Model save
Browse files- README.md +28 -12
- all_results.json +5 -5
- config.json +1 -1
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
- runs/Sep27_17-24-19_action-graph-trainer/events.out.tfevents.1727460461.action-graph-trainer.379760.0 +3 -0
- runs/Sep27_20-11-03_action-graph-trainer/events.out.tfevents.1727468262.action-graph-trainer.430650.0 +3 -0
- tokenizer.json +1 -1
- train_results.json +5 -5
- trainer_state.json +853 -685
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -3,15 +3,10 @@ library_name: transformers
|
|
| 3 |
license: llama3.2
|
| 4 |
base_model: tanliboy/llama-3.2-3b
|
| 5 |
tags:
|
| 6 |
-
- alignment-handbook
|
| 7 |
-
- trl
|
| 8 |
-
- sft
|
| 9 |
-
- generated_from_trainer
|
| 10 |
- trl
|
| 11 |
- sft
|
|
|
|
| 12 |
- generated_from_trainer
|
| 13 |
-
datasets:
|
| 14 |
-
- tanliboy/OpenHermes-2.5-reformat
|
| 15 |
model-index:
|
| 16 |
- name: llama-3.2-3b-sft
|
| 17 |
results: []
|
|
@@ -22,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 22 |
|
| 23 |
# llama-3.2-3b-sft
|
| 24 |
|
| 25 |
-
This model is a fine-tuned version of [tanliboy/llama-3.2-3b](https://huggingface.co/tanliboy/llama-3.2-3b) on
|
| 26 |
It achieves the following results on the evaluation set:
|
| 27 |
-
- Loss: 0.
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
@@ -43,7 +38,7 @@ More information needed
|
|
| 43 |
### Training hyperparameters
|
| 44 |
|
| 45 |
The following hyperparameters were used during training:
|
| 46 |
-
- learning_rate:
|
| 47 |
- train_batch_size: 8
|
| 48 |
- eval_batch_size: 8
|
| 49 |
- seed: 42
|
|
@@ -59,9 +54,30 @@ The following hyperparameters were used during training:
|
|
| 59 |
|
| 60 |
### Training results
|
| 61 |
|
| 62 |
-
| Training Loss | Epoch
|
| 63 |
-
|
| 64 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65 |
|
| 66 |
|
| 67 |
### Framework versions
|
|
|
|
| 3 |
license: llama3.2
|
| 4 |
base_model: tanliboy/llama-3.2-3b
|
| 5 |
tags:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
- trl
|
| 7 |
- sft
|
| 8 |
+
- alignment-handbook
|
| 9 |
- generated_from_trainer
|
|
|
|
|
|
|
| 10 |
model-index:
|
| 11 |
- name: llama-3.2-3b-sft
|
| 12 |
results: []
|
|
|
|
| 17 |
|
| 18 |
# llama-3.2-3b-sft
|
| 19 |
|
| 20 |
+
This model is a fine-tuned version of [tanliboy/llama-3.2-3b](https://huggingface.co/tanliboy/llama-3.2-3b) on an unknown dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.7216
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 38 |
### Training hyperparameters
|
| 39 |
|
| 40 |
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 3e-06
|
| 42 |
- train_batch_size: 8
|
| 43 |
- eval_batch_size: 8
|
| 44 |
- seed: 42
|
|
|
|
| 54 |
|
| 55 |
### Training results
|
| 56 |
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 58 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 59 |
+
| 0.8741 | 0.0448 | 100 | 0.8600 |
|
| 60 |
+
| 0.8038 | 0.0897 | 200 | 0.8095 |
|
| 61 |
+
| 0.7937 | 0.1345 | 300 | 0.7789 |
|
| 62 |
+
| 0.7712 | 0.1794 | 400 | 0.7644 |
|
| 63 |
+
| 0.7393 | 0.2242 | 500 | 0.7565 |
|
| 64 |
+
| 0.7458 | 0.2691 | 600 | 0.7506 |
|
| 65 |
+
| 0.7694 | 0.3139 | 700 | 0.7458 |
|
| 66 |
+
| 0.713 | 0.3587 | 800 | 0.7422 |
|
| 67 |
+
| 0.7347 | 0.4036 | 900 | 0.7387 |
|
| 68 |
+
| 0.7243 | 0.4484 | 1000 | 0.7356 |
|
| 69 |
+
| 0.7161 | 0.4933 | 1100 | 0.7331 |
|
| 70 |
+
| 0.7247 | 0.5381 | 1200 | 0.7308 |
|
| 71 |
+
| 0.7477 | 0.5830 | 1300 | 0.7288 |
|
| 72 |
+
| 0.7429 | 0.6278 | 1400 | 0.7273 |
|
| 73 |
+
| 0.7317 | 0.6726 | 1500 | 0.7256 |
|
| 74 |
+
| 0.7226 | 0.7175 | 1600 | 0.7243 |
|
| 75 |
+
| 0.695 | 0.7623 | 1700 | 0.7234 |
|
| 76 |
+
| 0.7167 | 0.8072 | 1800 | 0.7226 |
|
| 77 |
+
| 0.686 | 0.8520 | 1900 | 0.7221 |
|
| 78 |
+
| 0.7214 | 0.8969 | 2000 | 0.7218 |
|
| 79 |
+
| 0.7358 | 0.9417 | 2100 | 0.7216 |
|
| 80 |
+
| 0.7259 | 0.9865 | 2200 | 0.7216 |
|
| 81 |
|
| 82 |
|
| 83 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -5,10 +5,10 @@
|
|
| 5 |
"eval_samples": 50077,
|
| 6 |
"eval_samples_per_second": 132.107,
|
| 7 |
"eval_steps_per_second": 2.066,
|
| 8 |
-
"total_flos":
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
"train_samples": 285435,
|
| 12 |
-
"train_samples_per_second":
|
| 13 |
-
"train_steps_per_second": 0.
|
| 14 |
}
|
|
|
|
| 5 |
"eval_samples": 50077,
|
| 6 |
"eval_samples_per_second": 132.107,
|
| 7 |
"eval_steps_per_second": 2.066,
|
| 8 |
+
"total_flos": 250303561007104.0,
|
| 9 |
+
"train_loss": 0.7492096503219262,
|
| 10 |
+
"train_runtime": 18007.2993,
|
| 11 |
"train_samples": 285435,
|
| 12 |
+
"train_samples_per_second": 15.851,
|
| 13 |
+
"train_steps_per_second": 0.124
|
| 14 |
}
|
config.json
CHANGED
|
@@ -35,6 +35,6 @@
|
|
| 35 |
"tie_word_embeddings": true,
|
| 36 |
"torch_dtype": "bfloat16",
|
| 37 |
"transformers_version": "4.44.2",
|
| 38 |
-
"use_cache":
|
| 39 |
"vocab_size": 128256
|
| 40 |
}
|
|
|
|
| 35 |
"tie_word_embeddings": true,
|
| 36 |
"torch_dtype": "bfloat16",
|
| 37 |
"transformers_version": "4.44.2",
|
| 38 |
+
"use_cache": false,
|
| 39 |
"vocab_size": 128256
|
| 40 |
}
|
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4965799096
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09efa89e7b43c24e8c1ab73f7e09196edd014cf14482fe5101aaf902a586d7f2
|
| 3 |
size 4965799096
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1459729952
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c08bcfff732c5238b56bd7df4c0e2c63a0a02d0592c022ee16a201dab2ea9820
|
| 3 |
size 1459729952
|
runs/Sep27_17-24-19_action-graph-trainer/events.out.tfevents.1727460461.action-graph-trainer.379760.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8664a4d576b88a2be33c4a2390982c36adcdf3a6711e183eecfb35752a6285e
|
| 3 |
+
size 29491
|
runs/Sep27_20-11-03_action-graph-trainer/events.out.tfevents.1727468262.action-graph-trainer.430650.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6c18947c9ba2697ba326b828d36458b2b45f1b8572f03289d81b56f7df7627a
|
| 3 |
+
size 59321
|
tokenizer.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
-
"max_length":
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
|
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
+
"max_length": 4096,
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
train_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
"train_samples": 285435,
|
| 7 |
-
"train_samples_per_second":
|
| 8 |
-
"train_steps_per_second": 0.
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"total_flos": 250303561007104.0,
|
| 4 |
+
"train_loss": 0.7492096503219262,
|
| 5 |
+
"train_runtime": 18007.2993,
|
| 6 |
"train_samples": 285435,
|
| 7 |
+
"train_samples_per_second": 15.851,
|
| 8 |
+
"train_steps_per_second": 0.124
|
| 9 |
}
|
trainer_state.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 1.0,
|
| 5 |
-
"eval_steps":
|
| 6 |
"global_step": 2230,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
|
@@ -10,1588 +10,1756 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.0004484304932735426,
|
| 13 |
-
"grad_norm": 4.
|
| 14 |
-
"learning_rate":
|
| 15 |
"loss": 0.9912,
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.004484304932735426,
|
| 20 |
-
"grad_norm": 5.
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss": 1.
|
| 23 |
"step": 10
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.008968609865470852,
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss": 1.
|
| 30 |
"step": 20
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.013452914798206279,
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss":
|
| 37 |
"step": 30
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.017937219730941704,
|
| 41 |
-
"grad_norm":
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss":
|
| 44 |
"step": 40
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.02242152466367713,
|
| 48 |
-
"grad_norm":
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 50
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.026905829596412557,
|
| 55 |
-
"grad_norm":
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 60
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.03139013452914798,
|
| 62 |
-
"grad_norm": 1.
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 70
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.03587443946188341,
|
| 69 |
-
"grad_norm": 1.
|
| 70 |
-
"learning_rate":
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 80
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.04035874439461883,
|
| 76 |
-
"grad_norm": 1.
|
| 77 |
-
"learning_rate":
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 90
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.04484304932735426,
|
| 83 |
-
"grad_norm": 1.
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 86 |
"step": 100
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.04932735426008968,
|
| 90 |
-
"grad_norm": 1.
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 110
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.053811659192825115,
|
| 97 |
-
"grad_norm": 1.
|
| 98 |
-
"learning_rate":
|
| 99 |
-
"loss": 0.
|
| 100 |
"step": 120
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.05829596412556054,
|
| 104 |
-
"grad_norm": 1.
|
| 105 |
-
"learning_rate":
|
| 106 |
-
"loss": 0.
|
| 107 |
"step": 130
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.06278026905829596,
|
| 111 |
-
"grad_norm": 1.
|
| 112 |
-
"learning_rate":
|
| 113 |
-
"loss": 0.
|
| 114 |
"step": 140
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.06726457399103139,
|
| 118 |
-
"grad_norm": 1.
|
| 119 |
-
"learning_rate":
|
| 120 |
-
"loss": 0.
|
| 121 |
"step": 150
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.07174887892376682,
|
| 125 |
-
"grad_norm": 1.
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 160
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.07623318385650224,
|
| 132 |
-
"grad_norm": 1.
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 170
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.08071748878923767,
|
| 139 |
-
"grad_norm": 1.
|
| 140 |
-
"learning_rate":
|
| 141 |
-
"loss": 0.
|
| 142 |
"step": 180
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.08520179372197309,
|
| 146 |
-
"grad_norm": 1.
|
| 147 |
-
"learning_rate":
|
| 148 |
-
"loss": 0.
|
| 149 |
"step": 190
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.08968609865470852,
|
| 153 |
-
"grad_norm": 1.
|
| 154 |
-
"learning_rate":
|
| 155 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 156 |
"step": 200
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 0.09417040358744394,
|
| 160 |
-
"grad_norm": 1.
|
| 161 |
-
"learning_rate":
|
| 162 |
-
"loss": 0.
|
| 163 |
"step": 210
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 0.09865470852017937,
|
| 167 |
-
"grad_norm": 1.
|
| 168 |
-
"learning_rate":
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 220
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.1031390134529148,
|
| 174 |
-
"grad_norm": 1.
|
| 175 |
-
"learning_rate":
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 230
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.10762331838565023,
|
| 181 |
-
"grad_norm": 1.
|
| 182 |
-
"learning_rate":
|
| 183 |
-
"loss": 0.
|
| 184 |
"step": 240
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 0.11210762331838565,
|
| 188 |
-
"grad_norm": 1.
|
| 189 |
-
"learning_rate":
|
| 190 |
-
"loss": 0.
|
| 191 |
"step": 250
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 0.11659192825112108,
|
| 195 |
-
"grad_norm": 1.
|
| 196 |
-
"learning_rate":
|
| 197 |
-
"loss": 0.
|
| 198 |
"step": 260
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 0.1210762331838565,
|
| 202 |
-
"grad_norm": 1.
|
| 203 |
-
"learning_rate":
|
| 204 |
-
"loss": 0.
|
| 205 |
"step": 270
|
| 206 |
},
|
| 207 |
{
|
| 208 |
"epoch": 0.12556053811659193,
|
| 209 |
-
"grad_norm": 1.
|
| 210 |
-
"learning_rate":
|
| 211 |
-
"loss": 0.
|
| 212 |
"step": 280
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 0.13004484304932734,
|
| 216 |
-
"grad_norm": 1.
|
| 217 |
-
"learning_rate":
|
| 218 |
-
"loss": 0.
|
| 219 |
"step": 290
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.13452914798206278,
|
| 223 |
-
"grad_norm": 1.
|
| 224 |
-
"learning_rate":
|
| 225 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 226 |
"step": 300
|
| 227 |
},
|
| 228 |
{
|
| 229 |
"epoch": 0.13901345291479822,
|
| 230 |
-
"grad_norm": 1.
|
| 231 |
-
"learning_rate":
|
| 232 |
-
"loss": 0.
|
| 233 |
"step": 310
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 0.14349775784753363,
|
| 237 |
-
"grad_norm":
|
| 238 |
-
"learning_rate":
|
| 239 |
-
"loss": 0.
|
| 240 |
"step": 320
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 0.14798206278026907,
|
| 244 |
-
"grad_norm": 1.
|
| 245 |
-
"learning_rate":
|
| 246 |
-
"loss": 0.
|
| 247 |
"step": 330
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"epoch": 0.15246636771300448,
|
| 251 |
-
"grad_norm": 1.
|
| 252 |
-
"learning_rate":
|
| 253 |
-
"loss": 0.
|
| 254 |
"step": 340
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 0.15695067264573992,
|
| 258 |
-
"grad_norm": 1.
|
| 259 |
-
"learning_rate":
|
| 260 |
-
"loss": 0.
|
| 261 |
"step": 350
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 0.16143497757847533,
|
| 265 |
-
"grad_norm": 1.
|
| 266 |
-
"learning_rate":
|
| 267 |
-
"loss": 0.
|
| 268 |
"step": 360
|
| 269 |
},
|
| 270 |
{
|
| 271 |
"epoch": 0.16591928251121077,
|
| 272 |
-
"grad_norm": 1.
|
| 273 |
-
"learning_rate":
|
| 274 |
-
"loss": 0.
|
| 275 |
"step": 370
|
| 276 |
},
|
| 277 |
{
|
| 278 |
"epoch": 0.17040358744394618,
|
| 279 |
-
"grad_norm": 1.
|
| 280 |
-
"learning_rate":
|
| 281 |
-
"loss": 0.
|
| 282 |
"step": 380
|
| 283 |
},
|
| 284 |
{
|
| 285 |
"epoch": 0.17488789237668162,
|
| 286 |
-
"grad_norm": 1.
|
| 287 |
-
"learning_rate":
|
| 288 |
-
"loss": 0.
|
| 289 |
"step": 390
|
| 290 |
},
|
| 291 |
{
|
| 292 |
"epoch": 0.17937219730941703,
|
| 293 |
-
"grad_norm": 1.
|
| 294 |
-
"learning_rate":
|
| 295 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 296 |
"step": 400
|
| 297 |
},
|
| 298 |
{
|
| 299 |
"epoch": 0.18385650224215247,
|
| 300 |
-
"grad_norm": 1.
|
| 301 |
-
"learning_rate":
|
| 302 |
-
"loss": 0.
|
| 303 |
"step": 410
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 0.18834080717488788,
|
| 307 |
-
"grad_norm": 1.
|
| 308 |
-
"learning_rate":
|
| 309 |
-
"loss": 0.
|
| 310 |
"step": 420
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"epoch": 0.19282511210762332,
|
| 314 |
-
"grad_norm": 1.
|
| 315 |
-
"learning_rate":
|
| 316 |
-
"loss": 0.
|
| 317 |
"step": 430
|
| 318 |
},
|
| 319 |
{
|
| 320 |
"epoch": 0.19730941704035873,
|
| 321 |
-
"grad_norm": 1.
|
| 322 |
-
"learning_rate":
|
| 323 |
-
"loss": 0.
|
| 324 |
"step": 440
|
| 325 |
},
|
| 326 |
{
|
| 327 |
"epoch": 0.20179372197309417,
|
| 328 |
-
"grad_norm": 1.
|
| 329 |
-
"learning_rate":
|
| 330 |
-
"loss": 0.
|
| 331 |
"step": 450
|
| 332 |
},
|
| 333 |
{
|
| 334 |
"epoch": 0.2062780269058296,
|
| 335 |
-
"grad_norm": 1.
|
| 336 |
-
"learning_rate":
|
| 337 |
-
"loss": 0.
|
| 338 |
"step": 460
|
| 339 |
},
|
| 340 |
{
|
| 341 |
"epoch": 0.21076233183856502,
|
| 342 |
-
"grad_norm": 1.
|
| 343 |
-
"learning_rate":
|
| 344 |
-
"loss": 0.
|
| 345 |
"step": 470
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 0.21524663677130046,
|
| 349 |
-
"grad_norm": 1.
|
| 350 |
-
"learning_rate":
|
| 351 |
-
"loss": 0.
|
| 352 |
"step": 480
|
| 353 |
},
|
| 354 |
{
|
| 355 |
"epoch": 0.21973094170403587,
|
| 356 |
-
"grad_norm": 1.
|
| 357 |
-
"learning_rate":
|
| 358 |
-
"loss": 0.
|
| 359 |
"step": 490
|
| 360 |
},
|
| 361 |
{
|
| 362 |
"epoch": 0.2242152466367713,
|
| 363 |
-
"grad_norm": 1.
|
| 364 |
-
"learning_rate":
|
| 365 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 366 |
"step": 500
|
| 367 |
},
|
| 368 |
{
|
| 369 |
"epoch": 0.22869955156950672,
|
| 370 |
-
"grad_norm": 1.
|
| 371 |
-
"learning_rate":
|
| 372 |
-
"loss": 0.
|
| 373 |
"step": 510
|
| 374 |
},
|
| 375 |
{
|
| 376 |
"epoch": 0.23318385650224216,
|
| 377 |
-
"grad_norm": 1.
|
| 378 |
-
"learning_rate":
|
| 379 |
-
"loss": 0.
|
| 380 |
"step": 520
|
| 381 |
},
|
| 382 |
{
|
| 383 |
"epoch": 0.23766816143497757,
|
| 384 |
-
"grad_norm": 1.
|
| 385 |
-
"learning_rate":
|
| 386 |
-
"loss": 0.
|
| 387 |
"step": 530
|
| 388 |
},
|
| 389 |
{
|
| 390 |
"epoch": 0.242152466367713,
|
| 391 |
-
"grad_norm": 1.
|
| 392 |
-
"learning_rate":
|
| 393 |
-
"loss": 0.
|
| 394 |
"step": 540
|
| 395 |
},
|
| 396 |
{
|
| 397 |
"epoch": 0.24663677130044842,
|
| 398 |
-
"grad_norm": 1.
|
| 399 |
-
"learning_rate":
|
| 400 |
-
"loss": 0.
|
| 401 |
"step": 550
|
| 402 |
},
|
| 403 |
{
|
| 404 |
"epoch": 0.25112107623318386,
|
| 405 |
-
"grad_norm": 1.
|
| 406 |
-
"learning_rate":
|
| 407 |
-
"loss": 0.
|
| 408 |
"step": 560
|
| 409 |
},
|
| 410 |
{
|
| 411 |
"epoch": 0.2556053811659193,
|
| 412 |
-
"grad_norm": 1.
|
| 413 |
-
"learning_rate":
|
| 414 |
-
"loss": 0.
|
| 415 |
"step": 570
|
| 416 |
},
|
| 417 |
{
|
| 418 |
"epoch": 0.2600896860986547,
|
| 419 |
-
"grad_norm": 1.
|
| 420 |
-
"learning_rate":
|
| 421 |
-
"loss": 0.
|
| 422 |
"step": 580
|
| 423 |
},
|
| 424 |
{
|
| 425 |
"epoch": 0.2645739910313901,
|
| 426 |
-
"grad_norm": 1.
|
| 427 |
-
"learning_rate":
|
| 428 |
-
"loss": 0.
|
| 429 |
"step": 590
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 0.26905829596412556,
|
| 433 |
-
"grad_norm": 1.
|
| 434 |
-
"learning_rate":
|
| 435 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 436 |
"step": 600
|
| 437 |
},
|
| 438 |
{
|
| 439 |
"epoch": 0.273542600896861,
|
| 440 |
-
"grad_norm": 1.
|
| 441 |
-
"learning_rate":
|
| 442 |
-
"loss": 0.
|
| 443 |
"step": 610
|
| 444 |
},
|
| 445 |
{
|
| 446 |
"epoch": 0.27802690582959644,
|
| 447 |
-
"grad_norm": 1.
|
| 448 |
-
"learning_rate":
|
| 449 |
-
"loss": 0.
|
| 450 |
"step": 620
|
| 451 |
},
|
| 452 |
{
|
| 453 |
"epoch": 0.2825112107623318,
|
| 454 |
-
"grad_norm": 1.
|
| 455 |
-
"learning_rate":
|
| 456 |
-
"loss": 0.
|
| 457 |
"step": 630
|
| 458 |
},
|
| 459 |
{
|
| 460 |
"epoch": 0.28699551569506726,
|
| 461 |
-
"grad_norm": 1.
|
| 462 |
-
"learning_rate":
|
| 463 |
-
"loss": 0.
|
| 464 |
"step": 640
|
| 465 |
},
|
| 466 |
{
|
| 467 |
"epoch": 0.2914798206278027,
|
| 468 |
-
"grad_norm": 1.
|
| 469 |
-
"learning_rate":
|
| 470 |
-
"loss": 0.
|
| 471 |
"step": 650
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 0.29596412556053814,
|
| 475 |
-
"grad_norm": 1.
|
| 476 |
-
"learning_rate":
|
| 477 |
-
"loss": 0.
|
| 478 |
"step": 660
|
| 479 |
},
|
| 480 |
{
|
| 481 |
"epoch": 0.3004484304932735,
|
| 482 |
-
"grad_norm": 1.
|
| 483 |
-
"learning_rate":
|
| 484 |
-
"loss": 0.
|
| 485 |
"step": 670
|
| 486 |
},
|
| 487 |
{
|
| 488 |
"epoch": 0.30493273542600896,
|
| 489 |
-
"grad_norm": 1.
|
| 490 |
-
"learning_rate":
|
| 491 |
-
"loss": 0.
|
| 492 |
"step": 680
|
| 493 |
},
|
| 494 |
{
|
| 495 |
"epoch": 0.3094170403587444,
|
| 496 |
-
"grad_norm": 1.
|
| 497 |
-
"learning_rate":
|
| 498 |
-
"loss": 0.
|
| 499 |
"step": 690
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"epoch": 0.31390134529147984,
|
| 503 |
-
"grad_norm": 1.
|
| 504 |
-
"learning_rate":
|
| 505 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 506 |
"step": 700
|
| 507 |
},
|
| 508 |
{
|
| 509 |
"epoch": 0.3183856502242152,
|
| 510 |
-
"grad_norm": 1.
|
| 511 |
-
"learning_rate":
|
| 512 |
-
"loss": 0.
|
| 513 |
"step": 710
|
| 514 |
},
|
| 515 |
{
|
| 516 |
"epoch": 0.32286995515695066,
|
| 517 |
-
"grad_norm": 1.
|
| 518 |
-
"learning_rate":
|
| 519 |
-
"loss": 0.
|
| 520 |
"step": 720
|
| 521 |
},
|
| 522 |
{
|
| 523 |
"epoch": 0.3273542600896861,
|
| 524 |
-
"grad_norm": 1.
|
| 525 |
-
"learning_rate":
|
| 526 |
-
"loss": 0.
|
| 527 |
"step": 730
|
| 528 |
},
|
| 529 |
{
|
| 530 |
"epoch": 0.33183856502242154,
|
| 531 |
-
"grad_norm": 1.
|
| 532 |
-
"learning_rate":
|
| 533 |
-
"loss": 0.
|
| 534 |
"step": 740
|
| 535 |
},
|
| 536 |
{
|
| 537 |
"epoch": 0.336322869955157,
|
| 538 |
-
"grad_norm": 1.
|
| 539 |
-
"learning_rate":
|
| 540 |
-
"loss": 0.
|
| 541 |
"step": 750
|
| 542 |
},
|
| 543 |
{
|
| 544 |
"epoch": 0.34080717488789236,
|
| 545 |
-
"grad_norm": 1.
|
| 546 |
-
"learning_rate":
|
| 547 |
-
"loss": 0.
|
| 548 |
"step": 760
|
| 549 |
},
|
| 550 |
{
|
| 551 |
"epoch": 0.3452914798206278,
|
| 552 |
-
"grad_norm": 1.
|
| 553 |
-
"learning_rate":
|
| 554 |
-
"loss": 0.
|
| 555 |
"step": 770
|
| 556 |
},
|
| 557 |
{
|
| 558 |
"epoch": 0.34977578475336324,
|
| 559 |
-
"grad_norm": 1.
|
| 560 |
-
"learning_rate":
|
| 561 |
-
"loss": 0.
|
| 562 |
"step": 780
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"epoch": 0.3542600896860987,
|
| 566 |
-
"grad_norm": 1.
|
| 567 |
-
"learning_rate":
|
| 568 |
-
"loss": 0.
|
| 569 |
"step": 790
|
| 570 |
},
|
| 571 |
{
|
| 572 |
"epoch": 0.35874439461883406,
|
| 573 |
-
"grad_norm": 1.
|
| 574 |
-
"learning_rate":
|
| 575 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 576 |
"step": 800
|
| 577 |
},
|
| 578 |
{
|
| 579 |
"epoch": 0.3632286995515695,
|
| 580 |
-
"grad_norm": 1.
|
| 581 |
-
"learning_rate":
|
| 582 |
-
"loss": 0.
|
| 583 |
"step": 810
|
| 584 |
},
|
| 585 |
{
|
| 586 |
"epoch": 0.36771300448430494,
|
| 587 |
-
"grad_norm": 1.
|
| 588 |
-
"learning_rate":
|
| 589 |
-
"loss": 0.
|
| 590 |
"step": 820
|
| 591 |
},
|
| 592 |
{
|
| 593 |
"epoch": 0.3721973094170404,
|
| 594 |
-
"grad_norm": 1.
|
| 595 |
-
"learning_rate":
|
| 596 |
-
"loss": 0.
|
| 597 |
"step": 830
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 0.37668161434977576,
|
| 601 |
-
"grad_norm": 1.
|
| 602 |
-
"learning_rate":
|
| 603 |
-
"loss": 0.
|
| 604 |
"step": 840
|
| 605 |
},
|
| 606 |
{
|
| 607 |
"epoch": 0.3811659192825112,
|
| 608 |
-
"grad_norm": 1.
|
| 609 |
-
"learning_rate":
|
| 610 |
-
"loss": 0.
|
| 611 |
"step": 850
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 0.38565022421524664,
|
| 615 |
-
"grad_norm": 1.
|
| 616 |
-
"learning_rate":
|
| 617 |
-
"loss": 0.
|
| 618 |
"step": 860
|
| 619 |
},
|
| 620 |
{
|
| 621 |
"epoch": 0.3901345291479821,
|
| 622 |
-
"grad_norm": 1.
|
| 623 |
-
"learning_rate":
|
| 624 |
-
"loss": 0.
|
| 625 |
"step": 870
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"epoch": 0.39461883408071746,
|
| 629 |
-
"grad_norm": 1.
|
| 630 |
-
"learning_rate":
|
| 631 |
-
"loss": 0.
|
| 632 |
"step": 880
|
| 633 |
},
|
| 634 |
{
|
| 635 |
"epoch": 0.3991031390134529,
|
| 636 |
-
"grad_norm": 1.
|
| 637 |
-
"learning_rate":
|
| 638 |
-
"loss": 0.
|
| 639 |
"step": 890
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"epoch": 0.40358744394618834,
|
| 643 |
-
"grad_norm": 1.
|
| 644 |
-
"learning_rate":
|
| 645 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 646 |
"step": 900
|
| 647 |
},
|
| 648 |
{
|
| 649 |
"epoch": 0.4080717488789238,
|
| 650 |
-
"grad_norm": 1.
|
| 651 |
-
"learning_rate":
|
| 652 |
-
"loss": 0.
|
| 653 |
"step": 910
|
| 654 |
},
|
| 655 |
{
|
| 656 |
"epoch": 0.4125560538116592,
|
| 657 |
-
"grad_norm": 1.
|
| 658 |
-
"learning_rate":
|
| 659 |
-
"loss": 0.
|
| 660 |
"step": 920
|
| 661 |
},
|
| 662 |
{
|
| 663 |
"epoch": 0.4170403587443946,
|
| 664 |
-
"grad_norm": 1.
|
| 665 |
-
"learning_rate":
|
| 666 |
-
"loss": 0.
|
| 667 |
"step": 930
|
| 668 |
},
|
| 669 |
{
|
| 670 |
"epoch": 0.42152466367713004,
|
| 671 |
-
"grad_norm": 1.
|
| 672 |
-
"learning_rate":
|
| 673 |
-
"loss": 0.
|
| 674 |
"step": 940
|
| 675 |
},
|
| 676 |
{
|
| 677 |
"epoch": 0.4260089686098655,
|
| 678 |
-
"grad_norm": 1.
|
| 679 |
-
"learning_rate":
|
| 680 |
-
"loss": 0.
|
| 681 |
"step": 950
|
| 682 |
},
|
| 683 |
{
|
| 684 |
"epoch": 0.4304932735426009,
|
| 685 |
-
"grad_norm": 1.
|
| 686 |
-
"learning_rate":
|
| 687 |
-
"loss": 0.
|
| 688 |
"step": 960
|
| 689 |
},
|
| 690 |
{
|
| 691 |
"epoch": 0.4349775784753363,
|
| 692 |
-
"grad_norm": 1.
|
| 693 |
-
"learning_rate":
|
| 694 |
-
"loss": 0.
|
| 695 |
"step": 970
|
| 696 |
},
|
| 697 |
{
|
| 698 |
"epoch": 0.43946188340807174,
|
| 699 |
-
"grad_norm": 1.
|
| 700 |
-
"learning_rate":
|
| 701 |
-
"loss": 0.
|
| 702 |
"step": 980
|
| 703 |
},
|
| 704 |
{
|
| 705 |
"epoch": 0.4439461883408072,
|
| 706 |
-
"grad_norm": 1.
|
| 707 |
-
"learning_rate":
|
| 708 |
-
"loss": 0.
|
| 709 |
"step": 990
|
| 710 |
},
|
| 711 |
{
|
| 712 |
"epoch": 0.4484304932735426,
|
| 713 |
-
"grad_norm": 1.
|
| 714 |
-
"learning_rate":
|
| 715 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 716 |
"step": 1000
|
| 717 |
},
|
| 718 |
{
|
| 719 |
"epoch": 0.452914798206278,
|
| 720 |
-
"grad_norm": 1.
|
| 721 |
-
"learning_rate":
|
| 722 |
-
"loss": 0.
|
| 723 |
"step": 1010
|
| 724 |
},
|
| 725 |
{
|
| 726 |
"epoch": 0.45739910313901344,
|
| 727 |
-
"grad_norm": 1.
|
| 728 |
-
"learning_rate":
|
| 729 |
-
"loss": 0.
|
| 730 |
"step": 1020
|
| 731 |
},
|
| 732 |
{
|
| 733 |
"epoch": 0.4618834080717489,
|
| 734 |
-
"grad_norm": 1.
|
| 735 |
-
"learning_rate":
|
| 736 |
-
"loss": 0.
|
| 737 |
"step": 1030
|
| 738 |
},
|
| 739 |
{
|
| 740 |
"epoch": 0.4663677130044843,
|
| 741 |
-
"grad_norm": 1.
|
| 742 |
-
"learning_rate":
|
| 743 |
-
"loss": 0.
|
| 744 |
"step": 1040
|
| 745 |
},
|
| 746 |
{
|
| 747 |
"epoch": 0.47085201793721976,
|
| 748 |
-
"grad_norm": 1.
|
| 749 |
-
"learning_rate":
|
| 750 |
-
"loss": 0.
|
| 751 |
"step": 1050
|
| 752 |
},
|
| 753 |
{
|
| 754 |
"epoch": 0.47533632286995514,
|
| 755 |
-
"grad_norm": 1.
|
| 756 |
-
"learning_rate":
|
| 757 |
-
"loss": 0.
|
| 758 |
"step": 1060
|
| 759 |
},
|
| 760 |
{
|
| 761 |
"epoch": 0.4798206278026906,
|
| 762 |
-
"grad_norm": 1.
|
| 763 |
-
"learning_rate":
|
| 764 |
-
"loss": 0.
|
| 765 |
"step": 1070
|
| 766 |
},
|
| 767 |
{
|
| 768 |
"epoch": 0.484304932735426,
|
| 769 |
-
"grad_norm": 1.
|
| 770 |
-
"learning_rate":
|
| 771 |
-
"loss": 0.
|
| 772 |
"step": 1080
|
| 773 |
},
|
| 774 |
{
|
| 775 |
"epoch": 0.48878923766816146,
|
| 776 |
-
"grad_norm": 1.
|
| 777 |
-
"learning_rate":
|
| 778 |
-
"loss": 0.
|
| 779 |
"step": 1090
|
| 780 |
},
|
| 781 |
{
|
| 782 |
"epoch": 0.49327354260089684,
|
| 783 |
-
"grad_norm": 1.
|
| 784 |
-
"learning_rate":
|
| 785 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 786 |
"step": 1100
|
| 787 |
},
|
| 788 |
{
|
| 789 |
"epoch": 0.4977578475336323,
|
| 790 |
-
"grad_norm": 1.
|
| 791 |
-
"learning_rate":
|
| 792 |
-
"loss": 0.
|
| 793 |
"step": 1110
|
| 794 |
},
|
| 795 |
{
|
| 796 |
"epoch": 0.5022421524663677,
|
| 797 |
-
"grad_norm": 1.
|
| 798 |
-
"learning_rate":
|
| 799 |
-
"loss": 0.
|
| 800 |
"step": 1120
|
| 801 |
},
|
| 802 |
{
|
| 803 |
"epoch": 0.5067264573991032,
|
| 804 |
-
"grad_norm": 1.
|
| 805 |
-
"learning_rate":
|
| 806 |
-
"loss": 0.
|
| 807 |
"step": 1130
|
| 808 |
},
|
| 809 |
{
|
| 810 |
"epoch": 0.5112107623318386,
|
| 811 |
-
"grad_norm": 1.
|
| 812 |
-
"learning_rate":
|
| 813 |
-
"loss": 0.
|
| 814 |
"step": 1140
|
| 815 |
},
|
| 816 |
{
|
| 817 |
"epoch": 0.515695067264574,
|
| 818 |
-
"grad_norm": 1.
|
| 819 |
-
"learning_rate":
|
| 820 |
-
"loss": 0.
|
| 821 |
"step": 1150
|
| 822 |
},
|
| 823 |
{
|
| 824 |
"epoch": 0.5201793721973094,
|
| 825 |
-
"grad_norm": 1.
|
| 826 |
-
"learning_rate":
|
| 827 |
-
"loss": 0.
|
| 828 |
"step": 1160
|
| 829 |
},
|
| 830 |
{
|
| 831 |
"epoch": 0.5246636771300448,
|
| 832 |
-
"grad_norm": 1.
|
| 833 |
-
"learning_rate":
|
| 834 |
-
"loss": 0.
|
| 835 |
"step": 1170
|
| 836 |
},
|
| 837 |
{
|
| 838 |
"epoch": 0.5291479820627802,
|
| 839 |
-
"grad_norm": 1.
|
| 840 |
-
"learning_rate":
|
| 841 |
-
"loss": 0.
|
| 842 |
"step": 1180
|
| 843 |
},
|
| 844 |
{
|
| 845 |
"epoch": 0.5336322869955157,
|
| 846 |
-
"grad_norm": 1.
|
| 847 |
-
"learning_rate":
|
| 848 |
-
"loss": 0.
|
| 849 |
"step": 1190
|
| 850 |
},
|
| 851 |
{
|
| 852 |
"epoch": 0.5381165919282511,
|
| 853 |
-
"grad_norm": 1.
|
| 854 |
-
"learning_rate":
|
| 855 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 856 |
"step": 1200
|
| 857 |
},
|
| 858 |
{
|
| 859 |
"epoch": 0.5426008968609866,
|
| 860 |
-
"grad_norm": 1.
|
| 861 |
-
"learning_rate":
|
| 862 |
-
"loss": 0.
|
| 863 |
"step": 1210
|
| 864 |
},
|
| 865 |
{
|
| 866 |
"epoch": 0.547085201793722,
|
| 867 |
-
"grad_norm": 1.
|
| 868 |
-
"learning_rate":
|
| 869 |
-
"loss": 0.
|
| 870 |
"step": 1220
|
| 871 |
},
|
| 872 |
{
|
| 873 |
"epoch": 0.5515695067264574,
|
| 874 |
-
"grad_norm": 1.
|
| 875 |
-
"learning_rate":
|
| 876 |
-
"loss": 0.
|
| 877 |
"step": 1230
|
| 878 |
},
|
| 879 |
{
|
| 880 |
"epoch": 0.5560538116591929,
|
| 881 |
-
"grad_norm": 1.
|
| 882 |
-
"learning_rate":
|
| 883 |
-
"loss": 0.
|
| 884 |
"step": 1240
|
| 885 |
},
|
| 886 |
{
|
| 887 |
"epoch": 0.5605381165919282,
|
| 888 |
-
"grad_norm": 1.
|
| 889 |
-
"learning_rate":
|
| 890 |
-
"loss": 0.
|
| 891 |
"step": 1250
|
| 892 |
},
|
| 893 |
{
|
| 894 |
"epoch": 0.5650224215246636,
|
| 895 |
-
"grad_norm": 1.
|
| 896 |
-
"learning_rate":
|
| 897 |
-
"loss": 0.
|
| 898 |
"step": 1260
|
| 899 |
},
|
| 900 |
{
|
| 901 |
"epoch": 0.5695067264573991,
|
| 902 |
-
"grad_norm": 1.
|
| 903 |
-
"learning_rate":
|
| 904 |
-
"loss": 0.
|
| 905 |
"step": 1270
|
| 906 |
},
|
| 907 |
{
|
| 908 |
"epoch": 0.5739910313901345,
|
| 909 |
-
"grad_norm": 1.
|
| 910 |
-
"learning_rate":
|
| 911 |
-
"loss": 0.
|
| 912 |
"step": 1280
|
| 913 |
},
|
| 914 |
{
|
| 915 |
"epoch": 0.57847533632287,
|
| 916 |
-
"grad_norm": 1.
|
| 917 |
-
"learning_rate":
|
| 918 |
-
"loss": 0.
|
| 919 |
"step": 1290
|
| 920 |
},
|
| 921 |
{
|
| 922 |
"epoch": 0.5829596412556054,
|
| 923 |
-
"grad_norm": 1.
|
| 924 |
-
"learning_rate":
|
| 925 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 926 |
"step": 1300
|
| 927 |
},
|
| 928 |
{
|
| 929 |
"epoch": 0.5874439461883408,
|
| 930 |
-
"grad_norm": 1.
|
| 931 |
-
"learning_rate":
|
| 932 |
-
"loss": 0.
|
| 933 |
"step": 1310
|
| 934 |
},
|
| 935 |
{
|
| 936 |
"epoch": 0.5919282511210763,
|
| 937 |
-
"grad_norm": 1.
|
| 938 |
-
"learning_rate":
|
| 939 |
-
"loss": 0.
|
| 940 |
"step": 1320
|
| 941 |
},
|
| 942 |
{
|
| 943 |
"epoch": 0.5964125560538116,
|
| 944 |
-
"grad_norm": 1.
|
| 945 |
-
"learning_rate":
|
| 946 |
-
"loss": 0.
|
| 947 |
"step": 1330
|
| 948 |
},
|
| 949 |
{
|
| 950 |
"epoch": 0.600896860986547,
|
| 951 |
-
"grad_norm": 1.
|
| 952 |
-
"learning_rate":
|
| 953 |
-
"loss": 0.
|
| 954 |
"step": 1340
|
| 955 |
},
|
| 956 |
{
|
| 957 |
"epoch": 0.6053811659192825,
|
| 958 |
-
"grad_norm": 1.
|
| 959 |
-
"learning_rate":
|
| 960 |
-
"loss": 0.
|
| 961 |
"step": 1350
|
| 962 |
},
|
| 963 |
{
|
| 964 |
"epoch": 0.6098654708520179,
|
| 965 |
-
"grad_norm": 1.
|
| 966 |
-
"learning_rate":
|
| 967 |
-
"loss": 0.
|
| 968 |
"step": 1360
|
| 969 |
},
|
| 970 |
{
|
| 971 |
"epoch": 0.6143497757847534,
|
| 972 |
-
"grad_norm": 1.
|
| 973 |
-
"learning_rate":
|
| 974 |
-
"loss": 0.
|
| 975 |
"step": 1370
|
| 976 |
},
|
| 977 |
{
|
| 978 |
"epoch": 0.6188340807174888,
|
| 979 |
-
"grad_norm": 1.
|
| 980 |
-
"learning_rate":
|
| 981 |
-
"loss": 0.
|
| 982 |
"step": 1380
|
| 983 |
},
|
| 984 |
{
|
| 985 |
"epoch": 0.6233183856502242,
|
| 986 |
-
"grad_norm": 1.
|
| 987 |
-
"learning_rate":
|
| 988 |
-
"loss": 0.
|
| 989 |
"step": 1390
|
| 990 |
},
|
| 991 |
{
|
| 992 |
"epoch": 0.6278026905829597,
|
| 993 |
-
"grad_norm": 1.
|
| 994 |
-
"learning_rate":
|
| 995 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 996 |
"step": 1400
|
| 997 |
},
|
| 998 |
{
|
| 999 |
"epoch": 0.6322869955156951,
|
| 1000 |
-
"grad_norm": 1.
|
| 1001 |
-
"learning_rate":
|
| 1002 |
-
"loss": 0.
|
| 1003 |
"step": 1410
|
| 1004 |
},
|
| 1005 |
{
|
| 1006 |
"epoch": 0.6367713004484304,
|
| 1007 |
-
"grad_norm": 1.
|
| 1008 |
-
"learning_rate":
|
| 1009 |
-
"loss": 0.
|
| 1010 |
"step": 1420
|
| 1011 |
},
|
| 1012 |
{
|
| 1013 |
"epoch": 0.6412556053811659,
|
| 1014 |
-
"grad_norm": 1.
|
| 1015 |
-
"learning_rate":
|
| 1016 |
-
"loss": 0.
|
| 1017 |
"step": 1430
|
| 1018 |
},
|
| 1019 |
{
|
| 1020 |
"epoch": 0.6457399103139013,
|
| 1021 |
-
"grad_norm": 1.
|
| 1022 |
-
"learning_rate":
|
| 1023 |
-
"loss": 0.
|
| 1024 |
"step": 1440
|
| 1025 |
},
|
| 1026 |
{
|
| 1027 |
"epoch": 0.6502242152466368,
|
| 1028 |
-
"grad_norm": 1.
|
| 1029 |
-
"learning_rate":
|
| 1030 |
-
"loss": 0.
|
| 1031 |
"step": 1450
|
| 1032 |
},
|
| 1033 |
{
|
| 1034 |
"epoch": 0.6547085201793722,
|
| 1035 |
-
"grad_norm": 1.
|
| 1036 |
-
"learning_rate":
|
| 1037 |
-
"loss": 0.
|
| 1038 |
"step": 1460
|
| 1039 |
},
|
| 1040 |
{
|
| 1041 |
"epoch": 0.6591928251121076,
|
| 1042 |
-
"grad_norm": 1.
|
| 1043 |
-
"learning_rate":
|
| 1044 |
-
"loss": 0.
|
| 1045 |
"step": 1470
|
| 1046 |
},
|
| 1047 |
{
|
| 1048 |
"epoch": 0.6636771300448431,
|
| 1049 |
-
"grad_norm": 1.
|
| 1050 |
-
"learning_rate":
|
| 1051 |
-
"loss": 0.
|
| 1052 |
"step": 1480
|
| 1053 |
},
|
| 1054 |
{
|
| 1055 |
"epoch": 0.6681614349775785,
|
| 1056 |
-
"grad_norm": 1.
|
| 1057 |
-
"learning_rate":
|
| 1058 |
-
"loss": 0.
|
| 1059 |
"step": 1490
|
| 1060 |
},
|
| 1061 |
{
|
| 1062 |
"epoch": 0.672645739910314,
|
| 1063 |
-
"grad_norm": 1.
|
| 1064 |
-
"learning_rate":
|
| 1065 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1066 |
"step": 1500
|
| 1067 |
},
|
| 1068 |
{
|
| 1069 |
"epoch": 0.6771300448430493,
|
| 1070 |
-
"grad_norm": 1.
|
| 1071 |
-
"learning_rate":
|
| 1072 |
-
"loss": 0.
|
| 1073 |
"step": 1510
|
| 1074 |
},
|
| 1075 |
{
|
| 1076 |
"epoch": 0.6816143497757847,
|
| 1077 |
-
"grad_norm": 1.
|
| 1078 |
-
"learning_rate":
|
| 1079 |
-
"loss": 0.
|
| 1080 |
"step": 1520
|
| 1081 |
},
|
| 1082 |
{
|
| 1083 |
"epoch": 0.6860986547085202,
|
| 1084 |
-
"grad_norm": 1.
|
| 1085 |
-
"learning_rate":
|
| 1086 |
-
"loss": 0.
|
| 1087 |
"step": 1530
|
| 1088 |
},
|
| 1089 |
{
|
| 1090 |
"epoch": 0.6905829596412556,
|
| 1091 |
-
"grad_norm": 1.
|
| 1092 |
-
"learning_rate":
|
| 1093 |
-
"loss": 0.
|
| 1094 |
"step": 1540
|
| 1095 |
},
|
| 1096 |
{
|
| 1097 |
"epoch": 0.695067264573991,
|
| 1098 |
-
"grad_norm": 1.
|
| 1099 |
-
"learning_rate":
|
| 1100 |
-
"loss": 0.
|
| 1101 |
"step": 1550
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
"epoch": 0.6995515695067265,
|
| 1105 |
-
"grad_norm": 1.
|
| 1106 |
-
"learning_rate":
|
| 1107 |
-
"loss": 0.
|
| 1108 |
"step": 1560
|
| 1109 |
},
|
| 1110 |
{
|
| 1111 |
"epoch": 0.7040358744394619,
|
| 1112 |
-
"grad_norm": 1.
|
| 1113 |
-
"learning_rate":
|
| 1114 |
-
"loss": 0.
|
| 1115 |
"step": 1570
|
| 1116 |
},
|
| 1117 |
{
|
| 1118 |
"epoch": 0.7085201793721974,
|
| 1119 |
-
"grad_norm": 1.
|
| 1120 |
-
"learning_rate":
|
| 1121 |
-
"loss": 0.
|
| 1122 |
"step": 1580
|
| 1123 |
},
|
| 1124 |
{
|
| 1125 |
"epoch": 0.7130044843049327,
|
| 1126 |
-
"grad_norm": 1.
|
| 1127 |
-
"learning_rate":
|
| 1128 |
-
"loss": 0.
|
| 1129 |
"step": 1590
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
"epoch": 0.7174887892376681,
|
| 1133 |
-
"grad_norm": 1.
|
| 1134 |
-
"learning_rate":
|
| 1135 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1136 |
"step": 1600
|
| 1137 |
},
|
| 1138 |
{
|
| 1139 |
"epoch": 0.7219730941704036,
|
| 1140 |
-
"grad_norm": 1.
|
| 1141 |
-
"learning_rate":
|
| 1142 |
-
"loss": 0.
|
| 1143 |
"step": 1610
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
"epoch": 0.726457399103139,
|
| 1147 |
-
"grad_norm": 1.
|
| 1148 |
-
"learning_rate":
|
| 1149 |
-
"loss": 0.
|
| 1150 |
"step": 1620
|
| 1151 |
},
|
| 1152 |
{
|
| 1153 |
"epoch": 0.7309417040358744,
|
| 1154 |
-
"grad_norm": 1.
|
| 1155 |
-
"learning_rate":
|
| 1156 |
-
"loss": 0.
|
| 1157 |
"step": 1630
|
| 1158 |
},
|
| 1159 |
{
|
| 1160 |
"epoch": 0.7354260089686099,
|
| 1161 |
-
"grad_norm": 1.
|
| 1162 |
-
"learning_rate":
|
| 1163 |
-
"loss": 0.
|
| 1164 |
"step": 1640
|
| 1165 |
},
|
| 1166 |
{
|
| 1167 |
"epoch": 0.7399103139013453,
|
| 1168 |
-
"grad_norm": 1.
|
| 1169 |
-
"learning_rate":
|
| 1170 |
-
"loss": 0.
|
| 1171 |
"step": 1650
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
"epoch": 0.7443946188340808,
|
| 1175 |
-
"grad_norm": 1.
|
| 1176 |
-
"learning_rate":
|
| 1177 |
-
"loss": 0.
|
| 1178 |
"step": 1660
|
| 1179 |
},
|
| 1180 |
{
|
| 1181 |
"epoch": 0.7488789237668162,
|
| 1182 |
-
"grad_norm": 1.
|
| 1183 |
-
"learning_rate":
|
| 1184 |
-
"loss": 0.
|
| 1185 |
"step": 1670
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
"epoch": 0.7533632286995515,
|
| 1189 |
-
"grad_norm": 1.
|
| 1190 |
-
"learning_rate":
|
| 1191 |
-
"loss": 0.
|
| 1192 |
"step": 1680
|
| 1193 |
},
|
| 1194 |
{
|
| 1195 |
"epoch": 0.757847533632287,
|
| 1196 |
-
"grad_norm": 1.
|
| 1197 |
-
"learning_rate":
|
| 1198 |
-
"loss": 0.
|
| 1199 |
"step": 1690
|
| 1200 |
},
|
| 1201 |
{
|
| 1202 |
"epoch": 0.7623318385650224,
|
| 1203 |
-
"grad_norm": 1.
|
| 1204 |
-
"learning_rate":
|
| 1205 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1206 |
"step": 1700
|
| 1207 |
},
|
| 1208 |
{
|
| 1209 |
"epoch": 0.7668161434977578,
|
| 1210 |
-
"grad_norm": 1.
|
| 1211 |
-
"learning_rate":
|
| 1212 |
-
"loss": 0.
|
| 1213 |
"step": 1710
|
| 1214 |
},
|
| 1215 |
{
|
| 1216 |
"epoch": 0.7713004484304933,
|
| 1217 |
-
"grad_norm": 1.
|
| 1218 |
-
"learning_rate":
|
| 1219 |
-
"loss": 0.
|
| 1220 |
"step": 1720
|
| 1221 |
},
|
| 1222 |
{
|
| 1223 |
"epoch": 0.7757847533632287,
|
| 1224 |
-
"grad_norm": 1.
|
| 1225 |
-
"learning_rate":
|
| 1226 |
-
"loss": 0.
|
| 1227 |
"step": 1730
|
| 1228 |
},
|
| 1229 |
{
|
| 1230 |
"epoch": 0.7802690582959642,
|
| 1231 |
-
"grad_norm": 1.
|
| 1232 |
-
"learning_rate":
|
| 1233 |
-
"loss": 0.
|
| 1234 |
"step": 1740
|
| 1235 |
},
|
| 1236 |
{
|
| 1237 |
"epoch": 0.7847533632286996,
|
| 1238 |
-
"grad_norm": 1.
|
| 1239 |
-
"learning_rate":
|
| 1240 |
-
"loss": 0.
|
| 1241 |
"step": 1750
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
"epoch": 0.7892376681614349,
|
| 1245 |
-
"grad_norm": 1.
|
| 1246 |
-
"learning_rate":
|
| 1247 |
-
"loss": 0.
|
| 1248 |
"step": 1760
|
| 1249 |
},
|
| 1250 |
{
|
| 1251 |
"epoch": 0.7937219730941704,
|
| 1252 |
-
"grad_norm": 1.
|
| 1253 |
-
"learning_rate":
|
| 1254 |
-
"loss": 0.
|
| 1255 |
"step": 1770
|
| 1256 |
},
|
| 1257 |
{
|
| 1258 |
"epoch": 0.7982062780269058,
|
| 1259 |
-
"grad_norm": 1.
|
| 1260 |
-
"learning_rate":
|
| 1261 |
-
"loss": 0.
|
| 1262 |
"step": 1780
|
| 1263 |
},
|
| 1264 |
{
|
| 1265 |
"epoch": 0.8026905829596412,
|
| 1266 |
-
"grad_norm": 1.
|
| 1267 |
-
"learning_rate":
|
| 1268 |
-
"loss": 0.
|
| 1269 |
"step": 1790
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
"epoch": 0.8071748878923767,
|
| 1273 |
-
"grad_norm": 1.
|
| 1274 |
-
"learning_rate":
|
| 1275 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1276 |
"step": 1800
|
| 1277 |
},
|
| 1278 |
{
|
| 1279 |
"epoch": 0.8116591928251121,
|
| 1280 |
-
"grad_norm": 1.
|
| 1281 |
-
"learning_rate":
|
| 1282 |
-
"loss": 0.
|
| 1283 |
"step": 1810
|
| 1284 |
},
|
| 1285 |
{
|
| 1286 |
"epoch": 0.8161434977578476,
|
| 1287 |
-
"grad_norm": 1.
|
| 1288 |
-
"learning_rate":
|
| 1289 |
-
"loss": 0.
|
| 1290 |
"step": 1820
|
| 1291 |
},
|
| 1292 |
{
|
| 1293 |
"epoch": 0.820627802690583,
|
| 1294 |
-
"grad_norm": 1.
|
| 1295 |
-
"learning_rate":
|
| 1296 |
-
"loss": 0.
|
| 1297 |
"step": 1830
|
| 1298 |
},
|
| 1299 |
{
|
| 1300 |
"epoch": 0.8251121076233184,
|
| 1301 |
-
"grad_norm": 1.
|
| 1302 |
-
"learning_rate":
|
| 1303 |
-
"loss": 0.
|
| 1304 |
"step": 1840
|
| 1305 |
},
|
| 1306 |
{
|
| 1307 |
"epoch": 0.8295964125560538,
|
| 1308 |
-
"grad_norm": 1.
|
| 1309 |
-
"learning_rate":
|
| 1310 |
-
"loss": 0.
|
| 1311 |
"step": 1850
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
"epoch": 0.8340807174887892,
|
| 1315 |
-
"grad_norm": 1.
|
| 1316 |
-
"learning_rate":
|
| 1317 |
-
"loss": 0.
|
| 1318 |
"step": 1860
|
| 1319 |
},
|
| 1320 |
{
|
| 1321 |
"epoch": 0.8385650224215246,
|
| 1322 |
-
"grad_norm": 1.
|
| 1323 |
-
"learning_rate":
|
| 1324 |
-
"loss": 0.
|
| 1325 |
"step": 1870
|
| 1326 |
},
|
| 1327 |
{
|
| 1328 |
"epoch": 0.8430493273542601,
|
| 1329 |
-
"grad_norm": 1.
|
| 1330 |
-
"learning_rate":
|
| 1331 |
-
"loss": 0.
|
| 1332 |
"step": 1880
|
| 1333 |
},
|
| 1334 |
{
|
| 1335 |
"epoch": 0.8475336322869955,
|
| 1336 |
-
"grad_norm": 1.
|
| 1337 |
-
"learning_rate":
|
| 1338 |
-
"loss": 0.
|
| 1339 |
"step": 1890
|
| 1340 |
},
|
| 1341 |
{
|
| 1342 |
"epoch": 0.852017937219731,
|
| 1343 |
-
"grad_norm": 1.
|
| 1344 |
-
"learning_rate":
|
| 1345 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1346 |
"step": 1900
|
| 1347 |
},
|
| 1348 |
{
|
| 1349 |
"epoch": 0.8565022421524664,
|
| 1350 |
-
"grad_norm": 1.
|
| 1351 |
-
"learning_rate":
|
| 1352 |
-
"loss": 0.
|
| 1353 |
"step": 1910
|
| 1354 |
},
|
| 1355 |
{
|
| 1356 |
"epoch": 0.8609865470852018,
|
| 1357 |
-
"grad_norm": 1.
|
| 1358 |
-
"learning_rate":
|
| 1359 |
-
"loss": 0.
|
| 1360 |
"step": 1920
|
| 1361 |
},
|
| 1362 |
{
|
| 1363 |
"epoch": 0.8654708520179372,
|
| 1364 |
-
"grad_norm": 1.
|
| 1365 |
-
"learning_rate":
|
| 1366 |
-
"loss": 0.
|
| 1367 |
"step": 1930
|
| 1368 |
},
|
| 1369 |
{
|
| 1370 |
"epoch": 0.8699551569506726,
|
| 1371 |
-
"grad_norm": 1.
|
| 1372 |
-
"learning_rate":
|
| 1373 |
-
"loss": 0.
|
| 1374 |
"step": 1940
|
| 1375 |
},
|
| 1376 |
{
|
| 1377 |
"epoch": 0.874439461883408,
|
| 1378 |
-
"grad_norm": 1.
|
| 1379 |
-
"learning_rate":
|
| 1380 |
-
"loss": 0.
|
| 1381 |
"step": 1950
|
| 1382 |
},
|
| 1383 |
{
|
| 1384 |
"epoch": 0.8789237668161435,
|
| 1385 |
-
"grad_norm": 1.
|
| 1386 |
-
"learning_rate":
|
| 1387 |
-
"loss": 0.
|
| 1388 |
"step": 1960
|
| 1389 |
},
|
| 1390 |
{
|
| 1391 |
"epoch": 0.8834080717488789,
|
| 1392 |
-
"grad_norm": 1.
|
| 1393 |
-
"learning_rate":
|
| 1394 |
-
"loss": 0.
|
| 1395 |
"step": 1970
|
| 1396 |
},
|
| 1397 |
{
|
| 1398 |
"epoch": 0.8878923766816144,
|
| 1399 |
-
"grad_norm": 1.
|
| 1400 |
-
"learning_rate":
|
| 1401 |
-
"loss": 0.
|
| 1402 |
"step": 1980
|
| 1403 |
},
|
| 1404 |
{
|
| 1405 |
"epoch": 0.8923766816143498,
|
| 1406 |
-
"grad_norm": 1.
|
| 1407 |
-
"learning_rate":
|
| 1408 |
-
"loss": 0.
|
| 1409 |
"step": 1990
|
| 1410 |
},
|
| 1411 |
{
|
| 1412 |
"epoch": 0.8968609865470852,
|
| 1413 |
-
"grad_norm": 1.
|
| 1414 |
-
"learning_rate":
|
| 1415 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1416 |
"step": 2000
|
| 1417 |
},
|
| 1418 |
{
|
| 1419 |
"epoch": 0.9013452914798207,
|
| 1420 |
-
"grad_norm": 1.
|
| 1421 |
-
"learning_rate":
|
| 1422 |
-
"loss": 0.
|
| 1423 |
"step": 2010
|
| 1424 |
},
|
| 1425 |
{
|
| 1426 |
"epoch": 0.905829596412556,
|
| 1427 |
-
"grad_norm": 1.
|
| 1428 |
-
"learning_rate":
|
| 1429 |
-
"loss": 0.
|
| 1430 |
"step": 2020
|
| 1431 |
},
|
| 1432 |
{
|
| 1433 |
"epoch": 0.9103139013452914,
|
| 1434 |
-
"grad_norm": 1.
|
| 1435 |
-
"learning_rate":
|
| 1436 |
-
"loss": 0.
|
| 1437 |
"step": 2030
|
| 1438 |
},
|
| 1439 |
{
|
| 1440 |
"epoch": 0.9147982062780269,
|
| 1441 |
-
"grad_norm": 1.
|
| 1442 |
-
"learning_rate":
|
| 1443 |
-
"loss": 0.
|
| 1444 |
"step": 2040
|
| 1445 |
},
|
| 1446 |
{
|
| 1447 |
"epoch": 0.9192825112107623,
|
| 1448 |
-
"grad_norm": 1.
|
| 1449 |
-
"learning_rate":
|
| 1450 |
-
"loss": 0.
|
| 1451 |
"step": 2050
|
| 1452 |
},
|
| 1453 |
{
|
| 1454 |
"epoch": 0.9237668161434978,
|
| 1455 |
-
"grad_norm": 1.
|
| 1456 |
-
"learning_rate":
|
| 1457 |
-
"loss": 0.
|
| 1458 |
"step": 2060
|
| 1459 |
},
|
| 1460 |
{
|
| 1461 |
"epoch": 0.9282511210762332,
|
| 1462 |
-
"grad_norm": 1.
|
| 1463 |
-
"learning_rate":
|
| 1464 |
-
"loss": 0.
|
| 1465 |
"step": 2070
|
| 1466 |
},
|
| 1467 |
{
|
| 1468 |
"epoch": 0.9327354260089686,
|
| 1469 |
-
"grad_norm": 1.
|
| 1470 |
-
"learning_rate":
|
| 1471 |
-
"loss": 0.
|
| 1472 |
"step": 2080
|
| 1473 |
},
|
| 1474 |
{
|
| 1475 |
"epoch": 0.9372197309417041,
|
| 1476 |
-
"grad_norm": 1.
|
| 1477 |
-
"learning_rate":
|
| 1478 |
-
"loss": 0.
|
| 1479 |
"step": 2090
|
| 1480 |
},
|
| 1481 |
{
|
| 1482 |
"epoch": 0.9417040358744395,
|
| 1483 |
-
"grad_norm": 1.
|
| 1484 |
-
"learning_rate":
|
| 1485 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1486 |
"step": 2100
|
| 1487 |
},
|
| 1488 |
{
|
| 1489 |
"epoch": 0.9461883408071748,
|
| 1490 |
-
"grad_norm": 1.
|
| 1491 |
-
"learning_rate":
|
| 1492 |
-
"loss": 0.
|
| 1493 |
"step": 2110
|
| 1494 |
},
|
| 1495 |
{
|
| 1496 |
"epoch": 0.9506726457399103,
|
| 1497 |
-
"grad_norm": 1.
|
| 1498 |
-
"learning_rate":
|
| 1499 |
-
"loss": 0.
|
| 1500 |
"step": 2120
|
| 1501 |
},
|
| 1502 |
{
|
| 1503 |
"epoch": 0.9551569506726457,
|
| 1504 |
-
"grad_norm": 1.
|
| 1505 |
-
"learning_rate":
|
| 1506 |
-
"loss": 0.
|
| 1507 |
"step": 2130
|
| 1508 |
},
|
| 1509 |
{
|
| 1510 |
"epoch": 0.9596412556053812,
|
| 1511 |
-
"grad_norm": 1.
|
| 1512 |
-
"learning_rate":
|
| 1513 |
-
"loss": 0.
|
| 1514 |
"step": 2140
|
| 1515 |
},
|
| 1516 |
{
|
| 1517 |
"epoch": 0.9641255605381166,
|
| 1518 |
-
"grad_norm": 1.
|
| 1519 |
-
"learning_rate":
|
| 1520 |
-
"loss": 0.
|
| 1521 |
"step": 2150
|
| 1522 |
},
|
| 1523 |
{
|
| 1524 |
"epoch": 0.968609865470852,
|
| 1525 |
-
"grad_norm": 1.
|
| 1526 |
-
"learning_rate":
|
| 1527 |
-
"loss": 0.
|
| 1528 |
"step": 2160
|
| 1529 |
},
|
| 1530 |
{
|
| 1531 |
"epoch": 0.9730941704035875,
|
| 1532 |
-
"grad_norm": 1.
|
| 1533 |
-
"learning_rate":
|
| 1534 |
-
"loss": 0.
|
| 1535 |
"step": 2170
|
| 1536 |
},
|
| 1537 |
{
|
| 1538 |
"epoch": 0.9775784753363229,
|
| 1539 |
-
"grad_norm": 1.
|
| 1540 |
-
"learning_rate":
|
| 1541 |
-
"loss": 0.
|
| 1542 |
"step": 2180
|
| 1543 |
},
|
| 1544 |
{
|
| 1545 |
"epoch": 0.9820627802690582,
|
| 1546 |
-
"grad_norm": 1.
|
| 1547 |
-
"learning_rate":
|
| 1548 |
-
"loss": 0.
|
| 1549 |
"step": 2190
|
| 1550 |
},
|
| 1551 |
{
|
| 1552 |
"epoch": 0.9865470852017937,
|
| 1553 |
-
"grad_norm": 1.
|
| 1554 |
-
"learning_rate":
|
| 1555 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1556 |
"step": 2200
|
| 1557 |
},
|
| 1558 |
{
|
| 1559 |
"epoch": 0.9910313901345291,
|
| 1560 |
-
"grad_norm": 1.
|
| 1561 |
-
"learning_rate":
|
| 1562 |
-
"loss": 0.
|
| 1563 |
"step": 2210
|
| 1564 |
},
|
| 1565 |
{
|
| 1566 |
"epoch": 0.9955156950672646,
|
| 1567 |
-
"grad_norm": 1.
|
| 1568 |
-
"learning_rate":
|
| 1569 |
-
"loss": 0.
|
| 1570 |
"step": 2220
|
| 1571 |
},
|
| 1572 |
{
|
| 1573 |
"epoch": 1.0,
|
| 1574 |
-
"grad_norm": 1.
|
| 1575 |
"learning_rate": 0.0,
|
| 1576 |
-
"loss": 0.
|
| 1577 |
-
"step": 2230
|
| 1578 |
-
},
|
| 1579 |
-
{
|
| 1580 |
-
"epoch": 1.0,
|
| 1581 |
-
"eval_loss": 0.7042345404624939,
|
| 1582 |
-
"eval_runtime": 381.2635,
|
| 1583 |
-
"eval_samples_per_second": 131.345,
|
| 1584 |
-
"eval_steps_per_second": 2.054,
|
| 1585 |
"step": 2230
|
| 1586 |
},
|
| 1587 |
{
|
| 1588 |
"epoch": 1.0,
|
| 1589 |
"step": 2230,
|
| 1590 |
-
"total_flos":
|
| 1591 |
-
"train_loss": 0.
|
| 1592 |
-
"train_runtime":
|
| 1593 |
-
"train_samples_per_second":
|
| 1594 |
-
"train_steps_per_second": 0.
|
| 1595 |
}
|
| 1596 |
],
|
| 1597 |
"logging_steps": 10,
|
|
@@ -1611,7 +1779,7 @@
|
|
| 1611 |
"attributes": {}
|
| 1612 |
}
|
| 1613 |
},
|
| 1614 |
-
"total_flos":
|
| 1615 |
"train_batch_size": 8,
|
| 1616 |
"trial_name": null,
|
| 1617 |
"trial_params": null
|
|
|
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
"global_step": 2230,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.0004484304932735426,
|
| 13 |
+
"grad_norm": 4.696539476451585,
|
| 14 |
+
"learning_rate": 1.3452914798206278e-08,
|
| 15 |
"loss": 0.9912,
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.004484304932735426,
|
| 20 |
+
"grad_norm": 5.089904667658368,
|
| 21 |
+
"learning_rate": 1.345291479820628e-07,
|
| 22 |
+
"loss": 1.0341,
|
| 23 |
"step": 10
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.008968609865470852,
|
| 27 |
+
"grad_norm": 5.546828630388097,
|
| 28 |
+
"learning_rate": 2.690582959641256e-07,
|
| 29 |
+
"loss": 1.0502,
|
| 30 |
"step": 20
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.013452914798206279,
|
| 34 |
+
"grad_norm": 4.113849381101499,
|
| 35 |
+
"learning_rate": 4.0358744394618834e-07,
|
| 36 |
+
"loss": 1.0386,
|
| 37 |
"step": 30
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.017937219730941704,
|
| 41 |
+
"grad_norm": 3.6548963622814887,
|
| 42 |
+
"learning_rate": 5.381165919282512e-07,
|
| 43 |
+
"loss": 1.0282,
|
| 44 |
"step": 40
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.02242152466367713,
|
| 48 |
+
"grad_norm": 2.157564670206396,
|
| 49 |
+
"learning_rate": 6.72645739910314e-07,
|
| 50 |
+
"loss": 0.9574,
|
| 51 |
"step": 50
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.026905829596412557,
|
| 55 |
+
"grad_norm": 2.0184475272019555,
|
| 56 |
+
"learning_rate": 8.071748878923767e-07,
|
| 57 |
+
"loss": 0.9263,
|
| 58 |
"step": 60
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.03139013452914798,
|
| 62 |
+
"grad_norm": 1.7894937443172652,
|
| 63 |
+
"learning_rate": 9.417040358744395e-07,
|
| 64 |
+
"loss": 0.9253,
|
| 65 |
"step": 70
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.03587443946188341,
|
| 69 |
+
"grad_norm": 1.6533764414432808,
|
| 70 |
+
"learning_rate": 1.0762331838565023e-06,
|
| 71 |
+
"loss": 0.9106,
|
| 72 |
"step": 80
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.04035874439461883,
|
| 76 |
+
"grad_norm": 1.9561381307359194,
|
| 77 |
+
"learning_rate": 1.2107623318385651e-06,
|
| 78 |
+
"loss": 0.8713,
|
| 79 |
"step": 90
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.04484304932735426,
|
| 83 |
+
"grad_norm": 1.5478472557018526,
|
| 84 |
+
"learning_rate": 1.345291479820628e-06,
|
| 85 |
+
"loss": 0.8741,
|
| 86 |
+
"step": 100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.04484304932735426,
|
| 90 |
+
"eval_loss": 0.8599640727043152,
|
| 91 |
+
"eval_runtime": 430.7233,
|
| 92 |
+
"eval_samples_per_second": 116.263,
|
| 93 |
+
"eval_steps_per_second": 1.818,
|
| 94 |
"step": 100
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"epoch": 0.04932735426008968,
|
| 98 |
+
"grad_norm": 1.5759592930264636,
|
| 99 |
+
"learning_rate": 1.4798206278026905e-06,
|
| 100 |
+
"loss": 0.8381,
|
| 101 |
"step": 110
|
| 102 |
},
|
| 103 |
{
|
| 104 |
"epoch": 0.053811659192825115,
|
| 105 |
+
"grad_norm": 1.5446577353242628,
|
| 106 |
+
"learning_rate": 1.6143497757847533e-06,
|
| 107 |
+
"loss": 0.8151,
|
| 108 |
"step": 120
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 0.05829596412556054,
|
| 112 |
+
"grad_norm": 1.6899841974229757,
|
| 113 |
+
"learning_rate": 1.7488789237668162e-06,
|
| 114 |
+
"loss": 0.8309,
|
| 115 |
"step": 130
|
| 116 |
},
|
| 117 |
{
|
| 118 |
"epoch": 0.06278026905829596,
|
| 119 |
+
"grad_norm": 1.6274283098945213,
|
| 120 |
+
"learning_rate": 1.883408071748879e-06,
|
| 121 |
+
"loss": 0.8509,
|
| 122 |
"step": 140
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.06726457399103139,
|
| 126 |
+
"grad_norm": 1.7690619100525546,
|
| 127 |
+
"learning_rate": 2.0179372197309418e-06,
|
| 128 |
+
"loss": 0.8057,
|
| 129 |
"step": 150
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 0.07174887892376682,
|
| 133 |
+
"grad_norm": 1.866473004768342,
|
| 134 |
+
"learning_rate": 2.1524663677130046e-06,
|
| 135 |
+
"loss": 0.8236,
|
| 136 |
"step": 160
|
| 137 |
},
|
| 138 |
{
|
| 139 |
"epoch": 0.07623318385650224,
|
| 140 |
+
"grad_norm": 1.5528009019380091,
|
| 141 |
+
"learning_rate": 2.2869955156950674e-06,
|
| 142 |
+
"loss": 0.7936,
|
| 143 |
"step": 170
|
| 144 |
},
|
| 145 |
{
|
| 146 |
"epoch": 0.08071748878923767,
|
| 147 |
+
"grad_norm": 1.8924349879943885,
|
| 148 |
+
"learning_rate": 2.4215246636771302e-06,
|
| 149 |
+
"loss": 0.8054,
|
| 150 |
"step": 180
|
| 151 |
},
|
| 152 |
{
|
| 153 |
"epoch": 0.08520179372197309,
|
| 154 |
+
"grad_norm": 1.5998254884542162,
|
| 155 |
+
"learning_rate": 2.556053811659193e-06,
|
| 156 |
+
"loss": 0.7971,
|
| 157 |
"step": 190
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"epoch": 0.08968609865470852,
|
| 161 |
+
"grad_norm": 1.553085624058612,
|
| 162 |
+
"learning_rate": 2.690582959641256e-06,
|
| 163 |
+
"loss": 0.8038,
|
| 164 |
+
"step": 200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.08968609865470852,
|
| 168 |
+
"eval_loss": 0.8094644546508789,
|
| 169 |
+
"eval_runtime": 412.1717,
|
| 170 |
+
"eval_samples_per_second": 121.495,
|
| 171 |
+
"eval_steps_per_second": 1.9,
|
| 172 |
"step": 200
|
| 173 |
},
|
| 174 |
{
|
| 175 |
"epoch": 0.09417040358744394,
|
| 176 |
+
"grad_norm": 1.6621378080442881,
|
| 177 |
+
"learning_rate": 2.8251121076233187e-06,
|
| 178 |
+
"loss": 0.7815,
|
| 179 |
"step": 210
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 0.09865470852017937,
|
| 183 |
+
"grad_norm": 1.5875832641605891,
|
| 184 |
+
"learning_rate": 2.959641255605381e-06,
|
| 185 |
+
"loss": 0.8088,
|
| 186 |
"step": 220
|
| 187 |
},
|
| 188 |
{
|
| 189 |
"epoch": 0.1031390134529148,
|
| 190 |
+
"grad_norm": 1.6006597094640902,
|
| 191 |
+
"learning_rate": 2.99990995533251e-06,
|
| 192 |
+
"loss": 0.8141,
|
| 193 |
"step": 230
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"epoch": 0.10762331838565023,
|
| 197 |
+
"grad_norm": 1.7932554350094232,
|
| 198 |
+
"learning_rate": 2.9994689462512194e-06,
|
| 199 |
+
"loss": 0.7834,
|
| 200 |
"step": 240
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"epoch": 0.11210762331838565,
|
| 204 |
+
"grad_norm": 1.6444723214299724,
|
| 205 |
+
"learning_rate": 2.998660541859271e-06,
|
| 206 |
+
"loss": 0.7797,
|
| 207 |
"step": 250
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 0.11659192825112108,
|
| 211 |
+
"grad_norm": 1.790145213655978,
|
| 212 |
+
"learning_rate": 2.9974849402294452e-06,
|
| 213 |
+
"loss": 0.8046,
|
| 214 |
"step": 260
|
| 215 |
},
|
| 216 |
{
|
| 217 |
"epoch": 0.1210762331838565,
|
| 218 |
+
"grad_norm": 1.8694283184605,
|
| 219 |
+
"learning_rate": 2.9959424294040703e-06,
|
| 220 |
+
"loss": 0.7802,
|
| 221 |
"step": 270
|
| 222 |
},
|
| 223 |
{
|
| 224 |
"epoch": 0.12556053811659193,
|
| 225 |
+
"grad_norm": 1.6030839509233756,
|
| 226 |
+
"learning_rate": 2.9940333873244464e-06,
|
| 227 |
+
"loss": 0.8032,
|
| 228 |
"step": 280
|
| 229 |
},
|
| 230 |
{
|
| 231 |
"epoch": 0.13004484304932734,
|
| 232 |
+
"grad_norm": 1.664910362160235,
|
| 233 |
+
"learning_rate": 2.991758281738245e-06,
|
| 234 |
+
"loss": 0.7802,
|
| 235 |
"step": 290
|
| 236 |
},
|
| 237 |
{
|
| 238 |
"epoch": 0.13452914798206278,
|
| 239 |
+
"grad_norm": 1.6726792291262853,
|
| 240 |
+
"learning_rate": 2.989117670084902e-06,
|
| 241 |
+
"loss": 0.7937,
|
| 242 |
+
"step": 300
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.13452914798206278,
|
| 246 |
+
"eval_loss": 0.7789004445075989,
|
| 247 |
+
"eval_runtime": 410.6605,
|
| 248 |
+
"eval_samples_per_second": 121.943,
|
| 249 |
+
"eval_steps_per_second": 1.907,
|
| 250 |
"step": 300
|
| 251 |
},
|
| 252 |
{
|
| 253 |
"epoch": 0.13901345291479822,
|
| 254 |
+
"grad_norm": 1.4685211047526556,
|
| 255 |
+
"learning_rate": 2.986112199359036e-06,
|
| 256 |
+
"loss": 0.7486,
|
| 257 |
"step": 310
|
| 258 |
},
|
| 259 |
{
|
| 260 |
"epoch": 0.14349775784753363,
|
| 261 |
+
"grad_norm": 2.0076694355781575,
|
| 262 |
+
"learning_rate": 2.9827426059519237e-06,
|
| 263 |
+
"loss": 0.808,
|
| 264 |
"step": 320
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 0.14798206278026907,
|
| 268 |
+
"grad_norm": 1.557780179088859,
|
| 269 |
+
"learning_rate": 2.9790097154710697e-06,
|
| 270 |
+
"loss": 0.7849,
|
| 271 |
"step": 330
|
| 272 |
},
|
| 273 |
{
|
| 274 |
"epoch": 0.15246636771300448,
|
| 275 |
+
"grad_norm": 1.3610248283116362,
|
| 276 |
+
"learning_rate": 2.9749144425379216e-06,
|
| 277 |
+
"loss": 0.7696,
|
| 278 |
"step": 340
|
| 279 |
},
|
| 280 |
{
|
| 281 |
"epoch": 0.15695067264573992,
|
| 282 |
+
"grad_norm": 1.5050628258310632,
|
| 283 |
+
"learning_rate": 2.9704577905637718e-06,
|
| 284 |
+
"loss": 0.7497,
|
| 285 |
"step": 350
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 0.16143497757847533,
|
| 289 |
+
"grad_norm": 1.4313536098763806,
|
| 290 |
+
"learning_rate": 2.9656408515039017e-06,
|
| 291 |
+
"loss": 0.7544,
|
| 292 |
"step": 360
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"epoch": 0.16591928251121077,
|
| 296 |
+
"grad_norm": 1.6003065628553548,
|
| 297 |
+
"learning_rate": 2.9604648055900368e-06,
|
| 298 |
+
"loss": 0.7648,
|
| 299 |
"step": 370
|
| 300 |
},
|
| 301 |
{
|
| 302 |
"epoch": 0.17040358744394618,
|
| 303 |
+
"grad_norm": 1.633334409956319,
|
| 304 |
+
"learning_rate": 2.9549309210411697e-06,
|
| 305 |
+
"loss": 0.7471,
|
| 306 |
"step": 380
|
| 307 |
},
|
| 308 |
{
|
| 309 |
"epoch": 0.17488789237668162,
|
| 310 |
+
"grad_norm": 1.5700271693529286,
|
| 311 |
+
"learning_rate": 2.949040553752826e-06,
|
| 312 |
+
"loss": 0.8009,
|
| 313 |
"step": 390
|
| 314 |
},
|
| 315 |
{
|
| 316 |
"epoch": 0.17937219730941703,
|
| 317 |
+
"grad_norm": 1.4854276734758955,
|
| 318 |
+
"learning_rate": 2.9427951469648425e-06,
|
| 319 |
+
"loss": 0.7712,
|
| 320 |
+
"step": 400
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.17937219730941703,
|
| 324 |
+
"eval_loss": 0.7643527388572693,
|
| 325 |
+
"eval_runtime": 413.4678,
|
| 326 |
+
"eval_samples_per_second": 121.115,
|
| 327 |
+
"eval_steps_per_second": 1.894,
|
| 328 |
"step": 400
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"epoch": 0.18385650224215247,
|
| 332 |
+
"grad_norm": 1.4160940764229815,
|
| 333 |
+
"learning_rate": 2.936196230907755e-06,
|
| 334 |
+
"loss": 0.7532,
|
| 335 |
"step": 410
|
| 336 |
},
|
| 337 |
{
|
| 338 |
"epoch": 0.18834080717488788,
|
| 339 |
+
"grad_norm": 1.4265290618310995,
|
| 340 |
+
"learning_rate": 2.929245422427861e-06,
|
| 341 |
+
"loss": 0.7703,
|
| 342 |
"step": 420
|
| 343 |
},
|
| 344 |
{
|
| 345 |
"epoch": 0.19282511210762332,
|
| 346 |
+
"grad_norm": 1.6899882763333507,
|
| 347 |
+
"learning_rate": 2.9219444245910674e-06,
|
| 348 |
+
"loss": 0.7919,
|
| 349 |
"step": 430
|
| 350 |
},
|
| 351 |
{
|
| 352 |
"epoch": 0.19730941704035873,
|
| 353 |
+
"grad_norm": 1.4186337044303068,
|
| 354 |
+
"learning_rate": 2.9142950262656098e-06,
|
| 355 |
+
"loss": 0.7477,
|
| 356 |
"step": 440
|
| 357 |
},
|
| 358 |
{
|
| 359 |
"epoch": 0.20179372197309417,
|
| 360 |
+
"grad_norm": 1.4178331376670448,
|
| 361 |
+
"learning_rate": 2.9062991016837496e-06,
|
| 362 |
+
"loss": 0.7734,
|
| 363 |
"step": 450
|
| 364 |
},
|
| 365 |
{
|
| 366 |
"epoch": 0.2062780269058296,
|
| 367 |
+
"grad_norm": 1.4503162574851487,
|
| 368 |
+
"learning_rate": 2.897958609982556e-06,
|
| 369 |
+
"loss": 0.7447,
|
| 370 |
"step": 460
|
| 371 |
},
|
| 372 |
{
|
| 373 |
"epoch": 0.21076233183856502,
|
| 374 |
+
"grad_norm": 1.558520612711291,
|
| 375 |
+
"learning_rate": 2.8892755947238818e-06,
|
| 376 |
+
"loss": 0.741,
|
| 377 |
"step": 470
|
| 378 |
},
|
| 379 |
{
|
| 380 |
"epoch": 0.21524663677130046,
|
| 381 |
+
"grad_norm": 1.4382572158325275,
|
| 382 |
+
"learning_rate": 2.8802521833936595e-06,
|
| 383 |
+
"loss": 0.7563,
|
| 384 |
"step": 480
|
| 385 |
},
|
| 386 |
{
|
| 387 |
"epoch": 0.21973094170403587,
|
| 388 |
+
"grad_norm": 1.5964216489171685,
|
| 389 |
+
"learning_rate": 2.870890586880629e-06,
|
| 390 |
+
"loss": 0.7554,
|
| 391 |
"step": 490
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"epoch": 0.2242152466367713,
|
| 395 |
+
"grad_norm": 1.496069010720812,
|
| 396 |
+
"learning_rate": 2.8611930989346322e-06,
|
| 397 |
+
"loss": 0.7393,
|
| 398 |
+
"step": 500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.2242152466367713,
|
| 402 |
+
"eval_loss": 0.7564548254013062,
|
| 403 |
+
"eval_runtime": 408.8965,
|
| 404 |
+
"eval_samples_per_second": 122.469,
|
| 405 |
+
"eval_steps_per_second": 1.915,
|
| 406 |
"step": 500
|
| 407 |
},
|
| 408 |
{
|
| 409 |
"epoch": 0.22869955156950672,
|
| 410 |
+
"grad_norm": 1.4866290735466012,
|
| 411 |
+
"learning_rate": 2.851162095604607e-06,
|
| 412 |
+
"loss": 0.7499,
|
| 413 |
"step": 510
|
| 414 |
},
|
| 415 |
{
|
| 416 |
"epoch": 0.23318385650224216,
|
| 417 |
+
"grad_norm": 1.3341919240907245,
|
| 418 |
+
"learning_rate": 2.8408000346564136e-06,
|
| 419 |
+
"loss": 0.7524,
|
| 420 |
"step": 520
|
| 421 |
},
|
| 422 |
{
|
| 423 |
"epoch": 0.23766816143497757,
|
| 424 |
+
"grad_norm": 1.6374942242171213,
|
| 425 |
+
"learning_rate": 2.8301094549706405e-06,
|
| 426 |
+
"loss": 0.7386,
|
| 427 |
"step": 530
|
| 428 |
},
|
| 429 |
{
|
| 430 |
"epoch": 0.242152466367713,
|
| 431 |
+
"grad_norm": 1.6225803035616944,
|
| 432 |
+
"learning_rate": 2.8190929759205366e-06,
|
| 433 |
+
"loss": 0.7616,
|
| 434 |
"step": 540
|
| 435 |
},
|
| 436 |
{
|
| 437 |
"epoch": 0.24663677130044842,
|
| 438 |
+
"grad_norm": 1.4683777464043755,
|
| 439 |
+
"learning_rate": 2.807753296730219e-06,
|
| 440 |
+
"loss": 0.7564,
|
| 441 |
"step": 550
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 0.25112107623318386,
|
| 445 |
+
"grad_norm": 1.350460716883926,
|
| 446 |
+
"learning_rate": 2.7960931958133183e-06,
|
| 447 |
+
"loss": 0.7424,
|
| 448 |
"step": 560
|
| 449 |
},
|
| 450 |
{
|
| 451 |
"epoch": 0.2556053811659193,
|
| 452 |
+
"grad_norm": 1.522474854464212,
|
| 453 |
+
"learning_rate": 2.7841155300922202e-06,
|
| 454 |
+
"loss": 0.7331,
|
| 455 |
"step": 570
|
| 456 |
},
|
| 457 |
{
|
| 458 |
"epoch": 0.2600896860986547,
|
| 459 |
+
"grad_norm": 1.448720887976205,
|
| 460 |
+
"learning_rate": 2.7718232342980693e-06,
|
| 461 |
+
"loss": 0.7657,
|
| 462 |
"step": 580
|
| 463 |
},
|
| 464 |
{
|
| 465 |
"epoch": 0.2645739910313901,
|
| 466 |
+
"grad_norm": 1.6744619426337854,
|
| 467 |
+
"learning_rate": 2.759219320251714e-06,
|
| 468 |
+
"loss": 0.7363,
|
| 469 |
"step": 590
|
| 470 |
},
|
| 471 |
{
|
| 472 |
"epoch": 0.26905829596412556,
|
| 473 |
+
"grad_norm": 1.3585539591402243,
|
| 474 |
+
"learning_rate": 2.7463068761257554e-06,
|
| 475 |
+
"loss": 0.7458,
|
| 476 |
+
"step": 600
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.26905829596412556,
|
| 480 |
+
"eval_loss": 0.7505608797073364,
|
| 481 |
+
"eval_runtime": 408.9234,
|
| 482 |
+
"eval_samples_per_second": 122.461,
|
| 483 |
+
"eval_steps_per_second": 1.915,
|
| 484 |
"step": 600
|
| 485 |
},
|
| 486 |
{
|
| 487 |
"epoch": 0.273542600896861,
|
| 488 |
+
"grad_norm": 1.580932873164111,
|
| 489 |
+
"learning_rate": 2.7330890656878943e-06,
|
| 490 |
+
"loss": 0.7565,
|
| 491 |
"step": 610
|
| 492 |
},
|
| 493 |
{
|
| 494 |
"epoch": 0.27802690582959644,
|
| 495 |
+
"grad_norm": 1.5329888412189265,
|
| 496 |
+
"learning_rate": 2.7195691275257547e-06,
|
| 497 |
+
"loss": 0.7457,
|
| 498 |
"step": 620
|
| 499 |
},
|
| 500 |
{
|
| 501 |
"epoch": 0.2825112107623318,
|
| 502 |
+
"grad_norm": 1.6754413400622026,
|
| 503 |
+
"learning_rate": 2.7057503742533753e-06,
|
| 504 |
+
"loss": 0.7392,
|
| 505 |
"step": 630
|
| 506 |
},
|
| 507 |
{
|
| 508 |
"epoch": 0.28699551569506726,
|
| 509 |
+
"grad_norm": 1.6247897070260917,
|
| 510 |
+
"learning_rate": 2.691636191699562e-06,
|
| 511 |
+
"loss": 0.758,
|
| 512 |
"step": 640
|
| 513 |
},
|
| 514 |
{
|
| 515 |
"epoch": 0.2914798206278027,
|
| 516 |
+
"grad_norm": 1.42356323236888,
|
| 517 |
+
"learning_rate": 2.6772300380783013e-06,
|
| 518 |
+
"loss": 0.7626,
|
| 519 |
"step": 650
|
| 520 |
},
|
| 521 |
{
|
| 522 |
"epoch": 0.29596412556053814,
|
| 523 |
+
"grad_norm": 1.4955853270730488,
|
| 524 |
+
"learning_rate": 2.662535443141443e-06,
|
| 525 |
+
"loss": 0.7355,
|
| 526 |
"step": 660
|
| 527 |
},
|
| 528 |
{
|
| 529 |
"epoch": 0.3004484304932735,
|
| 530 |
+
"grad_norm": 1.4879073313151545,
|
| 531 |
+
"learning_rate": 2.647556007313847e-06,
|
| 532 |
+
"loss": 0.7545,
|
| 533 |
"step": 670
|
| 534 |
},
|
| 535 |
{
|
| 536 |
"epoch": 0.30493273542600896,
|
| 537 |
+
"grad_norm": 1.4153755477305148,
|
| 538 |
+
"learning_rate": 2.6322954008112213e-06,
|
| 539 |
+
"loss": 0.7378,
|
| 540 |
"step": 680
|
| 541 |
},
|
| 542 |
{
|
| 543 |
"epoch": 0.3094170403587444,
|
| 544 |
+
"grad_norm": 1.4019993036978922,
|
| 545 |
+
"learning_rate": 2.616757362740855e-06,
|
| 546 |
+
"loss": 0.7387,
|
| 547 |
"step": 690
|
| 548 |
},
|
| 549 |
{
|
| 550 |
"epoch": 0.31390134529147984,
|
| 551 |
+
"grad_norm": 1.5335241758091316,
|
| 552 |
+
"learning_rate": 2.600945700185474e-06,
|
| 553 |
+
"loss": 0.7694,
|
| 554 |
+
"step": 700
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.31390134529147984,
|
| 558 |
+
"eval_loss": 0.7457958459854126,
|
| 559 |
+
"eval_runtime": 408.7761,
|
| 560 |
+
"eval_samples_per_second": 122.505,
|
| 561 |
+
"eval_steps_per_second": 1.915,
|
| 562 |
"step": 700
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"epoch": 0.3183856502242152,
|
| 566 |
+
"grad_norm": 1.47263429505246,
|
| 567 |
+
"learning_rate": 2.5848642872704417e-06,
|
| 568 |
+
"loss": 0.7246,
|
| 569 |
"step": 710
|
| 570 |
},
|
| 571 |
{
|
| 572 |
"epoch": 0.32286995515695066,
|
| 573 |
+
"grad_norm": 1.5062835613914285,
|
| 574 |
+
"learning_rate": 2.5685170642145337e-06,
|
| 575 |
+
"loss": 0.7338,
|
| 576 |
"step": 720
|
| 577 |
},
|
| 578 |
{
|
| 579 |
"epoch": 0.3273542600896861,
|
| 580 |
+
"grad_norm": 1.6182138547104117,
|
| 581 |
+
"learning_rate": 2.5519080363645134e-06,
|
| 582 |
+
"loss": 0.73,
|
| 583 |
"step": 730
|
| 584 |
},
|
| 585 |
{
|
| 586 |
"epoch": 0.33183856502242154,
|
| 587 |
+
"grad_norm": 1.3515300425343295,
|
| 588 |
+
"learning_rate": 2.53504127321376e-06,
|
| 589 |
+
"loss": 0.7299,
|
| 590 |
"step": 740
|
| 591 |
},
|
| 592 |
{
|
| 593 |
"epoch": 0.336322869955157,
|
| 594 |
+
"grad_norm": 1.5798782493243635,
|
| 595 |
+
"learning_rate": 2.517920907405168e-06,
|
| 596 |
+
"loss": 0.7293,
|
| 597 |
"step": 750
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 0.34080717488789236,
|
| 601 |
+
"grad_norm": 1.4549259580353344,
|
| 602 |
+
"learning_rate": 2.5005511337185824e-06,
|
| 603 |
+
"loss": 0.7621,
|
| 604 |
"step": 760
|
| 605 |
},
|
| 606 |
{
|
| 607 |
"epoch": 0.3452914798206278,
|
| 608 |
+
"grad_norm": 1.456599605633329,
|
| 609 |
+
"learning_rate": 2.4829362080430077e-06,
|
| 610 |
+
"loss": 0.7438,
|
| 611 |
"step": 770
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 0.34977578475336324,
|
| 615 |
+
"grad_norm": 1.4128813340833153,
|
| 616 |
+
"learning_rate": 2.4650804463338406e-06,
|
| 617 |
+
"loss": 0.7413,
|
| 618 |
"step": 780
|
| 619 |
},
|
| 620 |
{
|
| 621 |
"epoch": 0.3542600896860987,
|
| 622 |
+
"grad_norm": 1.5613737124434628,
|
| 623 |
+
"learning_rate": 2.4469882235553887e-06,
|
| 624 |
+
"loss": 0.7477,
|
| 625 |
"step": 790
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"epoch": 0.35874439461883406,
|
| 629 |
+
"grad_norm": 1.6383373422678345,
|
| 630 |
+
"learning_rate": 2.4286639726089293e-06,
|
| 631 |
+
"loss": 0.713,
|
| 632 |
+
"step": 800
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.35874439461883406,
|
| 636 |
+
"eval_loss": 0.7421520352363586,
|
| 637 |
+
"eval_runtime": 408.0589,
|
| 638 |
+
"eval_samples_per_second": 122.72,
|
| 639 |
+
"eval_steps_per_second": 1.919,
|
| 640 |
"step": 800
|
| 641 |
},
|
| 642 |
{
|
| 643 |
"epoch": 0.3632286995515695,
|
| 644 |
+
"grad_norm": 1.3492102003393152,
|
| 645 |
+
"learning_rate": 2.4101121832465754e-06,
|
| 646 |
+
"loss": 0.7185,
|
| 647 |
"step": 810
|
| 648 |
},
|
| 649 |
{
|
| 650 |
"epoch": 0.36771300448430494,
|
| 651 |
+
"grad_norm": 1.4117655797526263,
|
| 652 |
+
"learning_rate": 2.3913374009712084e-06,
|
| 653 |
+
"loss": 0.7379,
|
| 654 |
"step": 820
|
| 655 |
},
|
| 656 |
{
|
| 657 |
"epoch": 0.3721973094170404,
|
| 658 |
+
"grad_norm": 1.5281693242796246,
|
| 659 |
+
"learning_rate": 2.3723442259227547e-06,
|
| 660 |
+
"loss": 0.7406,
|
| 661 |
"step": 830
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"epoch": 0.37668161434977576,
|
| 665 |
+
"grad_norm": 1.6990323130848894,
|
| 666 |
+
"learning_rate": 2.3531373117510695e-06,
|
| 667 |
+
"loss": 0.7388,
|
| 668 |
"step": 840
|
| 669 |
},
|
| 670 |
{
|
| 671 |
"epoch": 0.3811659192825112,
|
| 672 |
+
"grad_norm": 1.476162200960684,
|
| 673 |
+
"learning_rate": 2.33372136447572e-06,
|
| 674 |
+
"loss": 0.7434,
|
| 675 |
"step": 850
|
| 676 |
},
|
| 677 |
{
|
| 678 |
"epoch": 0.38565022421524664,
|
| 679 |
+
"grad_norm": 1.3930484173784414,
|
| 680 |
+
"learning_rate": 2.3141011413329244e-06,
|
| 681 |
+
"loss": 0.7372,
|
| 682 |
"step": 860
|
| 683 |
},
|
| 684 |
{
|
| 685 |
"epoch": 0.3901345291479821,
|
| 686 |
+
"grad_norm": 1.4071716332679987,
|
| 687 |
+
"learning_rate": 2.2942814496099532e-06,
|
| 688 |
+
"loss": 0.7531,
|
| 689 |
"step": 870
|
| 690 |
},
|
| 691 |
{
|
| 692 |
"epoch": 0.39461883408071746,
|
| 693 |
+
"grad_norm": 1.5479232446038012,
|
| 694 |
+
"learning_rate": 2.274267145467259e-06,
|
| 695 |
+
"loss": 0.7216,
|
| 696 |
"step": 880
|
| 697 |
},
|
| 698 |
{
|
| 699 |
"epoch": 0.3991031390134529,
|
| 700 |
+
"grad_norm": 1.4255077423798548,
|
| 701 |
+
"learning_rate": 2.254063132748637e-06,
|
| 702 |
+
"loss": 0.7343,
|
| 703 |
"step": 890
|
| 704 |
},
|
| 705 |
{
|
| 706 |
"epoch": 0.40358744394618834,
|
| 707 |
+
"grad_norm": 1.57276996130409,
|
| 708 |
+
"learning_rate": 2.2336743617797006e-06,
|
| 709 |
+
"loss": 0.7347,
|
| 710 |
+
"step": 900
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.40358744394618834,
|
| 714 |
+
"eval_loss": 0.7386789321899414,
|
| 715 |
+
"eval_runtime": 408.1839,
|
| 716 |
+
"eval_samples_per_second": 122.682,
|
| 717 |
+
"eval_steps_per_second": 1.918,
|
| 718 |
"step": 900
|
| 719 |
},
|
| 720 |
{
|
| 721 |
"epoch": 0.4080717488789238,
|
| 722 |
+
"grad_norm": 1.4568107529063017,
|
| 723 |
+
"learning_rate": 2.213105828154964e-06,
|
| 724 |
+
"loss": 0.7266,
|
| 725 |
"step": 910
|
| 726 |
},
|
| 727 |
{
|
| 728 |
"epoch": 0.4125560538116592,
|
| 729 |
+
"grad_norm": 1.374198091231606,
|
| 730 |
+
"learning_rate": 2.192362571513841e-06,
|
| 731 |
+
"loss": 0.7465,
|
| 732 |
"step": 920
|
| 733 |
},
|
| 734 |
{
|
| 735 |
"epoch": 0.4170403587443946,
|
| 736 |
+
"grad_norm": 1.3925457206301284,
|
| 737 |
+
"learning_rate": 2.171449674305846e-06,
|
| 738 |
+
"loss": 0.7427,
|
| 739 |
"step": 930
|
| 740 |
},
|
| 741 |
{
|
| 742 |
"epoch": 0.42152466367713004,
|
| 743 |
+
"grad_norm": 1.4443502855856463,
|
| 744 |
+
"learning_rate": 2.1503722605453083e-06,
|
| 745 |
+
"loss": 0.7428,
|
| 746 |
"step": 940
|
| 747 |
},
|
| 748 |
{
|
| 749 |
"epoch": 0.4260089686098655,
|
| 750 |
+
"grad_norm": 1.5268146365443709,
|
| 751 |
+
"learning_rate": 2.1291354945559004e-06,
|
| 752 |
+
"loss": 0.7163,
|
| 753 |
"step": 950
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 0.4304932735426009,
|
| 757 |
+
"grad_norm": 1.5000325455240473,
|
| 758 |
+
"learning_rate": 2.1077445797052945e-06,
|
| 759 |
+
"loss": 0.7472,
|
| 760 |
"step": 960
|
| 761 |
},
|
| 762 |
{
|
| 763 |
"epoch": 0.4349775784753363,
|
| 764 |
+
"grad_norm": 1.4869091852092478,
|
| 765 |
+
"learning_rate": 2.086204757130243e-06,
|
| 766 |
+
"loss": 0.7427,
|
| 767 |
"step": 970
|
| 768 |
},
|
| 769 |
{
|
| 770 |
"epoch": 0.43946188340807174,
|
| 771 |
+
"grad_norm": 1.4430282256544564,
|
| 772 |
+
"learning_rate": 2.0645213044524194e-06,
|
| 773 |
+
"loss": 0.7174,
|
| 774 |
"step": 980
|
| 775 |
},
|
| 776 |
{
|
| 777 |
"epoch": 0.4439461883408072,
|
| 778 |
+
"grad_norm": 1.4822025498870304,
|
| 779 |
+
"learning_rate": 2.0426995344853043e-06,
|
| 780 |
+
"loss": 0.7538,
|
| 781 |
"step": 990
|
| 782 |
},
|
| 783 |
{
|
| 784 |
"epoch": 0.4484304932735426,
|
| 785 |
+
"grad_norm": 1.5186234240452396,
|
| 786 |
+
"learning_rate": 2.0207447939324598e-06,
|
| 787 |
+
"loss": 0.7243,
|
| 788 |
+
"step": 1000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.4484304932735426,
|
| 792 |
+
"eval_loss": 0.7356163859367371,
|
| 793 |
+
"eval_runtime": 407.0139,
|
| 794 |
+
"eval_samples_per_second": 123.035,
|
| 795 |
+
"eval_steps_per_second": 1.924,
|
| 796 |
"step": 1000
|
| 797 |
},
|
| 798 |
{
|
| 799 |
"epoch": 0.452914798206278,
|
| 800 |
+
"grad_norm": 1.5742685454152958,
|
| 801 |
+
"learning_rate": 1.998662462077496e-06,
|
| 802 |
+
"loss": 0.7475,
|
| 803 |
"step": 1010
|
| 804 |
},
|
| 805 |
{
|
| 806 |
"epoch": 0.45739910313901344,
|
| 807 |
+
"grad_norm": 1.3834168469611057,
|
| 808 |
+
"learning_rate": 1.976457949466054e-06,
|
| 809 |
+
"loss": 0.7568,
|
| 810 |
"step": 1020
|
| 811 |
},
|
| 812 |
{
|
| 813 |
"epoch": 0.4618834080717489,
|
| 814 |
+
"grad_norm": 1.4947961999330186,
|
| 815 |
+
"learning_rate": 1.954136696580132e-06,
|
| 816 |
+
"loss": 0.7464,
|
| 817 |
"step": 1030
|
| 818 |
},
|
| 819 |
{
|
| 820 |
"epoch": 0.4663677130044843,
|
| 821 |
+
"grad_norm": 1.4284253764088304,
|
| 822 |
+
"learning_rate": 1.9317041725050747e-06,
|
| 823 |
+
"loss": 0.7456,
|
| 824 |
"step": 1040
|
| 825 |
},
|
| 826 |
{
|
| 827 |
"epoch": 0.47085201793721976,
|
| 828 |
+
"grad_norm": 1.4247354157320633,
|
| 829 |
+
"learning_rate": 1.909165873589554e-06,
|
| 830 |
+
"loss": 0.7008,
|
| 831 |
"step": 1050
|
| 832 |
},
|
| 833 |
{
|
| 834 |
"epoch": 0.47533632286995514,
|
| 835 |
+
"grad_norm": 1.4525308368306575,
|
| 836 |
+
"learning_rate": 1.886527322098871e-06,
|
| 837 |
+
"loss": 0.7121,
|
| 838 |
"step": 1060
|
| 839 |
},
|
| 840 |
{
|
| 841 |
"epoch": 0.4798206278026906,
|
| 842 |
+
"grad_norm": 1.43738036112722,
|
| 843 |
+
"learning_rate": 1.8637940648619065e-06,
|
| 844 |
+
"loss": 0.7308,
|
| 845 |
"step": 1070
|
| 846 |
},
|
| 847 |
{
|
| 848 |
"epoch": 0.484304932735426,
|
| 849 |
+
"grad_norm": 1.402086349899742,
|
| 850 |
+
"learning_rate": 1.8409716719120561e-06,
|
| 851 |
+
"loss": 0.7164,
|
| 852 |
"step": 1080
|
| 853 |
},
|
| 854 |
{
|
| 855 |
"epoch": 0.48878923766816146,
|
| 856 |
+
"grad_norm": 1.5227358428935063,
|
| 857 |
+
"learning_rate": 1.8180657351224739e-06,
|
| 858 |
+
"loss": 0.732,
|
| 859 |
"step": 1090
|
| 860 |
},
|
| 861 |
{
|
| 862 |
"epoch": 0.49327354260089684,
|
| 863 |
+
"grad_norm": 1.5813743714389112,
|
| 864 |
+
"learning_rate": 1.7950818668359733e-06,
|
| 865 |
+
"loss": 0.7161,
|
| 866 |
+
"step": 1100
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.49327354260089684,
|
| 870 |
+
"eval_loss": 0.7330535054206848,
|
| 871 |
+
"eval_runtime": 408.4081,
|
| 872 |
+
"eval_samples_per_second": 122.615,
|
| 873 |
+
"eval_steps_per_second": 1.917,
|
| 874 |
"step": 1100
|
| 875 |
},
|
| 876 |
{
|
| 877 |
"epoch": 0.4977578475336323,
|
| 878 |
+
"grad_norm": 1.4881819590713468,
|
| 879 |
+
"learning_rate": 1.772025698489903e-06,
|
| 880 |
+
"loss": 0.7144,
|
| 881 |
"step": 1110
|
| 882 |
},
|
| 883 |
{
|
| 884 |
"epoch": 0.5022421524663677,
|
| 885 |
+
"grad_norm": 1.4750319990458514,
|
| 886 |
+
"learning_rate": 1.7489028792363549e-06,
|
| 887 |
+
"loss": 0.7365,
|
| 888 |
"step": 1120
|
| 889 |
},
|
| 890 |
{
|
| 891 |
"epoch": 0.5067264573991032,
|
| 892 |
+
"grad_norm": 1.4443590686278198,
|
| 893 |
+
"learning_rate": 1.7257190745580209e-06,
|
| 894 |
+
"loss": 0.7487,
|
| 895 |
"step": 1130
|
| 896 |
},
|
| 897 |
{
|
| 898 |
"epoch": 0.5112107623318386,
|
| 899 |
+
"grad_norm": 1.4695293763109774,
|
| 900 |
+
"learning_rate": 1.7024799648800555e-06,
|
| 901 |
+
"loss": 0.7233,
|
| 902 |
"step": 1140
|
| 903 |
},
|
| 904 |
{
|
| 905 |
"epoch": 0.515695067264574,
|
| 906 |
+
"grad_norm": 1.4328944860273993,
|
| 907 |
+
"learning_rate": 1.679191244178278e-06,
|
| 908 |
+
"loss": 0.7322,
|
| 909 |
"step": 1150
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 0.5201793721973094,
|
| 913 |
+
"grad_norm": 1.4157130638413895,
|
| 914 |
+
"learning_rate": 1.6558586185840473e-06,
|
| 915 |
+
"loss": 0.728,
|
| 916 |
"step": 1160
|
| 917 |
},
|
| 918 |
{
|
| 919 |
"epoch": 0.5246636771300448,
|
| 920 |
+
"grad_norm": 1.4117533616122613,
|
| 921 |
+
"learning_rate": 1.6324878049861656e-06,
|
| 922 |
+
"loss": 0.7331,
|
| 923 |
"step": 1170
|
| 924 |
},
|
| 925 |
{
|
| 926 |
"epoch": 0.5291479820627802,
|
| 927 |
+
"grad_norm": 1.4255877674393056,
|
| 928 |
+
"learning_rate": 1.609084529630145e-06,
|
| 929 |
+
"loss": 0.7491,
|
| 930 |
"step": 1180
|
| 931 |
},
|
| 932 |
{
|
| 933 |
"epoch": 0.5336322869955157,
|
| 934 |
+
"grad_norm": 1.4486300200418207,
|
| 935 |
+
"learning_rate": 1.5856545267151759e-06,
|
| 936 |
+
"loss": 0.7261,
|
| 937 |
"step": 1190
|
| 938 |
},
|
| 939 |
{
|
| 940 |
"epoch": 0.5381165919282511,
|
| 941 |
+
"grad_norm": 1.4628618883782867,
|
| 942 |
+
"learning_rate": 1.5622035369891561e-06,
|
| 943 |
+
"loss": 0.7247,
|
| 944 |
+
"step": 1200
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 0.5381165919282511,
|
| 948 |
+
"eval_loss": 0.7308038473129272,
|
| 949 |
+
"eval_runtime": 406.6873,
|
| 950 |
+
"eval_samples_per_second": 123.134,
|
| 951 |
+
"eval_steps_per_second": 1.925,
|
| 952 |
"step": 1200
|
| 953 |
},
|
| 954 |
{
|
| 955 |
"epoch": 0.5426008968609866,
|
| 956 |
+
"grad_norm": 1.4112256357672157,
|
| 957 |
+
"learning_rate": 1.5387373063421062e-06,
|
| 958 |
+
"loss": 0.7307,
|
| 959 |
"step": 1210
|
| 960 |
},
|
| 961 |
{
|
| 962 |
"epoch": 0.547085201793722,
|
| 963 |
+
"grad_norm": 1.3994109954542429,
|
| 964 |
+
"learning_rate": 1.515261584398333e-06,
|
| 965 |
+
"loss": 0.7062,
|
| 966 |
"step": 1220
|
| 967 |
},
|
| 968 |
{
|
| 969 |
"epoch": 0.5515695067264574,
|
| 970 |
+
"grad_norm": 1.5279436893984248,
|
| 971 |
+
"learning_rate": 1.491782123107669e-06,
|
| 972 |
+
"loss": 0.7314,
|
| 973 |
"step": 1230
|
| 974 |
},
|
| 975 |
{
|
| 976 |
"epoch": 0.5560538116591929,
|
| 977 |
+
"grad_norm": 1.4092281762272858,
|
| 978 |
+
"learning_rate": 1.4683046753361521e-06,
|
| 979 |
+
"loss": 0.7044,
|
| 980 |
"step": 1240
|
| 981 |
},
|
| 982 |
{
|
| 983 |
"epoch": 0.5605381165919282,
|
| 984 |
+
"grad_norm": 1.4363381867810665,
|
| 985 |
+
"learning_rate": 1.4448349934564736e-06,
|
| 986 |
+
"loss": 0.7287,
|
| 987 |
"step": 1250
|
| 988 |
},
|
| 989 |
{
|
| 990 |
"epoch": 0.5650224215246636,
|
| 991 |
+
"grad_norm": 1.4913351223697051,
|
| 992 |
+
"learning_rate": 1.421378827938549e-06,
|
| 993 |
+
"loss": 0.7254,
|
| 994 |
"step": 1260
|
| 995 |
},
|
| 996 |
{
|
| 997 |
"epoch": 0.5695067264573991,
|
| 998 |
+
"grad_norm": 1.5096384680619075,
|
| 999 |
+
"learning_rate": 1.3979419259405563e-06,
|
| 1000 |
+
"loss": 0.7389,
|
| 1001 |
"step": 1270
|
| 1002 |
},
|
| 1003 |
{
|
| 1004 |
"epoch": 0.5739910313901345,
|
| 1005 |
+
"grad_norm": 1.3495144573299676,
|
| 1006 |
+
"learning_rate": 1.3745300299007856e-06,
|
| 1007 |
+
"loss": 0.7247,
|
| 1008 |
"step": 1280
|
| 1009 |
},
|
| 1010 |
{
|
| 1011 |
"epoch": 0.57847533632287,
|
| 1012 |
+
"grad_norm": 1.3641879848291365,
|
| 1013 |
+
"learning_rate": 1.3511488761306412e-06,
|
| 1014 |
+
"loss": 0.7312,
|
| 1015 |
"step": 1290
|
| 1016 |
},
|
| 1017 |
{
|
| 1018 |
"epoch": 0.5829596412556054,
|
| 1019 |
+
"grad_norm": 1.3879105033157129,
|
| 1020 |
+
"learning_rate": 1.3278041934091524e-06,
|
| 1021 |
+
"loss": 0.7477,
|
| 1022 |
+
"step": 1300
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 0.5829596412556054,
|
| 1026 |
+
"eval_loss": 0.7287724018096924,
|
| 1027 |
+
"eval_runtime": 406.882,
|
| 1028 |
+
"eval_samples_per_second": 123.075,
|
| 1029 |
+
"eval_steps_per_second": 1.924,
|
| 1030 |
"step": 1300
|
| 1031 |
},
|
| 1032 |
{
|
| 1033 |
"epoch": 0.5874439461883408,
|
| 1034 |
+
"grad_norm": 1.3916697284582622,
|
| 1035 |
+
"learning_rate": 1.3045017015793217e-06,
|
| 1036 |
+
"loss": 0.7246,
|
| 1037 |
"step": 1310
|
| 1038 |
},
|
| 1039 |
{
|
| 1040 |
"epoch": 0.5919282511210763,
|
| 1041 |
+
"grad_norm": 1.4328511876779917,
|
| 1042 |
+
"learning_rate": 1.2812471101466687e-06,
|
| 1043 |
+
"loss": 0.7303,
|
| 1044 |
"step": 1320
|
| 1045 |
},
|
| 1046 |
{
|
| 1047 |
"epoch": 0.5964125560538116,
|
| 1048 |
+
"grad_norm": 1.4411092846252307,
|
| 1049 |
+
"learning_rate": 1.2580461168803038e-06,
|
| 1050 |
+
"loss": 0.7318,
|
| 1051 |
"step": 1330
|
| 1052 |
},
|
| 1053 |
{
|
| 1054 |
"epoch": 0.600896860986547,
|
| 1055 |
+
"grad_norm": 1.4703965551927338,
|
| 1056 |
+
"learning_rate": 1.2349044064168782e-06,
|
| 1057 |
+
"loss": 0.7375,
|
| 1058 |
"step": 1340
|
| 1059 |
},
|
| 1060 |
{
|
| 1061 |
"epoch": 0.6053811659192825,
|
| 1062 |
+
"grad_norm": 1.4319057117061509,
|
| 1063 |
+
"learning_rate": 1.21182764886775e-06,
|
| 1064 |
+
"loss": 0.7302,
|
| 1065 |
"step": 1350
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
"epoch": 0.6098654708520179,
|
| 1069 |
+
"grad_norm": 1.5017976848926429,
|
| 1070 |
+
"learning_rate": 1.188821498429714e-06,
|
| 1071 |
+
"loss": 0.7262,
|
| 1072 |
"step": 1360
|
| 1073 |
},
|
| 1074 |
{
|
| 1075 |
"epoch": 0.6143497757847534,
|
| 1076 |
+
"grad_norm": 1.4553869576056546,
|
| 1077 |
+
"learning_rate": 1.165891591999626e-06,
|
| 1078 |
+
"loss": 0.7447,
|
| 1079 |
"step": 1370
|
| 1080 |
},
|
| 1081 |
{
|
| 1082 |
"epoch": 0.6188340807174888,
|
| 1083 |
+
"grad_norm": 1.4128744043127173,
|
| 1084 |
+
"learning_rate": 1.1430435477932646e-06,
|
| 1085 |
+
"loss": 0.7423,
|
| 1086 |
"step": 1380
|
| 1087 |
},
|
| 1088 |
{
|
| 1089 |
"epoch": 0.6233183856502242,
|
| 1090 |
+
"grad_norm": 1.3797159286061107,
|
| 1091 |
+
"learning_rate": 1.1202829639687785e-06,
|
| 1092 |
+
"loss": 0.744,
|
| 1093 |
"step": 1390
|
| 1094 |
},
|
| 1095 |
{
|
| 1096 |
"epoch": 0.6278026905829597,
|
| 1097 |
+
"grad_norm": 1.487304571595245,
|
| 1098 |
+
"learning_rate": 1.0976154172550408e-06,
|
| 1099 |
+
"loss": 0.7429,
|
| 1100 |
+
"step": 1400
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 0.6278026905829597,
|
| 1104 |
+
"eval_loss": 0.7272571921348572,
|
| 1105 |
+
"eval_runtime": 406.7541,
|
| 1106 |
+
"eval_samples_per_second": 123.114,
|
| 1107 |
+
"eval_steps_per_second": 1.925,
|
| 1108 |
"step": 1400
|
| 1109 |
},
|
| 1110 |
{
|
| 1111 |
"epoch": 0.6322869955156951,
|
| 1112 |
+
"grad_norm": 1.544512062570189,
|
| 1113 |
+
"learning_rate": 1.0750464615852523e-06,
|
| 1114 |
+
"loss": 0.7251,
|
| 1115 |
"step": 1410
|
| 1116 |
},
|
| 1117 |
{
|
| 1118 |
"epoch": 0.6367713004484304,
|
| 1119 |
+
"grad_norm": 1.422563130817404,
|
| 1120 |
+
"learning_rate": 1.0525816267361398e-06,
|
| 1121 |
+
"loss": 0.712,
|
| 1122 |
"step": 1420
|
| 1123 |
},
|
| 1124 |
{
|
| 1125 |
"epoch": 0.6412556053811659,
|
| 1126 |
+
"grad_norm": 1.4937681764382644,
|
| 1127 |
+
"learning_rate": 1.0302264169730613e-06,
|
| 1128 |
+
"loss": 0.7203,
|
| 1129 |
"step": 1430
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
"epoch": 0.6457399103139013,
|
| 1133 |
+
"grad_norm": 1.50738757049434,
|
| 1134 |
+
"learning_rate": 1.0079863097013722e-06,
|
| 1135 |
+
"loss": 0.7121,
|
| 1136 |
"step": 1440
|
| 1137 |
},
|
| 1138 |
{
|
| 1139 |
"epoch": 0.6502242152466368,
|
| 1140 |
+
"grad_norm": 1.286396172710849,
|
| 1141 |
+
"learning_rate": 9.85866754124367e-07,
|
| 1142 |
+
"loss": 0.7193,
|
| 1143 |
"step": 1450
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
"epoch": 0.6547085201793722,
|
| 1147 |
+
"grad_norm": 1.4997539342741677,
|
| 1148 |
+
"learning_rate": 9.638731699081281e-07,
|
| 1149 |
+
"loss": 0.7288,
|
| 1150 |
"step": 1460
|
| 1151 |
},
|
| 1152 |
{
|
| 1153 |
"epoch": 0.6591928251121076,
|
| 1154 |
+
"grad_norm": 1.37434247409356,
|
| 1155 |
+
"learning_rate": 9.42010945853623e-07,
|
| 1156 |
+
"loss": 0.7597,
|
| 1157 |
"step": 1470
|
| 1158 |
},
|
| 1159 |
{
|
| 1160 |
"epoch": 0.6636771300448431,
|
| 1161 |
+
"grad_norm": 1.3869436283100607,
|
| 1162 |
+
"learning_rate": 9.202854385763502e-07,
|
| 1163 |
+
"loss": 0.7184,
|
| 1164 |
"step": 1480
|
| 1165 |
},
|
| 1166 |
{
|
| 1167 |
"epoch": 0.6681614349775785,
|
| 1168 |
+
"grad_norm": 1.3970067087387381,
|
| 1169 |
+
"learning_rate": 8.987019711938812e-07,
|
| 1170 |
+
"loss": 0.7326,
|
| 1171 |
"step": 1490
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
"epoch": 0.672645739910314,
|
| 1175 |
+
"grad_norm": 1.553183464191494,
|
| 1176 |
+
"learning_rate": 8.772658320216047e-07,
|
| 1177 |
+
"loss": 0.7317,
|
| 1178 |
+
"step": 1500
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.672645739910314,
|
| 1182 |
+
"eval_loss": 0.7256098389625549,
|
| 1183 |
+
"eval_runtime": 406.6132,
|
| 1184 |
+
"eval_samples_per_second": 123.156,
|
| 1185 |
+
"eval_steps_per_second": 1.926,
|
| 1186 |
"step": 1500
|
| 1187 |
},
|
| 1188 |
{
|
| 1189 |
"epoch": 0.6771300448430493,
|
| 1190 |
+
"grad_norm": 1.3357768297094936,
|
| 1191 |
+
"learning_rate": 8.55982273277002e-07,
|
| 1192 |
+
"loss": 0.7347,
|
| 1193 |
"step": 1510
|
| 1194 |
},
|
| 1195 |
{
|
| 1196 |
"epoch": 0.6816143497757847,
|
| 1197 |
+
"grad_norm": 1.3249788097985131,
|
| 1198 |
+
"learning_rate": 8.348565097927605e-07,
|
| 1199 |
+
"loss": 0.7496,
|
| 1200 |
"step": 1520
|
| 1201 |
},
|
| 1202 |
{
|
| 1203 |
"epoch": 0.6860986547085202,
|
| 1204 |
+
"grad_norm": 1.4578138220875878,
|
| 1205 |
+
"learning_rate": 8.13893717739056e-07,
|
| 1206 |
+
"loss": 0.7308,
|
| 1207 |
"step": 1530
|
| 1208 |
},
|
| 1209 |
{
|
| 1210 |
"epoch": 0.6905829596412556,
|
| 1211 |
+
"grad_norm": 1.3268077719441809,
|
| 1212 |
+
"learning_rate": 7.930990333553013e-07,
|
| 1213 |
+
"loss": 0.7094,
|
| 1214 |
"step": 1540
|
| 1215 |
},
|
| 1216 |
{
|
| 1217 |
"epoch": 0.695067264573991,
|
| 1218 |
+
"grad_norm": 1.47562182506043,
|
| 1219 |
+
"learning_rate": 7.72477551691678e-07,
|
| 1220 |
+
"loss": 0.697,
|
| 1221 |
"step": 1550
|
| 1222 |
},
|
| 1223 |
{
|
| 1224 |
"epoch": 0.6995515695067265,
|
| 1225 |
+
"grad_norm": 1.4850843190566259,
|
| 1226 |
+
"learning_rate": 7.520343253607677e-07,
|
| 1227 |
+
"loss": 0.7301,
|
| 1228 |
"step": 1560
|
| 1229 |
},
|
| 1230 |
{
|
| 1231 |
"epoch": 0.7040358744394619,
|
| 1232 |
+
"grad_norm": 1.5097763618083517,
|
| 1233 |
+
"learning_rate": 7.317743632995731e-07,
|
| 1234 |
+
"loss": 0.7217,
|
| 1235 |
"step": 1570
|
| 1236 |
},
|
| 1237 |
{
|
| 1238 |
"epoch": 0.7085201793721974,
|
| 1239 |
+
"grad_norm": 1.3914348509226637,
|
| 1240 |
+
"learning_rate": 7.117026295422425e-07,
|
| 1241 |
+
"loss": 0.6957,
|
| 1242 |
"step": 1580
|
| 1243 |
},
|
| 1244 |
{
|
| 1245 |
"epoch": 0.7130044843049327,
|
| 1246 |
+
"grad_norm": 1.5175208261545492,
|
| 1247 |
+
"learning_rate": 6.918240420038007e-07,
|
| 1248 |
+
"loss": 0.7317,
|
| 1249 |
"step": 1590
|
| 1250 |
},
|
| 1251 |
{
|
| 1252 |
"epoch": 0.7174887892376681,
|
| 1253 |
+
"grad_norm": 1.4947559578839034,
|
| 1254 |
+
"learning_rate": 6.721434712751745e-07,
|
| 1255 |
+
"loss": 0.7226,
|
| 1256 |
+
"step": 1600
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.7174887892376681,
|
| 1260 |
+
"eval_loss": 0.7243176102638245,
|
| 1261 |
+
"eval_runtime": 406.7899,
|
| 1262 |
+
"eval_samples_per_second": 123.103,
|
| 1263 |
+
"eval_steps_per_second": 1.925,
|
| 1264 |
"step": 1600
|
| 1265 |
},
|
| 1266 |
{
|
| 1267 |
"epoch": 0.7219730941704036,
|
| 1268 |
+
"grad_norm": 1.5192098207309965,
|
| 1269 |
+
"learning_rate": 6.526657394298154e-07,
|
| 1270 |
+
"loss": 0.705,
|
| 1271 |
"step": 1610
|
| 1272 |
},
|
| 1273 |
{
|
| 1274 |
"epoch": 0.726457399103139,
|
| 1275 |
+
"grad_norm": 1.3665027387136646,
|
| 1276 |
+
"learning_rate": 6.333956188422088e-07,
|
| 1277 |
+
"loss": 0.706,
|
| 1278 |
"step": 1620
|
| 1279 |
},
|
| 1280 |
{
|
| 1281 |
"epoch": 0.7309417040358744,
|
| 1282 |
+
"grad_norm": 1.4974912840899435,
|
| 1283 |
+
"learning_rate": 6.143378310185643e-07,
|
| 1284 |
+
"loss": 0.6983,
|
| 1285 |
"step": 1630
|
| 1286 |
},
|
| 1287 |
{
|
| 1288 |
"epoch": 0.7354260089686099,
|
| 1289 |
+
"grad_norm": 1.5477574584643699,
|
| 1290 |
+
"learning_rate": 5.954970454399638e-07,
|
| 1291 |
+
"loss": 0.7252,
|
| 1292 |
"step": 1640
|
| 1293 |
},
|
| 1294 |
{
|
| 1295 |
"epoch": 0.7399103139013453,
|
| 1296 |
+
"grad_norm": 1.525090065151942,
|
| 1297 |
+
"learning_rate": 5.768778784182616e-07,
|
| 1298 |
+
"loss": 0.7087,
|
| 1299 |
"step": 1650
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
"epoch": 0.7443946188340808,
|
| 1303 |
+
"grad_norm": 1.4837554579437873,
|
| 1304 |
+
"learning_rate": 5.584848919650069e-07,
|
| 1305 |
+
"loss": 0.7075,
|
| 1306 |
"step": 1660
|
| 1307 |
},
|
| 1308 |
{
|
| 1309 |
"epoch": 0.7488789237668162,
|
| 1310 |
+
"grad_norm": 1.3538329119260115,
|
| 1311 |
+
"learning_rate": 5.403225926736772e-07,
|
| 1312 |
+
"loss": 0.7057,
|
| 1313 |
"step": 1670
|
| 1314 |
},
|
| 1315 |
{
|
| 1316 |
"epoch": 0.7533632286995515,
|
| 1317 |
+
"grad_norm": 1.359895087573495,
|
| 1318 |
+
"learning_rate": 5.223954306154843e-07,
|
| 1319 |
+
"loss": 0.7306,
|
| 1320 |
"step": 1680
|
| 1321 |
},
|
| 1322 |
{
|
| 1323 |
"epoch": 0.757847533632287,
|
| 1324 |
+
"grad_norm": 1.4168148218595764,
|
| 1325 |
+
"learning_rate": 5.047077982490311e-07,
|
| 1326 |
+
"loss": 0.7424,
|
| 1327 |
"step": 1690
|
| 1328 |
},
|
| 1329 |
{
|
| 1330 |
"epoch": 0.7623318385650224,
|
| 1331 |
+
"grad_norm": 1.4815842671642683,
|
| 1332 |
+
"learning_rate": 4.872640293440861e-07,
|
| 1333 |
+
"loss": 0.695,
|
| 1334 |
+
"step": 1700
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 0.7623318385650224,
|
| 1338 |
+
"eval_loss": 0.7233718633651733,
|
| 1339 |
+
"eval_runtime": 406.8015,
|
| 1340 |
+
"eval_samples_per_second": 123.099,
|
| 1341 |
+
"eval_steps_per_second": 1.925,
|
| 1342 |
"step": 1700
|
| 1343 |
},
|
| 1344 |
{
|
| 1345 |
"epoch": 0.7668161434977578,
|
| 1346 |
+
"grad_norm": 1.5501655544071418,
|
| 1347 |
+
"learning_rate": 4.7006839791973673e-07,
|
| 1348 |
+
"loss": 0.7327,
|
| 1349 |
"step": 1710
|
| 1350 |
},
|
| 1351 |
{
|
| 1352 |
"epoch": 0.7713004484304933,
|
| 1353 |
+
"grad_norm": 1.3834984705411,
|
| 1354 |
+
"learning_rate": 4.53125117197179e-07,
|
| 1355 |
+
"loss": 0.7245,
|
| 1356 |
"step": 1720
|
| 1357 |
},
|
| 1358 |
{
|
| 1359 |
"epoch": 0.7757847533632287,
|
| 1360 |
+
"grad_norm": 1.4041748328697374,
|
| 1361 |
+
"learning_rate": 4.364383385674112e-07,
|
| 1362 |
+
"loss": 0.7054,
|
| 1363 |
"step": 1730
|
| 1364 |
},
|
| 1365 |
{
|
| 1366 |
"epoch": 0.7802690582959642,
|
| 1367 |
+
"grad_norm": 1.443104622604103,
|
| 1368 |
+
"learning_rate": 4.2001215057407026e-07,
|
| 1369 |
+
"loss": 0.7037,
|
| 1370 |
"step": 1740
|
| 1371 |
},
|
| 1372 |
{
|
| 1373 |
"epoch": 0.7847533632286996,
|
| 1374 |
+
"grad_norm": 1.5632699202433824,
|
| 1375 |
+
"learning_rate": 4.038505779116687e-07,
|
| 1376 |
+
"loss": 0.705,
|
| 1377 |
"step": 1750
|
| 1378 |
},
|
| 1379 |
{
|
| 1380 |
"epoch": 0.7892376681614349,
|
| 1381 |
+
"grad_norm": 1.349615732583278,
|
| 1382 |
+
"learning_rate": 3.879575804394782e-07,
|
| 1383 |
+
"loss": 0.7071,
|
| 1384 |
"step": 1760
|
| 1385 |
},
|
| 1386 |
{
|
| 1387 |
"epoch": 0.7937219730941704,
|
| 1388 |
+
"grad_norm": 1.3657530768128234,
|
| 1389 |
+
"learning_rate": 3.7233705221129646e-07,
|
| 1390 |
+
"loss": 0.7273,
|
| 1391 |
"step": 1770
|
| 1392 |
},
|
| 1393 |
{
|
| 1394 |
"epoch": 0.7982062780269058,
|
| 1395 |
+
"grad_norm": 1.5107387856649341,
|
| 1396 |
+
"learning_rate": 3.569928205213354e-07,
|
| 1397 |
+
"loss": 0.6975,
|
| 1398 |
"step": 1780
|
| 1399 |
},
|
| 1400 |
{
|
| 1401 |
"epoch": 0.8026905829596412,
|
| 1402 |
+
"grad_norm": 1.4525568524987686,
|
| 1403 |
+
"learning_rate": 3.419286449664741e-07,
|
| 1404 |
+
"loss": 0.7095,
|
| 1405 |
"step": 1790
|
| 1406 |
},
|
| 1407 |
{
|
| 1408 |
"epoch": 0.8071748878923767,
|
| 1409 |
+
"grad_norm": 1.4847854049722584,
|
| 1410 |
+
"learning_rate": 3.2714821652508854e-07,
|
| 1411 |
+
"loss": 0.7167,
|
| 1412 |
+
"step": 1800
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 0.8071748878923767,
|
| 1416 |
+
"eval_loss": 0.7225807309150696,
|
| 1417 |
+
"eval_runtime": 406.5326,
|
| 1418 |
+
"eval_samples_per_second": 123.181,
|
| 1419 |
+
"eval_steps_per_second": 1.926,
|
| 1420 |
"step": 1800
|
| 1421 |
},
|
| 1422 |
{
|
| 1423 |
"epoch": 0.8116591928251121,
|
| 1424 |
+
"grad_norm": 1.2447161837361285,
|
| 1425 |
+
"learning_rate": 3.126551566527036e-07,
|
| 1426 |
+
"loss": 0.7156,
|
| 1427 |
"step": 1810
|
| 1428 |
},
|
| 1429 |
{
|
| 1430 |
"epoch": 0.8161434977578476,
|
| 1431 |
+
"grad_norm": 1.4139333132454484,
|
| 1432 |
+
"learning_rate": 2.9845301639467284e-07,
|
| 1433 |
+
"loss": 0.7537,
|
| 1434 |
"step": 1820
|
| 1435 |
},
|
| 1436 |
{
|
| 1437 |
"epoch": 0.820627802690583,
|
| 1438 |
+
"grad_norm": 1.3663031642715642,
|
| 1439 |
+
"learning_rate": 2.8454527551611205e-07,
|
| 1440 |
+
"loss": 0.7238,
|
| 1441 |
"step": 1830
|
| 1442 |
},
|
| 1443 |
{
|
| 1444 |
"epoch": 0.8251121076233184,
|
| 1445 |
+
"grad_norm": 1.389263976301968,
|
| 1446 |
+
"learning_rate": 2.7093534164929904e-07,
|
| 1447 |
+
"loss": 0.738,
|
| 1448 |
"step": 1840
|
| 1449 |
},
|
| 1450 |
{
|
| 1451 |
"epoch": 0.8295964125560538,
|
| 1452 |
+
"grad_norm": 1.5068808968575202,
|
| 1453 |
+
"learning_rate": 2.576265494587458e-07,
|
| 1454 |
+
"loss": 0.7067,
|
| 1455 |
"step": 1850
|
| 1456 |
},
|
| 1457 |
{
|
| 1458 |
"epoch": 0.8340807174887892,
|
| 1459 |
+
"grad_norm": 1.4226178531466935,
|
| 1460 |
+
"learning_rate": 2.446221598241472e-07,
|
| 1461 |
+
"loss": 0.7143,
|
| 1462 |
"step": 1860
|
| 1463 |
},
|
| 1464 |
{
|
| 1465 |
"epoch": 0.8385650224215246,
|
| 1466 |
+
"grad_norm": 1.6881847148932905,
|
| 1467 |
+
"learning_rate": 2.319253590414132e-07,
|
| 1468 |
+
"loss": 0.7376,
|
| 1469 |
"step": 1870
|
| 1470 |
},
|
| 1471 |
{
|
| 1472 |
"epoch": 0.8430493273542601,
|
| 1473 |
+
"grad_norm": 1.4353283330892004,
|
| 1474 |
+
"learning_rate": 2.1953925804197056e-07,
|
| 1475 |
+
"loss": 0.7095,
|
| 1476 |
"step": 1880
|
| 1477 |
},
|
| 1478 |
{
|
| 1479 |
"epoch": 0.8475336322869955,
|
| 1480 |
+
"grad_norm": 1.4639605071750654,
|
| 1481 |
+
"learning_rate": 2.0746689163053113e-07,
|
| 1482 |
+
"loss": 0.7102,
|
| 1483 |
"step": 1890
|
| 1484 |
},
|
| 1485 |
{
|
| 1486 |
"epoch": 0.852017937219731,
|
| 1487 |
+
"grad_norm": 1.458703799588621,
|
| 1488 |
+
"learning_rate": 1.9571121774151545e-07,
|
| 1489 |
+
"loss": 0.686,
|
| 1490 |
+
"step": 1900
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 0.852017937219731,
|
| 1494 |
+
"eval_loss": 0.7220604419708252,
|
| 1495 |
+
"eval_runtime": 406.5609,
|
| 1496 |
+
"eval_samples_per_second": 123.172,
|
| 1497 |
+
"eval_steps_per_second": 1.926,
|
| 1498 |
"step": 1900
|
| 1499 |
},
|
| 1500 |
{
|
| 1501 |
"epoch": 0.8565022421524664,
|
| 1502 |
+
"grad_norm": 1.470148783910905,
|
| 1503 |
+
"learning_rate": 1.8427511671430757e-07,
|
| 1504 |
+
"loss": 0.72,
|
| 1505 |
"step": 1910
|
| 1506 |
},
|
| 1507 |
{
|
| 1508 |
"epoch": 0.8609865470852018,
|
| 1509 |
+
"grad_norm": 1.3891242748262451,
|
| 1510 |
+
"learning_rate": 1.7316139058752194e-07,
|
| 1511 |
+
"loss": 0.7318,
|
| 1512 |
"step": 1920
|
| 1513 |
},
|
| 1514 |
{
|
| 1515 |
"epoch": 0.8654708520179372,
|
| 1516 |
+
"grad_norm": 1.2245069775705093,
|
| 1517 |
+
"learning_rate": 1.6237276241245867e-07,
|
| 1518 |
+
"loss": 0.7155,
|
| 1519 |
"step": 1930
|
| 1520 |
},
|
| 1521 |
{
|
| 1522 |
"epoch": 0.8699551569506726,
|
| 1523 |
+
"grad_norm": 1.360510189488915,
|
| 1524 |
+
"learning_rate": 1.519118755859084e-07,
|
| 1525 |
+
"loss": 0.7255,
|
| 1526 |
"step": 1940
|
| 1527 |
},
|
| 1528 |
{
|
| 1529 |
"epoch": 0.874439461883408,
|
| 1530 |
+
"grad_norm": 1.495119615923585,
|
| 1531 |
+
"learning_rate": 1.4178129320247486e-07,
|
| 1532 |
+
"loss": 0.7484,
|
| 1533 |
"step": 1950
|
| 1534 |
},
|
| 1535 |
{
|
| 1536 |
"epoch": 0.8789237668161435,
|
| 1537 |
+
"grad_norm": 1.3674856635367474,
|
| 1538 |
+
"learning_rate": 1.31983497426575e-07,
|
| 1539 |
+
"loss": 0.7366,
|
| 1540 |
"step": 1960
|
| 1541 |
},
|
| 1542 |
{
|
| 1543 |
"epoch": 0.8834080717488789,
|
| 1544 |
+
"grad_norm": 1.4494730150421093,
|
| 1545 |
+
"learning_rate": 1.2252088888426431e-07,
|
| 1546 |
+
"loss": 0.742,
|
| 1547 |
"step": 1970
|
| 1548 |
},
|
| 1549 |
{
|
| 1550 |
"epoch": 0.8878923766816144,
|
| 1551 |
+
"grad_norm": 1.4368197978682802,
|
| 1552 |
+
"learning_rate": 1.1339578607504536e-07,
|
| 1553 |
+
"loss": 0.7269,
|
| 1554 |
"step": 1980
|
| 1555 |
},
|
| 1556 |
{
|
| 1557 |
"epoch": 0.8923766816143498,
|
| 1558 |
+
"grad_norm": 1.4017197990051706,
|
| 1559 |
+
"learning_rate": 1.0461042480379402e-07,
|
| 1560 |
+
"loss": 0.7234,
|
| 1561 |
"step": 1990
|
| 1562 |
},
|
| 1563 |
{
|
| 1564 |
"epoch": 0.8968609865470852,
|
| 1565 |
+
"grad_norm": 1.426560347266084,
|
| 1566 |
+
"learning_rate": 9.616695763295007e-08,
|
| 1567 |
+
"loss": 0.7214,
|
| 1568 |
+
"step": 2000
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 0.8968609865470852,
|
| 1572 |
+
"eval_loss": 0.721759557723999,
|
| 1573 |
+
"eval_runtime": 406.5838,
|
| 1574 |
+
"eval_samples_per_second": 123.165,
|
| 1575 |
+
"eval_steps_per_second": 1.926,
|
| 1576 |
"step": 2000
|
| 1577 |
},
|
| 1578 |
{
|
| 1579 |
"epoch": 0.9013452914798207,
|
| 1580 |
+
"grad_norm": 1.489947255967281,
|
| 1581 |
+
"learning_rate": 8.806745335510297e-08,
|
| 1582 |
+
"loss": 0.7341,
|
| 1583 |
"step": 2010
|
| 1584 |
},
|
| 1585 |
{
|
| 1586 |
"epoch": 0.905829596412556,
|
| 1587 |
+
"grad_norm": 1.4312716003053576,
|
| 1588 |
+
"learning_rate": 8.031389648610266e-08,
|
| 1589 |
+
"loss": 0.7264,
|
| 1590 |
"step": 2020
|
| 1591 |
},
|
| 1592 |
{
|
| 1593 |
"epoch": 0.9103139013452914,
|
| 1594 |
+
"grad_norm": 1.4764400641380824,
|
| 1595 |
+
"learning_rate": 7.290818677881966e-08,
|
| 1596 |
+
"loss": 0.7301,
|
| 1597 |
"step": 2030
|
| 1598 |
},
|
| 1599 |
{
|
| 1600 |
"epoch": 0.9147982062780269,
|
| 1601 |
+
"grad_norm": 1.4381108917682341,
|
| 1602 |
+
"learning_rate": 6.585213875767305e-08,
|
| 1603 |
+
"loss": 0.6997,
|
| 1604 |
"step": 2040
|
| 1605 |
},
|
| 1606 |
{
|
| 1607 |
"epoch": 0.9192825112107623,
|
| 1608 |
+
"grad_norm": 1.459723127188453,
|
| 1609 |
+
"learning_rate": 5.914748127404102e-08,
|
| 1610 |
+
"loss": 0.7168,
|
| 1611 |
"step": 2050
|
| 1612 |
},
|
| 1613 |
{
|
| 1614 |
"epoch": 0.9237668161434978,
|
| 1615 |
+
"grad_norm": 1.5776619173541433,
|
| 1616 |
+
"learning_rate": 5.2795857082663655e-08,
|
| 1617 |
+
"loss": 0.72,
|
| 1618 |
"step": 2060
|
| 1619 |
},
|
| 1620 |
{
|
| 1621 |
"epoch": 0.9282511210762332,
|
| 1622 |
+
"grad_norm": 1.438610611700907,
|
| 1623 |
+
"learning_rate": 4.6798822439140185e-08,
|
| 1624 |
+
"loss": 0.7035,
|
| 1625 |
"step": 2070
|
| 1626 |
},
|
| 1627 |
{
|
| 1628 |
"epoch": 0.9327354260089686,
|
| 1629 |
+
"grad_norm": 1.4350411032390504,
|
| 1630 |
+
"learning_rate": 4.115784671861916e-08,
|
| 1631 |
+
"loss": 0.735,
|
| 1632 |
"step": 2080
|
| 1633 |
},
|
| 1634 |
{
|
| 1635 |
"epoch": 0.9372197309417041,
|
| 1636 |
+
"grad_norm": 1.4822578142933729,
|
| 1637 |
+
"learning_rate": 3.587431205577713e-08,
|
| 1638 |
+
"loss": 0.7178,
|
| 1639 |
"step": 2090
|
| 1640 |
},
|
| 1641 |
{
|
| 1642 |
"epoch": 0.9417040358744395,
|
| 1643 |
+
"grad_norm": 1.5001233187138816,
|
| 1644 |
+
"learning_rate": 3.0949513006172325e-08,
|
| 1645 |
+
"loss": 0.7358,
|
| 1646 |
+
"step": 2100
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 0.9417040358744395,
|
| 1650 |
+
"eval_loss": 0.7216091752052307,
|
| 1651 |
+
"eval_runtime": 406.6258,
|
| 1652 |
+
"eval_samples_per_second": 123.153,
|
| 1653 |
+
"eval_steps_per_second": 1.926,
|
| 1654 |
"step": 2100
|
| 1655 |
},
|
| 1656 |
{
|
| 1657 |
"epoch": 0.9461883408071748,
|
| 1658 |
+
"grad_norm": 1.4457564058059627,
|
| 1659 |
+
"learning_rate": 2.6384656229056946e-08,
|
| 1660 |
+
"loss": 0.7285,
|
| 1661 |
"step": 2110
|
| 1662 |
},
|
| 1663 |
{
|
| 1664 |
"epoch": 0.9506726457399103,
|
| 1665 |
+
"grad_norm": 1.6789172768348999,
|
| 1666 |
+
"learning_rate": 2.218086019172394e-08,
|
| 1667 |
+
"loss": 0.7027,
|
| 1668 |
"step": 2120
|
| 1669 |
},
|
| 1670 |
{
|
| 1671 |
"epoch": 0.9551569506726457,
|
| 1672 |
+
"grad_norm": 1.4039832008414181,
|
| 1673 |
+
"learning_rate": 1.8339154895464894e-08,
|
| 1674 |
+
"loss": 0.7285,
|
| 1675 |
"step": 2130
|
| 1676 |
},
|
| 1677 |
{
|
| 1678 |
"epoch": 0.9596412556053812,
|
| 1679 |
+
"grad_norm": 1.7674026844330886,
|
| 1680 |
+
"learning_rate": 1.4860481623201417e-08,
|
| 1681 |
+
"loss": 0.713,
|
| 1682 |
"step": 2140
|
| 1683 |
},
|
| 1684 |
{
|
| 1685 |
"epoch": 0.9641255605381166,
|
| 1686 |
+
"grad_norm": 1.531580121339593,
|
| 1687 |
+
"learning_rate": 1.1745692708855282e-08,
|
| 1688 |
+
"loss": 0.7328,
|
| 1689 |
"step": 2150
|
| 1690 |
},
|
| 1691 |
{
|
| 1692 |
"epoch": 0.968609865470852,
|
| 1693 |
+
"grad_norm": 1.455884868550825,
|
| 1694 |
+
"learning_rate": 8.99555132851232e-09,
|
| 1695 |
+
"loss": 0.7196,
|
| 1696 |
"step": 2160
|
| 1697 |
},
|
| 1698 |
{
|
| 1699 |
"epoch": 0.9730941704035875,
|
| 1700 |
+
"grad_norm": 1.3157536936429735,
|
| 1701 |
+
"learning_rate": 6.610731313430318e-09,
|
| 1702 |
+
"loss": 0.7277,
|
| 1703 |
"step": 2170
|
| 1704 |
},
|
| 1705 |
{
|
| 1706 |
"epoch": 0.9775784753363229,
|
| 1707 |
+
"grad_norm": 1.5586404477319191,
|
| 1708 |
+
"learning_rate": 4.5918169849406e-09,
|
| 1709 |
+
"loss": 0.7265,
|
| 1710 |
"step": 2180
|
| 1711 |
},
|
| 1712 |
{
|
| 1713 |
"epoch": 0.9820627802690582,
|
| 1714 |
+
"grad_norm": 1.3596393082767964,
|
| 1715 |
+
"learning_rate": 2.939303011277872e-09,
|
| 1716 |
+
"loss": 0.719,
|
| 1717 |
"step": 2190
|
| 1718 |
},
|
| 1719 |
{
|
| 1720 |
"epoch": 0.9865470852017937,
|
| 1721 |
+
"grad_norm": 1.3866642718972106,
|
| 1722 |
+
"learning_rate": 1.6535942863788456e-09,
|
| 1723 |
+
"loss": 0.7259,
|
| 1724 |
+
"step": 2200
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.9865470852017937,
|
| 1728 |
+
"eval_loss": 0.7215752005577087,
|
| 1729 |
+
"eval_runtime": 408.9437,
|
| 1730 |
+
"eval_samples_per_second": 122.455,
|
| 1731 |
+
"eval_steps_per_second": 1.915,
|
| 1732 |
"step": 2200
|
| 1733 |
},
|
| 1734 |
{
|
| 1735 |
"epoch": 0.9910313901345291,
|
| 1736 |
+
"grad_norm": 1.6643780128489514,
|
| 1737 |
+
"learning_rate": 7.350058306764273e-10,
|
| 1738 |
+
"loss": 0.7044,
|
| 1739 |
"step": 2210
|
| 1740 |
},
|
| 1741 |
{
|
| 1742 |
"epoch": 0.9955156950672646,
|
| 1743 |
+
"grad_norm": 1.428221428067804,
|
| 1744 |
+
"learning_rate": 1.8376271391412624e-10,
|
| 1745 |
+
"loss": 0.7109,
|
| 1746 |
"step": 2220
|
| 1747 |
},
|
| 1748 |
{
|
| 1749 |
"epoch": 1.0,
|
| 1750 |
+
"grad_norm": 1.3882910125414851,
|
| 1751 |
"learning_rate": 0.0,
|
| 1752 |
+
"loss": 0.7123,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1753 |
"step": 2230
|
| 1754 |
},
|
| 1755 |
{
|
| 1756 |
"epoch": 1.0,
|
| 1757 |
"step": 2230,
|
| 1758 |
+
"total_flos": 250303561007104.0,
|
| 1759 |
+
"train_loss": 0.7492096503219262,
|
| 1760 |
+
"train_runtime": 18007.2993,
|
| 1761 |
+
"train_samples_per_second": 15.851,
|
| 1762 |
+
"train_steps_per_second": 0.124
|
| 1763 |
}
|
| 1764 |
],
|
| 1765 |
"logging_steps": 10,
|
|
|
|
| 1779 |
"attributes": {}
|
| 1780 |
}
|
| 1781 |
},
|
| 1782 |
+
"total_flos": 250303561007104.0,
|
| 1783 |
"train_batch_size": 8,
|
| 1784 |
"trial_name": null,
|
| 1785 |
"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 6968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c10bdb747e6aa533e359cc0a3925f648df006fc2f6bd836e9cca6e77438744b9
|
| 3 |
size 6968
|