Ben Buddendorff commited on
Commit ·
9548349
1
Parent(s): 352c3ca
train_residue_list_lr_3e-4_epochs_4
Browse files- README.md +17 -19
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- all_results.json +11 -11
- eval_results.json +6 -6
- model_eval_results.csv +0 -0
- trainer_log.jsonl +0 -0
- trainer_state.json +572 -941
- training_args.bin +2 -2
- training_eval_loss.png +2 -2
- training_loss.png +2 -2
README.md
CHANGED
|
@@ -7,19 +7,19 @@ tags:
|
|
| 7 |
- lora
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
-
- name:
|
| 11 |
results: []
|
| 12 |
---
|
| 13 |
|
| 14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
|
| 17 |
-
#
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [GreatCaptainNemo/ProLLaMA_Stage_1](https://huggingface.co/GreatCaptainNemo/ProLLaMA_Stage_1) on the adpr_train dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
-
- Num Input Tokens Seen:
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
@@ -38,7 +38,7 @@ More information needed
|
|
| 38 |
### Training hyperparameters
|
| 39 |
|
| 40 |
The following hyperparameters were used during training:
|
| 41 |
-
- learning_rate: 0.
|
| 42 |
- train_batch_size: 16
|
| 43 |
- eval_batch_size: 16
|
| 44 |
- seed: 42
|
|
@@ -46,29 +46,27 @@ The following hyperparameters were used during training:
|
|
| 46 |
- total_train_batch_size: 128
|
| 47 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
- lr_scheduler_type: cosine
|
| 49 |
-
- lr_scheduler_warmup_steps:
|
| 50 |
-
- num_epochs:
|
| 51 |
|
| 52 |
### Training results
|
| 53 |
|
| 54 |
| Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
|
| 55 |
|:-------------:|:------:|:----:|:---------------:|:-----------------:|
|
| 56 |
-
|
|
| 57 |
-
| 0.
|
| 58 |
-
|
|
| 59 |
-
|
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.5305 | 4.0912 | 900 | 0.5296 | 11019520 |
|
| 65 |
-
| 0.5281 | 4.5473 | 1000 | 0.5262 | 12247168 |
|
| 66 |
|
| 67 |
|
| 68 |
### Framework versions
|
| 69 |
|
| 70 |
- PEFT 0.14.0
|
| 71 |
-
- Transformers 4.
|
| 72 |
- Pytorch 2.3.1+cu121
|
| 73 |
- Datasets 3.5.0
|
| 74 |
-
- Tokenizers 0.21.
|
|
|
|
| 7 |
- lora
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
+
- name: train_residue_list_lr_3e-4_epochs_4
|
| 11 |
results: []
|
| 12 |
---
|
| 13 |
|
| 14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
|
| 17 |
+
# train_residue_list_lr_3e-4_epochs_4
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [GreatCaptainNemo/ProLLaMA_Stage_1](https://huggingface.co/GreatCaptainNemo/ProLLaMA_Stage_1) on the adpr_train dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2245
|
| 22 |
+
- Num Input Tokens Seen: 10733712
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 38 |
### Training hyperparameters
|
| 39 |
|
| 40 |
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.0003
|
| 42 |
- train_batch_size: 16
|
| 43 |
- eval_batch_size: 16
|
| 44 |
- seed: 42
|
|
|
|
| 46 |
- total_train_batch_size: 128
|
| 47 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_steps: 40
|
| 50 |
+
- num_epochs: 4.0
|
| 51 |
|
| 52 |
### Training results
|
| 53 |
|
| 54 |
| Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
|
| 55 |
|:-------------:|:------:|:----:|:---------------:|:-----------------:|
|
| 56 |
+
| 0.4689 | 0.4561 | 100 | 0.4738 | 1230464 |
|
| 57 |
+
| 0.4141 | 0.9122 | 200 | 0.4266 | 2455680 |
|
| 58 |
+
| 0.3463 | 1.3649 | 300 | 0.3486 | 3673744 |
|
| 59 |
+
| 0.3069 | 1.8210 | 400 | 0.3009 | 4901648 |
|
| 60 |
+
| 0.2464 | 2.2737 | 500 | 0.2616 | 6120272 |
|
| 61 |
+
| 0.2138 | 2.7298 | 600 | 0.2381 | 7348944 |
|
| 62 |
+
| 0.1573 | 3.1824 | 700 | 0.2320 | 8570128 |
|
| 63 |
+
| 0.1488 | 3.6385 | 800 | 0.2253 | 9801744 |
|
|
|
|
|
|
|
| 64 |
|
| 65 |
|
| 66 |
### Framework versions
|
| 67 |
|
| 68 |
- PEFT 0.14.0
|
| 69 |
+
- Transformers 4.51.3
|
| 70 |
- Pytorch 2.3.1+cu121
|
| 71 |
- Datasets 3.5.0
|
| 72 |
+
- Tokenizers 0.21.1
|
adapter_config.json
CHANGED
|
@@ -23,13 +23,13 @@
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
| 26 |
-
"k_proj",
|
| 27 |
"v_proj",
|
| 28 |
"gate_proj",
|
| 29 |
"o_proj",
|
| 30 |
-
"
|
| 31 |
"q_proj",
|
| 32 |
-
"
|
|
|
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
|
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
|
|
|
| 26 |
"v_proj",
|
| 27 |
"gate_proj",
|
| 28 |
"o_proj",
|
| 29 |
+
"down_proj",
|
| 30 |
"q_proj",
|
| 31 |
+
"k_proj",
|
| 32 |
+
"up_proj"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 639691872
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c417ab81a9172e2a85c9b83ccfb71d2596b0cc38e57deb91dbd023414ba198be
|
| 3 |
size 639691872
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss": 0.
|
| 4 |
-
"eval_runtime": 33.
|
| 5 |
-
"eval_samples_per_second":
|
| 6 |
-
"eval_steps_per_second": 5.
|
| 7 |
-
"num_input_tokens_seen":
|
| 8 |
-
"total_flos":
|
| 9 |
-
"train_loss":
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second": 25.
|
| 12 |
-
"train_steps_per_second": 0.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 3.9851767388825543,
|
| 3 |
+
"eval_loss": 0.22454006969928741,
|
| 4 |
+
"eval_runtime": 33.7031,
|
| 5 |
+
"eval_samples_per_second": 92.514,
|
| 6 |
+
"eval_steps_per_second": 5.786,
|
| 7 |
+
"num_input_tokens_seen": 10733712,
|
| 8 |
+
"total_flos": 4.35826368961708e+17,
|
| 9 |
+
"train_loss": 0.4072538570726299,
|
| 10 |
+
"train_runtime": 4401.9239,
|
| 11 |
+
"train_samples_per_second": 25.496,
|
| 12 |
+
"train_steps_per_second": 0.199
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss": 0.
|
| 4 |
-
"eval_runtime": 33.
|
| 5 |
-
"eval_samples_per_second":
|
| 6 |
-
"eval_steps_per_second": 5.
|
| 7 |
-
"num_input_tokens_seen":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 3.9851767388825543,
|
| 3 |
+
"eval_loss": 0.22454006969928741,
|
| 4 |
+
"eval_runtime": 33.7031,
|
| 5 |
+
"eval_samples_per_second": 92.514,
|
| 6 |
+
"eval_steps_per_second": 5.786,
|
| 7 |
+
"num_input_tokens_seen": 10733712
|
| 8 |
}
|
model_eval_results.csv
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
trainer_log.jsonl
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
trainer_state.json
CHANGED
|
@@ -1,1870 +1,1501 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 100,
|
| 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": 0.02280501710376283,
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss": 12.
|
| 16 |
"num_input_tokens_seen": 61696,
|
| 17 |
"step": 5
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 0.04561003420752566,
|
| 21 |
-
"grad_norm":
|
| 22 |
-
"learning_rate":
|
| 23 |
-
"loss":
|
| 24 |
"num_input_tokens_seen": 123136,
|
| 25 |
"step": 10
|
| 26 |
},
|
| 27 |
{
|
| 28 |
"epoch": 0.06841505131128849,
|
| 29 |
-
"grad_norm":
|
| 30 |
-
"learning_rate": 0.
|
| 31 |
-
"loss": 1.
|
| 32 |
"num_input_tokens_seen": 184832,
|
| 33 |
"step": 15
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.09122006841505131,
|
| 37 |
-
"grad_norm":
|
| 38 |
-
"learning_rate": 0.
|
| 39 |
-
"loss": 0.
|
| 40 |
"num_input_tokens_seen": 247552,
|
| 41 |
"step": 20
|
| 42 |
},
|
| 43 |
{
|
| 44 |
"epoch": 0.11402508551881414,
|
| 45 |
-
"grad_norm":
|
| 46 |
-
"learning_rate": 0.
|
| 47 |
-
"loss": 0.
|
| 48 |
"num_input_tokens_seen": 308992,
|
| 49 |
"step": 25
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"epoch": 0.13683010262257697,
|
| 53 |
-
"grad_norm":
|
| 54 |
-
"learning_rate": 0.
|
| 55 |
-
"loss": 0.
|
| 56 |
"num_input_tokens_seen": 370176,
|
| 57 |
"step": 30
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.15963511972633979,
|
| 61 |
-
"grad_norm": 0.
|
| 62 |
-
"learning_rate": 0.
|
| 63 |
-
"loss": 0.
|
| 64 |
"num_input_tokens_seen": 430720,
|
| 65 |
"step": 35
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.18244013683010263,
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate": 0.
|
| 71 |
-
"loss": 0.
|
| 72 |
"num_input_tokens_seen": 492800,
|
| 73 |
"step": 40
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 0.20524515393386544,
|
| 77 |
-
"grad_norm":
|
| 78 |
-
"learning_rate": 0.
|
| 79 |
-
"loss":
|
| 80 |
"num_input_tokens_seen": 553984,
|
| 81 |
"step": 45
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 0.22805017103762829,
|
| 85 |
-
"grad_norm":
|
| 86 |
-
"learning_rate": 0.
|
| 87 |
-
"loss": 0.
|
| 88 |
"num_input_tokens_seen": 615040,
|
| 89 |
"step": 50
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"epoch": 0.2508551881413911,
|
| 93 |
-
"grad_norm":
|
| 94 |
-
"learning_rate": 0.
|
| 95 |
-
"loss":
|
| 96 |
"num_input_tokens_seen": 676736,
|
| 97 |
"step": 55
|
| 98 |
},
|
| 99 |
{
|
| 100 |
"epoch": 0.27366020524515394,
|
| 101 |
-
"grad_norm":
|
| 102 |
-
"learning_rate": 0.
|
| 103 |
-
"loss":
|
| 104 |
"num_input_tokens_seen": 738176,
|
| 105 |
"step": 60
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 0.29646522234891676,
|
| 109 |
-
"grad_norm":
|
| 110 |
-
"learning_rate": 0.
|
| 111 |
-
"loss":
|
| 112 |
"num_input_tokens_seen": 799488,
|
| 113 |
"step": 65
|
| 114 |
},
|
| 115 |
{
|
| 116 |
"epoch": 0.31927023945267957,
|
| 117 |
-
"grad_norm":
|
| 118 |
-
"learning_rate": 0.
|
| 119 |
-
"loss":
|
| 120 |
"num_input_tokens_seen": 861568,
|
| 121 |
"step": 70
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.34207525655644244,
|
| 125 |
-
"grad_norm":
|
| 126 |
-
"learning_rate": 0.
|
| 127 |
-
"loss":
|
| 128 |
"num_input_tokens_seen": 924544,
|
| 129 |
"step": 75
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 0.36488027366020526,
|
| 133 |
-
"grad_norm":
|
| 134 |
-
"learning_rate": 0.
|
| 135 |
-
"loss":
|
| 136 |
"num_input_tokens_seen": 985472,
|
| 137 |
"step": 80
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"epoch": 0.38768529076396807,
|
| 141 |
-
"grad_norm":
|
| 142 |
-
"learning_rate": 0.
|
| 143 |
-
"loss":
|
| 144 |
"num_input_tokens_seen": 1046912,
|
| 145 |
"step": 85
|
| 146 |
},
|
| 147 |
{
|
| 148 |
"epoch": 0.4104903078677309,
|
| 149 |
-
"grad_norm":
|
| 150 |
-
"learning_rate": 0.
|
| 151 |
-
"loss":
|
| 152 |
"num_input_tokens_seen": 1108992,
|
| 153 |
"step": 90
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 0.43329532497149376,
|
| 157 |
-
"grad_norm":
|
| 158 |
-
"learning_rate": 0.
|
| 159 |
-
"loss":
|
| 160 |
"num_input_tokens_seen": 1170048,
|
| 161 |
"step": 95
|
| 162 |
},
|
| 163 |
{
|
| 164 |
"epoch": 0.45610034207525657,
|
| 165 |
-
"grad_norm":
|
| 166 |
-
"learning_rate": 0.
|
| 167 |
-
"loss":
|
| 168 |
"num_input_tokens_seen": 1230464,
|
| 169 |
"step": 100
|
| 170 |
},
|
| 171 |
{
|
| 172 |
"epoch": 0.45610034207525657,
|
| 173 |
-
"eval_loss":
|
| 174 |
-
"eval_runtime": 33.
|
| 175 |
-
"eval_samples_per_second":
|
| 176 |
-
"eval_steps_per_second": 5.
|
| 177 |
"num_input_tokens_seen": 1230464,
|
| 178 |
"step": 100
|
| 179 |
},
|
| 180 |
{
|
| 181 |
"epoch": 0.4789053591790194,
|
| 182 |
-
"grad_norm":
|
| 183 |
-
"learning_rate": 0.
|
| 184 |
-
"loss":
|
| 185 |
"num_input_tokens_seen": 1292288,
|
| 186 |
"step": 105
|
| 187 |
},
|
| 188 |
{
|
| 189 |
"epoch": 0.5017103762827823,
|
| 190 |
-
"grad_norm":
|
| 191 |
-
"learning_rate": 0.
|
| 192 |
-
"loss":
|
| 193 |
"num_input_tokens_seen": 1353344,
|
| 194 |
"step": 110
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 0.5245153933865451,
|
| 198 |
-
"grad_norm":
|
| 199 |
-
"learning_rate": 0.
|
| 200 |
-
"loss":
|
| 201 |
"num_input_tokens_seen": 1415040,
|
| 202 |
"step": 115
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"epoch": 0.5473204104903079,
|
| 206 |
-
"grad_norm":
|
| 207 |
-
"learning_rate": 0.
|
| 208 |
-
"loss":
|
| 209 |
"num_input_tokens_seen": 1476480,
|
| 210 |
"step": 120
|
| 211 |
},
|
| 212 |
{
|
| 213 |
"epoch": 0.5701254275940707,
|
| 214 |
-
"grad_norm":
|
| 215 |
-
"learning_rate": 0.
|
| 216 |
-
"loss":
|
| 217 |
"num_input_tokens_seen": 1537664,
|
| 218 |
"step": 125
|
| 219 |
},
|
| 220 |
{
|
| 221 |
"epoch": 0.5929304446978335,
|
| 222 |
-
"grad_norm":
|
| 223 |
-
"learning_rate": 0.
|
| 224 |
-
"loss":
|
| 225 |
"num_input_tokens_seen": 1598848,
|
| 226 |
"step": 130
|
| 227 |
},
|
| 228 |
{
|
| 229 |
"epoch": 0.6157354618015963,
|
| 230 |
-
"grad_norm":
|
| 231 |
-
"learning_rate": 0.
|
| 232 |
-
"loss":
|
| 233 |
"num_input_tokens_seen": 1660800,
|
| 234 |
"step": 135
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 0.6385404789053591,
|
| 238 |
-
"grad_norm":
|
| 239 |
-
"learning_rate": 0.
|
| 240 |
-
"loss":
|
| 241 |
"num_input_tokens_seen": 1721600,
|
| 242 |
"step": 140
|
| 243 |
},
|
| 244 |
{
|
| 245 |
"epoch": 0.661345496009122,
|
| 246 |
-
"grad_norm":
|
| 247 |
-
"learning_rate": 0.
|
| 248 |
-
"loss":
|
| 249 |
"num_input_tokens_seen": 1783168,
|
| 250 |
"step": 145
|
| 251 |
},
|
| 252 |
{
|
| 253 |
"epoch": 0.6841505131128849,
|
| 254 |
-
"grad_norm":
|
| 255 |
-
"learning_rate": 0.
|
| 256 |
-
"loss":
|
| 257 |
"num_input_tokens_seen": 1844992,
|
| 258 |
"step": 150
|
| 259 |
},
|
| 260 |
{
|
| 261 |
"epoch": 0.7069555302166477,
|
| 262 |
-
"grad_norm":
|
| 263 |
-
"learning_rate": 0.
|
| 264 |
-
"loss":
|
| 265 |
"num_input_tokens_seen": 1906048,
|
| 266 |
"step": 155
|
| 267 |
},
|
| 268 |
{
|
| 269 |
"epoch": 0.7297605473204105,
|
| 270 |
-
"grad_norm":
|
| 271 |
-
"learning_rate": 0.
|
| 272 |
-
"loss":
|
| 273 |
"num_input_tokens_seen": 1967744,
|
| 274 |
"step": 160
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"epoch": 0.7525655644241733,
|
| 278 |
-
"grad_norm":
|
| 279 |
-
"learning_rate": 0.
|
| 280 |
-
"loss": 0.
|
| 281 |
"num_input_tokens_seen": 2028032,
|
| 282 |
"step": 165
|
| 283 |
},
|
| 284 |
{
|
| 285 |
"epoch": 0.7753705815279361,
|
| 286 |
-
"grad_norm":
|
| 287 |
-
"learning_rate": 0.
|
| 288 |
-
"loss": 0.
|
| 289 |
"num_input_tokens_seen": 2088448,
|
| 290 |
"step": 170
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 0.798175598631699,
|
| 294 |
-
"grad_norm":
|
| 295 |
-
"learning_rate": 0.
|
| 296 |
-
"loss": 0.
|
| 297 |
"num_input_tokens_seen": 2150144,
|
| 298 |
"step": 175
|
| 299 |
},
|
| 300 |
{
|
| 301 |
"epoch": 0.8209806157354618,
|
| 302 |
-
"grad_norm":
|
| 303 |
-
"learning_rate": 0.
|
| 304 |
-
"loss": 0.
|
| 305 |
"num_input_tokens_seen": 2211584,
|
| 306 |
"step": 180
|
| 307 |
},
|
| 308 |
{
|
| 309 |
"epoch": 0.8437856328392246,
|
| 310 |
-
"grad_norm":
|
| 311 |
-
"learning_rate": 0.
|
| 312 |
-
"loss": 0.
|
| 313 |
"num_input_tokens_seen": 2272256,
|
| 314 |
"step": 185
|
| 315 |
},
|
| 316 |
{
|
| 317 |
"epoch": 0.8665906499429875,
|
| 318 |
-
"grad_norm":
|
| 319 |
-
"learning_rate": 0.
|
| 320 |
-
"loss": 0.
|
| 321 |
"num_input_tokens_seen": 2333696,
|
| 322 |
"step": 190
|
| 323 |
},
|
| 324 |
{
|
| 325 |
"epoch": 0.8893956670467503,
|
| 326 |
-
"grad_norm":
|
| 327 |
-
"learning_rate": 0.
|
| 328 |
-
"loss": 0.
|
| 329 |
"num_input_tokens_seen": 2394880,
|
| 330 |
"step": 195
|
| 331 |
},
|
| 332 |
{
|
| 333 |
"epoch": 0.9122006841505131,
|
| 334 |
-
"grad_norm":
|
| 335 |
-
"learning_rate": 0.
|
| 336 |
-
"loss": 0.
|
| 337 |
"num_input_tokens_seen": 2455680,
|
| 338 |
"step": 200
|
| 339 |
},
|
| 340 |
{
|
| 341 |
"epoch": 0.9122006841505131,
|
| 342 |
-
"eval_loss": 0.
|
| 343 |
-
"eval_runtime": 33.
|
| 344 |
-
"eval_samples_per_second":
|
| 345 |
-
"eval_steps_per_second": 5.
|
| 346 |
"num_input_tokens_seen": 2455680,
|
| 347 |
"step": 200
|
| 348 |
},
|
| 349 |
{
|
| 350 |
"epoch": 0.935005701254276,
|
| 351 |
-
"grad_norm":
|
| 352 |
-
"learning_rate": 0.
|
| 353 |
-
"loss": 0.
|
| 354 |
"num_input_tokens_seen": 2517376,
|
| 355 |
"step": 205
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"epoch": 0.9578107183580388,
|
| 359 |
-
"grad_norm":
|
| 360 |
-
"learning_rate": 0.
|
| 361 |
-
"loss": 0.
|
| 362 |
"num_input_tokens_seen": 2578816,
|
| 363 |
"step": 210
|
| 364 |
},
|
| 365 |
{
|
| 366 |
"epoch": 0.9806157354618016,
|
| 367 |
-
"grad_norm":
|
| 368 |
-
"learning_rate": 0.
|
| 369 |
-
"loss": 0.
|
| 370 |
"num_input_tokens_seen": 2640128,
|
| 371 |
"step": 215
|
| 372 |
},
|
| 373 |
{
|
| 374 |
"epoch": 1.0,
|
| 375 |
-
"grad_norm":
|
| 376 |
-
"learning_rate": 0.
|
| 377 |
-
"loss": 0.
|
| 378 |
"num_input_tokens_seen": 2691984,
|
| 379 |
"step": 220
|
| 380 |
},
|
| 381 |
{
|
| 382 |
"epoch": 1.0228050171037628,
|
| 383 |
-
"grad_norm":
|
| 384 |
-
"learning_rate": 0.
|
| 385 |
-
"loss": 0.
|
| 386 |
"num_input_tokens_seen": 2753808,
|
| 387 |
"step": 225
|
| 388 |
},
|
| 389 |
{
|
| 390 |
"epoch": 1.0456100342075256,
|
| 391 |
-
"grad_norm":
|
| 392 |
-
"learning_rate": 0.
|
| 393 |
-
"loss":
|
| 394 |
"num_input_tokens_seen": 2815248,
|
| 395 |
"step": 230
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 1.0684150513112884,
|
| 399 |
-
"grad_norm":
|
| 400 |
-
"learning_rate": 0.
|
| 401 |
-
"loss":
|
| 402 |
"num_input_tokens_seen": 2877456,
|
| 403 |
"step": 235
|
| 404 |
},
|
| 405 |
{
|
| 406 |
"epoch": 1.0912200684150513,
|
| 407 |
-
"grad_norm":
|
| 408 |
-
"learning_rate": 0.
|
| 409 |
-
"loss":
|
| 410 |
"num_input_tokens_seen": 2939280,
|
| 411 |
"step": 240
|
| 412 |
},
|
| 413 |
{
|
| 414 |
"epoch": 1.114025085518814,
|
| 415 |
-
"grad_norm":
|
| 416 |
-
"learning_rate": 0.
|
| 417 |
-
"loss":
|
| 418 |
"num_input_tokens_seen": 3000336,
|
| 419 |
"step": 245
|
| 420 |
},
|
| 421 |
{
|
| 422 |
"epoch": 1.1368301026225769,
|
| 423 |
-
"grad_norm":
|
| 424 |
-
"learning_rate": 0.
|
| 425 |
-
"loss":
|
| 426 |
"num_input_tokens_seen": 3062416,
|
| 427 |
"step": 250
|
| 428 |
},
|
| 429 |
{
|
| 430 |
"epoch": 1.1596351197263397,
|
| 431 |
-
"grad_norm":
|
| 432 |
-
"learning_rate": 0.
|
| 433 |
-
"loss":
|
| 434 |
"num_input_tokens_seen": 3124368,
|
| 435 |
"step": 255
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 1.1824401368301025,
|
| 439 |
-
"grad_norm":
|
| 440 |
-
"learning_rate": 0.
|
| 441 |
-
"loss":
|
| 442 |
"num_input_tokens_seen": 3185424,
|
| 443 |
"step": 260
|
| 444 |
},
|
| 445 |
{
|
| 446 |
"epoch": 1.2052451539338653,
|
| 447 |
-
"grad_norm":
|
| 448 |
-
"learning_rate": 0.
|
| 449 |
-
"loss":
|
| 450 |
"num_input_tokens_seen": 3246096,
|
| 451 |
"step": 265
|
| 452 |
},
|
| 453 |
{
|
| 454 |
"epoch": 1.2280501710376284,
|
| 455 |
-
"grad_norm":
|
| 456 |
-
"learning_rate": 0.
|
| 457 |
-
"loss":
|
| 458 |
"num_input_tokens_seen": 3307536,
|
| 459 |
"step": 270
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 1.2508551881413912,
|
| 463 |
-
"grad_norm":
|
| 464 |
-
"learning_rate": 0.
|
| 465 |
-
"loss":
|
| 466 |
"num_input_tokens_seen": 3368976,
|
| 467 |
"step": 275
|
| 468 |
},
|
| 469 |
{
|
| 470 |
"epoch": 1.273660205245154,
|
| 471 |
-
"grad_norm":
|
| 472 |
-
"learning_rate": 0.
|
| 473 |
-
"loss":
|
| 474 |
"num_input_tokens_seen": 3429520,
|
| 475 |
"step": 280
|
| 476 |
},
|
| 477 |
{
|
| 478 |
"epoch": 1.2964652223489168,
|
| 479 |
-
"grad_norm":
|
| 480 |
-
"learning_rate": 0.
|
| 481 |
-
"loss":
|
| 482 |
"num_input_tokens_seen": 3490448,
|
| 483 |
"step": 285
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 1.3192702394526796,
|
| 487 |
-
"grad_norm":
|
| 488 |
-
"learning_rate": 0.
|
| 489 |
-
"loss":
|
| 490 |
"num_input_tokens_seen": 3551120,
|
| 491 |
"step": 290
|
| 492 |
},
|
| 493 |
{
|
| 494 |
"epoch": 1.3420752565564424,
|
| 495 |
-
"grad_norm":
|
| 496 |
-
"learning_rate": 0.
|
| 497 |
-
"loss":
|
| 498 |
"num_input_tokens_seen": 3611920,
|
| 499 |
"step": 295
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"epoch": 1.3648802736602053,
|
| 503 |
-
"grad_norm":
|
| 504 |
-
"learning_rate": 0.
|
| 505 |
-
"loss":
|
| 506 |
"num_input_tokens_seen": 3673744,
|
| 507 |
"step": 300
|
| 508 |
},
|
| 509 |
{
|
| 510 |
"epoch": 1.3648802736602053,
|
| 511 |
-
"eval_loss":
|
| 512 |
-
"eval_runtime": 33.
|
| 513 |
-
"eval_samples_per_second":
|
| 514 |
-
"eval_steps_per_second": 5.
|
| 515 |
"num_input_tokens_seen": 3673744,
|
| 516 |
"step": 300
|
| 517 |
},
|
| 518 |
{
|
| 519 |
"epoch": 1.387685290763968,
|
| 520 |
-
"grad_norm":
|
| 521 |
-
"learning_rate": 0.
|
| 522 |
-
"loss":
|
| 523 |
"num_input_tokens_seen": 3735568,
|
| 524 |
"step": 305
|
| 525 |
},
|
| 526 |
{
|
| 527 |
"epoch": 1.4104903078677309,
|
| 528 |
-
"grad_norm":
|
| 529 |
-
"learning_rate": 0.
|
| 530 |
-
"loss":
|
| 531 |
"num_input_tokens_seen": 3798160,
|
| 532 |
"step": 310
|
| 533 |
},
|
| 534 |
{
|
| 535 |
"epoch": 1.4332953249714937,
|
| 536 |
-
"grad_norm":
|
| 537 |
-
"learning_rate": 0.
|
| 538 |
-
"loss":
|
| 539 |
"num_input_tokens_seen": 3859600,
|
| 540 |
"step": 315
|
| 541 |
},
|
| 542 |
{
|
| 543 |
"epoch": 1.4561003420752565,
|
| 544 |
-
"grad_norm":
|
| 545 |
-
"learning_rate": 0.
|
| 546 |
-
"loss":
|
| 547 |
"num_input_tokens_seen": 3920528,
|
| 548 |
"step": 320
|
| 549 |
},
|
| 550 |
{
|
| 551 |
"epoch": 1.4789053591790193,
|
| 552 |
-
"grad_norm":
|
| 553 |
-
"learning_rate": 0.
|
| 554 |
-
"loss":
|
| 555 |
"num_input_tokens_seen": 3982096,
|
| 556 |
"step": 325
|
| 557 |
},
|
| 558 |
{
|
| 559 |
"epoch": 1.5017103762827824,
|
| 560 |
-
"grad_norm":
|
| 561 |
-
"learning_rate": 0.
|
| 562 |
-
"loss":
|
| 563 |
"num_input_tokens_seen": 4044048,
|
| 564 |
"step": 330
|
| 565 |
},
|
| 566 |
{
|
| 567 |
"epoch": 1.5245153933865452,
|
| 568 |
-
"grad_norm":
|
| 569 |
-
"learning_rate": 0.
|
| 570 |
-
"loss":
|
| 571 |
"num_input_tokens_seen": 4105104,
|
| 572 |
"step": 335
|
| 573 |
},
|
| 574 |
{
|
| 575 |
"epoch": 1.547320410490308,
|
| 576 |
-
"grad_norm":
|
| 577 |
-
"learning_rate": 0.
|
| 578 |
-
"loss":
|
| 579 |
"num_input_tokens_seen": 4165904,
|
| 580 |
"step": 340
|
| 581 |
},
|
| 582 |
{
|
| 583 |
"epoch": 1.5701254275940708,
|
| 584 |
-
"grad_norm":
|
| 585 |
-
"learning_rate": 0.
|
| 586 |
-
"loss":
|
| 587 |
"num_input_tokens_seen": 4226704,
|
| 588 |
"step": 345
|
| 589 |
},
|
| 590 |
{
|
| 591 |
"epoch": 1.5929304446978336,
|
| 592 |
-
"grad_norm":
|
| 593 |
-
"learning_rate": 0.
|
| 594 |
-
"loss":
|
| 595 |
"num_input_tokens_seen": 4288400,
|
| 596 |
"step": 350
|
| 597 |
},
|
| 598 |
{
|
| 599 |
"epoch": 1.6157354618015964,
|
| 600 |
-
"grad_norm":
|
| 601 |
-
"learning_rate": 0.
|
| 602 |
-
"loss":
|
| 603 |
"num_input_tokens_seen": 4349712,
|
| 604 |
"step": 355
|
| 605 |
},
|
| 606 |
{
|
| 607 |
"epoch": 1.6385404789053593,
|
| 608 |
-
"grad_norm":
|
| 609 |
-
"learning_rate": 0.
|
| 610 |
-
"loss":
|
| 611 |
"num_input_tokens_seen": 4410256,
|
| 612 |
"step": 360
|
| 613 |
},
|
| 614 |
{
|
| 615 |
"epoch": 1.661345496009122,
|
| 616 |
-
"grad_norm":
|
| 617 |
-
"learning_rate": 0.
|
| 618 |
-
"loss":
|
| 619 |
"num_input_tokens_seen": 4471440,
|
| 620 |
"step": 365
|
| 621 |
},
|
| 622 |
{
|
| 623 |
"epoch": 1.6841505131128849,
|
| 624 |
-
"grad_norm":
|
| 625 |
-
"learning_rate": 0.
|
| 626 |
-
"loss": 0.
|
| 627 |
"num_input_tokens_seen": 4533008,
|
| 628 |
"step": 370
|
| 629 |
},
|
| 630 |
{
|
| 631 |
"epoch": 1.7069555302166477,
|
| 632 |
-
"grad_norm":
|
| 633 |
-
"learning_rate": 0.
|
| 634 |
-
"loss":
|
| 635 |
"num_input_tokens_seen": 4594320,
|
| 636 |
"step": 375
|
| 637 |
},
|
| 638 |
{
|
| 639 |
"epoch": 1.7297605473204105,
|
| 640 |
-
"grad_norm":
|
| 641 |
-
"learning_rate": 0.
|
| 642 |
-
"loss":
|
| 643 |
"num_input_tokens_seen": 4655760,
|
| 644 |
"step": 380
|
| 645 |
},
|
| 646 |
{
|
| 647 |
"epoch": 1.7525655644241733,
|
| 648 |
-
"grad_norm":
|
| 649 |
-
"learning_rate": 0.
|
| 650 |
-
"loss":
|
| 651 |
"num_input_tokens_seen": 4717328,
|
| 652 |
"step": 385
|
| 653 |
},
|
| 654 |
{
|
| 655 |
"epoch": 1.7753705815279361,
|
| 656 |
-
"grad_norm":
|
| 657 |
-
"learning_rate": 0.
|
| 658 |
-
"loss":
|
| 659 |
"num_input_tokens_seen": 4779152,
|
| 660 |
"step": 390
|
| 661 |
},
|
| 662 |
{
|
| 663 |
"epoch": 1.798175598631699,
|
| 664 |
-
"grad_norm":
|
| 665 |
-
"learning_rate": 0.
|
| 666 |
-
"loss":
|
| 667 |
"num_input_tokens_seen": 4840336,
|
| 668 |
"step": 395
|
| 669 |
},
|
| 670 |
{
|
| 671 |
"epoch": 1.8209806157354618,
|
| 672 |
-
"grad_norm":
|
| 673 |
-
"learning_rate": 0.
|
| 674 |
-
"loss":
|
| 675 |
"num_input_tokens_seen": 4901648,
|
| 676 |
"step": 400
|
| 677 |
},
|
| 678 |
{
|
| 679 |
"epoch": 1.8209806157354618,
|
| 680 |
-
"eval_loss":
|
| 681 |
-
"eval_runtime": 33.
|
| 682 |
-
"eval_samples_per_second":
|
| 683 |
-
"eval_steps_per_second": 5.
|
| 684 |
"num_input_tokens_seen": 4901648,
|
| 685 |
"step": 400
|
| 686 |
},
|
| 687 |
{
|
| 688 |
"epoch": 1.8437856328392246,
|
| 689 |
-
"grad_norm":
|
| 690 |
-
"learning_rate": 0.
|
| 691 |
-
"loss":
|
| 692 |
"num_input_tokens_seen": 4963216,
|
| 693 |
"step": 405
|
| 694 |
},
|
| 695 |
{
|
| 696 |
"epoch": 1.8665906499429874,
|
| 697 |
-
"grad_norm":
|
| 698 |
-
"learning_rate": 0.
|
| 699 |
-
"loss":
|
| 700 |
"num_input_tokens_seen": 5024912,
|
| 701 |
"step": 410
|
| 702 |
},
|
| 703 |
{
|
| 704 |
"epoch": 1.8893956670467502,
|
| 705 |
-
"grad_norm":
|
| 706 |
-
"learning_rate": 0.
|
| 707 |
-
"loss": 0.
|
| 708 |
"num_input_tokens_seen": 5086224,
|
| 709 |
"step": 415
|
| 710 |
},
|
| 711 |
{
|
| 712 |
"epoch": 1.912200684150513,
|
| 713 |
-
"grad_norm":
|
| 714 |
-
"learning_rate": 0.
|
| 715 |
-
"loss": 0.
|
| 716 |
"num_input_tokens_seen": 5148048,
|
| 717 |
"step": 420
|
| 718 |
},
|
| 719 |
{
|
| 720 |
"epoch": 1.9350057012542758,
|
| 721 |
-
"grad_norm":
|
| 722 |
-
"learning_rate": 0.
|
| 723 |
-
"loss": 0.
|
| 724 |
"num_input_tokens_seen": 5209104,
|
| 725 |
"step": 425
|
| 726 |
},
|
| 727 |
{
|
| 728 |
"epoch": 1.9578107183580387,
|
| 729 |
-
"grad_norm":
|
| 730 |
-
"learning_rate": 0.
|
| 731 |
-
"loss": 0.
|
| 732 |
"num_input_tokens_seen": 5270544,
|
| 733 |
"step": 430
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"epoch": 1.9806157354618015,
|
| 737 |
-
"grad_norm":
|
| 738 |
-
"learning_rate": 0.
|
| 739 |
-
"loss": 0.
|
| 740 |
"num_input_tokens_seen": 5331472,
|
| 741 |
"step": 435
|
| 742 |
},
|
| 743 |
{
|
| 744 |
"epoch": 2.0,
|
| 745 |
-
"grad_norm": 0.
|
| 746 |
-
"learning_rate": 0.
|
| 747 |
-
"loss": 0.
|
| 748 |
"num_input_tokens_seen": 5382864,
|
| 749 |
"step": 440
|
| 750 |
},
|
| 751 |
{
|
| 752 |
"epoch": 2.022805017103763,
|
| 753 |
-
"grad_norm":
|
| 754 |
-
"learning_rate": 0.
|
| 755 |
-
"loss": 0.
|
| 756 |
"num_input_tokens_seen": 5444176,
|
| 757 |
"step": 445
|
| 758 |
},
|
| 759 |
{
|
| 760 |
"epoch": 2.0456100342075256,
|
| 761 |
-
"grad_norm":
|
| 762 |
-
"learning_rate": 0.
|
| 763 |
-
"loss": 0.
|
| 764 |
"num_input_tokens_seen": 5505872,
|
| 765 |
"step": 450
|
| 766 |
},
|
| 767 |
{
|
| 768 |
"epoch": 2.0684150513112884,
|
| 769 |
-
"grad_norm": 0.
|
| 770 |
-
"learning_rate": 0.
|
| 771 |
-
"loss": 0.
|
| 772 |
"num_input_tokens_seen": 5568208,
|
| 773 |
"step": 455
|
| 774 |
},
|
| 775 |
{
|
| 776 |
"epoch": 2.0912200684150513,
|
| 777 |
-
"grad_norm": 0.
|
| 778 |
-
"learning_rate": 0.
|
| 779 |
-
"loss": 0.
|
| 780 |
"num_input_tokens_seen": 5628880,
|
| 781 |
"step": 460
|
| 782 |
},
|
| 783 |
{
|
| 784 |
"epoch": 2.114025085518814,
|
| 785 |
-
"grad_norm": 0.
|
| 786 |
-
"learning_rate": 0.
|
| 787 |
-
"loss": 0.
|
| 788 |
"num_input_tokens_seen": 5690320,
|
| 789 |
"step": 465
|
| 790 |
},
|
| 791 |
{
|
| 792 |
"epoch": 2.136830102622577,
|
| 793 |
-
"grad_norm": 0.
|
| 794 |
-
"learning_rate": 0.
|
| 795 |
-
"loss": 0.
|
| 796 |
"num_input_tokens_seen": 5752912,
|
| 797 |
"step": 470
|
| 798 |
},
|
| 799 |
{
|
| 800 |
"epoch": 2.1596351197263397,
|
| 801 |
-
"grad_norm": 0.
|
| 802 |
-
"learning_rate": 0.
|
| 803 |
-
"loss": 0.
|
| 804 |
"num_input_tokens_seen": 5813968,
|
| 805 |
"step": 475
|
| 806 |
},
|
| 807 |
{
|
| 808 |
"epoch": 2.1824401368301025,
|
| 809 |
-
"grad_norm": 0.
|
| 810 |
-
"learning_rate": 0.
|
| 811 |
-
"loss": 0.
|
| 812 |
"num_input_tokens_seen": 5874896,
|
| 813 |
"step": 480
|
| 814 |
},
|
| 815 |
{
|
| 816 |
"epoch": 2.2052451539338653,
|
| 817 |
-
"grad_norm": 0.
|
| 818 |
-
"learning_rate": 0.
|
| 819 |
-
"loss": 0.
|
| 820 |
"num_input_tokens_seen": 5935952,
|
| 821 |
"step": 485
|
| 822 |
},
|
| 823 |
{
|
| 824 |
"epoch": 2.228050171037628,
|
| 825 |
-
"grad_norm": 0.
|
| 826 |
-
"learning_rate": 0.
|
| 827 |
-
"loss": 0.
|
| 828 |
"num_input_tokens_seen": 5997008,
|
| 829 |
"step": 490
|
| 830 |
},
|
| 831 |
{
|
| 832 |
"epoch": 2.250855188141391,
|
| 833 |
-
"grad_norm":
|
| 834 |
-
"learning_rate": 0.
|
| 835 |
-
"loss": 0.
|
| 836 |
"num_input_tokens_seen": 6058704,
|
| 837 |
"step": 495
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"epoch": 2.2736602052451538,
|
| 841 |
-
"grad_norm": 0.
|
| 842 |
-
"learning_rate": 0.
|
| 843 |
-
"loss": 0.
|
| 844 |
"num_input_tokens_seen": 6120272,
|
| 845 |
"step": 500
|
| 846 |
},
|
| 847 |
{
|
| 848 |
"epoch": 2.2736602052451538,
|
| 849 |
-
"eval_loss": 0.
|
| 850 |
-
"eval_runtime": 33.
|
| 851 |
-
"eval_samples_per_second":
|
| 852 |
-
"eval_steps_per_second": 5.
|
| 853 |
"num_input_tokens_seen": 6120272,
|
| 854 |
"step": 500
|
| 855 |
},
|
| 856 |
{
|
| 857 |
"epoch": 2.2964652223489166,
|
| 858 |
-
"grad_norm": 0.
|
| 859 |
-
"learning_rate": 0.
|
| 860 |
-
"loss": 0.
|
| 861 |
"num_input_tokens_seen": 6180816,
|
| 862 |
"step": 505
|
| 863 |
},
|
| 864 |
{
|
| 865 |
"epoch": 2.3192702394526794,
|
| 866 |
-
"grad_norm": 0.
|
| 867 |
-
"learning_rate": 0.
|
| 868 |
-
"loss": 0.
|
| 869 |
"num_input_tokens_seen": 6242128,
|
| 870 |
"step": 510
|
| 871 |
},
|
| 872 |
{
|
| 873 |
"epoch": 2.342075256556442,
|
| 874 |
-
"grad_norm": 0.
|
| 875 |
-
"learning_rate": 0.
|
| 876 |
-
"loss": 0.
|
| 877 |
"num_input_tokens_seen": 6303312,
|
| 878 |
"step": 515
|
| 879 |
},
|
| 880 |
{
|
| 881 |
"epoch": 2.364880273660205,
|
| 882 |
-
"grad_norm": 0.
|
| 883 |
-
"learning_rate": 0.
|
| 884 |
-
"loss": 0.
|
| 885 |
"num_input_tokens_seen": 6364624,
|
| 886 |
"step": 520
|
| 887 |
},
|
| 888 |
{
|
| 889 |
"epoch": 2.387685290763968,
|
| 890 |
-
"grad_norm": 0.
|
| 891 |
-
"learning_rate": 0.
|
| 892 |
-
"loss": 0.
|
| 893 |
"num_input_tokens_seen": 6425040,
|
| 894 |
"step": 525
|
| 895 |
},
|
| 896 |
{
|
| 897 |
"epoch": 2.4104903078677307,
|
| 898 |
-
"grad_norm": 0.
|
| 899 |
-
"learning_rate": 0.
|
| 900 |
-
"loss": 0.
|
| 901 |
"num_input_tokens_seen": 6486736,
|
| 902 |
"step": 530
|
| 903 |
},
|
| 904 |
{
|
| 905 |
"epoch": 2.433295324971494,
|
| 906 |
-
"grad_norm": 0.
|
| 907 |
-
"learning_rate": 0.
|
| 908 |
-
"loss": 0.
|
| 909 |
"num_input_tokens_seen": 6548304,
|
| 910 |
"step": 535
|
| 911 |
},
|
| 912 |
{
|
| 913 |
"epoch": 2.4561003420752567,
|
| 914 |
-
"grad_norm": 0.
|
| 915 |
-
"learning_rate": 0.
|
| 916 |
-
"loss": 0.
|
| 917 |
"num_input_tokens_seen": 6610000,
|
| 918 |
"step": 540
|
| 919 |
},
|
| 920 |
{
|
| 921 |
"epoch": 2.4789053591790196,
|
| 922 |
-
"grad_norm": 0.
|
| 923 |
-
"learning_rate": 0.
|
| 924 |
-
"loss": 0.
|
| 925 |
"num_input_tokens_seen": 6670672,
|
| 926 |
"step": 545
|
| 927 |
},
|
| 928 |
{
|
| 929 |
"epoch": 2.5017103762827824,
|
| 930 |
-
"grad_norm": 0.
|
| 931 |
-
"learning_rate":
|
| 932 |
-
"loss": 0.
|
| 933 |
"num_input_tokens_seen": 6732112,
|
| 934 |
"step": 550
|
| 935 |
},
|
| 936 |
{
|
| 937 |
"epoch": 2.524515393386545,
|
| 938 |
-
"grad_norm": 0.
|
| 939 |
-
"learning_rate":
|
| 940 |
-
"loss": 0.
|
| 941 |
"num_input_tokens_seen": 6793424,
|
| 942 |
"step": 555
|
| 943 |
},
|
| 944 |
{
|
| 945 |
"epoch": 2.547320410490308,
|
| 946 |
-
"grad_norm": 0.
|
| 947 |
-
"learning_rate":
|
| 948 |
-
"loss": 0.
|
| 949 |
"num_input_tokens_seen": 6855760,
|
| 950 |
"step": 560
|
| 951 |
},
|
| 952 |
{
|
| 953 |
"epoch": 2.570125427594071,
|
| 954 |
-
"grad_norm": 0.
|
| 955 |
-
"learning_rate":
|
| 956 |
-
"loss": 0.
|
| 957 |
"num_input_tokens_seen": 6916688,
|
| 958 |
"step": 565
|
| 959 |
},
|
| 960 |
{
|
| 961 |
"epoch": 2.5929304446978336,
|
| 962 |
-
"grad_norm": 0.
|
| 963 |
-
"learning_rate":
|
| 964 |
-
"loss": 0.
|
| 965 |
"num_input_tokens_seen": 6978512,
|
| 966 |
"step": 570
|
| 967 |
},
|
| 968 |
{
|
| 969 |
"epoch": 2.6157354618015964,
|
| 970 |
-
"grad_norm": 0.
|
| 971 |
-
"learning_rate":
|
| 972 |
-
"loss": 0.
|
| 973 |
"num_input_tokens_seen": 7040208,
|
| 974 |
"step": 575
|
| 975 |
},
|
| 976 |
{
|
| 977 |
"epoch": 2.6385404789053593,
|
| 978 |
-
"grad_norm": 0.
|
| 979 |
-
"learning_rate":
|
| 980 |
-
"loss": 0.
|
| 981 |
"num_input_tokens_seen": 7101264,
|
| 982 |
"step": 580
|
| 983 |
},
|
| 984 |
{
|
| 985 |
"epoch": 2.661345496009122,
|
| 986 |
-
"grad_norm": 0.
|
| 987 |
-
"learning_rate":
|
| 988 |
-
"loss": 0.
|
| 989 |
"num_input_tokens_seen": 7163600,
|
| 990 |
"step": 585
|
| 991 |
},
|
| 992 |
{
|
| 993 |
"epoch": 2.684150513112885,
|
| 994 |
-
"grad_norm": 0.
|
| 995 |
-
"learning_rate":
|
| 996 |
-
"loss": 0.
|
| 997 |
"num_input_tokens_seen": 7225936,
|
| 998 |
"step": 590
|
| 999 |
},
|
| 1000 |
{
|
| 1001 |
"epoch": 2.7069555302166477,
|
| 1002 |
-
"grad_norm": 0.
|
| 1003 |
-
"learning_rate":
|
| 1004 |
-
"loss": 0.
|
| 1005 |
"num_input_tokens_seen": 7287760,
|
| 1006 |
"step": 595
|
| 1007 |
},
|
| 1008 |
{
|
| 1009 |
"epoch": 2.7297605473204105,
|
| 1010 |
-
"grad_norm": 0.
|
| 1011 |
-
"learning_rate":
|
| 1012 |
-
"loss": 0.
|
| 1013 |
"num_input_tokens_seen": 7348944,
|
| 1014 |
"step": 600
|
| 1015 |
},
|
| 1016 |
{
|
| 1017 |
"epoch": 2.7297605473204105,
|
| 1018 |
-
"eval_loss": 0.
|
| 1019 |
-
"eval_runtime": 33.
|
| 1020 |
-
"eval_samples_per_second":
|
| 1021 |
-
"eval_steps_per_second": 5.
|
| 1022 |
"num_input_tokens_seen": 7348944,
|
| 1023 |
"step": 600
|
| 1024 |
},
|
| 1025 |
{
|
| 1026 |
"epoch": 2.7525655644241733,
|
| 1027 |
-
"grad_norm": 0.
|
| 1028 |
-
"learning_rate":
|
| 1029 |
-
"loss": 0.
|
| 1030 |
"num_input_tokens_seen": 7410640,
|
| 1031 |
"step": 605
|
| 1032 |
},
|
| 1033 |
{
|
| 1034 |
"epoch": 2.775370581527936,
|
| 1035 |
-
"grad_norm": 0.
|
| 1036 |
-
"learning_rate":
|
| 1037 |
-
"loss": 0.
|
| 1038 |
"num_input_tokens_seen": 7471184,
|
| 1039 |
"step": 610
|
| 1040 |
},
|
| 1041 |
{
|
| 1042 |
"epoch": 2.798175598631699,
|
| 1043 |
-
"grad_norm": 0.
|
| 1044 |
-
"learning_rate":
|
| 1045 |
-
"loss": 0.
|
| 1046 |
"num_input_tokens_seen": 7533392,
|
| 1047 |
"step": 615
|
| 1048 |
},
|
| 1049 |
{
|
| 1050 |
"epoch": 2.8209806157354618,
|
| 1051 |
-
"grad_norm": 0.
|
| 1052 |
-
"learning_rate":
|
| 1053 |
-
"loss": 0.
|
| 1054 |
"num_input_tokens_seen": 7594832,
|
| 1055 |
"step": 620
|
| 1056 |
},
|
| 1057 |
{
|
| 1058 |
"epoch": 2.8437856328392246,
|
| 1059 |
-
"grad_norm": 0.
|
| 1060 |
-
"learning_rate":
|
| 1061 |
-
"loss": 0.
|
| 1062 |
"num_input_tokens_seen": 7656656,
|
| 1063 |
"step": 625
|
| 1064 |
},
|
| 1065 |
{
|
| 1066 |
"epoch": 2.8665906499429874,
|
| 1067 |
-
"grad_norm": 0.
|
| 1068 |
-
"learning_rate":
|
| 1069 |
-
"loss": 0.
|
| 1070 |
"num_input_tokens_seen": 7717712,
|
| 1071 |
"step": 630
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
"epoch": 2.88939566704675,
|
| 1075 |
-
"grad_norm": 0.
|
| 1076 |
-
"learning_rate":
|
| 1077 |
-
"loss": 0.
|
| 1078 |
"num_input_tokens_seen": 7779920,
|
| 1079 |
"step": 635
|
| 1080 |
},
|
| 1081 |
{
|
| 1082 |
"epoch": 2.912200684150513,
|
| 1083 |
-
"grad_norm": 0.
|
| 1084 |
-
"learning_rate":
|
| 1085 |
-
"loss": 0.
|
| 1086 |
"num_input_tokens_seen": 7840976,
|
| 1087 |
"step": 640
|
| 1088 |
},
|
| 1089 |
{
|
| 1090 |
"epoch": 2.935005701254276,
|
| 1091 |
-
"grad_norm": 0.
|
| 1092 |
-
"learning_rate":
|
| 1093 |
-
"loss": 0.
|
| 1094 |
"num_input_tokens_seen": 7902160,
|
| 1095 |
"step": 645
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
"epoch": 2.9578107183580387,
|
| 1099 |
-
"grad_norm": 0.
|
| 1100 |
-
"learning_rate":
|
| 1101 |
-
"loss": 0.
|
| 1102 |
"num_input_tokens_seen": 7963856,
|
| 1103 |
"step": 650
|
| 1104 |
},
|
| 1105 |
{
|
| 1106 |
"epoch": 2.9806157354618015,
|
| 1107 |
-
"grad_norm": 0.
|
| 1108 |
-
"learning_rate":
|
| 1109 |
-
"loss": 0.
|
| 1110 |
"num_input_tokens_seen": 8026448,
|
| 1111 |
"step": 655
|
| 1112 |
},
|
| 1113 |
{
|
| 1114 |
"epoch": 3.0,
|
| 1115 |
-
"grad_norm": 0.
|
| 1116 |
-
"learning_rate":
|
| 1117 |
-
"loss": 0.
|
| 1118 |
"num_input_tokens_seen": 8078224,
|
| 1119 |
"step": 660
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"epoch": 3.022805017103763,
|
| 1123 |
-
"grad_norm": 0.
|
| 1124 |
-
"learning_rate":
|
| 1125 |
-
"loss": 0.
|
| 1126 |
"num_input_tokens_seen": 8140176,
|
| 1127 |
"step": 665
|
| 1128 |
},
|
| 1129 |
{
|
| 1130 |
"epoch": 3.0456100342075256,
|
| 1131 |
-
"grad_norm": 0.
|
| 1132 |
-
"learning_rate":
|
| 1133 |
-
"loss": 0.
|
| 1134 |
"num_input_tokens_seen": 8201616,
|
| 1135 |
"step": 670
|
| 1136 |
},
|
| 1137 |
{
|
| 1138 |
"epoch": 3.0684150513112884,
|
| 1139 |
-
"grad_norm": 0.
|
| 1140 |
-
"learning_rate":
|
| 1141 |
-
"loss": 0.
|
| 1142 |
"num_input_tokens_seen": 8262928,
|
| 1143 |
"step": 675
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
"epoch": 3.0912200684150513,
|
| 1147 |
-
"grad_norm": 0.
|
| 1148 |
-
"learning_rate":
|
| 1149 |
-
"loss": 0.
|
| 1150 |
"num_input_tokens_seen": 8324496,
|
| 1151 |
"step": 680
|
| 1152 |
},
|
| 1153 |
{
|
| 1154 |
"epoch": 3.114025085518814,
|
| 1155 |
-
"grad_norm": 0.
|
| 1156 |
-
"learning_rate":
|
| 1157 |
-
"loss": 0.
|
| 1158 |
"num_input_tokens_seen": 8385680,
|
| 1159 |
"step": 685
|
| 1160 |
},
|
| 1161 |
{
|
| 1162 |
"epoch": 3.136830102622577,
|
| 1163 |
-
"grad_norm": 0.
|
| 1164 |
-
"learning_rate":
|
| 1165 |
-
"loss": 0.
|
| 1166 |
"num_input_tokens_seen": 8447632,
|
| 1167 |
"step": 690
|
| 1168 |
},
|
| 1169 |
{
|
| 1170 |
"epoch": 3.1596351197263397,
|
| 1171 |
-
"grad_norm": 0.
|
| 1172 |
-
"learning_rate":
|
| 1173 |
-
"loss": 0.
|
| 1174 |
"num_input_tokens_seen": 8508432,
|
| 1175 |
"step": 695
|
| 1176 |
},
|
| 1177 |
{
|
| 1178 |
"epoch": 3.1824401368301025,
|
| 1179 |
-
"grad_norm": 0.
|
| 1180 |
-
"learning_rate":
|
| 1181 |
-
"loss": 0.
|
| 1182 |
"num_input_tokens_seen": 8570128,
|
| 1183 |
"step": 700
|
| 1184 |
},
|
| 1185 |
{
|
| 1186 |
"epoch": 3.1824401368301025,
|
| 1187 |
-
"eval_loss": 0.
|
| 1188 |
-
"eval_runtime": 33.
|
| 1189 |
-
"eval_samples_per_second":
|
| 1190 |
-
"eval_steps_per_second": 5.
|
| 1191 |
"num_input_tokens_seen": 8570128,
|
| 1192 |
"step": 700
|
| 1193 |
},
|
| 1194 |
{
|
| 1195 |
"epoch": 3.2052451539338653,
|
| 1196 |
-
"grad_norm": 0.
|
| 1197 |
-
"learning_rate":
|
| 1198 |
-
"loss": 0.
|
| 1199 |
"num_input_tokens_seen": 8631952,
|
| 1200 |
"step": 705
|
| 1201 |
},
|
| 1202 |
{
|
| 1203 |
"epoch": 3.228050171037628,
|
| 1204 |
-
"grad_norm": 0.
|
| 1205 |
-
"learning_rate":
|
| 1206 |
-
"loss": 0.
|
| 1207 |
"num_input_tokens_seen": 8694032,
|
| 1208 |
"step": 710
|
| 1209 |
},
|
| 1210 |
{
|
| 1211 |
"epoch": 3.250855188141391,
|
| 1212 |
-
"grad_norm": 0.
|
| 1213 |
-
"learning_rate":
|
| 1214 |
-
"loss": 0.
|
| 1215 |
"num_input_tokens_seen": 8754576,
|
| 1216 |
"step": 715
|
| 1217 |
},
|
| 1218 |
{
|
| 1219 |
"epoch": 3.2736602052451538,
|
| 1220 |
-
"grad_norm": 0.
|
| 1221 |
-
"learning_rate":
|
| 1222 |
-
"loss": 0.
|
| 1223 |
"num_input_tokens_seen": 8816528,
|
| 1224 |
"step": 720
|
| 1225 |
},
|
| 1226 |
{
|
| 1227 |
"epoch": 3.2964652223489166,
|
| 1228 |
-
"grad_norm": 0.
|
| 1229 |
-
"learning_rate":
|
| 1230 |
-
"loss": 0.
|
| 1231 |
"num_input_tokens_seen": 8877200,
|
| 1232 |
"step": 725
|
| 1233 |
},
|
| 1234 |
{
|
| 1235 |
"epoch": 3.3192702394526794,
|
| 1236 |
-
"grad_norm": 0.
|
| 1237 |
-
"learning_rate":
|
| 1238 |
-
"loss": 0.
|
| 1239 |
"num_input_tokens_seen": 8938512,
|
| 1240 |
"step": 730
|
| 1241 |
},
|
| 1242 |
{
|
| 1243 |
"epoch": 3.342075256556442,
|
| 1244 |
-
"grad_norm": 0.
|
| 1245 |
-
"learning_rate":
|
| 1246 |
-
"loss": 0.
|
| 1247 |
"num_input_tokens_seen": 9000464,
|
| 1248 |
"step": 735
|
| 1249 |
},
|
| 1250 |
{
|
| 1251 |
"epoch": 3.364880273660205,
|
| 1252 |
-
"grad_norm": 0.
|
| 1253 |
-
"learning_rate":
|
| 1254 |
-
"loss": 0.
|
| 1255 |
"num_input_tokens_seen": 9061648,
|
| 1256 |
"step": 740
|
| 1257 |
},
|
| 1258 |
{
|
| 1259 |
"epoch": 3.387685290763968,
|
| 1260 |
-
"grad_norm": 0.
|
| 1261 |
-
"learning_rate":
|
| 1262 |
-
"loss": 0.
|
| 1263 |
"num_input_tokens_seen": 9122704,
|
| 1264 |
"step": 745
|
| 1265 |
},
|
| 1266 |
{
|
| 1267 |
"epoch": 3.4104903078677307,
|
| 1268 |
-
"grad_norm": 0.
|
| 1269 |
-
"learning_rate":
|
| 1270 |
-
"loss": 0.
|
| 1271 |
"num_input_tokens_seen": 9183504,
|
| 1272 |
"step": 750
|
| 1273 |
},
|
| 1274 |
{
|
| 1275 |
"epoch": 3.433295324971494,
|
| 1276 |
-
"grad_norm": 0.
|
| 1277 |
-
"learning_rate":
|
| 1278 |
-
"loss": 0.
|
| 1279 |
"num_input_tokens_seen": 9245072,
|
| 1280 |
"step": 755
|
| 1281 |
},
|
| 1282 |
{
|
| 1283 |
"epoch": 3.4561003420752567,
|
| 1284 |
-
"grad_norm": 0.
|
| 1285 |
-
"learning_rate":
|
| 1286 |
-
"loss": 0.
|
| 1287 |
"num_input_tokens_seen": 9307152,
|
| 1288 |
"step": 760
|
| 1289 |
},
|
| 1290 |
{
|
| 1291 |
"epoch": 3.4789053591790196,
|
| 1292 |
-
"grad_norm": 0.
|
| 1293 |
-
"learning_rate":
|
| 1294 |
-
"loss": 0.
|
| 1295 |
"num_input_tokens_seen": 9369616,
|
| 1296 |
"step": 765
|
| 1297 |
},
|
| 1298 |
{
|
| 1299 |
"epoch": 3.5017103762827824,
|
| 1300 |
-
"grad_norm": 0.
|
| 1301 |
-
"learning_rate":
|
| 1302 |
-
"loss": 0.
|
| 1303 |
"num_input_tokens_seen": 9431568,
|
| 1304 |
"step": 770
|
| 1305 |
},
|
| 1306 |
{
|
| 1307 |
"epoch": 3.524515393386545,
|
| 1308 |
-
"grad_norm": 0.
|
| 1309 |
-
"learning_rate":
|
| 1310 |
-
"loss": 0.
|
| 1311 |
"num_input_tokens_seen": 9493264,
|
| 1312 |
"step": 775
|
| 1313 |
},
|
| 1314 |
{
|
| 1315 |
"epoch": 3.547320410490308,
|
| 1316 |
-
"grad_norm": 0.
|
| 1317 |
-
"learning_rate":
|
| 1318 |
-
"loss": 0.
|
| 1319 |
"num_input_tokens_seen": 9554448,
|
| 1320 |
"step": 780
|
| 1321 |
},
|
| 1322 |
{
|
| 1323 |
"epoch": 3.570125427594071,
|
| 1324 |
-
"grad_norm": 0.
|
| 1325 |
-
"learning_rate":
|
| 1326 |
-
"loss": 0.
|
| 1327 |
"num_input_tokens_seen": 9615760,
|
| 1328 |
"step": 785
|
| 1329 |
},
|
| 1330 |
{
|
| 1331 |
"epoch": 3.5929304446978336,
|
| 1332 |
-
"grad_norm": 0.
|
| 1333 |
-
"learning_rate":
|
| 1334 |
-
"loss": 0.
|
| 1335 |
"num_input_tokens_seen": 9678608,
|
| 1336 |
"step": 790
|
| 1337 |
},
|
| 1338 |
{
|
| 1339 |
"epoch": 3.6157354618015964,
|
| 1340 |
-
"grad_norm": 0.
|
| 1341 |
-
"learning_rate":
|
| 1342 |
-
"loss": 0.
|
| 1343 |
"num_input_tokens_seen": 9740304,
|
| 1344 |
"step": 795
|
| 1345 |
},
|
| 1346 |
{
|
| 1347 |
"epoch": 3.6385404789053593,
|
| 1348 |
-
"grad_norm": 0.
|
| 1349 |
-
"learning_rate":
|
| 1350 |
-
"loss": 0.
|
| 1351 |
"num_input_tokens_seen": 9801744,
|
| 1352 |
"step": 800
|
| 1353 |
},
|
| 1354 |
{
|
| 1355 |
"epoch": 3.6385404789053593,
|
| 1356 |
-
"eval_loss": 0.
|
| 1357 |
-
"eval_runtime": 33.
|
| 1358 |
-
"eval_samples_per_second":
|
| 1359 |
-
"eval_steps_per_second": 5.
|
| 1360 |
"num_input_tokens_seen": 9801744,
|
| 1361 |
"step": 800
|
| 1362 |
},
|
| 1363 |
{
|
| 1364 |
"epoch": 3.661345496009122,
|
| 1365 |
-
"grad_norm": 0.
|
| 1366 |
-
"learning_rate":
|
| 1367 |
-
"loss": 0.
|
| 1368 |
"num_input_tokens_seen": 9862928,
|
| 1369 |
"step": 805
|
| 1370 |
},
|
| 1371 |
{
|
| 1372 |
"epoch": 3.684150513112885,
|
| 1373 |
-
"grad_norm": 0.
|
| 1374 |
-
"learning_rate":
|
| 1375 |
-
"loss": 0.
|
| 1376 |
"num_input_tokens_seen": 9924112,
|
| 1377 |
"step": 810
|
| 1378 |
},
|
| 1379 |
{
|
| 1380 |
"epoch": 3.7069555302166477,
|
| 1381 |
-
"grad_norm": 0.
|
| 1382 |
-
"learning_rate":
|
| 1383 |
-
"loss": 0.
|
| 1384 |
"num_input_tokens_seen": 9984784,
|
| 1385 |
"step": 815
|
| 1386 |
},
|
| 1387 |
{
|
| 1388 |
"epoch": 3.7297605473204105,
|
| 1389 |
-
"grad_norm": 0.
|
| 1390 |
-
"learning_rate":
|
| 1391 |
-
"loss": 0.
|
| 1392 |
"num_input_tokens_seen": 10046736,
|
| 1393 |
"step": 820
|
| 1394 |
},
|
| 1395 |
{
|
| 1396 |
"epoch": 3.7525655644241733,
|
| 1397 |
-
"grad_norm": 0.
|
| 1398 |
-
"learning_rate":
|
| 1399 |
-
"loss": 0.
|
| 1400 |
"num_input_tokens_seen": 10108176,
|
| 1401 |
"step": 825
|
| 1402 |
},
|
| 1403 |
{
|
| 1404 |
"epoch": 3.775370581527936,
|
| 1405 |
-
"grad_norm": 0.
|
| 1406 |
-
"learning_rate":
|
| 1407 |
-
"loss": 0.
|
| 1408 |
"num_input_tokens_seen": 10169744,
|
| 1409 |
"step": 830
|
| 1410 |
},
|
| 1411 |
{
|
| 1412 |
"epoch": 3.798175598631699,
|
| 1413 |
-
"grad_norm": 0.
|
| 1414 |
-
"learning_rate":
|
| 1415 |
-
"loss": 0.
|
| 1416 |
"num_input_tokens_seen": 10231696,
|
| 1417 |
"step": 835
|
| 1418 |
},
|
| 1419 |
{
|
| 1420 |
"epoch": 3.8209806157354618,
|
| 1421 |
-
"grad_norm": 0.
|
| 1422 |
-
"learning_rate":
|
| 1423 |
-
"loss": 0.
|
| 1424 |
"num_input_tokens_seen": 10292624,
|
| 1425 |
"step": 840
|
| 1426 |
},
|
| 1427 |
{
|
| 1428 |
"epoch": 3.8437856328392246,
|
| 1429 |
-
"grad_norm": 0.
|
| 1430 |
-
"learning_rate":
|
| 1431 |
-
"loss": 0.
|
| 1432 |
"num_input_tokens_seen": 10353040,
|
| 1433 |
"step": 845
|
| 1434 |
},
|
| 1435 |
{
|
| 1436 |
"epoch": 3.8665906499429874,
|
| 1437 |
-
"grad_norm": 0.
|
| 1438 |
-
"learning_rate":
|
| 1439 |
-
"loss": 0.
|
| 1440 |
"num_input_tokens_seen": 10414480,
|
| 1441 |
"step": 850
|
| 1442 |
},
|
| 1443 |
{
|
| 1444 |
"epoch": 3.88939566704675,
|
| 1445 |
-
"grad_norm": 0.
|
| 1446 |
-
"learning_rate":
|
| 1447 |
-
"loss": 0.
|
| 1448 |
"num_input_tokens_seen": 10476432,
|
| 1449 |
"step": 855
|
| 1450 |
},
|
| 1451 |
{
|
| 1452 |
"epoch": 3.912200684150513,
|
| 1453 |
-
"grad_norm": 0.
|
| 1454 |
-
"learning_rate":
|
| 1455 |
-
"loss": 0.
|
| 1456 |
"num_input_tokens_seen": 10538128,
|
| 1457 |
"step": 860
|
| 1458 |
},
|
| 1459 |
{
|
| 1460 |
"epoch": 3.935005701254276,
|
| 1461 |
-
"grad_norm": 0.
|
| 1462 |
-
"learning_rate":
|
| 1463 |
-
"loss": 0.
|
| 1464 |
"num_input_tokens_seen": 10600080,
|
| 1465 |
"step": 865
|
| 1466 |
},
|
| 1467 |
{
|
| 1468 |
"epoch": 3.9578107183580387,
|
| 1469 |
-
"grad_norm": 0.
|
| 1470 |
-
"learning_rate": 5.
|
| 1471 |
-
"loss": 0.
|
| 1472 |
"num_input_tokens_seen": 10660752,
|
| 1473 |
"step": 870
|
| 1474 |
},
|
| 1475 |
{
|
| 1476 |
"epoch": 3.9806157354618015,
|
| 1477 |
-
"grad_norm": 0.
|
| 1478 |
-
"learning_rate":
|
| 1479 |
-
"loss": 0.
|
| 1480 |
"num_input_tokens_seen": 10721680,
|
| 1481 |
"step": 875
|
| 1482 |
},
|
| 1483 |
{
|
| 1484 |
-
"epoch":
|
| 1485 |
-
"
|
| 1486 |
-
"
|
| 1487 |
-
"
|
| 1488 |
-
"
|
| 1489 |
-
"
|
| 1490 |
-
|
| 1491 |
-
|
| 1492 |
-
"epoch": 4.022805017103763,
|
| 1493 |
-
"grad_norm": 0.2072031944990158,
|
| 1494 |
-
"learning_rate": 4.8188430704355604e-05,
|
| 1495 |
-
"loss": 0.5379,
|
| 1496 |
-
"num_input_tokens_seen": 10834816,
|
| 1497 |
-
"step": 885
|
| 1498 |
-
},
|
| 1499 |
-
{
|
| 1500 |
-
"epoch": 4.045610034207526,
|
| 1501 |
-
"grad_norm": 0.2549310624599457,
|
| 1502 |
-
"learning_rate": 4.5993353482221695e-05,
|
| 1503 |
-
"loss": 0.5375,
|
| 1504 |
-
"num_input_tokens_seen": 10897152,
|
| 1505 |
-
"step": 890
|
| 1506 |
-
},
|
| 1507 |
-
{
|
| 1508 |
-
"epoch": 4.068415051311288,
|
| 1509 |
-
"grad_norm": 0.15964680910110474,
|
| 1510 |
-
"learning_rate": 4.384437014496215e-05,
|
| 1511 |
-
"loss": 0.5324,
|
| 1512 |
-
"num_input_tokens_seen": 10958592,
|
| 1513 |
-
"step": 895
|
| 1514 |
-
},
|
| 1515 |
-
{
|
| 1516 |
-
"epoch": 4.091220068415051,
|
| 1517 |
-
"grad_norm": 0.16902554035186768,
|
| 1518 |
-
"learning_rate": 4.174196624043644e-05,
|
| 1519 |
-
"loss": 0.5305,
|
| 1520 |
-
"num_input_tokens_seen": 11019520,
|
| 1521 |
-
"step": 900
|
| 1522 |
-
},
|
| 1523 |
-
{
|
| 1524 |
-
"epoch": 4.091220068415051,
|
| 1525 |
-
"eval_loss": 0.5296227335929871,
|
| 1526 |
-
"eval_runtime": 33.4665,
|
| 1527 |
-
"eval_samples_per_second": 93.168,
|
| 1528 |
-
"eval_steps_per_second": 5.827,
|
| 1529 |
-
"num_input_tokens_seen": 11019520,
|
| 1530 |
-
"step": 900
|
| 1531 |
-
},
|
| 1532 |
-
{
|
| 1533 |
-
"epoch": 4.114025085518814,
|
| 1534 |
-
"grad_norm": 0.20468637347221375,
|
| 1535 |
-
"learning_rate": 3.968661679220467e-05,
|
| 1536 |
-
"loss": 0.5405,
|
| 1537 |
-
"num_input_tokens_seen": 11081600,
|
| 1538 |
-
"step": 905
|
| 1539 |
-
},
|
| 1540 |
-
{
|
| 1541 |
-
"epoch": 4.136830102622577,
|
| 1542 |
-
"grad_norm": 0.16220460832118988,
|
| 1543 |
-
"learning_rate": 3.7678786192199695e-05,
|
| 1544 |
-
"loss": 0.5397,
|
| 1545 |
-
"num_input_tokens_seen": 11143552,
|
| 1546 |
-
"step": 910
|
| 1547 |
-
},
|
| 1548 |
-
{
|
| 1549 |
-
"epoch": 4.15963511972634,
|
| 1550 |
-
"grad_norm": 0.2483651041984558,
|
| 1551 |
-
"learning_rate": 3.571892809580013e-05,
|
| 1552 |
-
"loss": 0.5246,
|
| 1553 |
-
"num_input_tokens_seen": 11204864,
|
| 1554 |
-
"step": 915
|
| 1555 |
-
},
|
| 1556 |
-
{
|
| 1557 |
-
"epoch": 4.1824401368301025,
|
| 1558 |
-
"grad_norm": 0.23086680471897125,
|
| 1559 |
-
"learning_rate": 3.380748531933103e-05,
|
| 1560 |
-
"loss": 0.5352,
|
| 1561 |
-
"num_input_tokens_seen": 11266176,
|
| 1562 |
-
"step": 920
|
| 1563 |
-
},
|
| 1564 |
-
{
|
| 1565 |
-
"epoch": 4.205245153933865,
|
| 1566 |
-
"grad_norm": 0.38906633853912354,
|
| 1567 |
-
"learning_rate": 3.194488974001203e-05,
|
| 1568 |
-
"loss": 0.5168,
|
| 1569 |
-
"num_input_tokens_seen": 11326464,
|
| 1570 |
-
"step": 925
|
| 1571 |
-
},
|
| 1572 |
-
{
|
| 1573 |
-
"epoch": 4.228050171037628,
|
| 1574 |
-
"grad_norm": 0.32216280698776245,
|
| 1575 |
-
"learning_rate": 3.013156219837776e-05,
|
| 1576 |
-
"loss": 0.5186,
|
| 1577 |
-
"num_input_tokens_seen": 11386880,
|
| 1578 |
-
"step": 930
|
| 1579 |
-
},
|
| 1580 |
-
{
|
| 1581 |
-
"epoch": 4.250855188141391,
|
| 1582 |
-
"grad_norm": 0.23735865950584412,
|
| 1583 |
-
"learning_rate": 2.8367912403191975e-05,
|
| 1584 |
-
"loss": 0.5331,
|
| 1585 |
-
"num_input_tokens_seen": 11448832,
|
| 1586 |
-
"step": 935
|
| 1587 |
-
},
|
| 1588 |
-
{
|
| 1589 |
-
"epoch": 4.273660205245154,
|
| 1590 |
-
"grad_norm": 0.1531517207622528,
|
| 1591 |
-
"learning_rate": 2.6654338838876664e-05,
|
| 1592 |
-
"loss": 0.5301,
|
| 1593 |
-
"num_input_tokens_seen": 11510784,
|
| 1594 |
-
"step": 940
|
| 1595 |
-
},
|
| 1596 |
-
{
|
| 1597 |
-
"epoch": 4.296465222348917,
|
| 1598 |
-
"grad_norm": 0.22485873103141785,
|
| 1599 |
-
"learning_rate": 2.4991228675477288e-05,
|
| 1600 |
-
"loss": 0.528,
|
| 1601 |
-
"num_input_tokens_seen": 11572480,
|
| 1602 |
-
"step": 945
|
| 1603 |
-
},
|
| 1604 |
-
{
|
| 1605 |
-
"epoch": 4.319270239452679,
|
| 1606 |
-
"grad_norm": 0.21253091096878052,
|
| 1607 |
-
"learning_rate": 2.3378957681184282e-05,
|
| 1608 |
-
"loss": 0.5254,
|
| 1609 |
-
"num_input_tokens_seen": 11633280,
|
| 1610 |
-
"step": 950
|
| 1611 |
-
},
|
| 1612 |
-
{
|
| 1613 |
-
"epoch": 4.342075256556442,
|
| 1614 |
-
"grad_norm": 0.291465699672699,
|
| 1615 |
-
"learning_rate": 2.1817890137430936e-05,
|
| 1616 |
-
"loss": 0.5253,
|
| 1617 |
-
"num_input_tokens_seen": 11694208,
|
| 1618 |
-
"step": 955
|
| 1619 |
-
},
|
| 1620 |
-
{
|
| 1621 |
-
"epoch": 4.364880273660205,
|
| 1622 |
-
"grad_norm": 0.2576054632663727,
|
| 1623 |
-
"learning_rate": 2.030837875658656e-05,
|
| 1624 |
-
"loss": 0.5244,
|
| 1625 |
-
"num_input_tokens_seen": 11755904,
|
| 1626 |
-
"step": 960
|
| 1627 |
-
},
|
| 1628 |
-
{
|
| 1629 |
-
"epoch": 4.387685290763968,
|
| 1630 |
-
"grad_norm": 0.18663591146469116,
|
| 1631 |
-
"learning_rate": 1.8850764602263425e-05,
|
| 1632 |
-
"loss": 0.5316,
|
| 1633 |
-
"num_input_tokens_seen": 11817728,
|
| 1634 |
-
"step": 965
|
| 1635 |
-
},
|
| 1636 |
-
{
|
| 1637 |
-
"epoch": 4.410490307867731,
|
| 1638 |
-
"grad_norm": 0.33847281336784363,
|
| 1639 |
-
"learning_rate": 1.7445377012256124e-05,
|
| 1640 |
-
"loss": 0.5341,
|
| 1641 |
-
"num_input_tokens_seen": 11878912,
|
| 1642 |
-
"step": 970
|
| 1643 |
-
},
|
| 1644 |
-
{
|
| 1645 |
-
"epoch": 4.4332953249714935,
|
| 1646 |
-
"grad_norm": 0.23964723944664001,
|
| 1647 |
-
"learning_rate": 1.609253352412962e-05,
|
| 1648 |
-
"loss": 0.5281,
|
| 1649 |
-
"num_input_tokens_seen": 11939712,
|
| 1650 |
-
"step": 975
|
| 1651 |
-
},
|
| 1652 |
-
{
|
| 1653 |
-
"epoch": 4.456100342075256,
|
| 1654 |
-
"grad_norm": 0.4568791389465332,
|
| 1655 |
-
"learning_rate": 1.479253980347392e-05,
|
| 1656 |
-
"loss": 0.5254,
|
| 1657 |
-
"num_input_tokens_seen": 12001408,
|
| 1658 |
-
"step": 980
|
| 1659 |
-
},
|
| 1660 |
-
{
|
| 1661 |
-
"epoch": 4.478905359179019,
|
| 1662 |
-
"grad_norm": 0.3590211272239685,
|
| 1663 |
-
"learning_rate": 1.354568957484134e-05,
|
| 1664 |
-
"loss": 0.5398,
|
| 1665 |
-
"num_input_tokens_seen": 12062976,
|
| 1666 |
-
"step": 985
|
| 1667 |
-
},
|
| 1668 |
-
{
|
| 1669 |
-
"epoch": 4.501710376282782,
|
| 1670 |
-
"grad_norm": 0.31133538484573364,
|
| 1671 |
-
"learning_rate": 1.2352264555381132e-05,
|
| 1672 |
-
"loss": 0.5227,
|
| 1673 |
-
"num_input_tokens_seen": 12124544,
|
| 1674 |
-
"step": 990
|
| 1675 |
-
},
|
| 1676 |
-
{
|
| 1677 |
-
"epoch": 4.524515393386545,
|
| 1678 |
-
"grad_norm": 0.2682982087135315,
|
| 1679 |
-
"learning_rate": 1.121253439118769e-05,
|
| 1680 |
-
"loss": 0.5189,
|
| 1681 |
-
"num_input_tokens_seen": 12185088,
|
| 1682 |
-
"step": 995
|
| 1683 |
-
},
|
| 1684 |
-
{
|
| 1685 |
-
"epoch": 4.5473204104903076,
|
| 1686 |
-
"grad_norm": 0.16184848546981812,
|
| 1687 |
-
"learning_rate": 1.0126756596375685e-05,
|
| 1688 |
-
"loss": 0.5281,
|
| 1689 |
-
"num_input_tokens_seen": 12247168,
|
| 1690 |
-
"step": 1000
|
| 1691 |
-
},
|
| 1692 |
-
{
|
| 1693 |
-
"epoch": 4.5473204104903076,
|
| 1694 |
-
"eval_loss": 0.5261592268943787,
|
| 1695 |
-
"eval_runtime": 33.4673,
|
| 1696 |
-
"eval_samples_per_second": 93.166,
|
| 1697 |
-
"eval_steps_per_second": 5.827,
|
| 1698 |
-
"num_input_tokens_seen": 12247168,
|
| 1699 |
-
"step": 1000
|
| 1700 |
-
},
|
| 1701 |
-
{
|
| 1702 |
-
"epoch": 4.57012542759407,
|
| 1703 |
-
"grad_norm": 0.30594030022621155,
|
| 1704 |
-
"learning_rate": 9.095176494896662e-06,
|
| 1705 |
-
"loss": 0.5298,
|
| 1706 |
-
"num_input_tokens_seen": 12307968,
|
| 1707 |
-
"step": 1005
|
| 1708 |
-
},
|
| 1709 |
-
{
|
| 1710 |
-
"epoch": 4.592930444697833,
|
| 1711 |
-
"grad_norm": 0.31577154994010925,
|
| 1712 |
-
"learning_rate": 8.118027165109926e-06,
|
| 1713 |
-
"loss": 0.5287,
|
| 1714 |
-
"num_input_tokens_seen": 12370176,
|
| 1715 |
-
"step": 1010
|
| 1716 |
-
},
|
| 1717 |
-
{
|
| 1718 |
-
"epoch": 4.615735461801596,
|
| 1719 |
-
"grad_norm": 0.40308743715286255,
|
| 1720 |
-
"learning_rate": 7.1955293871198145e-06,
|
| 1721 |
-
"loss": 0.5306,
|
| 1722 |
-
"num_input_tokens_seen": 12431488,
|
| 1723 |
-
"step": 1015
|
| 1724 |
-
},
|
| 1725 |
-
{
|
| 1726 |
-
"epoch": 4.638540478905359,
|
| 1727 |
-
"grad_norm": 0.1486368328332901,
|
| 1728 |
-
"learning_rate": 6.3278915928921264e-06,
|
| 1729 |
-
"loss": 0.526,
|
| 1730 |
-
"num_input_tokens_seen": 12492672,
|
| 1731 |
-
"step": 1020
|
| 1732 |
-
},
|
| 1733 |
-
{
|
| 1734 |
-
"epoch": 4.661345496009122,
|
| 1735 |
-
"grad_norm": 0.18577809631824493,
|
| 1736 |
-
"learning_rate": 5.515309819160402e-06,
|
| 1737 |
-
"loss": 0.5355,
|
| 1738 |
-
"num_input_tokens_seen": 12553856,
|
| 1739 |
-
"step": 1025
|
| 1740 |
-
},
|
| 1741 |
-
{
|
| 1742 |
-
"epoch": 4.684150513112884,
|
| 1743 |
-
"grad_norm": 0.19534601271152496,
|
| 1744 |
-
"learning_rate": 4.7579676631326895e-06,
|
| 1745 |
-
"loss": 0.5173,
|
| 1746 |
-
"num_input_tokens_seen": 12615040,
|
| 1747 |
-
"step": 1030
|
| 1748 |
-
},
|
| 1749 |
-
{
|
| 1750 |
-
"epoch": 4.706955530216648,
|
| 1751 |
-
"grad_norm": 0.3114343583583832,
|
| 1752 |
-
"learning_rate": 4.05603624100917e-06,
|
| 1753 |
-
"loss": 0.5355,
|
| 1754 |
-
"num_input_tokens_seen": 12677120,
|
| 1755 |
-
"step": 1035
|
| 1756 |
-
},
|
| 1757 |
-
{
|
| 1758 |
-
"epoch": 4.72976054732041,
|
| 1759 |
-
"grad_norm": 0.2684144675731659,
|
| 1760 |
-
"learning_rate": 3.4096741493194194e-06,
|
| 1761 |
-
"loss": 0.5383,
|
| 1762 |
-
"num_input_tokens_seen": 12739328,
|
| 1763 |
-
"step": 1040
|
| 1764 |
-
},
|
| 1765 |
-
{
|
| 1766 |
-
"epoch": 4.752565564424174,
|
| 1767 |
-
"grad_norm": 0.19341741502285004,
|
| 1768 |
-
"learning_rate": 2.819027429088822e-06,
|
| 1769 |
-
"loss": 0.5289,
|
| 1770 |
-
"num_input_tokens_seen": 12800768,
|
| 1771 |
-
"step": 1045
|
| 1772 |
-
},
|
| 1773 |
-
{
|
| 1774 |
-
"epoch": 4.775370581527936,
|
| 1775 |
-
"grad_norm": 0.14532065391540527,
|
| 1776 |
-
"learning_rate": 2.284229532841603e-06,
|
| 1777 |
-
"loss": 0.513,
|
| 1778 |
-
"num_input_tokens_seen": 12861184,
|
| 1779 |
-
"step": 1050
|
| 1780 |
-
},
|
| 1781 |
-
{
|
| 1782 |
-
"epoch": 4.798175598631699,
|
| 1783 |
-
"grad_norm": 0.18731112778186798,
|
| 1784 |
-
"learning_rate": 1.8054012944479226e-06,
|
| 1785 |
-
"loss": 0.5337,
|
| 1786 |
-
"num_input_tokens_seen": 12923904,
|
| 1787 |
-
"step": 1055
|
| 1788 |
-
},
|
| 1789 |
-
{
|
| 1790 |
-
"epoch": 4.820980615735461,
|
| 1791 |
-
"grad_norm": 0.3189660906791687,
|
| 1792 |
-
"learning_rate": 1.382650901822713e-06,
|
| 1793 |
-
"loss": 0.5231,
|
| 1794 |
-
"num_input_tokens_seen": 12985216,
|
| 1795 |
-
"step": 1060
|
| 1796 |
-
},
|
| 1797 |
-
{
|
| 1798 |
-
"epoch": 4.843785632839225,
|
| 1799 |
-
"grad_norm": 0.17671965062618256,
|
| 1800 |
-
"learning_rate": 1.0160738724809548e-06,
|
| 1801 |
-
"loss": 0.5448,
|
| 1802 |
-
"num_input_tokens_seen": 13047296,
|
| 1803 |
-
"step": 1065
|
| 1804 |
-
},
|
| 1805 |
-
{
|
| 1806 |
-
"epoch": 4.866590649942988,
|
| 1807 |
-
"grad_norm": 0.28340452909469604,
|
| 1808 |
-
"learning_rate": 7.057530319564409e-07,
|
| 1809 |
-
"loss": 0.5294,
|
| 1810 |
-
"num_input_tokens_seen": 13108736,
|
| 1811 |
-
"step": 1070
|
| 1812 |
-
},
|
| 1813 |
-
{
|
| 1814 |
-
"epoch": 4.889395667046751,
|
| 1815 |
-
"grad_norm": 0.17847564816474915,
|
| 1816 |
-
"learning_rate": 4.5175849508774516e-07,
|
| 1817 |
-
"loss": 0.5096,
|
| 1818 |
-
"num_input_tokens_seen": 13169280,
|
| 1819 |
-
"step": 1075
|
| 1820 |
-
},
|
| 1821 |
-
{
|
| 1822 |
-
"epoch": 4.9122006841505135,
|
| 1823 |
-
"grad_norm": 0.21711522340774536,
|
| 1824 |
-
"learning_rate": 2.541476501764228e-07,
|
| 1825 |
-
"loss": 0.5284,
|
| 1826 |
-
"num_input_tokens_seen": 13231232,
|
| 1827 |
-
"step": 1080
|
| 1828 |
-
},
|
| 1829 |
-
{
|
| 1830 |
-
"epoch": 4.935005701254276,
|
| 1831 |
-
"grad_norm": 0.20016862452030182,
|
| 1832 |
-
"learning_rate": 1.1296514602038287e-07,
|
| 1833 |
-
"loss": 0.5377,
|
| 1834 |
-
"num_input_tokens_seen": 13293056,
|
| 1835 |
-
"step": 1085
|
| 1836 |
-
},
|
| 1837 |
-
{
|
| 1838 |
-
"epoch": 4.957810718358039,
|
| 1839 |
-
"grad_norm": 0.11549129337072372,
|
| 1840 |
-
"learning_rate": 2.8242881825846223e-08,
|
| 1841 |
-
"loss": 0.5449,
|
| 1842 |
-
"num_input_tokens_seen": 13355776,
|
| 1843 |
-
"step": 1090
|
| 1844 |
-
},
|
| 1845 |
-
{
|
| 1846 |
-
"epoch": 4.980615735461802,
|
| 1847 |
-
"grad_norm": 0.39569395780563354,
|
| 1848 |
-
"learning_rate": 0.0,
|
| 1849 |
-
"loss": 0.5154,
|
| 1850 |
-
"num_input_tokens_seen": 13416448,
|
| 1851 |
-
"step": 1095
|
| 1852 |
-
},
|
| 1853 |
-
{
|
| 1854 |
-
"epoch": 4.980615735461802,
|
| 1855 |
-
"num_input_tokens_seen": 13416448,
|
| 1856 |
-
"step": 1095,
|
| 1857 |
-
"total_flos": 5.447548635740897e+17,
|
| 1858 |
-
"train_loss": 1.1898179768427322,
|
| 1859 |
-
"train_runtime": 5468.9169,
|
| 1860 |
-
"train_samples_per_second": 25.652,
|
| 1861 |
-
"train_steps_per_second": 0.2
|
| 1862 |
}
|
| 1863 |
],
|
| 1864 |
"logging_steps": 5,
|
| 1865 |
-
"max_steps":
|
| 1866 |
-
"num_input_tokens_seen":
|
| 1867 |
-
"num_train_epochs":
|
| 1868 |
"save_steps": 3000,
|
| 1869 |
"stateful_callbacks": {
|
| 1870 |
"TrainerControl": {
|
|
@@ -1878,7 +1509,7 @@
|
|
| 1878 |
"attributes": {}
|
| 1879 |
}
|
| 1880 |
},
|
| 1881 |
-
"total_flos":
|
| 1882 |
"train_batch_size": 16,
|
| 1883 |
"trial_name": null,
|
| 1884 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.9851767388825543,
|
| 6 |
"eval_steps": 100,
|
| 7 |
+
"global_step": 876,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 0.02280501710376283,
|
| 14 |
+
"grad_norm": 37.674232482910156,
|
| 15 |
+
"learning_rate": 2.9999999999999997e-05,
|
| 16 |
+
"loss": 12.6681,
|
| 17 |
"num_input_tokens_seen": 61696,
|
| 18 |
"step": 5
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 0.04561003420752566,
|
| 22 |
+
"grad_norm": 14.371489524841309,
|
| 23 |
+
"learning_rate": 6.75e-05,
|
| 24 |
+
"loss": 5.1135,
|
| 25 |
"num_input_tokens_seen": 123136,
|
| 26 |
"step": 10
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.06841505131128849,
|
| 30 |
+
"grad_norm": 4.319124221801758,
|
| 31 |
+
"learning_rate": 0.00010499999999999999,
|
| 32 |
+
"loss": 1.4998,
|
| 33 |
"num_input_tokens_seen": 184832,
|
| 34 |
"step": 15
|
| 35 |
},
|
| 36 |
{
|
| 37 |
"epoch": 0.09122006841505131,
|
| 38 |
+
"grad_norm": 6.58219051361084,
|
| 39 |
+
"learning_rate": 0.0001425,
|
| 40 |
+
"loss": 0.6984,
|
| 41 |
"num_input_tokens_seen": 247552,
|
| 42 |
"step": 20
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 0.11402508551881414,
|
| 46 |
+
"grad_norm": 21.287355422973633,
|
| 47 |
+
"learning_rate": 0.00017999999999999998,
|
| 48 |
+
"loss": 0.6184,
|
| 49 |
"num_input_tokens_seen": 308992,
|
| 50 |
"step": 25
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.13683010262257697,
|
| 54 |
+
"grad_norm": 4.697451591491699,
|
| 55 |
+
"learning_rate": 0.00021749999999999997,
|
| 56 |
+
"loss": 0.7155,
|
| 57 |
"num_input_tokens_seen": 370176,
|
| 58 |
"step": 30
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.15963511972633979,
|
| 62 |
+
"grad_norm": 0.9988905191421509,
|
| 63 |
+
"learning_rate": 0.00025499999999999996,
|
| 64 |
+
"loss": 0.5481,
|
| 65 |
"num_input_tokens_seen": 430720,
|
| 66 |
"step": 35
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 0.18244013683010263,
|
| 70 |
+
"grad_norm": 68.91044616699219,
|
| 71 |
+
"learning_rate": 0.00029249999999999995,
|
| 72 |
+
"loss": 0.8554,
|
| 73 |
"num_input_tokens_seen": 492800,
|
| 74 |
"step": 40
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.20524515393386544,
|
| 78 |
+
"grad_norm": 52.393184661865234,
|
| 79 |
+
"learning_rate": 0.0002999830542709045,
|
| 80 |
+
"loss": 0.8986,
|
| 81 |
"num_input_tokens_seen": 553984,
|
| 82 |
"step": 45
|
| 83 |
},
|
| 84 |
{
|
| 85 |
"epoch": 0.22805017103762829,
|
| 86 |
+
"grad_norm": 1.0367604494094849,
|
| 87 |
+
"learning_rate": 0.0002999142188084044,
|
| 88 |
+
"loss": 0.5173,
|
| 89 |
"num_input_tokens_seen": 615040,
|
| 90 |
"step": 50
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"epoch": 0.2508551881413911,
|
| 94 |
+
"grad_norm": 0.6331456303596497,
|
| 95 |
+
"learning_rate": 0.0002997924587868761,
|
| 96 |
+
"loss": 0.6497,
|
| 97 |
"num_input_tokens_seen": 676736,
|
| 98 |
"step": 55
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 0.27366020524515394,
|
| 102 |
+
"grad_norm": 13.769452095031738,
|
| 103 |
+
"learning_rate": 0.000299617817191538,
|
| 104 |
+
"loss": 0.5197,
|
| 105 |
"num_input_tokens_seen": 738176,
|
| 106 |
"step": 60
|
| 107 |
},
|
| 108 |
{
|
| 109 |
"epoch": 0.29646522234891676,
|
| 110 |
+
"grad_norm": 0.3195483982563019,
|
| 111 |
+
"learning_rate": 0.00029939035567651143,
|
| 112 |
+
"loss": 0.502,
|
| 113 |
"num_input_tokens_seen": 799488,
|
| 114 |
"step": 65
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.31927023945267957,
|
| 118 |
+
"grad_norm": 0.2712125778198242,
|
| 119 |
+
"learning_rate": 0.00029911015454305435,
|
| 120 |
+
"loss": 0.494,
|
| 121 |
"num_input_tokens_seen": 861568,
|
| 122 |
"step": 70
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.34207525655644244,
|
| 126 |
+
"grad_norm": 0.2729420065879822,
|
| 127 |
+
"learning_rate": 0.00029877731271121295,
|
| 128 |
+
"loss": 0.4924,
|
| 129 |
"num_input_tokens_seen": 924544,
|
| 130 |
"step": 75
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 0.36488027366020526,
|
| 134 |
+
"grad_norm": 0.2902171313762665,
|
| 135 |
+
"learning_rate": 0.0002983919476848992,
|
| 136 |
+
"loss": 0.4805,
|
| 137 |
"num_input_tokens_seen": 985472,
|
| 138 |
"step": 80
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 0.38768529076396807,
|
| 142 |
+
"grad_norm": 0.5374093055725098,
|
| 143 |
+
"learning_rate": 0.00029795419551040833,
|
| 144 |
+
"loss": 0.4934,
|
| 145 |
"num_input_tokens_seen": 1046912,
|
| 146 |
"step": 85
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 0.4104903078677309,
|
| 150 |
+
"grad_norm": 0.35348376631736755,
|
| 151 |
+
"learning_rate": 0.0002974642107283903,
|
| 152 |
+
"loss": 0.4886,
|
| 153 |
"num_input_tokens_seen": 1108992,
|
| 154 |
"step": 90
|
| 155 |
},
|
| 156 |
{
|
| 157 |
"epoch": 0.43329532497149376,
|
| 158 |
+
"grad_norm": 0.17245665192604065,
|
| 159 |
+
"learning_rate": 0.00029692216631929165,
|
| 160 |
+
"loss": 0.4628,
|
| 161 |
"num_input_tokens_seen": 1170048,
|
| 162 |
"step": 95
|
| 163 |
},
|
| 164 |
{
|
| 165 |
"epoch": 0.45610034207525657,
|
| 166 |
+
"grad_norm": 0.22592011094093323,
|
| 167 |
+
"learning_rate": 0.000296328253642288,
|
| 168 |
+
"loss": 0.4689,
|
| 169 |
"num_input_tokens_seen": 1230464,
|
| 170 |
"step": 100
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.45610034207525657,
|
| 174 |
+
"eval_loss": 0.4737529754638672,
|
| 175 |
+
"eval_runtime": 33.8471,
|
| 176 |
+
"eval_samples_per_second": 92.12,
|
| 177 |
+
"eval_steps_per_second": 5.761,
|
| 178 |
"num_input_tokens_seen": 1230464,
|
| 179 |
"step": 100
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 0.4789053591790194,
|
| 183 |
+
"grad_norm": 0.1636808067560196,
|
| 184 |
+
"learning_rate": 0.0002956826823677281,
|
| 185 |
+
"loss": 0.4753,
|
| 186 |
"num_input_tokens_seen": 1292288,
|
| 187 |
"step": 105
|
| 188 |
},
|
| 189 |
{
|
| 190 |
"epoch": 0.5017103762827823,
|
| 191 |
+
"grad_norm": 0.27978241443634033,
|
| 192 |
+
"learning_rate": 0.00029498568040311324,
|
| 193 |
+
"loss": 0.4831,
|
| 194 |
"num_input_tokens_seen": 1353344,
|
| 195 |
"step": 110
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 0.5245153933865451,
|
| 199 |
+
"grad_norm": 0.3377664089202881,
|
| 200 |
+
"learning_rate": 0.00029423749381263877,
|
| 201 |
+
"loss": 0.4831,
|
| 202 |
"num_input_tokens_seen": 1415040,
|
| 203 |
"step": 115
|
| 204 |
},
|
| 205 |
{
|
| 206 |
"epoch": 0.5473204104903079,
|
| 207 |
+
"grad_norm": 0.1405085176229477,
|
| 208 |
+
"learning_rate": 0.00029343838673032537,
|
| 209 |
+
"loss": 0.4764,
|
| 210 |
"num_input_tokens_seen": 1476480,
|
| 211 |
"step": 120
|
| 212 |
},
|
| 213 |
{
|
| 214 |
"epoch": 0.5701254275940707,
|
| 215 |
+
"grad_norm": 0.12328118830919266,
|
| 216 |
+
"learning_rate": 0.0002925886412667713,
|
| 217 |
+
"loss": 0.4643,
|
| 218 |
"num_input_tokens_seen": 1537664,
|
| 219 |
"step": 125
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.5929304446978335,
|
| 223 |
+
"grad_norm": 0.1404685229063034,
|
| 224 |
+
"learning_rate": 0.00029168855740955803,
|
| 225 |
+
"loss": 0.4655,
|
| 226 |
"num_input_tokens_seen": 1598848,
|
| 227 |
"step": 130
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 0.6157354618015963,
|
| 231 |
+
"grad_norm": 0.18596184253692627,
|
| 232 |
+
"learning_rate": 0.00029073845291734536,
|
| 233 |
+
"loss": 0.4739,
|
| 234 |
"num_input_tokens_seen": 1660800,
|
| 235 |
"step": 135
|
| 236 |
},
|
| 237 |
{
|
| 238 |
"epoch": 0.6385404789053591,
|
| 239 |
+
"grad_norm": 0.15524207055568695,
|
| 240 |
+
"learning_rate": 0.00028973866320769183,
|
| 241 |
+
"loss": 0.4646,
|
| 242 |
"num_input_tokens_seen": 1721600,
|
| 243 |
"step": 140
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"epoch": 0.661345496009122,
|
| 247 |
+
"grad_norm": 0.18459920585155487,
|
| 248 |
+
"learning_rate": 0.0002886895412386419,
|
| 249 |
+
"loss": 0.478,
|
| 250 |
"num_input_tokens_seen": 1783168,
|
| 251 |
"step": 145
|
| 252 |
},
|
| 253 |
{
|
| 254 |
"epoch": 0.6841505131128849,
|
| 255 |
+
"grad_norm": 0.26990625262260437,
|
| 256 |
+
"learning_rate": 0.00028759145738412023,
|
| 257 |
+
"loss": 0.4648,
|
| 258 |
"num_input_tokens_seen": 1844992,
|
| 259 |
"step": 150
|
| 260 |
},
|
| 261 |
{
|
| 262 |
"epoch": 0.7069555302166477,
|
| 263 |
+
"grad_norm": 0.26559221744537354,
|
| 264 |
+
"learning_rate": 0.00028644479930317775,
|
| 265 |
+
"loss": 0.4545,
|
| 266 |
"num_input_tokens_seen": 1906048,
|
| 267 |
"step": 155
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 0.7297605473204105,
|
| 271 |
+
"grad_norm": 0.15647485852241516,
|
| 272 |
+
"learning_rate": 0.0002852499718031353,
|
| 273 |
+
"loss": 0.4611,
|
| 274 |
"num_input_tokens_seen": 1967744,
|
| 275 |
"step": 160
|
| 276 |
},
|
| 277 |
{
|
| 278 |
"epoch": 0.7525655644241733,
|
| 279 |
+
"grad_norm": 0.3244103789329529,
|
| 280 |
+
"learning_rate": 0.00028400739669667396,
|
| 281 |
+
"loss": 0.4347,
|
| 282 |
"num_input_tokens_seen": 2028032,
|
| 283 |
"step": 165
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"epoch": 0.7753705815279361,
|
| 287 |
+
"grad_norm": 0.2574285864830017,
|
| 288 |
+
"learning_rate": 0.00028271751265292124,
|
| 289 |
+
"loss": 0.4417,
|
| 290 |
"num_input_tokens_seen": 2088448,
|
| 291 |
"step": 170
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 0.798175598631699,
|
| 295 |
+
"grad_norm": 0.23050425946712494,
|
| 296 |
+
"learning_rate": 0.0002813807750425869,
|
| 297 |
+
"loss": 0.4532,
|
| 298 |
"num_input_tokens_seen": 2150144,
|
| 299 |
"step": 175
|
| 300 |
},
|
| 301 |
{
|
| 302 |
"epoch": 0.8209806157354618,
|
| 303 |
+
"grad_norm": 0.24787545204162598,
|
| 304 |
+
"learning_rate": 0.0002799976557772021,
|
| 305 |
+
"loss": 0.4444,
|
| 306 |
"num_input_tokens_seen": 2211584,
|
| 307 |
"step": 180
|
| 308 |
},
|
| 309 |
{
|
| 310 |
"epoch": 0.8437856328392246,
|
| 311 |
+
"grad_norm": 0.22476541996002197,
|
| 312 |
+
"learning_rate": 0.0002785686431425199,
|
| 313 |
+
"loss": 0.4232,
|
| 314 |
"num_input_tokens_seen": 2272256,
|
| 315 |
"step": 185
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 0.8665906499429875,
|
| 319 |
+
"grad_norm": 0.213558167219162,
|
| 320 |
+
"learning_rate": 0.00027709424162613417,
|
| 321 |
+
"loss": 0.4251,
|
| 322 |
"num_input_tokens_seen": 2333696,
|
| 323 |
"step": 190
|
| 324 |
},
|
| 325 |
{
|
| 326 |
"epoch": 0.8893956670467503,
|
| 327 |
+
"grad_norm": 0.599111795425415,
|
| 328 |
+
"learning_rate": 0.00027557497173937923,
|
| 329 |
+
"loss": 0.4351,
|
| 330 |
"num_input_tokens_seen": 2394880,
|
| 331 |
"step": 195
|
| 332 |
},
|
| 333 |
{
|
| 334 |
"epoch": 0.9122006841505131,
|
| 335 |
+
"grad_norm": 0.22037360072135925,
|
| 336 |
+
"learning_rate": 0.000274011369833573,
|
| 337 |
+
"loss": 0.4141,
|
| 338 |
"num_input_tokens_seen": 2455680,
|
| 339 |
"step": 200
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 0.9122006841505131,
|
| 343 |
+
"eval_loss": 0.4265781044960022,
|
| 344 |
+
"eval_runtime": 33.7975,
|
| 345 |
+
"eval_samples_per_second": 92.255,
|
| 346 |
+
"eval_steps_per_second": 5.77,
|
| 347 |
"num_input_tokens_seen": 2455680,
|
| 348 |
"step": 200
|
| 349 |
},
|
| 350 |
{
|
| 351 |
"epoch": 0.935005701254276,
|
| 352 |
+
"grad_norm": 0.4435230791568756,
|
| 353 |
+
"learning_rate": 0.00027240398791066696,
|
| 354 |
+
"loss": 0.4219,
|
| 355 |
"num_input_tokens_seen": 2517376,
|
| 356 |
"step": 205
|
| 357 |
},
|
| 358 |
{
|
| 359 |
"epoch": 0.9578107183580388,
|
| 360 |
+
"grad_norm": 0.24863602221012115,
|
| 361 |
+
"learning_rate": 0.0002707533934283722,
|
| 362 |
+
"loss": 0.4189,
|
| 363 |
"num_input_tokens_seen": 2578816,
|
| 364 |
"step": 210
|
| 365 |
},
|
| 366 |
{
|
| 367 |
"epoch": 0.9806157354618016,
|
| 368 |
+
"grad_norm": 0.22515784204006195,
|
| 369 |
+
"learning_rate": 0.0002690601690998284,
|
| 370 |
+
"loss": 0.3962,
|
| 371 |
"num_input_tokens_seen": 2640128,
|
| 372 |
"step": 215
|
| 373 |
},
|
| 374 |
{
|
| 375 |
"epoch": 1.0,
|
| 376 |
+
"grad_norm": 0.3822718560695648,
|
| 377 |
+
"learning_rate": 0.00026732491268788695,
|
| 378 |
+
"loss": 0.4017,
|
| 379 |
"num_input_tokens_seen": 2691984,
|
| 380 |
"step": 220
|
| 381 |
},
|
| 382 |
{
|
| 383 |
"epoch": 1.0228050171037628,
|
| 384 |
+
"grad_norm": 0.2513326108455658,
|
| 385 |
+
"learning_rate": 0.0002655482367940819,
|
| 386 |
+
"loss": 0.3983,
|
| 387 |
"num_input_tokens_seen": 2753808,
|
| 388 |
"step": 225
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 1.0456100342075256,
|
| 392 |
+
"grad_norm": 0.2268570065498352,
|
| 393 |
+
"learning_rate": 0.0002637307686423615,
|
| 394 |
+
"loss": 0.3922,
|
| 395 |
"num_input_tokens_seen": 2815248,
|
| 396 |
"step": 230
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 1.0684150513112884,
|
| 400 |
+
"grad_norm": 0.2299157828092575,
|
| 401 |
+
"learning_rate": 0.0002618731498576579,
|
| 402 |
+
"loss": 0.4045,
|
| 403 |
"num_input_tokens_seen": 2877456,
|
| 404 |
"step": 235
|
| 405 |
},
|
| 406 |
{
|
| 407 |
"epoch": 1.0912200684150513,
|
| 408 |
+
"grad_norm": 0.24534684419631958,
|
| 409 |
+
"learning_rate": 0.0002599760362393729,
|
| 410 |
+
"loss": 0.3937,
|
| 411 |
"num_input_tokens_seen": 2939280,
|
| 412 |
"step": 240
|
| 413 |
},
|
| 414 |
{
|
| 415 |
"epoch": 1.114025085518814,
|
| 416 |
+
"grad_norm": 0.36554455757141113,
|
| 417 |
+
"learning_rate": 0.00025804009752985975,
|
| 418 |
+
"loss": 0.3841,
|
| 419 |
"num_input_tokens_seen": 3000336,
|
| 420 |
"step": 245
|
| 421 |
},
|
| 422 |
{
|
| 423 |
"epoch": 1.1368301026225769,
|
| 424 |
+
"grad_norm": 0.31855228543281555,
|
| 425 |
+
"learning_rate": 0.00025606601717798207,
|
| 426 |
+
"loss": 0.3865,
|
| 427 |
"num_input_tokens_seen": 3062416,
|
| 428 |
"step": 250
|
| 429 |
},
|
| 430 |
{
|
| 431 |
"epoch": 1.1596351197263397,
|
| 432 |
+
"grad_norm": 0.2641734480857849,
|
| 433 |
+
"learning_rate": 0.0002540544920978349,
|
| 434 |
+
"loss": 0.3771,
|
| 435 |
"num_input_tokens_seen": 3124368,
|
| 436 |
"step": 255
|
| 437 |
},
|
| 438 |
{
|
| 439 |
"epoch": 1.1824401368301025,
|
| 440 |
+
"grad_norm": 0.2617756426334381,
|
| 441 |
+
"learning_rate": 0.00025200623242271095,
|
| 442 |
+
"loss": 0.381,
|
| 443 |
"num_input_tokens_seen": 3185424,
|
| 444 |
"step": 260
|
| 445 |
},
|
| 446 |
{
|
| 447 |
"epoch": 1.2052451539338653,
|
| 448 |
+
"grad_norm": 0.22252124547958374,
|
| 449 |
+
"learning_rate": 0.00024992196125440096,
|
| 450 |
+
"loss": 0.3563,
|
| 451 |
"num_input_tokens_seen": 3246096,
|
| 452 |
"step": 265
|
| 453 |
},
|
| 454 |
{
|
| 455 |
"epoch": 1.2280501710376284,
|
| 456 |
+
"grad_norm": 0.33859676122665405,
|
| 457 |
+
"learning_rate": 0.00024780241440791546,
|
| 458 |
+
"loss": 0.3783,
|
| 459 |
"num_input_tokens_seen": 3307536,
|
| 460 |
"step": 270
|
| 461 |
},
|
| 462 |
{
|
| 463 |
"epoch": 1.2508551881413912,
|
| 464 |
+
"grad_norm": 0.30068618059158325,
|
| 465 |
+
"learning_rate": 0.0002456483401517181,
|
| 466 |
+
"loss": 0.3672,
|
| 467 |
"num_input_tokens_seen": 3368976,
|
| 468 |
"step": 275
|
| 469 |
},
|
| 470 |
{
|
| 471 |
"epoch": 1.273660205245154,
|
| 472 |
+
"grad_norm": 0.4228454530239105,
|
| 473 |
+
"learning_rate": 0.00024346049894356274,
|
| 474 |
+
"loss": 0.3597,
|
| 475 |
"num_input_tokens_seen": 3429520,
|
| 476 |
"step": 280
|
| 477 |
},
|
| 478 |
{
|
| 479 |
"epoch": 1.2964652223489168,
|
| 480 |
+
"grad_norm": 0.22735142707824707,
|
| 481 |
+
"learning_rate": 0.00024123966316202765,
|
| 482 |
+
"loss": 0.3493,
|
| 483 |
"num_input_tokens_seen": 3490448,
|
| 484 |
"step": 285
|
| 485 |
},
|
| 486 |
{
|
| 487 |
"epoch": 1.3192702394526796,
|
| 488 |
+
"grad_norm": 0.2932782769203186,
|
| 489 |
+
"learning_rate": 0.0002389866168338405,
|
| 490 |
+
"loss": 0.3426,
|
| 491 |
"num_input_tokens_seen": 3551120,
|
| 492 |
"step": 290
|
| 493 |
},
|
| 494 |
{
|
| 495 |
"epoch": 1.3420752565564424,
|
| 496 |
+
"grad_norm": 0.20311766862869263,
|
| 497 |
+
"learning_rate": 0.00023670215535709184,
|
| 498 |
+
"loss": 0.3438,
|
| 499 |
"num_input_tokens_seen": 3611920,
|
| 500 |
"step": 295
|
| 501 |
},
|
| 502 |
{
|
| 503 |
"epoch": 1.3648802736602053,
|
| 504 |
+
"grad_norm": 0.2872684895992279,
|
| 505 |
+
"learning_rate": 0.0002343870852204339,
|
| 506 |
+
"loss": 0.3463,
|
| 507 |
"num_input_tokens_seen": 3673744,
|
| 508 |
"step": 300
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"epoch": 1.3648802736602053,
|
| 512 |
+
"eval_loss": 0.34857267141342163,
|
| 513 |
+
"eval_runtime": 33.7901,
|
| 514 |
+
"eval_samples_per_second": 92.275,
|
| 515 |
+
"eval_steps_per_second": 5.771,
|
| 516 |
"num_input_tokens_seen": 3673744,
|
| 517 |
"step": 300
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"epoch": 1.387685290763968,
|
| 521 |
+
"grad_norm": 0.2765709161758423,
|
| 522 |
+
"learning_rate": 0.00023204222371836405,
|
| 523 |
+
"loss": 0.3446,
|
| 524 |
"num_input_tokens_seen": 3735568,
|
| 525 |
"step": 305
|
| 526 |
},
|
| 527 |
{
|
| 528 |
"epoch": 1.4104903078677309,
|
| 529 |
+
"grad_norm": 0.2969816029071808,
|
| 530 |
+
"learning_rate": 0.00022966839866269325,
|
| 531 |
+
"loss": 0.3439,
|
| 532 |
"num_input_tokens_seen": 3798160,
|
| 533 |
"step": 310
|
| 534 |
},
|
| 535 |
{
|
| 536 |
"epoch": 1.4332953249714937,
|
| 537 |
+
"grad_norm": 0.38774895668029785,
|
| 538 |
+
"learning_rate": 0.00022726644809030217,
|
| 539 |
+
"loss": 0.3308,
|
| 540 |
"num_input_tokens_seen": 3859600,
|
| 541 |
"step": 315
|
| 542 |
},
|
| 543 |
{
|
| 544 |
"epoch": 1.4561003420752565,
|
| 545 |
+
"grad_norm": 0.39645934104919434,
|
| 546 |
+
"learning_rate": 0.00022483721996728677,
|
| 547 |
+
"loss": 0.3303,
|
| 548 |
"num_input_tokens_seen": 3920528,
|
| 549 |
"step": 320
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"epoch": 1.4789053591790193,
|
| 553 |
+
"grad_norm": 0.34188687801361084,
|
| 554 |
+
"learning_rate": 0.00022238157188959892,
|
| 555 |
+
"loss": 0.3352,
|
| 556 |
"num_input_tokens_seen": 3982096,
|
| 557 |
"step": 325
|
| 558 |
},
|
| 559 |
{
|
| 560 |
"epoch": 1.5017103762827824,
|
| 561 |
+
"grad_norm": 0.34944671392440796,
|
| 562 |
+
"learning_rate": 0.00021990037078028755,
|
| 563 |
+
"loss": 0.3429,
|
| 564 |
"num_input_tokens_seen": 4044048,
|
| 565 |
"step": 330
|
| 566 |
},
|
| 567 |
{
|
| 568 |
"epoch": 1.5245153933865452,
|
| 569 |
+
"grad_norm": 0.3915162682533264,
|
| 570 |
+
"learning_rate": 0.00021739449258344665,
|
| 571 |
+
"loss": 0.323,
|
| 572 |
"num_input_tokens_seen": 4105104,
|
| 573 |
"step": 335
|
| 574 |
},
|
| 575 |
{
|
| 576 |
"epoch": 1.547320410490308,
|
| 577 |
+
"grad_norm": 0.2683054506778717,
|
| 578 |
+
"learning_rate": 0.00021486482195497877,
|
| 579 |
+
"loss": 0.323,
|
| 580 |
"num_input_tokens_seen": 4165904,
|
| 581 |
"step": 340
|
| 582 |
},
|
| 583 |
{
|
| 584 |
"epoch": 1.5701254275940708,
|
| 585 |
+
"grad_norm": 0.4083855152130127,
|
| 586 |
+
"learning_rate": 0.00021231225195028297,
|
| 587 |
+
"loss": 0.3279,
|
| 588 |
"num_input_tokens_seen": 4226704,
|
| 589 |
"step": 345
|
| 590 |
},
|
| 591 |
{
|
| 592 |
"epoch": 1.5929304446978336,
|
| 593 |
+
"grad_norm": 0.31224071979522705,
|
| 594 |
+
"learning_rate": 0.00020973768370897728,
|
| 595 |
+
"loss": 0.3274,
|
| 596 |
"num_input_tokens_seen": 4288400,
|
| 597 |
"step": 350
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 1.6157354618015964,
|
| 601 |
+
"grad_norm": 0.3287370204925537,
|
| 602 |
+
"learning_rate": 0.00020714202613676764,
|
| 603 |
+
"loss": 0.3197,
|
| 604 |
"num_input_tokens_seen": 4349712,
|
| 605 |
"step": 355
|
| 606 |
},
|
| 607 |
{
|
| 608 |
"epoch": 1.6385404789053593,
|
| 609 |
+
"grad_norm": 0.26583436131477356,
|
| 610 |
+
"learning_rate": 0.00020452619558457446,
|
| 611 |
+
"loss": 0.293,
|
| 612 |
"num_input_tokens_seen": 4410256,
|
| 613 |
"step": 360
|
| 614 |
},
|
| 615 |
{
|
| 616 |
"epoch": 1.661345496009122,
|
| 617 |
+
"grad_norm": 1.2303223609924316,
|
| 618 |
+
"learning_rate": 0.0002018911155250314,
|
| 619 |
+
"loss": 0.3091,
|
| 620 |
"num_input_tokens_seen": 4471440,
|
| 621 |
"step": 365
|
| 622 |
},
|
| 623 |
{
|
| 624 |
"epoch": 1.6841505131128849,
|
| 625 |
+
"grad_norm": 0.3120308220386505,
|
| 626 |
+
"learning_rate": 0.00019923771622646974,
|
| 627 |
+
"loss": 0.2911,
|
| 628 |
"num_input_tokens_seen": 4533008,
|
| 629 |
"step": 370
|
| 630 |
},
|
| 631 |
{
|
| 632 |
"epoch": 1.7069555302166477,
|
| 633 |
+
"grad_norm": 0.5297182202339172,
|
| 634 |
+
"learning_rate": 0.0001965669344245034,
|
| 635 |
+
"loss": 0.3066,
|
| 636 |
"num_input_tokens_seen": 4594320,
|
| 637 |
"step": 375
|
| 638 |
},
|
| 639 |
{
|
| 640 |
"epoch": 1.7297605473204105,
|
| 641 |
+
"grad_norm": 0.23600246012210846,
|
| 642 |
+
"learning_rate": 0.00019387971299133128,
|
| 643 |
+
"loss": 0.3143,
|
| 644 |
"num_input_tokens_seen": 4655760,
|
| 645 |
"step": 380
|
| 646 |
},
|
| 647 |
{
|
| 648 |
"epoch": 1.7525655644241733,
|
| 649 |
+
"grad_norm": 0.2890896797180176,
|
| 650 |
+
"learning_rate": 0.0001911770006028728,
|
| 651 |
+
"loss": 0.3025,
|
| 652 |
"num_input_tokens_seen": 4717328,
|
| 653 |
"step": 385
|
| 654 |
},
|
| 655 |
{
|
| 656 |
"epoch": 1.7753705815279361,
|
| 657 |
+
"grad_norm": 0.2806335985660553,
|
| 658 |
+
"learning_rate": 0.00018845975140385464,
|
| 659 |
+
"loss": 0.2926,
|
| 660 |
"num_input_tokens_seen": 4779152,
|
| 661 |
"step": 390
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"epoch": 1.798175598631699,
|
| 665 |
+
"grad_norm": 0.3417849540710449,
|
| 666 |
+
"learning_rate": 0.00018572892467096707,
|
| 667 |
+
"loss": 0.3134,
|
| 668 |
"num_input_tokens_seen": 4840336,
|
| 669 |
"step": 395
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"epoch": 1.8209806157354618,
|
| 673 |
+
"grad_norm": 0.32188060879707336,
|
| 674 |
+
"learning_rate": 0.00018298548447420797,
|
| 675 |
+
"loss": 0.3069,
|
| 676 |
"num_input_tokens_seen": 4901648,
|
| 677 |
"step": 400
|
| 678 |
},
|
| 679 |
{
|
| 680 |
"epoch": 1.8209806157354618,
|
| 681 |
+
"eval_loss": 0.30086231231689453,
|
| 682 |
+
"eval_runtime": 33.7818,
|
| 683 |
+
"eval_samples_per_second": 92.298,
|
| 684 |
+
"eval_steps_per_second": 5.772,
|
| 685 |
"num_input_tokens_seen": 4901648,
|
| 686 |
"step": 400
|
| 687 |
},
|
| 688 |
{
|
| 689 |
"epoch": 1.8437856328392246,
|
| 690 |
+
"grad_norm": 0.29339122772216797,
|
| 691 |
+
"learning_rate": 0.0001802303993365353,
|
| 692 |
+
"loss": 0.2994,
|
| 693 |
"num_input_tokens_seen": 4963216,
|
| 694 |
"step": 405
|
| 695 |
},
|
| 696 |
{
|
| 697 |
"epoch": 1.8665906499429874,
|
| 698 |
+
"grad_norm": 0.3036775290966034,
|
| 699 |
+
"learning_rate": 0.00017746464189194705,
|
| 700 |
+
"loss": 0.3037,
|
| 701 |
"num_input_tokens_seen": 5024912,
|
| 702 |
"step": 410
|
| 703 |
},
|
| 704 |
{
|
| 705 |
"epoch": 1.8893956670467502,
|
| 706 |
+
"grad_norm": 0.34781789779663086,
|
| 707 |
+
"learning_rate": 0.00017468918854211007,
|
| 708 |
+
"loss": 0.2846,
|
| 709 |
"num_input_tokens_seen": 5086224,
|
| 710 |
"step": 415
|
| 711 |
},
|
| 712 |
{
|
| 713 |
"epoch": 1.912200684150513,
|
| 714 |
+
"grad_norm": 0.3571913242340088,
|
| 715 |
+
"learning_rate": 0.00017190501911165887,
|
| 716 |
+
"loss": 0.2973,
|
| 717 |
"num_input_tokens_seen": 5148048,
|
| 718 |
"step": 420
|
| 719 |
},
|
| 720 |
{
|
| 721 |
"epoch": 1.9350057012542758,
|
| 722 |
+
"grad_norm": 0.35188090801239014,
|
| 723 |
+
"learning_rate": 0.00016911311650228572,
|
| 724 |
+
"loss": 0.2957,
|
| 725 |
"num_input_tokens_seen": 5209104,
|
| 726 |
"step": 425
|
| 727 |
},
|
| 728 |
{
|
| 729 |
"epoch": 1.9578107183580387,
|
| 730 |
+
"grad_norm": 0.309939980506897,
|
| 731 |
+
"learning_rate": 0.00016631446634574474,
|
| 732 |
+
"loss": 0.2819,
|
| 733 |
"num_input_tokens_seen": 5270544,
|
| 734 |
"step": 430
|
| 735 |
},
|
| 736 |
{
|
| 737 |
"epoch": 1.9806157354618015,
|
| 738 |
+
"grad_norm": 0.4763481020927429,
|
| 739 |
+
"learning_rate": 0.000163510056655892,
|
| 740 |
+
"loss": 0.2836,
|
| 741 |
"num_input_tokens_seen": 5331472,
|
| 742 |
"step": 435
|
| 743 |
},
|
| 744 |
{
|
| 745 |
"epoch": 2.0,
|
| 746 |
+
"grad_norm": 0.505473256111145,
|
| 747 |
+
"learning_rate": 0.00016070087747988482,
|
| 748 |
+
"loss": 0.2771,
|
| 749 |
"num_input_tokens_seen": 5382864,
|
| 750 |
"step": 440
|
| 751 |
},
|
| 752 |
{
|
| 753 |
"epoch": 2.022805017103763,
|
| 754 |
+
"grad_norm": 0.31896135210990906,
|
| 755 |
+
"learning_rate": 0.00015788792054866312,
|
| 756 |
+
"loss": 0.2603,
|
| 757 |
"num_input_tokens_seen": 5444176,
|
| 758 |
"step": 445
|
| 759 |
},
|
| 760 |
{
|
| 761 |
"epoch": 2.0456100342075256,
|
| 762 |
+
"grad_norm": 0.2938978970050812,
|
| 763 |
+
"learning_rate": 0.00015507217892683631,
|
| 764 |
+
"loss": 0.2486,
|
| 765 |
"num_input_tokens_seen": 5505872,
|
| 766 |
"step": 450
|
| 767 |
},
|
| 768 |
{
|
| 769 |
"epoch": 2.0684150513112884,
|
| 770 |
+
"grad_norm": 0.4180850386619568,
|
| 771 |
+
"learning_rate": 0.00015225464666209957,
|
| 772 |
+
"loss": 0.2489,
|
| 773 |
"num_input_tokens_seen": 5568208,
|
| 774 |
"step": 455
|
| 775 |
},
|
| 776 |
{
|
| 777 |
"epoch": 2.0912200684150513,
|
| 778 |
+
"grad_norm": 0.4759632647037506,
|
| 779 |
+
"learning_rate": 0.0001494363184343026,
|
| 780 |
+
"loss": 0.2497,
|
| 781 |
"num_input_tokens_seen": 5628880,
|
| 782 |
"step": 460
|
| 783 |
},
|
| 784 |
{
|
| 785 |
"epoch": 2.114025085518814,
|
| 786 |
+
"grad_norm": 0.4155760705471039,
|
| 787 |
+
"learning_rate": 0.0001466181892042962,
|
| 788 |
+
"loss": 0.2435,
|
| 789 |
"num_input_tokens_seen": 5690320,
|
| 790 |
"step": 465
|
| 791 |
},
|
| 792 |
{
|
| 793 |
"epoch": 2.136830102622577,
|
| 794 |
+
"grad_norm": 0.37975725531578064,
|
| 795 |
+
"learning_rate": 0.000143801253862678,
|
| 796 |
+
"loss": 0.2554,
|
| 797 |
"num_input_tokens_seen": 5752912,
|
| 798 |
"step": 470
|
| 799 |
},
|
| 800 |
{
|
| 801 |
"epoch": 2.1596351197263397,
|
| 802 |
+
"grad_norm": 0.3845106065273285,
|
| 803 |
+
"learning_rate": 0.00014098650687856495,
|
| 804 |
+
"loss": 0.2517,
|
| 805 |
"num_input_tokens_seen": 5813968,
|
| 806 |
"step": 475
|
| 807 |
},
|
| 808 |
{
|
| 809 |
"epoch": 2.1824401368301025,
|
| 810 |
+
"grad_norm": 0.3614867329597473,
|
| 811 |
+
"learning_rate": 0.00013817494194851278,
|
| 812 |
+
"loss": 0.2523,
|
| 813 |
"num_input_tokens_seen": 5874896,
|
| 814 |
"step": 480
|
| 815 |
},
|
| 816 |
{
|
| 817 |
"epoch": 2.2052451539338653,
|
| 818 |
+
"grad_norm": 0.2901840806007385,
|
| 819 |
+
"learning_rate": 0.00013536755164570975,
|
| 820 |
+
"loss": 0.2485,
|
| 821 |
"num_input_tokens_seen": 5935952,
|
| 822 |
"step": 485
|
| 823 |
},
|
| 824 |
{
|
| 825 |
"epoch": 2.228050171037628,
|
| 826 |
+
"grad_norm": 0.2848447561264038,
|
| 827 |
+
"learning_rate": 0.00013256532706956562,
|
| 828 |
+
"loss": 0.2447,
|
| 829 |
"num_input_tokens_seen": 5997008,
|
| 830 |
"step": 490
|
| 831 |
},
|
| 832 |
{
|
| 833 |
"epoch": 2.250855188141391,
|
| 834 |
+
"grad_norm": 2.4172873497009277,
|
| 835 |
+
"learning_rate": 0.00012976925749582212,
|
| 836 |
+
"loss": 0.2537,
|
| 837 |
"num_input_tokens_seen": 6058704,
|
| 838 |
"step": 495
|
| 839 |
},
|
| 840 |
{
|
| 841 |
"epoch": 2.2736602052451538,
|
| 842 |
+
"grad_norm": 0.2737313508987427,
|
| 843 |
+
"learning_rate": 0.00012698033002730622,
|
| 844 |
+
"loss": 0.2464,
|
| 845 |
"num_input_tokens_seen": 6120272,
|
| 846 |
"step": 500
|
| 847 |
},
|
| 848 |
{
|
| 849 |
"epoch": 2.2736602052451538,
|
| 850 |
+
"eval_loss": 0.2616419792175293,
|
| 851 |
+
"eval_runtime": 33.7593,
|
| 852 |
+
"eval_samples_per_second": 92.36,
|
| 853 |
+
"eval_steps_per_second": 5.776,
|
| 854 |
"num_input_tokens_seen": 6120272,
|
| 855 |
"step": 500
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 2.2964652223489166,
|
| 859 |
+
"grad_norm": 0.369161993265152,
|
| 860 |
+
"learning_rate": 0.00012419952924545125,
|
| 861 |
+
"loss": 0.234,
|
| 862 |
"num_input_tokens_seen": 6180816,
|
| 863 |
"step": 505
|
| 864 |
},
|
| 865 |
{
|
| 866 |
"epoch": 2.3192702394526794,
|
| 867 |
+
"grad_norm": 0.34000036120414734,
|
| 868 |
+
"learning_rate": 0.00012142783686270789,
|
| 869 |
+
"loss": 0.2428,
|
| 870 |
"num_input_tokens_seen": 6242128,
|
| 871 |
"step": 510
|
| 872 |
},
|
| 873 |
{
|
| 874 |
"epoch": 2.342075256556442,
|
| 875 |
+
"grad_norm": 0.26815497875213623,
|
| 876 |
+
"learning_rate": 0.00011866623137596771,
|
| 877 |
+
"loss": 0.2344,
|
| 878 |
"num_input_tokens_seen": 6303312,
|
| 879 |
"step": 515
|
| 880 |
},
|
| 881 |
{
|
| 882 |
"epoch": 2.364880273660205,
|
| 883 |
+
"grad_norm": 0.5366767644882202,
|
| 884 |
+
"learning_rate": 0.0001159156877211225,
|
| 885 |
+
"loss": 0.2434,
|
| 886 |
"num_input_tokens_seen": 6364624,
|
| 887 |
"step": 520
|
| 888 |
},
|
| 889 |
{
|
| 890 |
"epoch": 2.387685290763968,
|
| 891 |
+
"grad_norm": 0.28581875562667847,
|
| 892 |
+
"learning_rate": 0.00011317717692888012,
|
| 893 |
+
"loss": 0.2397,
|
| 894 |
"num_input_tokens_seen": 6425040,
|
| 895 |
"step": 525
|
| 896 |
},
|
| 897 |
{
|
| 898 |
"epoch": 2.4104903078677307,
|
| 899 |
+
"grad_norm": 0.4306572675704956,
|
| 900 |
+
"learning_rate": 0.00011045166578195969,
|
| 901 |
+
"loss": 0.24,
|
| 902 |
"num_input_tokens_seen": 6486736,
|
| 903 |
"step": 530
|
| 904 |
},
|
| 905 |
{
|
| 906 |
"epoch": 2.433295324971494,
|
| 907 |
+
"grad_norm": 0.2597582936286926,
|
| 908 |
+
"learning_rate": 0.00010774011647378553,
|
| 909 |
+
"loss": 0.2375,
|
| 910 |
"num_input_tokens_seen": 6548304,
|
| 911 |
"step": 535
|
| 912 |
},
|
| 913 |
{
|
| 914 |
"epoch": 2.4561003420752567,
|
| 915 |
+
"grad_norm": 0.6010730266571045,
|
| 916 |
+
"learning_rate": 0.00010504348626880252,
|
| 917 |
+
"loss": 0.2243,
|
| 918 |
"num_input_tokens_seen": 6610000,
|
| 919 |
"step": 540
|
| 920 |
},
|
| 921 |
{
|
| 922 |
"epoch": 2.4789053591790196,
|
| 923 |
+
"grad_norm": 0.5287556052207947,
|
| 924 |
+
"learning_rate": 0.00010236272716453011,
|
| 925 |
+
"loss": 0.2513,
|
| 926 |
"num_input_tokens_seen": 6670672,
|
| 927 |
"step": 545
|
| 928 |
},
|
| 929 |
{
|
| 930 |
"epoch": 2.5017103762827824,
|
| 931 |
+
"grad_norm": 0.6922413110733032,
|
| 932 |
+
"learning_rate": 9.969878555547712e-05,
|
| 933 |
+
"loss": 0.2279,
|
| 934 |
"num_input_tokens_seen": 6732112,
|
| 935 |
"step": 550
|
| 936 |
},
|
| 937 |
{
|
| 938 |
"epoch": 2.524515393386545,
|
| 939 |
+
"grad_norm": 0.3706778287887573,
|
| 940 |
+
"learning_rate": 9.705260189903339e-05,
|
| 941 |
+
"loss": 0.2293,
|
| 942 |
"num_input_tokens_seen": 6793424,
|
| 943 |
"step": 555
|
| 944 |
},
|
| 945 |
{
|
| 946 |
"epoch": 2.547320410490308,
|
| 947 |
+
"grad_norm": 0.27397939562797546,
|
| 948 |
+
"learning_rate": 9.442511038345843e-05,
|
| 949 |
+
"loss": 0.2354,
|
| 950 |
"num_input_tokens_seen": 6855760,
|
| 951 |
"step": 560
|
| 952 |
},
|
| 953 |
{
|
| 954 |
"epoch": 2.570125427594071,
|
| 955 |
+
"grad_norm": 0.37428924441337585,
|
| 956 |
+
"learning_rate": 9.181723859808224e-05,
|
| 957 |
+
"loss": 0.2282,
|
| 958 |
"num_input_tokens_seen": 6916688,
|
| 959 |
"step": 565
|
| 960 |
},
|
| 961 |
{
|
| 962 |
"epoch": 2.5929304446978336,
|
| 963 |
+
"grad_norm": 0.3262987732887268,
|
| 964 |
+
"learning_rate": 8.92299072058371e-05,
|
| 965 |
+
"loss": 0.2133,
|
| 966 |
"num_input_tokens_seen": 6978512,
|
| 967 |
"step": 570
|
| 968 |
},
|
| 969 |
{
|
| 970 |
"epoch": 2.6157354618015964,
|
| 971 |
+
"grad_norm": 0.33271142840385437,
|
| 972 |
+
"learning_rate": 8.666402961823298e-05,
|
| 973 |
+
"loss": 0.2315,
|
| 974 |
"num_input_tokens_seen": 7040208,
|
| 975 |
"step": 575
|
| 976 |
},
|
| 977 |
{
|
| 978 |
"epoch": 2.6385404789053593,
|
| 979 |
+
"grad_norm": 0.2985271215438843,
|
| 980 |
+
"learning_rate": 8.412051167289446e-05,
|
| 981 |
+
"loss": 0.2192,
|
| 982 |
"num_input_tokens_seen": 7101264,
|
| 983 |
"step": 580
|
| 984 |
},
|
| 985 |
{
|
| 986 |
"epoch": 2.661345496009122,
|
| 987 |
+
"grad_norm": 0.2889564335346222,
|
| 988 |
+
"learning_rate": 8.160025131377044e-05,
|
| 989 |
+
"loss": 0.2158,
|
| 990 |
"num_input_tokens_seen": 7163600,
|
| 991 |
"step": 585
|
| 992 |
},
|
| 993 |
{
|
| 994 |
"epoch": 2.684150513112885,
|
| 995 |
+
"grad_norm": 0.34043222665786743,
|
| 996 |
+
"learning_rate": 7.910413827413108e-05,
|
| 997 |
+
"loss": 0.2232,
|
| 998 |
"num_input_tokens_seen": 7225936,
|
| 999 |
"step": 590
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
"epoch": 2.7069555302166477,
|
| 1003 |
+
"grad_norm": 0.411795049905777,
|
| 1004 |
+
"learning_rate": 7.663305376246321e-05,
|
| 1005 |
+
"loss": 0.2136,
|
| 1006 |
"num_input_tokens_seen": 7287760,
|
| 1007 |
"step": 595
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
"epoch": 2.7297605473204105,
|
| 1011 |
+
"grad_norm": 0.3642204701900482,
|
| 1012 |
+
"learning_rate": 7.418787015137526e-05,
|
| 1013 |
+
"loss": 0.2138,
|
| 1014 |
"num_input_tokens_seen": 7348944,
|
| 1015 |
"step": 600
|
| 1016 |
},
|
| 1017 |
{
|
| 1018 |
"epoch": 2.7297605473204105,
|
| 1019 |
+
"eval_loss": 0.23808355629444122,
|
| 1020 |
+
"eval_runtime": 33.8048,
|
| 1021 |
+
"eval_samples_per_second": 92.236,
|
| 1022 |
+
"eval_steps_per_second": 5.768,
|
| 1023 |
"num_input_tokens_seen": 7348944,
|
| 1024 |
"step": 600
|
| 1025 |
},
|
| 1026 |
{
|
| 1027 |
"epoch": 2.7525655644241733,
|
| 1028 |
+
"grad_norm": 0.34160295128822327,
|
| 1029 |
+
"learning_rate": 7.176945066962152e-05,
|
| 1030 |
+
"loss": 0.2272,
|
| 1031 |
"num_input_tokens_seen": 7410640,
|
| 1032 |
"step": 605
|
| 1033 |
},
|
| 1034 |
{
|
| 1035 |
"epoch": 2.775370581527936,
|
| 1036 |
+
"grad_norm": 0.3042212128639221,
|
| 1037 |
+
"learning_rate": 6.937864909735467e-05,
|
| 1038 |
+
"loss": 0.2069,
|
| 1039 |
"num_input_tokens_seen": 7471184,
|
| 1040 |
"step": 610
|
| 1041 |
},
|
| 1042 |
{
|
| 1043 |
"epoch": 2.798175598631699,
|
| 1044 |
+
"grad_norm": 0.37479183077812195,
|
| 1045 |
+
"learning_rate": 6.701630946471367e-05,
|
| 1046 |
+
"loss": 0.2238,
|
| 1047 |
"num_input_tokens_seen": 7533392,
|
| 1048 |
"step": 615
|
| 1049 |
},
|
| 1050 |
{
|
| 1051 |
"epoch": 2.8209806157354618,
|
| 1052 |
+
"grad_norm": 0.354877233505249,
|
| 1053 |
+
"learning_rate": 6.468326575385397e-05,
|
| 1054 |
+
"loss": 0.2166,
|
| 1055 |
"num_input_tokens_seen": 7594832,
|
| 1056 |
"step": 620
|
| 1057 |
},
|
| 1058 |
{
|
| 1059 |
"epoch": 2.8437856328392246,
|
| 1060 |
+
"grad_norm": 0.2989479899406433,
|
| 1061 |
+
"learning_rate": 6.238034160452485e-05,
|
| 1062 |
+
"loss": 0.2128,
|
| 1063 |
"num_input_tokens_seen": 7656656,
|
| 1064 |
"step": 625
|
| 1065 |
},
|
| 1066 |
{
|
| 1067 |
"epoch": 2.8665906499429874,
|
| 1068 |
+
"grad_norm": 0.296024888753891,
|
| 1069 |
+
"learning_rate": 6.010835002329795e-05,
|
| 1070 |
+
"loss": 0.2083,
|
| 1071 |
"num_input_tokens_seen": 7717712,
|
| 1072 |
"step": 630
|
| 1073 |
},
|
| 1074 |
{
|
| 1075 |
"epoch": 2.88939566704675,
|
| 1076 |
+
"grad_norm": 0.4711114466190338,
|
| 1077 |
+
"learning_rate": 5.786809309654982e-05,
|
| 1078 |
+
"loss": 0.2067,
|
| 1079 |
"num_input_tokens_seen": 7779920,
|
| 1080 |
"step": 635
|
| 1081 |
},
|
| 1082 |
{
|
| 1083 |
"epoch": 2.912200684150513,
|
| 1084 |
+
"grad_norm": 0.4123808443546295,
|
| 1085 |
+
"learning_rate": 5.566036170729942e-05,
|
| 1086 |
+
"loss": 0.2089,
|
| 1087 |
"num_input_tokens_seen": 7840976,
|
| 1088 |
"step": 640
|
| 1089 |
},
|
| 1090 |
{
|
| 1091 |
"epoch": 2.935005701254276,
|
| 1092 |
+
"grad_norm": 0.4928493797779083,
|
| 1093 |
+
"learning_rate": 5.348593525600093e-05,
|
| 1094 |
+
"loss": 0.2105,
|
| 1095 |
"num_input_tokens_seen": 7902160,
|
| 1096 |
"step": 645
|
| 1097 |
},
|
| 1098 |
{
|
| 1099 |
"epoch": 2.9578107183580387,
|
| 1100 |
+
"grad_norm": 0.34217992424964905,
|
| 1101 |
+
"learning_rate": 5.1345581385390247e-05,
|
| 1102 |
+
"loss": 0.2029,
|
| 1103 |
"num_input_tokens_seen": 7963856,
|
| 1104 |
"step": 650
|
| 1105 |
},
|
| 1106 |
{
|
| 1107 |
"epoch": 2.9806157354618015,
|
| 1108 |
+
"grad_norm": 0.3095628023147583,
|
| 1109 |
+
"learning_rate": 4.924005570948228e-05,
|
| 1110 |
+
"loss": 0.2105,
|
| 1111 |
"num_input_tokens_seen": 8026448,
|
| 1112 |
"step": 655
|
| 1113 |
},
|
| 1114 |
{
|
| 1115 |
"epoch": 3.0,
|
| 1116 |
+
"grad_norm": 0.5380539894104004,
|
| 1117 |
+
"learning_rate": 4.7170101546814886e-05,
|
| 1118 |
+
"loss": 0.1806,
|
| 1119 |
"num_input_tokens_seen": 8078224,
|
| 1120 |
"step": 660
|
| 1121 |
},
|
| 1122 |
{
|
| 1123 |
"epoch": 3.022805017103763,
|
| 1124 |
+
"grad_norm": 0.40921372175216675,
|
| 1125 |
+
"learning_rate": 4.5136449658033155e-05,
|
| 1126 |
+
"loss": 0.1738,
|
| 1127 |
"num_input_tokens_seen": 8140176,
|
| 1128 |
"step": 665
|
| 1129 |
},
|
| 1130 |
{
|
| 1131 |
"epoch": 3.0456100342075256,
|
| 1132 |
+
"grad_norm": 0.2657362222671509,
|
| 1133 |
+
"learning_rate": 4.313981798790788e-05,
|
| 1134 |
+
"loss": 0.1637,
|
| 1135 |
"num_input_tokens_seen": 8201616,
|
| 1136 |
"step": 670
|
| 1137 |
},
|
| 1138 |
{
|
| 1139 |
"epoch": 3.0684150513112884,
|
| 1140 |
+
"grad_norm": 0.32306888699531555,
|
| 1141 |
+
"learning_rate": 4.118091141187711e-05,
|
| 1142 |
+
"loss": 0.1676,
|
| 1143 |
"num_input_tokens_seen": 8262928,
|
| 1144 |
"step": 675
|
| 1145 |
},
|
| 1146 |
{
|
| 1147 |
"epoch": 3.0912200684150513,
|
| 1148 |
+
"grad_norm": 0.3567180335521698,
|
| 1149 |
+
"learning_rate": 3.926042148720318e-05,
|
| 1150 |
+
"loss": 0.1642,
|
| 1151 |
"num_input_tokens_seen": 8324496,
|
| 1152 |
"step": 680
|
| 1153 |
},
|
| 1154 |
{
|
| 1155 |
"epoch": 3.114025085518814,
|
| 1156 |
+
"grad_norm": 0.45754119753837585,
|
| 1157 |
+
"learning_rate": 3.737902620882986e-05,
|
| 1158 |
+
"loss": 0.1694,
|
| 1159 |
"num_input_tokens_seen": 8385680,
|
| 1160 |
"step": 685
|
| 1161 |
},
|
| 1162 |
{
|
| 1163 |
"epoch": 3.136830102622577,
|
| 1164 |
+
"grad_norm": 0.3723002076148987,
|
| 1165 |
+
"learning_rate": 3.5537389770029046e-05,
|
| 1166 |
+
"loss": 0.1606,
|
| 1167 |
"num_input_tokens_seen": 8447632,
|
| 1168 |
"step": 690
|
| 1169 |
},
|
| 1170 |
{
|
| 1171 |
"epoch": 3.1596351197263397,
|
| 1172 |
+
"grad_norm": 0.33842238783836365,
|
| 1173 |
+
"learning_rate": 3.3736162327918357e-05,
|
| 1174 |
+
"loss": 0.1606,
|
| 1175 |
"num_input_tokens_seen": 8508432,
|
| 1176 |
"step": 695
|
| 1177 |
},
|
| 1178 |
{
|
| 1179 |
"epoch": 3.1824401368301025,
|
| 1180 |
+
"grad_norm": 0.361547589302063,
|
| 1181 |
+
"learning_rate": 3.197597977393532e-05,
|
| 1182 |
+
"loss": 0.1573,
|
| 1183 |
"num_input_tokens_seen": 8570128,
|
| 1184 |
"step": 700
|
| 1185 |
},
|
| 1186 |
{
|
| 1187 |
"epoch": 3.1824401368301025,
|
| 1188 |
+
"eval_loss": 0.23201464116573334,
|
| 1189 |
+
"eval_runtime": 33.776,
|
| 1190 |
+
"eval_samples_per_second": 92.314,
|
| 1191 |
+
"eval_steps_per_second": 5.773,
|
| 1192 |
"num_input_tokens_seen": 8570128,
|
| 1193 |
"step": 700
|
| 1194 |
},
|
| 1195 |
{
|
| 1196 |
"epoch": 3.2052451539338653,
|
| 1197 |
+
"grad_norm": 0.3323177993297577,
|
| 1198 |
+
"learning_rate": 3.02574635093466e-05,
|
| 1199 |
+
"loss": 0.1606,
|
| 1200 |
"num_input_tokens_seen": 8631952,
|
| 1201 |
"step": 705
|
| 1202 |
},
|
| 1203 |
{
|
| 1204 |
"epoch": 3.228050171037628,
|
| 1205 |
+
"grad_norm": 0.4198802709579468,
|
| 1206 |
+
"learning_rate": 2.8581220225873825e-05,
|
| 1207 |
+
"loss": 0.1588,
|
| 1208 |
"num_input_tokens_seen": 8694032,
|
| 1209 |
"step": 710
|
| 1210 |
},
|
| 1211 |
{
|
| 1212 |
"epoch": 3.250855188141391,
|
| 1213 |
+
"grad_norm": 0.41473400592803955,
|
| 1214 |
+
"learning_rate": 2.6947841691511313e-05,
|
| 1215 |
+
"loss": 0.1518,
|
| 1216 |
"num_input_tokens_seen": 8754576,
|
| 1217 |
"step": 715
|
| 1218 |
},
|
| 1219 |
{
|
| 1220 |
"epoch": 3.2736602052451538,
|
| 1221 |
+
"grad_norm": 0.30949723720550537,
|
| 1222 |
+
"learning_rate": 2.5357904541613345e-05,
|
| 1223 |
+
"loss": 0.1515,
|
| 1224 |
"num_input_tokens_seen": 8816528,
|
| 1225 |
"step": 720
|
| 1226 |
},
|
| 1227 |
{
|
| 1228 |
"epoch": 3.2964652223489166,
|
| 1229 |
+
"grad_norm": 0.30058419704437256,
|
| 1230 |
+
"learning_rate": 2.38119700753228e-05,
|
| 1231 |
+
"loss": 0.1575,
|
| 1232 |
"num_input_tokens_seen": 8877200,
|
| 1233 |
"step": 725
|
| 1234 |
},
|
| 1235 |
{
|
| 1236 |
"epoch": 3.3192702394526794,
|
| 1237 |
+
"grad_norm": 0.3597671091556549,
|
| 1238 |
+
"learning_rate": 2.2310584057414938e-05,
|
| 1239 |
+
"loss": 0.1545,
|
| 1240 |
"num_input_tokens_seen": 8938512,
|
| 1241 |
"step": 730
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
"epoch": 3.342075256556442,
|
| 1245 |
+
"grad_norm": 0.3647618889808655,
|
| 1246 |
+
"learning_rate": 2.0854276525624292e-05,
|
| 1247 |
+
"loss": 0.1504,
|
| 1248 |
"num_input_tokens_seen": 9000464,
|
| 1249 |
"step": 735
|
| 1250 |
},
|
| 1251 |
{
|
| 1252 |
"epoch": 3.364880273660205,
|
| 1253 |
+
"grad_norm": 0.36206144094467163,
|
| 1254 |
+
"learning_rate": 1.944356160352466e-05,
|
| 1255 |
+
"loss": 0.1534,
|
| 1256 |
"num_input_tokens_seen": 9061648,
|
| 1257 |
"step": 740
|
| 1258 |
},
|
| 1259 |
{
|
| 1260 |
"epoch": 3.387685290763968,
|
| 1261 |
+
"grad_norm": 0.37280526757240295,
|
| 1262 |
+
"learning_rate": 1.8078937319026654e-05,
|
| 1263 |
+
"loss": 0.1537,
|
| 1264 |
"num_input_tokens_seen": 9122704,
|
| 1265 |
"step": 745
|
| 1266 |
},
|
| 1267 |
{
|
| 1268 |
"epoch": 3.4104903078677307,
|
| 1269 |
+
"grad_norm": 0.4054957628250122,
|
| 1270 |
+
"learning_rate": 1.6760885428557858e-05,
|
| 1271 |
+
"loss": 0.149,
|
| 1272 |
"num_input_tokens_seen": 9183504,
|
| 1273 |
"step": 750
|
| 1274 |
},
|
| 1275 |
{
|
| 1276 |
"epoch": 3.433295324971494,
|
| 1277 |
+
"grad_norm": 0.4534494876861572,
|
| 1278 |
+
"learning_rate": 1.5489871246987224e-05,
|
| 1279 |
+
"loss": 0.1565,
|
| 1280 |
"num_input_tokens_seen": 9245072,
|
| 1281 |
"step": 755
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
"epoch": 3.4561003420752567,
|
| 1285 |
+
"grad_norm": 0.3463543653488159,
|
| 1286 |
+
"learning_rate": 1.4266343483353925e-05,
|
| 1287 |
+
"loss": 0.1502,
|
| 1288 |
"num_input_tokens_seen": 9307152,
|
| 1289 |
"step": 760
|
| 1290 |
},
|
| 1291 |
{
|
| 1292 |
"epoch": 3.4789053591790196,
|
| 1293 |
+
"grad_norm": 0.38458961248397827,
|
| 1294 |
+
"learning_rate": 1.3090734082458559e-05,
|
| 1295 |
+
"loss": 0.1501,
|
| 1296 |
"num_input_tokens_seen": 9369616,
|
| 1297 |
"step": 765
|
| 1298 |
},
|
| 1299 |
{
|
| 1300 |
"epoch": 3.5017103762827824,
|
| 1301 |
+
"grad_norm": 0.36486777663230896,
|
| 1302 |
+
"learning_rate": 1.1963458072372667e-05,
|
| 1303 |
+
"loss": 0.1536,
|
| 1304 |
"num_input_tokens_seen": 9431568,
|
| 1305 |
"step": 770
|
| 1306 |
},
|
| 1307 |
{
|
| 1308 |
"epoch": 3.524515393386545,
|
| 1309 |
+
"grad_norm": 0.3857269287109375,
|
| 1310 |
+
"learning_rate": 1.0884913417920476e-05,
|
| 1311 |
+
"loss": 0.1521,
|
| 1312 |
"num_input_tokens_seen": 9493264,
|
| 1313 |
"step": 775
|
| 1314 |
},
|
| 1315 |
{
|
| 1316 |
"epoch": 3.547320410490308,
|
| 1317 |
+
"grad_norm": 0.3137882649898529,
|
| 1318 |
+
"learning_rate": 9.85548088018447e-06,
|
| 1319 |
+
"loss": 0.1476,
|
| 1320 |
"num_input_tokens_seen": 9554448,
|
| 1321 |
"step": 780
|
| 1322 |
},
|
| 1323 |
{
|
| 1324 |
"epoch": 3.570125427594071,
|
| 1325 |
+
"grad_norm": 0.3451816439628601,
|
| 1326 |
+
"learning_rate": 8.875523882084351e-06,
|
| 1327 |
+
"loss": 0.1541,
|
| 1328 |
"num_input_tokens_seen": 9615760,
|
| 1329 |
"step": 785
|
| 1330 |
},
|
| 1331 |
{
|
| 1332 |
"epoch": 3.5929304446978336,
|
| 1333 |
+
"grad_norm": 0.3642246425151825,
|
| 1334 |
+
"learning_rate": 7.945388380077121e-06,
|
| 1335 |
+
"loss": 0.1599,
|
| 1336 |
"num_input_tokens_seen": 9678608,
|
| 1337 |
"step": 790
|
| 1338 |
},
|
| 1339 |
{
|
| 1340 |
"epoch": 3.6157354618015964,
|
| 1341 |
+
"grad_norm": 0.3282772898674011,
|
| 1342 |
+
"learning_rate": 7.065402742023218e-06,
|
| 1343 |
+
"loss": 0.1516,
|
| 1344 |
"num_input_tokens_seen": 9740304,
|
| 1345 |
"step": 795
|
| 1346 |
},
|
| 1347 |
{
|
| 1348 |
"epoch": 3.6385404789053593,
|
| 1349 |
+
"grad_norm": 0.3353286385536194,
|
| 1350 |
+
"learning_rate": 6.235877631262093e-06,
|
| 1351 |
+
"loss": 0.1488,
|
| 1352 |
"num_input_tokens_seen": 9801744,
|
| 1353 |
"step": 800
|
| 1354 |
},
|
| 1355 |
{
|
| 1356 |
"epoch": 3.6385404789053593,
|
| 1357 |
+
"eval_loss": 0.22533652186393738,
|
| 1358 |
+
"eval_runtime": 33.8161,
|
| 1359 |
+
"eval_samples_per_second": 92.205,
|
| 1360 |
+
"eval_steps_per_second": 5.766,
|
| 1361 |
"num_input_tokens_seen": 9801744,
|
| 1362 |
"step": 800
|
| 1363 |
},
|
| 1364 |
{
|
| 1365 |
"epoch": 3.661345496009122,
|
| 1366 |
+
"grad_norm": 0.37417271733283997,
|
| 1367 |
+
"learning_rate": 5.457105896937997e-06,
|
| 1368 |
+
"loss": 0.1474,
|
| 1369 |
"num_input_tokens_seen": 9862928,
|
| 1370 |
"step": 805
|
| 1371 |
},
|
| 1372 |
{
|
| 1373 |
"epoch": 3.684150513112885,
|
| 1374 |
+
"grad_norm": 0.35965585708618164,
|
| 1375 |
+
"learning_rate": 4.729362470614812e-06,
|
| 1376 |
+
"loss": 0.1515,
|
| 1377 |
"num_input_tokens_seen": 9924112,
|
| 1378 |
"step": 810
|
| 1379 |
},
|
| 1380 |
{
|
| 1381 |
"epoch": 3.7069555302166477,
|
| 1382 |
+
"grad_norm": 0.3677230775356293,
|
| 1383 |
+
"learning_rate": 4.052904269216273e-06,
|
| 1384 |
+
"loss": 0.1426,
|
| 1385 |
"num_input_tokens_seen": 9984784,
|
| 1386 |
"step": 815
|
| 1387 |
},
|
| 1388 |
{
|
| 1389 |
"epoch": 3.7297605473204105,
|
| 1390 |
+
"grad_norm": 0.39658358693122864,
|
| 1391 |
+
"learning_rate": 3.4279701043260886e-06,
|
| 1392 |
+
"loss": 0.1492,
|
| 1393 |
"num_input_tokens_seen": 10046736,
|
| 1394 |
"step": 820
|
| 1395 |
},
|
| 1396 |
{
|
| 1397 |
"epoch": 3.7525655644241733,
|
| 1398 |
+
"grad_norm": 0.33549442887306213,
|
| 1399 |
+
"learning_rate": 2.8547805978796136e-06,
|
| 1400 |
+
"loss": 0.1497,
|
| 1401 |
"num_input_tokens_seen": 10108176,
|
| 1402 |
"step": 825
|
| 1403 |
},
|
| 1404 |
{
|
| 1405 |
"epoch": 3.775370581527936,
|
| 1406 |
+
"grad_norm": 0.3981316387653351,
|
| 1407 |
+
"learning_rate": 2.3335381042773825e-06,
|
| 1408 |
+
"loss": 0.1498,
|
| 1409 |
"num_input_tokens_seen": 10169744,
|
| 1410 |
"step": 830
|
| 1411 |
},
|
| 1412 |
{
|
| 1413 |
"epoch": 3.798175598631699,
|
| 1414 |
+
"grad_norm": 0.3489813804626465,
|
| 1415 |
+
"learning_rate": 1.864426638947225e-06,
|
| 1416 |
+
"loss": 0.1444,
|
| 1417 |
"num_input_tokens_seen": 10231696,
|
| 1418 |
"step": 835
|
| 1419 |
},
|
| 1420 |
{
|
| 1421 |
"epoch": 3.8209806157354618,
|
| 1422 |
+
"grad_norm": 0.4486742913722992,
|
| 1423 |
+
"learning_rate": 1.447611813381111e-06,
|
| 1424 |
+
"loss": 0.1485,
|
| 1425 |
"num_input_tokens_seen": 10292624,
|
| 1426 |
"step": 840
|
| 1427 |
},
|
| 1428 |
{
|
| 1429 |
"epoch": 3.8437856328392246,
|
| 1430 |
+
"grad_norm": 0.37580201029777527,
|
| 1431 |
+
"learning_rate": 1.0832407766687534e-06,
|
| 1432 |
+
"loss": 0.1471,
|
| 1433 |
"num_input_tokens_seen": 10353040,
|
| 1434 |
"step": 845
|
| 1435 |
},
|
| 1436 |
{
|
| 1437 |
"epoch": 3.8665906499429874,
|
| 1438 |
+
"grad_norm": 0.36614516377449036,
|
| 1439 |
+
"learning_rate": 7.714421635494295e-07,
|
| 1440 |
+
"loss": 0.1504,
|
| 1441 |
"num_input_tokens_seen": 10414480,
|
| 1442 |
"step": 850
|
| 1443 |
},
|
| 1444 |
{
|
| 1445 |
"epoch": 3.88939566704675,
|
| 1446 |
+
"grad_norm": 0.36510002613067627,
|
| 1447 |
+
"learning_rate": 5.123260489995229e-07,
|
| 1448 |
+
"loss": 0.1514,
|
| 1449 |
"num_input_tokens_seen": 10476432,
|
| 1450 |
"step": 855
|
| 1451 |
},
|
| 1452 |
{
|
| 1453 |
"epoch": 3.912200684150513,
|
| 1454 |
+
"grad_norm": 0.3150339722633362,
|
| 1455 |
+
"learning_rate": 3.059839093727423e-07,
|
| 1456 |
+
"loss": 0.1417,
|
| 1457 |
"num_input_tokens_seen": 10538128,
|
| 1458 |
"step": 860
|
| 1459 |
},
|
| 1460 |
{
|
| 1461 |
"epoch": 3.935005701254276,
|
| 1462 |
+
"grad_norm": 0.4335091710090637,
|
| 1463 |
+
"learning_rate": 1.5248859010585369e-07,
|
| 1464 |
+
"loss": 0.1442,
|
| 1465 |
"num_input_tokens_seen": 10600080,
|
| 1466 |
"step": 865
|
| 1467 |
},
|
| 1468 |
{
|
| 1469 |
"epoch": 3.9578107183580387,
|
| 1470 |
+
"grad_norm": 0.33608052134513855,
|
| 1471 |
+
"learning_rate": 5.1894280001968383e-08,
|
| 1472 |
+
"loss": 0.1545,
|
| 1473 |
"num_input_tokens_seen": 10660752,
|
| 1474 |
"step": 870
|
| 1475 |
},
|
| 1476 |
{
|
| 1477 |
"epoch": 3.9806157354618015,
|
| 1478 |
+
"grad_norm": 0.3944770395755768,
|
| 1479 |
+
"learning_rate": 4.236492100095912e-09,
|
| 1480 |
+
"loss": 0.1468,
|
| 1481 |
"num_input_tokens_seen": 10721680,
|
| 1482 |
"step": 875
|
| 1483 |
},
|
| 1484 |
{
|
| 1485 |
+
"epoch": 3.9851767388825543,
|
| 1486 |
+
"num_input_tokens_seen": 10733712,
|
| 1487 |
+
"step": 876,
|
| 1488 |
+
"total_flos": 4.35826368961708e+17,
|
| 1489 |
+
"train_loss": 0.4072538570726299,
|
| 1490 |
+
"train_runtime": 4401.9239,
|
| 1491 |
+
"train_samples_per_second": 25.496,
|
| 1492 |
+
"train_steps_per_second": 0.199
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1493 |
}
|
| 1494 |
],
|
| 1495 |
"logging_steps": 5,
|
| 1496 |
+
"max_steps": 876,
|
| 1497 |
+
"num_input_tokens_seen": 10733712,
|
| 1498 |
+
"num_train_epochs": 4,
|
| 1499 |
"save_steps": 3000,
|
| 1500 |
"stateful_callbacks": {
|
| 1501 |
"TrainerControl": {
|
|
|
|
| 1509 |
"attributes": {}
|
| 1510 |
}
|
| 1511 |
},
|
| 1512 |
+
"total_flos": 4.35826368961708e+17,
|
| 1513 |
"train_batch_size": 16,
|
| 1514 |
"trial_name": null,
|
| 1515 |
"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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa1e0664877bfd3e60ffadd0a5980c4aa10cf847bec512de8baf0384073aad2a
|
| 3 |
+
size 5752
|
training_eval_loss.png
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
training_loss.png
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|