376953125,
|
| 1118 |
"learning_rate": 0.00016506894986130171,
|
| 1119 |
+
"loss": 0.9736,
|
| 1120 |
"step": 760
|
| 1121 |
},
|
| 1122 |
{
|
| 1123 |
"epoch": 5.239726027397261,
|
| 1124 |
+
"grad_norm": 0.486328125,
|
| 1125 |
"learning_rate": 0.00016446172773254629,
|
| 1126 |
+
"loss": 0.972,
|
| 1127 |
"step": 765
|
| 1128 |
},
|
| 1129 |
{
|
| 1130 |
"epoch": 5.273972602739726,
|
| 1131 |
+
"grad_norm": 0.470703125,
|
| 1132 |
"learning_rate": 0.00016385041143118255,
|
| 1133 |
+
"loss": 0.9813,
|
| 1134 |
"step": 770
|
| 1135 |
},
|
| 1136 |
{
|
| 1137 |
"epoch": 5.308219178082192,
|
| 1138 |
+
"grad_norm": 0.5546875,
|
| 1139 |
"learning_rate": 0.000163235039783884,
|
| 1140 |
+
"loss": 0.9855,
|
| 1141 |
"step": 775
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
"epoch": 5.342465753424658,
|
| 1145 |
+
"grad_norm": 0.462890625,
|
| 1146 |
"learning_rate": 0.0001626156518748922,
|
| 1147 |
+
"loss": 0.9765,
|
| 1148 |
"step": 780
|
| 1149 |
},
|
| 1150 |
{
|
| 1151 |
"epoch": 5.376712328767123,
|
| 1152 |
+
"grad_norm": 0.59375,
|
| 1153 |
"learning_rate": 0.00016199228704353455,
|
| 1154 |
+
"loss": 0.9876,
|
| 1155 |
"step": 785
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
"epoch": 5.410958904109589,
|
| 1159 |
+
"grad_norm": 0.53125,
|
| 1160 |
"learning_rate": 0.00016136498488172568,
|
| 1161 |
+
"loss": 0.9772,
|
| 1162 |
"step": 790
|
| 1163 |
},
|
| 1164 |
{
|
| 1165 |
"epoch": 5.445205479452055,
|
| 1166 |
+
"grad_norm": 0.3984375,
|
| 1167 |
"learning_rate": 0.0001607337852314527,
|
| 1168 |
+
"loss": 0.9861,
|
| 1169 |
"step": 795
|
| 1170 |
},
|
| 1171 |
{
|
| 1172 |
"epoch": 5.47945205479452,
|
| 1173 |
+
"grad_norm": 0.3671875,
|
| 1174 |
"learning_rate": 0.00016009872818224485,
|
| 1175 |
+
"loss": 0.9879,
|
| 1176 |
"step": 800
|
| 1177 |
},
|
| 1178 |
{
|
| 1179 |
"epoch": 5.513698630136986,
|
| 1180 |
+
"grad_norm": 0.357421875,
|
| 1181 |
"learning_rate": 0.00015945985406862721,
|
| 1182 |
+
"loss": 0.9821,
|
| 1183 |
"step": 805
|
| 1184 |
},
|
| 1185 |
{
|
| 1186 |
"epoch": 5.5479452054794525,
|
| 1187 |
+
"grad_norm": 0.4375,
|
| 1188 |
"learning_rate": 0.00015881720346755905,
|
| 1189 |
+
"loss": 0.9748,
|
| 1190 |
"step": 810
|
| 1191 |
},
|
| 1192 |
{
|
| 1193 |
"epoch": 5.582191780821918,
|
| 1194 |
+
"grad_norm": 0.376953125,
|
| 1195 |
"learning_rate": 0.00015817081719585643,
|
| 1196 |
+
"loss": 0.9726,
|
| 1197 |
"step": 815
|
| 1198 |
},
|
| 1199 |
{
|
| 1200 |
"epoch": 5.616438356164384,
|
| 1201 |
+
"grad_norm": 0.37890625,
|
| 1202 |
"learning_rate": 0.00015752073630759998,
|
| 1203 |
+
"loss": 0.9918,
|
| 1204 |
"step": 820
|
| 1205 |
},
|
| 1206 |
{
|
| 1207 |
"epoch": 5.6506849315068495,
|
| 1208 |
+
"grad_norm": 0.419921875,
|
| 1209 |
"learning_rate": 0.00015686700209152738,
|
| 1210 |
+
"loss": 0.9775,
|
| 1211 |
"step": 825
|
| 1212 |
},
|
| 1213 |
{
|
| 1214 |
"epoch": 5.684931506849315,
|
| 1215 |
+
"grad_norm": 0.33203125,
|
| 1216 |
"learning_rate": 0.00015620965606841098,
|
| 1217 |
+
"loss": 0.9734,
|
| 1218 |
"step": 830
|
| 1219 |
},
|
| 1220 |
{
|
| 1221 |
"epoch": 5.719178082191781,
|
| 1222 |
+
"grad_norm": 0.37890625,
|
| 1223 |
"learning_rate": 0.0001555487399884206,
|
| 1224 |
+
"loss": 0.9753,
|
| 1225 |
"step": 835
|
| 1226 |
},
|
| 1227 |
{
|
| 1228 |
"epoch": 5.7534246575342465,
|
| 1229 |
+
"grad_norm": 0.39453125,
|
| 1230 |
"learning_rate": 0.00015488429582847192,
|
| 1231 |
+
"loss": 0.9701,
|
| 1232 |
"step": 840
|
| 1233 |
},
|
| 1234 |
{
|
| 1235 |
"epoch": 5.787671232876712,
|
| 1236 |
+
"grad_norm": 0.357421875,
|
| 1237 |
"learning_rate": 0.0001542163657895605,
|
| 1238 |
+
"loss": 0.9726,
|
| 1239 |
"step": 845
|
| 1240 |
},
|
| 1241 |
{
|
| 1242 |
"epoch": 5.821917808219178,
|
| 1243 |
+
"grad_norm": 0.4375,
|
| 1244 |
"learning_rate": 0.00015354499229408114,
|
| 1245 |
+
"loss": 0.9755,
|
| 1246 |
"step": 850
|
| 1247 |
},
|
| 1248 |
{
|
| 1249 |
"epoch": 5.8561643835616435,
|
| 1250 |
+
"grad_norm": 0.50390625,
|
| 1251 |
"learning_rate": 0.0001528702179831338,
|
| 1252 |
+
"loss": 0.9733,
|
| 1253 |
"step": 855
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
"epoch": 5.890410958904109,
|
| 1257 |
+
"grad_norm": 0.419921875,
|
| 1258 |
"learning_rate": 0.00015219208571381525,
|
| 1259 |
+
"loss": 0.9795,
|
| 1260 |
"step": 860
|
| 1261 |
},
|
| 1262 |
{
|
| 1263 |
"epoch": 5.924657534246576,
|
| 1264 |
+
"grad_norm": 0.466796875,
|
| 1265 |
"learning_rate": 0.00015151063855649698,
|
| 1266 |
+
"loss": 0.9906,
|
| 1267 |
"step": 865
|
| 1268 |
},
|
| 1269 |
{
|
| 1270 |
"epoch": 5.958904109589041,
|
| 1271 |
+
"grad_norm": 0.35546875,
|
| 1272 |
"learning_rate": 0.00015082591979208976,
|
| 1273 |
+
"loss": 0.983,
|
| 1274 |
"step": 870
|
| 1275 |
},
|
| 1276 |
{
|
| 1277 |
"epoch": 5.993150684931507,
|
| 1278 |
+
"grad_norm": 0.51953125,
|
| 1279 |
"learning_rate": 0.00015013797290929466,
|
| 1280 |
+
"loss": 0.9823,
|
| 1281 |
"step": 875
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
"epoch": 6.0,
|
| 1285 |
+
"eval_loss": 2.5500409603118896,
|
| 1286 |
+
"eval_runtime": 0.5455,
|
| 1287 |
+
"eval_samples_per_second": 18.332,
|
| 1288 |
+
"eval_steps_per_second": 1.833,
|
| 1289 |
"step": 876
|
| 1290 |
},
|
| 1291 |
{
|
| 1292 |
"epoch": 6.027397260273973,
|
| 1293 |
+
"grad_norm": 0.380859375,
|
| 1294 |
"learning_rate": 0.00014944684160184108,
|
| 1295 |
+
"loss": 0.9588,
|
| 1296 |
"step": 880
|
| 1297 |
},
|
| 1298 |
{
|
| 1299 |
"epoch": 6.061643835616438,
|
| 1300 |
+
"grad_norm": 0.435546875,
|
| 1301 |
"learning_rate": 0.00014875256976571135,
|
| 1302 |
+
"loss": 0.9449,
|
| 1303 |
"step": 885
|
| 1304 |
},
|
| 1305 |
{
|
| 1306 |
"epoch": 6.095890410958904,
|
| 1307 |
+
"grad_norm": 0.41796875,
|
| 1308 |
"learning_rate": 0.00014805520149635307,
|
| 1309 |
+
"loss": 0.9336,
|
| 1310 |
"step": 890
|
| 1311 |
},
|
| 1312 |
{
|
| 1313 |
"epoch": 6.13013698630137,
|
| 1314 |
+
"grad_norm": 0.388671875,
|
| 1315 |
"learning_rate": 0.00014735478108587828,
|
| 1316 |
+
"loss": 0.9428,
|
| 1317 |
"step": 895
|
| 1318 |
},
|
| 1319 |
{
|
| 1320 |
"epoch": 6.164383561643835,
|
| 1321 |
+
"grad_norm": 0.578125,
|
| 1322 |
"learning_rate": 0.00014665135302025035,
|
| 1323 |
+
"loss": 0.9457,
|
| 1324 |
"step": 900
|
| 1325 |
},
|
| 1326 |
{
|
| 1327 |
"epoch": 6.198630136986301,
|
| 1328 |
+
"grad_norm": 0.375,
|
| 1329 |
"learning_rate": 0.00014594496197645852,
|
| 1330 |
+
"loss": 0.9425,
|
| 1331 |
"step": 905
|
| 1332 |
},
|
| 1333 |
{
|
| 1334 |
"epoch": 6.232876712328767,
|
| 1335 |
+
"grad_norm": 0.361328125,
|
| 1336 |
"learning_rate": 0.0001452356528196804,
|
| 1337 |
+
"loss": 0.9492,
|
| 1338 |
"step": 910
|
| 1339 |
},
|
| 1340 |
{
|
| 1341 |
"epoch": 6.267123287671233,
|
| 1342 |
+
"grad_norm": 0.34375,
|
| 1343 |
"learning_rate": 0.00014452347060043237,
|
| 1344 |
+
"loss": 0.9542,
|
| 1345 |
"step": 915
|
| 1346 |
},
|
| 1347 |
{
|
| 1348 |
"epoch": 6.301369863013699,
|
| 1349 |
+
"grad_norm": 0.375,
|
| 1350 |
"learning_rate": 0.00014380846055170828,
|
| 1351 |
+
"loss": 0.9488,
|
| 1352 |
"step": 920
|
| 1353 |
},
|
| 1354 |
{
|
| 1355 |
"epoch": 6.335616438356165,
|
| 1356 |
+
"grad_norm": 0.56640625,
|
| 1357 |
"learning_rate": 0.00014309066808610655,
|
| 1358 |
+
"loss": 0.9532,
|
| 1359 |
"step": 925
|
| 1360 |
},
|
| 1361 |
{
|
| 1362 |
"epoch": 6.36986301369863,
|
| 1363 |
+
"grad_norm": 0.451171875,
|
| 1364 |
"learning_rate": 0.0001423701387929459,
|
| 1365 |
+
"loss": 0.954,
|
| 1366 |
"step": 930
|
| 1367 |
},
|
| 1368 |
{
|
| 1369 |
"epoch": 6.404109589041096,
|
| 1370 |
+
"grad_norm": 0.361328125,
|
| 1371 |
"learning_rate": 0.00014164691843536982,
|
| 1372 |
+
"loss": 0.9513,
|
| 1373 |
"step": 935
|
| 1374 |
},
|
| 1375 |
{
|
| 1376 |
"epoch": 6.438356164383562,
|
| 1377 |
+
"grad_norm": 0.4375,
|
| 1378 |
"learning_rate": 0.00014092105294744,
|
| 1379 |
+
"loss": 0.954,
|
| 1380 |
"step": 940
|
| 1381 |
},
|
| 1382 |
{
|
| 1383 |
"epoch": 6.472602739726027,
|
| 1384 |
+
"grad_norm": 0.404296875,
|
| 1385 |
"learning_rate": 0.00014019258843121893,
|
| 1386 |
+
"loss": 0.9549,
|
| 1387 |
"step": 945
|
| 1388 |
},
|
| 1389 |
{
|
| 1390 |
"epoch": 6.506849315068493,
|
| 1391 |
+
"grad_norm": 0.38671875,
|
| 1392 |
"learning_rate": 0.0001394615711538417,
|
| 1393 |
+
"loss": 0.9509,
|
| 1394 |
"step": 950
|
| 1395 |
},
|
| 1396 |
{
|
| 1397 |
"epoch": 6.541095890410959,
|
| 1398 |
+
"grad_norm": 0.376953125,
|
| 1399 |
"learning_rate": 0.00013872804754457759,
|
| 1400 |
+
"loss": 0.9556,
|
| 1401 |
"step": 955
|
| 1402 |
},
|
| 1403 |
{
|
| 1404 |
"epoch": 6.575342465753424,
|
| 1405 |
+
"grad_norm": 0.400390625,
|
| 1406 |
"learning_rate": 0.00013799206419188103,
|
| 1407 |
+
"loss": 0.9596,
|
| 1408 |
"step": 960
|
| 1409 |
},
|
| 1410 |
{
|
| 1411 |
"epoch": 6.609589041095891,
|
| 1412 |
+
"grad_norm": 0.37890625,
|
| 1413 |
"learning_rate": 0.00013725366784043288,
|
| 1414 |
+
"loss": 0.9532,
|
| 1415 |
"step": 965
|
| 1416 |
},
|
| 1417 |
{
|
| 1418 |
"epoch": 6.6438356164383565,
|
| 1419 |
+
"grad_norm": 0.361328125,
|
| 1420 |
"learning_rate": 0.00013651290538817113,
|
| 1421 |
+
"loss": 0.9547,
|
| 1422 |
"step": 970
|
| 1423 |
},
|
| 1424 |
{
|
| 1425 |
"epoch": 6.678082191780822,
|
| 1426 |
+
"grad_norm": 0.392578125,
|
| 1427 |
"learning_rate": 0.0001357698238833126,
|
| 1428 |
+
"loss": 0.9619,
|
| 1429 |
"step": 975
|
| 1430 |
},
|
| 1431 |
{
|
| 1432 |
"epoch": 6.712328767123288,
|
| 1433 |
+
"grad_norm": 0.38671875,
|
| 1434 |
"learning_rate": 0.00013502447052136455,
|
| 1435 |
+
"loss": 0.9457,
|
| 1436 |
"step": 980
|
| 1437 |
},
|
| 1438 |
{
|
| 1439 |
"epoch": 6.7465753424657535,
|
| 1440 |
+
"grad_norm": 0.384765625,
|
| 1441 |
"learning_rate": 0.00013427689264212738,
|
| 1442 |
+
"loss": 0.9595,
|
| 1443 |
"step": 985
|
| 1444 |
},
|
| 1445 |
{
|
| 1446 |
"epoch": 6.780821917808219,
|
| 1447 |
+
"grad_norm": 0.3984375,
|
| 1448 |
"learning_rate": 0.00013352713772668765,
|
| 1449 |
+
"loss": 0.9501,
|
| 1450 |
"step": 990
|
| 1451 |
},
|
| 1452 |
{
|
| 1453 |
"epoch": 6.815068493150685,
|
| 1454 |
+
"grad_norm": 0.404296875,
|
| 1455 |
"learning_rate": 0.0001327752533944025,
|
| 1456 |
+
"loss": 0.9542,
|
| 1457 |
"step": 995
|
| 1458 |
},
|
| 1459 |
{
|
| 1460 |
"epoch": 6.8493150684931505,
|
| 1461 |
+
"grad_norm": 0.5546875,
|
| 1462 |
"learning_rate": 0.00013202128739987532,
|
| 1463 |
+
"loss": 0.957,
|
| 1464 |
"step": 1000
|
| 1465 |
},
|
| 1466 |
{
|
| 1467 |
"epoch": 6.883561643835616,
|
| 1468 |
+
"grad_norm": 0.388671875,
|
| 1469 |
"learning_rate": 0.00013126528762992247,
|
| 1470 |
+
"loss": 0.9597,
|
| 1471 |
"step": 1005
|
| 1472 |
},
|
| 1473 |
{
|
| 1474 |
"epoch": 6.917808219178082,
|
| 1475 |
+
"grad_norm": 0.4140625,
|
| 1476 |
"learning_rate": 0.0001305073021005321,
|
| 1477 |
+
"loss": 0.9525,
|
| 1478 |
"step": 1010
|
| 1479 |
},
|
| 1480 |
{
|
| 1481 |
"epoch": 6.9520547945205475,
|
| 1482 |
+
"grad_norm": 0.400390625,
|
| 1483 |
"learning_rate": 0.0001297473789538142,
|
| 1484 |
+
"loss": 0.9554,
|
| 1485 |
"step": 1015
|
| 1486 |
},
|
| 1487 |
{
|
| 1488 |
"epoch": 6.986301369863014,
|
| 1489 |
+
"grad_norm": 0.37890625,
|
| 1490 |
"learning_rate": 0.00012898556645494325,
|
| 1491 |
+
"loss": 0.955,
|
| 1492 |
"step": 1020
|
| 1493 |
},
|
| 1494 |
{
|
| 1495 |
"epoch": 7.0,
|
| 1496 |
+
"eval_loss": 2.5866098403930664,
|
| 1497 |
+
"eval_runtime": 0.5603,
|
| 1498 |
+
"eval_samples_per_second": 17.847,
|
| 1499 |
+
"eval_steps_per_second": 1.785,
|
| 1500 |
"step": 1022
|
| 1501 |
},
|
| 1502 |
{
|
| 1503 |
"epoch": 7.02054794520548,
|
| 1504 |
+
"grad_norm": 0.380859375,
|
| 1505 |
"learning_rate": 0.0001282219129890925,
|
| 1506 |
+
"loss": 0.9357,
|
| 1507 |
"step": 1025
|
| 1508 |
},
|
| 1509 |
{
|
| 1510 |
"epoch": 7.054794520547945,
|
| 1511 |
+
"grad_norm": 0.373046875,
|
| 1512 |
"learning_rate": 0.00012745646705836097,
|
| 1513 |
+
"loss": 0.9228,
|
| 1514 |
"step": 1030
|
| 1515 |
},
|
| 1516 |
{
|
| 1517 |
"epoch": 7.089041095890411,
|
| 1518 |
+
"grad_norm": 0.5390625,
|
| 1519 |
"learning_rate": 0.0001266892772786929,
|
| 1520 |
+
"loss": 0.9121,
|
| 1521 |
"step": 1035
|
| 1522 |
},
|
| 1523 |
{
|
| 1524 |
"epoch": 7.123287671232877,
|
| 1525 |
+
"grad_norm": 0.37109375,
|
| 1526 |
"learning_rate": 0.0001259203923767901,
|
| 1527 |
+
"loss": 0.9181,
|
| 1528 |
"step": 1040
|
| 1529 |
},
|
| 1530 |
{
|
| 1531 |
"epoch": 7.157534246575342,
|
| 1532 |
+
"grad_norm": 0.37109375,
|
| 1533 |
"learning_rate": 0.00012514986118701695,
|
| 1534 |
+
"loss": 0.9176,
|
| 1535 |
"step": 1045
|
| 1536 |
},
|
| 1537 |
{
|
| 1538 |
"epoch": 7.191780821917808,
|
| 1539 |
+
"grad_norm": 0.3984375,
|
| 1540 |
"learning_rate": 0.00012437773264829897,
|
| 1541 |
+
"loss": 0.9241,
|
| 1542 |
"step": 1050
|
| 1543 |
},
|
| 1544 |
{
|
| 1545 |
"epoch": 7.226027397260274,
|
| 1546 |
+
"grad_norm": 0.376953125,
|
| 1547 |
"learning_rate": 0.00012360405580101448,
|
| 1548 |
+
"loss": 0.9287,
|
| 1549 |
"step": 1055
|
| 1550 |
},
|
| 1551 |
{
|
| 1552 |
"epoch": 7.260273972602739,
|
| 1553 |
+
"grad_norm": 0.375,
|
| 1554 |
"learning_rate": 0.00012282887978387976,
|
| 1555 |
+
"loss": 0.9347,
|
| 1556 |
"step": 1060
|
| 1557 |
},
|
| 1558 |
{
|
| 1559 |
"epoch": 7.294520547945205,
|
| 1560 |
+
"grad_norm": 0.3984375,
|
| 1561 |
"learning_rate": 0.00012205225383082843,
|
| 1562 |
+
"loss": 0.9275,
|
| 1563 |
"step": 1065
|
| 1564 |
},
|
| 1565 |
{
|
| 1566 |
"epoch": 7.328767123287671,
|
| 1567 |
+
"grad_norm": 0.404296875,
|
| 1568 |
"learning_rate": 0.000121274227267884,
|
| 1569 |
+
"loss": 0.923,
|
| 1570 |
"step": 1070
|
| 1571 |
},
|
| 1572 |
{
|
| 1573 |
"epoch": 7.363013698630137,
|
| 1574 |
+
"grad_norm": 0.388671875,
|
| 1575 |
"learning_rate": 0.00012049484951002739,
|
| 1576 |
+
"loss": 0.9332,
|
| 1577 |
"step": 1075
|
| 1578 |
},
|
| 1579 |
{
|
| 1580 |
"epoch": 7.397260273972603,
|
| 1581 |
+
"grad_norm": 0.37890625,
|
| 1582 |
"learning_rate": 0.00011971417005805818,
|
| 1583 |
+
"loss": 0.9238,
|
| 1584 |
"step": 1080
|
| 1585 |
},
|
| 1586 |
{
|
| 1587 |
"epoch": 7.431506849315069,
|
| 1588 |
+
"grad_norm": 0.37109375,
|
| 1589 |
"learning_rate": 0.00011893223849545084,
|
| 1590 |
+
"loss": 0.9278,
|
| 1591 |
"step": 1085
|
| 1592 |
},
|
| 1593 |
{
|
| 1594 |
"epoch": 7.465753424657534,
|
| 1595 |
+
"grad_norm": 0.388671875,
|
| 1596 |
"learning_rate": 0.00011814910448520536,
|
| 1597 |
+
"loss": 0.9268,
|
| 1598 |
"step": 1090
|
| 1599 |
},
|
| 1600 |
{
|
| 1601 |
"epoch": 7.5,
|
| 1602 |
"grad_norm": 0.404296875,
|
| 1603 |
"learning_rate": 0.00011736481776669306,
|
| 1604 |
+
"loss": 0.931,
|
| 1605 |
"step": 1095
|
| 1606 |
},
|
| 1607 |
{
|
| 1608 |
"epoch": 7.534246575342466,
|
| 1609 |
+
"grad_norm": 0.390625,
|
| 1610 |
"learning_rate": 0.00011657942815249754,
|
| 1611 |
+
"loss": 0.9283,
|
| 1612 |
"step": 1100
|
| 1613 |
},
|
| 1614 |
{
|
| 1615 |
"epoch": 7.568493150684931,
|
| 1616 |
+
"grad_norm": 0.369140625,
|
| 1617 |
"learning_rate": 0.00011579298552525084,
|
| 1618 |
+
"loss": 0.9246,
|
| 1619 |
"step": 1105
|
| 1620 |
},
|
| 1621 |
{
|
| 1622 |
"epoch": 7.602739726027397,
|
| 1623 |
+
"grad_norm": 0.390625,
|
| 1624 |
"learning_rate": 0.00011500553983446527,
|
| 1625 |
+
"loss": 0.9293,
|
| 1626 |
"step": 1110
|
| 1627 |
},
|
| 1628 |
{
|
| 1629 |
"epoch": 7.636986301369863,
|
| 1630 |
+
"grad_norm": 0.365234375,
|
| 1631 |
"learning_rate": 0.00011421714109336097,
|
| 1632 |
+
"loss": 0.9335,
|
| 1633 |
"step": 1115
|
| 1634 |
},
|
| 1635 |
{
|
| 1636 |
"epoch": 7.671232876712329,
|
| 1637 |
+
"grad_norm": 0.453125,
|
| 1638 |
"learning_rate": 0.00011342783937568926,
|
| 1639 |
+
"loss": 0.9359,
|
| 1640 |
"step": 1120
|
| 1641 |
},
|
| 1642 |
{
|
| 1643 |
"epoch": 7.705479452054795,
|
| 1644 |
+
"grad_norm": 0.416015625,
|
| 1645 |
"learning_rate": 0.00011263768481255264,
|
| 1646 |
+
"loss": 0.9295,
|
| 1647 |
"step": 1125
|
| 1648 |
},
|
| 1649 |
{
|
| 1650 |
"epoch": 7.739726027397261,
|
| 1651 |
+
"grad_norm": 0.380859375,
|
| 1652 |
"learning_rate": 0.00011184672758922034,
|
| 1653 |
+
"loss": 0.9404,
|
| 1654 |
"step": 1130
|
| 1655 |
},
|
| 1656 |
{
|
| 1657 |
"epoch": 7.773972602739726,
|
| 1658 |
+
"grad_norm": 0.396484375,
|
| 1659 |
"learning_rate": 0.00011105501794194131,
|
| 1660 |
+
"loss": 0.9289,
|
| 1661 |
"step": 1135
|
| 1662 |
},
|
| 1663 |
{
|
| 1664 |
"epoch": 7.808219178082192,
|
| 1665 |
+
"grad_norm": 0.39453125,
|
| 1666 |
"learning_rate": 0.00011026260615475333,
|
| 1667 |
+
"loss": 0.9409,
|
| 1668 |
"step": 1140
|
| 1669 |
},
|
| 1670 |
{
|
| 1671 |
"epoch": 7.842465753424658,
|
| 1672 |
+
"grad_norm": 0.396484375,
|
| 1673 |
"learning_rate": 0.00010946954255628928,
|
| 1674 |
+
"loss": 0.9355,
|
| 1675 |
"step": 1145
|
| 1676 |
},
|
| 1677 |
{
|
| 1678 |
"epoch": 7.876712328767123,
|
| 1679 |
+
"grad_norm": 0.443359375,
|
| 1680 |
"learning_rate": 0.00010867587751658079,
|
| 1681 |
+
"loss": 0.9257,
|
| 1682 |
"step": 1150
|
| 1683 |
},
|
| 1684 |
{
|
| 1685 |
"epoch": 7.910958904109589,
|
| 1686 |
+
"grad_norm": 0.365234375,
|
| 1687 |
"learning_rate": 0.00010788166144385888,
|
| 1688 |
+
"loss": 0.924,
|
| 1689 |
"step": 1155
|
| 1690 |
},
|
| 1691 |
{
|
| 1692 |
"epoch": 7.945205479452055,
|
| 1693 |
+
"grad_norm": 0.427734375,
|
| 1694 |
"learning_rate": 0.0001070869447813525,
|
| 1695 |
+
"loss": 0.9202,
|
| 1696 |
"step": 1160
|
| 1697 |
},
|
| 1698 |
{
|
| 1699 |
"epoch": 7.97945205479452,
|
| 1700 |
+
"grad_norm": 0.3515625,
|
| 1701 |
"learning_rate": 0.0001062917780040847,
|
| 1702 |
+
"loss": 0.9214,
|
| 1703 |
"step": 1165
|
| 1704 |
},
|
| 1705 |
{
|
| 1706 |
"epoch": 8.0,
|
| 1707 |
+
"eval_loss": 2.6224260330200195,
|
| 1708 |
+
"eval_runtime": 0.5566,
|
| 1709 |
+
"eval_samples_per_second": 17.965,
|
| 1710 |
+
"eval_steps_per_second": 1.797,
|
| 1711 |
"step": 1168
|
| 1712 |
},
|
| 1713 |
{
|
| 1714 |
"epoch": 8.013698630136986,
|
| 1715 |
+
"grad_norm": 0.388671875,
|
| 1716 |
"learning_rate": 0.0001054962116156667,
|
| 1717 |
+
"loss": 0.9133,
|
| 1718 |
"step": 1170
|
| 1719 |
},
|
| 1720 |
{
|
| 1721 |
"epoch": 8.047945205479452,
|
| 1722 |
"grad_norm": 0.41796875,
|
| 1723 |
"learning_rate": 0.00010470029614509041,
|
| 1724 |
+
"loss": 0.8952,
|
| 1725 |
"step": 1175
|
| 1726 |
},
|
| 1727 |
{
|
| 1728 |
"epoch": 8.082191780821917,
|
| 1729 |
+
"grad_norm": 0.3984375,
|
| 1730 |
"learning_rate": 0.00010390408214351892,
|
| 1731 |
+
"loss": 0.8963,
|
| 1732 |
"step": 1180
|
| 1733 |
},
|
| 1734 |
{
|
| 1735 |
"epoch": 8.116438356164384,
|
| 1736 |
+
"grad_norm": 0.388671875,
|
| 1737 |
"learning_rate": 0.0001031076201810762,
|
| 1738 |
+
"loss": 0.8996,
|
| 1739 |
"step": 1185
|
| 1740 |
},
|
| 1741 |
{
|
| 1742 |
"epoch": 8.150684931506849,
|
| 1743 |
+
"grad_norm": 0.38671875,
|
| 1744 |
"learning_rate": 0.00010231096084363483,
|
| 1745 |
+
"loss": 0.8898,
|
| 1746 |
"step": 1190
|
| 1747 |
},
|
| 1748 |
{
|
| 1749 |
"epoch": 8.184931506849315,
|
| 1750 |
+
"grad_norm": 0.390625,
|
| 1751 |
"learning_rate": 0.00010151415472960342,
|
| 1752 |
+
"loss": 0.9138,
|
| 1753 |
"step": 1195
|
| 1754 |
},
|
| 1755 |
{
|
| 1756 |
"epoch": 8.219178082191782,
|
| 1757 |
+
"grad_norm": 0.388671875,
|
| 1758 |
"learning_rate": 0.00010071725244671282,
|
| 1759 |
+
"loss": 0.9023,
|
| 1760 |
"step": 1200
|
| 1761 |
},
|
| 1762 |
{
|
| 1763 |
"epoch": 8.253424657534246,
|
| 1764 |
+
"grad_norm": 0.388671875,
|
| 1765 |
"learning_rate": 9.992030460880181e-05,
|
| 1766 |
+
"loss": 0.8929,
|
| 1767 |
"step": 1205
|
| 1768 |
},
|
| 1769 |
{
|
| 1770 |
"epoch": 8.287671232876713,
|
| 1771 |
+
"grad_norm": 0.392578125,
|
| 1772 |
"learning_rate": 9.91233618326026e-05,
|
| 1773 |
+
"loss": 0.9089,
|
| 1774 |
"step": 1210
|
| 1775 |
},
|
| 1776 |
{
|
| 1777 |
"epoch": 8.321917808219178,
|
| 1778 |
+
"grad_norm": 0.41015625,
|
| 1779 |
"learning_rate": 9.83264747345259e-05,
|
| 1780 |
+
"loss": 0.9037,
|
| 1781 |
"step": 1215
|
| 1782 |
},
|
| 1783 |
{
|
| 1784 |
"epoch": 8.356164383561644,
|
| 1785 |
+
"grad_norm": 0.369140625,
|
| 1786 |
"learning_rate": 9.752969392744606e-05,
|
| 1787 |
+
"loss": 0.9062,
|
| 1788 |
"step": 1220
|
| 1789 |
},
|
| 1790 |
{
|
| 1791 |
"epoch": 8.39041095890411,
|
| 1792 |
+
"grad_norm": 0.40234375,
|
| 1793 |
"learning_rate": 9.673307001748661e-05,
|
| 1794 |
+
"loss": 0.8982,
|
| 1795 |
"step": 1225
|
| 1796 |
},
|
| 1797 |
{
|
| 1798 |
"epoch": 8.424657534246576,
|
| 1799 |
+
"grad_norm": 0.392578125,
|
| 1800 |
"learning_rate": 9.593665360080599e-05,
|
| 1801 |
+
"loss": 0.8994,
|
| 1802 |
"step": 1230
|
| 1803 |
},
|
| 1804 |
{
|
| 1805 |
"epoch": 8.45890410958904,
|
| 1806 |
+
"grad_norm": 0.4140625,
|
| 1807 |
"learning_rate": 9.514049526038418e-05,
|
| 1808 |
+
"loss": 0.9045,
|
| 1809 |
"step": 1235
|
| 1810 |
},
|
| 1811 |
{
|
| 1812 |
"epoch": 8.493150684931507,
|
| 1813 |
+
"grad_norm": 0.400390625,
|
| 1814 |
"learning_rate": 9.43446455628097e-05,
|
| 1815 |
+
"loss": 0.9062,
|
| 1816 |
"step": 1240
|
| 1817 |
},
|
| 1818 |
{
|
| 1819 |
"epoch": 8.527397260273972,
|
| 1820 |
+
"grad_norm": 0.427734375,
|
| 1821 |
"learning_rate": 9.354915505506839e-05,
|
| 1822 |
+
"loss": 0.9056,
|
| 1823 |
"step": 1245
|
| 1824 |
},
|
| 1825 |
{
|
| 1826 |
"epoch": 8.561643835616438,
|
| 1827 |
+
"grad_norm": 0.3828125,
|
| 1828 |
"learning_rate": 9.27540742613326e-05,
|
| 1829 |
+
"loss": 0.9078,
|
| 1830 |
"step": 1250
|
| 1831 |
},
|
| 1832 |
{
|
| 1833 |
"epoch": 8.595890410958905,
|
| 1834 |
+
"grad_norm": 0.431640625,
|
| 1835 |
"learning_rate": 9.195945367975256e-05,
|
| 1836 |
+
"loss": 0.8994,
|
| 1837 |
"step": 1255
|
| 1838 |
},
|
| 1839 |
{
|
| 1840 |
"epoch": 8.63013698630137,
|
| 1841 |
+
"grad_norm": 0.404296875,
|
| 1842 |
"learning_rate": 9.116534377924883e-05,
|
| 1843 |
+
"loss": 0.9088,
|
| 1844 |
"step": 1260
|
| 1845 |
},
|
| 1846 |
{
|
| 1847 |
"epoch": 8.664383561643836,
|
| 1848 |
+
"grad_norm": 0.44921875,
|
| 1849 |
"learning_rate": 9.037179499630703e-05,
|
| 1850 |
+
"loss": 0.9035,
|
| 1851 |
"step": 1265
|
| 1852 |
},
|
| 1853 |
{
|
| 1854 |
"epoch": 8.698630136986301,
|
| 1855 |
+
"grad_norm": 0.40625,
|
| 1856 |
"learning_rate": 8.957885773177438e-05,
|
| 1857 |
+
"loss": 0.9178,
|
| 1858 |
"step": 1270
|
| 1859 |
},
|
| 1860 |
{
|
| 1861 |
"epoch": 8.732876712328768,
|
| 1862 |
+
"grad_norm": 0.51953125,
|
| 1863 |
"learning_rate": 8.878658234765858e-05,
|
| 1864 |
+
"loss": 0.9062,
|
| 1865 |
"step": 1275
|
| 1866 |
},
|
| 1867 |
{
|
| 1868 |
"epoch": 8.767123287671232,
|
| 1869 |
+
"grad_norm": 0.486328125,
|
| 1870 |
"learning_rate": 8.799501916392912e-05,
|
| 1871 |
+
"loss": 0.9157,
|
| 1872 |
"step": 1280
|
| 1873 |
},
|
| 1874 |
{
|
| 1875 |
"epoch": 8.801369863013699,
|
| 1876 |
+
"grad_norm": 0.392578125,
|
| 1877 |
"learning_rate": 8.720421845532151e-05,
|
| 1878 |
+
"loss": 0.912,
|
| 1879 |
"step": 1285
|
| 1880 |
},
|
| 1881 |
{
|
| 1882 |
"epoch": 8.835616438356164,
|
| 1883 |
+
"grad_norm": 0.37109375,
|
| 1884 |
"learning_rate": 8.641423044814374e-05,
|
| 1885 |
+
"loss": 0.9085,
|
| 1886 |
"step": 1290
|
| 1887 |
},
|
| 1888 |
{
|
| 1889 |
"epoch": 8.86986301369863,
|
| 1890 |
+
"grad_norm": 0.396484375,
|
| 1891 |
"learning_rate": 8.562510531708677e-05,
|
| 1892 |
+
"loss": 0.9158,
|
| 1893 |
"step": 1295
|
| 1894 |
},
|
| 1895 |
{
|
| 1896 |
"epoch": 8.904109589041095,
|
| 1897 |
+
"grad_norm": 0.384765625,
|
| 1898 |
"learning_rate": 8.48368931820373e-05,
|
| 1899 |
+
"loss": 0.909,
|
| 1900 |
"step": 1300
|
| 1901 |
},
|
| 1902 |
{
|
| 1903 |
"epoch": 8.938356164383562,
|
| 1904 |
+
"grad_norm": 0.39453125,
|
| 1905 |
"learning_rate": 8.404964410489485e-05,
|
| 1906 |
+
"loss": 0.9121,
|
| 1907 |
"step": 1305
|
| 1908 |
},
|
| 1909 |
{
|
| 1910 |
"epoch": 8.972602739726028,
|
| 1911 |
+
"grad_norm": 0.39453125,
|
| 1912 |
"learning_rate": 8.32634080863919e-05,
|
| 1913 |
+
"loss": 0.913,
|
| 1914 |
"step": 1310
|
| 1915 |
},
|
| 1916 |
{
|
| 1917 |
"epoch": 9.0,
|
| 1918 |
+
"eval_loss": 2.6512458324432373,
|
| 1919 |
+
"eval_runtime": 0.5534,
|
| 1920 |
+
"eval_samples_per_second": 18.07,
|
| 1921 |
+
"eval_steps_per_second": 1.807,
|
| 1922 |
"step": 1314
|
| 1923 |
},
|
| 1924 |
{
|
| 1925 |
"epoch": 9.006849315068493,
|
| 1926 |
+
"grad_norm": 0.408203125,
|
| 1927 |
"learning_rate": 8.247823506291844e-05,
|
| 1928 |
+
"loss": 0.9034,
|
| 1929 |
"step": 1315
|
| 1930 |
},
|
| 1931 |
{
|
| 1932 |
"epoch": 9.04109589041096,
|
| 1933 |
+
"grad_norm": 0.404296875,
|
| 1934 |
"learning_rate": 8.169417490335007e-05,
|
| 1935 |
+
"loss": 0.8821,
|
| 1936 |
"step": 1320
|
| 1937 |
},
|
| 1938 |
{
|
| 1939 |
"epoch": 9.075342465753424,
|
| 1940 |
+
"grad_norm": 0.416015625,
|
| 1941 |
"learning_rate": 8.091127740588094e-05,
|
| 1942 |
+
"loss": 0.8702,
|
| 1943 |
"step": 1325
|
| 1944 |
},
|
| 1945 |
{
|
| 1946 |
"epoch": 9.10958904109589,
|
| 1947 |
+
"grad_norm": 0.39453125,
|
| 1948 |
"learning_rate": 8.012959229486061e-05,
|
| 1949 |
+
"loss": 0.8755,
|
| 1950 |
"step": 1330
|
| 1951 |
},
|
| 1952 |
{
|
| 1953 |
"epoch": 9.143835616438356,
|
| 1954 |
+
"grad_norm": 0.43359375,
|
| 1955 |
"learning_rate": 7.934916921763628e-05,
|
| 1956 |
+
"loss": 0.8783,
|
| 1957 |
"step": 1335
|
| 1958 |
},
|
| 1959 |
{
|
| 1960 |
"epoch": 9.178082191780822,
|
| 1961 |
+
"grad_norm": 0.421875,
|
| 1962 |
"learning_rate": 7.857005774139907e-05,
|
| 1963 |
+
"loss": 0.8794,
|
| 1964 |
"step": 1340
|
| 1965 |
},
|
| 1966 |
{
|
| 1967 |
"epoch": 9.212328767123287,
|
| 1968 |
+
"grad_norm": 0.400390625,
|
| 1969 |
"learning_rate": 7.779230735003628e-05,
|
| 1970 |
+
"loss": 0.8844,
|
| 1971 |
"step": 1345
|
| 1972 |
},
|
| 1973 |
{
|
| 1974 |
"epoch": 9.246575342465754,
|
| 1975 |
+
"grad_norm": 0.3984375,
|
| 1976 |
"learning_rate": 7.701596744098818e-05,
|
| 1977 |
+
"loss": 0.8775,
|
| 1978 |
"step": 1350
|
| 1979 |
},
|
| 1980 |
{
|
| 1981 |
"epoch": 9.280821917808218,
|
| 1982 |
+
"grad_norm": 0.404296875,
|
| 1983 |
"learning_rate": 7.624108732211081e-05,
|
| 1984 |
+
"loss": 0.8705,
|
| 1985 |
"step": 1355
|
| 1986 |
},
|
| 1987 |
{
|
| 1988 |
"epoch": 9.315068493150685,
|
| 1989 |
+
"grad_norm": 0.408203125,
|
| 1990 |
"learning_rate": 7.54677162085442e-05,
|
| 1991 |
+
"loss": 0.8897,
|
| 1992 |
"step": 1360
|
| 1993 |
},
|
| 1994 |
{
|
| 1995 |
"epoch": 9.349315068493151,
|
| 1996 |
+
"grad_norm": 0.3984375,
|
| 1997 |
"learning_rate": 7.469590321958662e-05,
|
| 1998 |
+
"loss": 0.882,
|
| 1999 |
"step": 1365
|
| 2000 |
},
|
| 2001 |
{
|
| 2002 |
"epoch": 9.383561643835616,
|
| 2003 |
"grad_norm": 0.43359375,
|
| 2004 |
"learning_rate": 7.392569737557474e-05,
|
| 2005 |
+
"loss": 0.8879,
|
| 2006 |
"step": 1370
|
| 2007 |
},
|
| 2008 |
{
|
| 2009 |
"epoch": 9.417808219178083,
|
| 2010 |
+
"grad_norm": 0.416015625,
|
| 2011 |
"learning_rate": 7.31571475947703e-05,
|
| 2012 |
+
"loss": 0.8827,
|
| 2013 |
"step": 1375
|
| 2014 |
},
|
| 2015 |
{
|
| 2016 |
"epoch": 9.452054794520548,
|
| 2017 |
+
"grad_norm": 0.412109375,
|
| 2018 |
"learning_rate": 7.239030269025311e-05,
|
| 2019 |
+
"loss": 0.8805,
|
| 2020 |
"step": 1380
|
| 2021 |
},
|
| 2022 |
{
|
| 2023 |
"epoch": 9.486301369863014,
|
| 2024 |
+
"grad_norm": 0.408203125,
|
| 2025 |
"learning_rate": 7.162521136682085e-05,
|
| 2026 |
+
"loss": 0.8966,
|
| 2027 |
"step": 1385
|
| 2028 |
},
|
| 2029 |
{
|
| 2030 |
"epoch": 9.520547945205479,
|
| 2031 |
+
"grad_norm": 0.431640625,
|
| 2032 |
"learning_rate": 7.08619222178954e-05,
|
| 2033 |
+
"loss": 0.8895,
|
| 2034 |
"step": 1390
|
| 2035 |
},
|
| 2036 |
{
|
| 2037 |
"epoch": 9.554794520547945,
|
| 2038 |
+
"grad_norm": 0.423828125,
|
| 2039 |
"learning_rate": 7.010048372243698e-05,
|
| 2040 |
+
"loss": 0.8907,
|
| 2041 |
"step": 1395
|
| 2042 |
},
|
| 2043 |
{
|
| 2044 |
"epoch": 9.58904109589041,
|
| 2045 |
+
"grad_norm": 0.42578125,
|
| 2046 |
"learning_rate": 6.934094424186459e-05,
|
| 2047 |
+
"loss": 0.8876,
|
| 2048 |
"step": 1400
|
| 2049 |
},
|
| 2050 |
{
|
| 2051 |
"epoch": 9.623287671232877,
|
| 2052 |
+
"grad_norm": 0.39453125,
|
| 2053 |
"learning_rate": 6.858335201698485e-05,
|
| 2054 |
+
"loss": 0.8936,
|
| 2055 |
"step": 1405
|
| 2056 |
},
|
| 2057 |
{
|
| 2058 |
"epoch": 9.657534246575342,
|
| 2059 |
+
"grad_norm": 0.451171875,
|
| 2060 |
"learning_rate": 6.782775516492771e-05,
|
| 2061 |
+
"loss": 0.8804,
|
| 2062 |
"step": 1410
|
| 2063 |
},
|
| 2064 |
{
|
| 2065 |
"epoch": 9.691780821917808,
|
| 2066 |
+
"grad_norm": 0.40234375,
|
| 2067 |
"learning_rate": 6.70742016760907e-05,
|
| 2068 |
+
"loss": 0.8907,
|
| 2069 |
"step": 1415
|
| 2070 |
},
|
| 2071 |
{
|
| 2072 |
"epoch": 9.726027397260275,
|
| 2073 |
+
"grad_norm": 0.4453125,
|
| 2074 |
"learning_rate": 6.632273941109064e-05,
|
| 2075 |
+
"loss": 0.8756,
|
| 2076 |
"step": 1420
|
| 2077 |
},
|
| 2078 |
{
|
| 2079 |
"epoch": 9.76027397260274,
|
| 2080 |
+
"grad_norm": 0.40625,
|
| 2081 |
"learning_rate": 6.5573416097724e-05,
|
| 2082 |
+
"loss": 0.8963,
|
| 2083 |
"step": 1425
|
| 2084 |
},
|
| 2085 |
{
|
| 2086 |
"epoch": 9.794520547945206,
|
| 2087 |
+
"grad_norm": 0.412109375,
|
| 2088 |
"learning_rate": 6.482627932793553e-05,
|
| 2089 |
+
"loss": 0.8998,
|
| 2090 |
"step": 1430
|
| 2091 |
},
|
| 2092 |
{
|
| 2093 |
"epoch": 9.82876712328767,
|
| 2094 |
+
"grad_norm": 0.419921875,
|
| 2095 |
"learning_rate": 6.408137655479554e-05,
|
| 2096 |
+
"loss": 0.9024,
|
| 2097 |
"step": 1435
|
| 2098 |
},
|
| 2099 |
{
|
| 2100 |
"epoch": 9.863013698630137,
|
| 2101 |
+
"grad_norm": 0.421875,
|
| 2102 |
"learning_rate": 6.333875508948593e-05,
|
| 2103 |
+
"loss": 0.8921,
|
| 2104 |
"step": 1440
|
| 2105 |
},
|
| 2106 |
{
|
| 2107 |
"epoch": 9.897260273972602,
|
| 2108 |
+
"grad_norm": 0.45703125,
|
| 2109 |
"learning_rate": 6.259846209829551e-05,
|
| 2110 |
+
"loss": 0.904,
|
| 2111 |
"step": 1445
|
| 2112 |
},
|
| 2113 |
{
|
| 2114 |
"epoch": 9.931506849315069,
|
| 2115 |
+
"grad_norm": 0.4140625,
|
| 2116 |
"learning_rate": 6.186054459962399e-05,
|
| 2117 |
+
"loss": 0.8899,
|
| 2118 |
"step": 1450
|
| 2119 |
},
|
| 2120 |
{
|
| 2121 |
"epoch": 9.965753424657533,
|
| 2122 |
+
"grad_norm": 0.40625,
|
| 2123 |
"learning_rate": 6.112504946099604e-05,
|
| 2124 |
+
"loss": 0.8875,
|
| 2125 |
"step": 1455
|
| 2126 |
},
|
| 2127 |
{
|
| 2128 |
"epoch": 10.0,
|
| 2129 |
+
"grad_norm": 0.431640625,
|
| 2130 |
"learning_rate": 6.039202339608432e-05,
|
| 2131 |
+
"loss": 0.889,
|
| 2132 |
"step": 1460
|
| 2133 |
},
|
| 2134 |
{
|
| 2135 |
"epoch": 10.0,
|
| 2136 |
+
"eval_loss": 2.6852145195007324,
|
| 2137 |
+
"eval_runtime": 0.5511,
|
| 2138 |
+
"eval_samples_per_second": 18.146,
|
| 2139 |
+
"eval_steps_per_second": 1.815,
|
| 2140 |
"step": 1460
|
| 2141 |
},
|
| 2142 |
{
|
| 2143 |
"epoch": 10.034246575342467,
|
| 2144 |
+
"grad_norm": 0.40625,
|
| 2145 |
"learning_rate": 5.966151296174268e-05,
|
| 2146 |
+
"loss": 0.8664,
|
| 2147 |
"step": 1465
|
| 2148 |
},
|
| 2149 |
{
|
| 2150 |
"epoch": 10.068493150684931,
|
| 2151 |
+
"grad_norm": 0.431640625,
|
| 2152 |
"learning_rate": 5.8933564555049105e-05,
|
| 2153 |
+
"loss": 0.8677,
|
| 2154 |
"step": 1470
|
| 2155 |
},
|
| 2156 |
{
|
| 2157 |
"epoch": 10.102739726027398,
|
| 2158 |
+
"grad_norm": 0.41796875,
|
| 2159 |
"learning_rate": 5.820822441035899e-05,
|
| 2160 |
+
"loss": 0.866,
|
| 2161 |
"step": 1475
|
| 2162 |
},
|
| 2163 |
{
|
| 2164 |
"epoch": 10.136986301369863,
|
| 2165 |
+
"grad_norm": 0.40625,
|
| 2166 |
"learning_rate": 5.7485538596368496e-05,
|
| 2167 |
+
"loss": 0.8664,
|
| 2168 |
"step": 1480
|
| 2169 |
},
|
| 2170 |
{
|
| 2171 |
"epoch": 10.17123287671233,
|
| 2172 |
"grad_norm": 0.41015625,
|
| 2173 |
"learning_rate": 5.6765553013188766e-05,
|
| 2174 |
+
"loss": 0.8645,
|
| 2175 |
"step": 1485
|
| 2176 |
},
|
| 2177 |
{
|
| 2178 |
"epoch": 10.205479452054794,
|
| 2179 |
+
"grad_norm": 0.400390625,
|
| 2180 |
"learning_rate": 5.6048313389430484e-05,
|
| 2181 |
+
"loss": 0.8624,
|
| 2182 |
"step": 1490
|
| 2183 |
},
|
| 2184 |
{
|
| 2185 |
"epoch": 10.23972602739726,
|
| 2186 |
+
"grad_norm": 0.408203125,
|
| 2187 |
"learning_rate": 5.533386527929962e-05,
|
| 2188 |
+
"loss": 0.874,
|
| 2189 |
"step": 1495
|
| 2190 |
},
|
| 2191 |
{
|
| 2192 |
"epoch": 10.273972602739725,
|
| 2193 |
+
"grad_norm": 0.40625,
|
| 2194 |
"learning_rate": 5.462225405970401e-05,
|
| 2195 |
+
"loss": 0.8708,
|
| 2196 |
"step": 1500
|
| 2197 |
},
|
| 2198 |
{
|
| 2199 |
+
"epoch": 10.273972602739725,
|
| 2200 |
+
"step": 1500,
|
| 2201 |
+
"total_flos": 8.853977907740017e+17,
|
| 2202 |
+
"train_loss": 0.0,
|
| 2203 |
+
"train_runtime": 2.8738,
|
| 2204 |
+
"train_samples_per_second": 24365.255,
|
| 2205 |
+
"train_steps_per_second": 508.044
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2206 |
}
|
| 2207 |
],
|
| 2208 |
"logging_steps": 5,
|
| 2209 |
+
"max_steps": 1460,
|
| 2210 |
"num_input_tokens_seen": 0,
|
| 2211 |
+
"num_train_epochs": 10,
|
| 2212 |
"save_steps": 100,
|
| 2213 |
"stateful_callbacks": {
|
| 2214 |
"TrainerControl": {
|
|
|
|
| 2222 |
"attributes": {}
|
| 2223 |
}
|
| 2224 |
},
|
| 2225 |
+
"total_flos": 8.853977907740017e+17,
|
| 2226 |
"train_batch_size": 8,
|
| 2227 |
"trial_name": null,
|
| 2228 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae681e8a9654a4e133111dfcf66660b6b957d55bd252fdde7dac3732a4ad91c9
|
| 3 |
size 5304
|