Training completed
Browse files- README.md +7 -9
- all_results.json +6 -6
- train_results.json +6 -6
- trainer_state.json +345 -30
README.md
CHANGED
|
@@ -1,20 +1,20 @@
|
|
| 1 |
---
|
| 2 |
library_name: peft
|
| 3 |
-
license:
|
| 4 |
-
base_model: Qwen/Qwen2.5-
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
| 8 |
-
- name:
|
| 9 |
results: []
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
|
| 15 |
-
#
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -38,14 +38,12 @@ The following hyperparameters were used during training:
|
|
| 38 |
- eval_batch_size: 8
|
| 39 |
- seed: 42
|
| 40 |
- distributed_type: multi-GPU
|
| 41 |
-
- num_devices: 8
|
| 42 |
- gradient_accumulation_steps: 10
|
| 43 |
-
- total_train_batch_size:
|
| 44 |
-
- total_eval_batch_size: 64
|
| 45 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 46 |
- lr_scheduler_type: cosine
|
| 47 |
- lr_scheduler_warmup_ratio: 0.05
|
| 48 |
-
- training_steps:
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
|
|
|
| 1 |
---
|
| 2 |
library_name: peft
|
| 3 |
+
license: other
|
| 4 |
+
base_model: Qwen/Qwen2.5-3B
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
| 8 |
+
- name: single-node-single-gpu-qwen-custom-sft
|
| 9 |
results: []
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
|
| 15 |
+
# single-node-single-gpu-qwen-custom-sft
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-3B](https://huggingface.co/Qwen/Qwen2.5-3B) on an unknown dataset.
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 38 |
- eval_batch_size: 8
|
| 39 |
- seed: 42
|
| 40 |
- distributed_type: multi-GPU
|
|
|
|
| 41 |
- gradient_accumulation_steps: 10
|
| 42 |
+
- total_train_batch_size: 20
|
|
|
|
| 43 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 44 |
- lr_scheduler_type: cosine
|
| 45 |
- lr_scheduler_warmup_ratio: 0.05
|
| 46 |
+
- training_steps: 500
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos": 6.
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 0.5,
|
| 3 |
+
"total_flos": 6.856066495152128e+17,
|
| 4 |
+
"train_loss": 0.07727908698283135,
|
| 5 |
+
"train_runtime": 9003.3191,
|
| 6 |
+
"train_samples_per_second": 1.111,
|
| 7 |
+
"train_steps_per_second": 0.056
|
| 8 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos": 6.
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 0.5,
|
| 3 |
+
"total_flos": 6.856066495152128e+17,
|
| 4 |
+
"train_loss": 0.07727908698283135,
|
| 5 |
+
"train_runtime": 9003.3191,
|
| 6 |
+
"train_samples_per_second": 1.111,
|
| 7 |
+
"train_steps_per_second": 0.056
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -2,63 +2,378 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 0,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
-
"epoch":
|
| 14 |
-
"grad_norm":
|
| 15 |
-
"learning_rate":
|
| 16 |
-
"loss":
|
| 17 |
"step": 10
|
| 18 |
},
|
| 19 |
{
|
| 20 |
-
"epoch":
|
| 21 |
-
"grad_norm": 0.
|
| 22 |
-
"learning_rate":
|
| 23 |
-
"loss": 0.
|
| 24 |
"step": 20
|
| 25 |
},
|
| 26 |
{
|
| 27 |
-
"epoch":
|
| 28 |
-
"grad_norm": 0.
|
| 29 |
"learning_rate": 0.0001,
|
| 30 |
-
"loss": 0.
|
| 31 |
"step": 30
|
| 32 |
},
|
| 33 |
{
|
| 34 |
-
"epoch":
|
| 35 |
-
"grad_norm": 0.
|
| 36 |
"learning_rate": 0.0001,
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 40
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch":
|
| 42 |
-
"grad_norm": 0.
|
| 43 |
"learning_rate": 0.0001,
|
| 44 |
-
"loss": 0.
|
| 45 |
"step": 50
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch":
|
| 49 |
-
"
|
| 50 |
-
"
|
| 51 |
-
"
|
| 52 |
-
"
|
| 53 |
-
|
| 54 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
}
|
| 56 |
],
|
| 57 |
"logging_steps": 10,
|
| 58 |
-
"max_steps":
|
| 59 |
"num_input_tokens_seen": 0,
|
| 60 |
-
"num_train_epochs":
|
| 61 |
-
"save_steps":
|
| 62 |
"stateful_callbacks": {
|
| 63 |
"TrainerControl": {
|
| 64 |
"args": {
|
|
@@ -71,7 +386,7 @@
|
|
| 71 |
"attributes": {}
|
| 72 |
}
|
| 73 |
},
|
| 74 |
-
"total_flos": 6.
|
| 75 |
"train_batch_size": 2,
|
| 76 |
"trial_name": null,
|
| 77 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5,
|
| 6 |
"eval_steps": 0,
|
| 7 |
+
"global_step": 500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
+
"epoch": 0.01,
|
| 14 |
+
"grad_norm": 6.734264373779297,
|
| 15 |
+
"learning_rate": 8.576691395183485e-05,
|
| 16 |
+
"loss": 3.5009,
|
| 17 |
"step": 10
|
| 18 |
},
|
| 19 |
{
|
| 20 |
+
"epoch": 0.02,
|
| 21 |
+
"grad_norm": 0.29098451137542725,
|
| 22 |
+
"learning_rate": 9.653382790366966e-05,
|
| 23 |
+
"loss": 0.1027,
|
| 24 |
"step": 20
|
| 25 |
},
|
| 26 |
{
|
| 27 |
+
"epoch": 0.03,
|
| 28 |
+
"grad_norm": 0.09549916535615921,
|
| 29 |
"learning_rate": 0.0001,
|
| 30 |
+
"loss": 0.0191,
|
| 31 |
"step": 30
|
| 32 |
},
|
| 33 |
{
|
| 34 |
+
"epoch": 0.04,
|
| 35 |
+
"grad_norm": 0.3484920263290405,
|
| 36 |
"learning_rate": 0.0001,
|
| 37 |
+
"loss": 0.0222,
|
| 38 |
"step": 40
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.05,
|
| 42 |
+
"grad_norm": 0.33001908659935,
|
| 43 |
"learning_rate": 0.0001,
|
| 44 |
+
"loss": 0.021,
|
| 45 |
"step": 50
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.06,
|
| 49 |
+
"grad_norm": 0.057511646300554276,
|
| 50 |
+
"learning_rate": 0.0001,
|
| 51 |
+
"loss": 0.0135,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.07,
|
| 56 |
+
"grad_norm": 0.05701196566224098,
|
| 57 |
+
"learning_rate": 0.0001,
|
| 58 |
+
"loss": 0.0117,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.08,
|
| 63 |
+
"grad_norm": 0.043988876044750214,
|
| 64 |
+
"learning_rate": 0.0001,
|
| 65 |
+
"loss": 0.0107,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.09,
|
| 70 |
+
"grad_norm": 0.03720390796661377,
|
| 71 |
+
"learning_rate": 0.0001,
|
| 72 |
+
"loss": 0.0098,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1,
|
| 77 |
+
"grad_norm": 0.0470854677259922,
|
| 78 |
+
"learning_rate": 0.0001,
|
| 79 |
+
"loss": 0.0091,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.11,
|
| 84 |
+
"grad_norm": 0.035510435700416565,
|
| 85 |
+
"learning_rate": 0.0001,
|
| 86 |
+
"loss": 0.0075,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.12,
|
| 91 |
+
"grad_norm": 0.0346401073038578,
|
| 92 |
+
"learning_rate": 0.0001,
|
| 93 |
+
"loss": 0.0069,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.13,
|
| 98 |
+
"grad_norm": 0.0329650416970253,
|
| 99 |
+
"learning_rate": 0.0001,
|
| 100 |
+
"loss": 0.0064,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.14,
|
| 105 |
+
"grad_norm": 0.056529607623815536,
|
| 106 |
+
"learning_rate": 0.0001,
|
| 107 |
+
"loss": 0.0061,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.15,
|
| 112 |
+
"grad_norm": 0.049417588859796524,
|
| 113 |
+
"learning_rate": 0.0001,
|
| 114 |
+
"loss": 0.0058,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.16,
|
| 119 |
+
"grad_norm": 0.031275127083063126,
|
| 120 |
+
"learning_rate": 0.0001,
|
| 121 |
+
"loss": 0.0046,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.17,
|
| 126 |
+
"grad_norm": 0.026077693328261375,
|
| 127 |
+
"learning_rate": 0.0001,
|
| 128 |
+
"loss": 0.0043,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.18,
|
| 133 |
+
"grad_norm": 0.03110571764409542,
|
| 134 |
+
"learning_rate": 0.0001,
|
| 135 |
+
"loss": 0.0035,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.19,
|
| 140 |
+
"grad_norm": 0.0256363395601511,
|
| 141 |
+
"learning_rate": 0.0001,
|
| 142 |
+
"loss": 0.0039,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.2,
|
| 147 |
+
"grad_norm": 0.13061155378818512,
|
| 148 |
+
"learning_rate": 0.0001,
|
| 149 |
+
"loss": 0.0042,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.21,
|
| 154 |
+
"grad_norm": 0.022342098876833916,
|
| 155 |
+
"learning_rate": 0.0001,
|
| 156 |
+
"loss": 0.0029,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.22,
|
| 161 |
+
"grad_norm": 0.06658010929822922,
|
| 162 |
+
"learning_rate": 0.0001,
|
| 163 |
+
"loss": 0.0028,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.23,
|
| 168 |
+
"grad_norm": 0.02203432098031044,
|
| 169 |
+
"learning_rate": 0.0001,
|
| 170 |
+
"loss": 0.0028,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.24,
|
| 175 |
+
"grad_norm": 0.04879545792937279,
|
| 176 |
+
"learning_rate": 0.0001,
|
| 177 |
+
"loss": 0.0022,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.25,
|
| 182 |
+
"grad_norm": 0.044768281280994415,
|
| 183 |
+
"learning_rate": 0.0001,
|
| 184 |
+
"loss": 0.0026,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.26,
|
| 189 |
+
"grad_norm": 0.030401039868593216,
|
| 190 |
+
"learning_rate": 0.0001,
|
| 191 |
+
"loss": 0.0018,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.27,
|
| 196 |
+
"grad_norm": 0.10380243510007858,
|
| 197 |
+
"learning_rate": 0.0001,
|
| 198 |
+
"loss": 0.0015,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.28,
|
| 203 |
+
"grad_norm": 0.019732531160116196,
|
| 204 |
+
"learning_rate": 0.0001,
|
| 205 |
+
"loss": 0.0017,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.29,
|
| 210 |
+
"grad_norm": 0.015292245894670486,
|
| 211 |
+
"learning_rate": 0.0001,
|
| 212 |
+
"loss": 0.0019,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.3,
|
| 217 |
+
"grad_norm": 0.030675368383526802,
|
| 218 |
+
"learning_rate": 0.0001,
|
| 219 |
+
"loss": 0.0022,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.31,
|
| 224 |
+
"grad_norm": 0.029702844098210335,
|
| 225 |
+
"learning_rate": 0.0001,
|
| 226 |
+
"loss": 0.0014,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.32,
|
| 231 |
+
"grad_norm": 0.016342662274837494,
|
| 232 |
+
"learning_rate": 0.0001,
|
| 233 |
+
"loss": 0.0014,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.33,
|
| 238 |
+
"grad_norm": 0.013499235734343529,
|
| 239 |
+
"learning_rate": 0.0001,
|
| 240 |
+
"loss": 0.0013,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.34,
|
| 245 |
+
"grad_norm": 0.011413372121751308,
|
| 246 |
+
"learning_rate": 0.0001,
|
| 247 |
+
"loss": 0.0012,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.35,
|
| 252 |
+
"grad_norm": 0.09215894341468811,
|
| 253 |
+
"learning_rate": 0.0001,
|
| 254 |
+
"loss": 0.0073,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.36,
|
| 259 |
+
"grad_norm": 0.06609797477722168,
|
| 260 |
+
"learning_rate": 0.0001,
|
| 261 |
+
"loss": 0.0084,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.37,
|
| 266 |
+
"grad_norm": 0.03970978036522865,
|
| 267 |
+
"learning_rate": 0.0001,
|
| 268 |
+
"loss": 0.0075,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.38,
|
| 273 |
+
"grad_norm": 0.029625259339809418,
|
| 274 |
+
"learning_rate": 0.0001,
|
| 275 |
+
"loss": 0.0059,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.39,
|
| 280 |
+
"grad_norm": 0.02456456422805786,
|
| 281 |
+
"learning_rate": 0.0001,
|
| 282 |
+
"loss": 0.005,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.4,
|
| 287 |
+
"grad_norm": 0.03191933035850525,
|
| 288 |
+
"learning_rate": 0.0001,
|
| 289 |
+
"loss": 0.0045,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.41,
|
| 294 |
+
"grad_norm": 0.01918269693851471,
|
| 295 |
+
"learning_rate": 0.0001,
|
| 296 |
+
"loss": 0.0037,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.42,
|
| 301 |
+
"grad_norm": 0.018161766231060028,
|
| 302 |
+
"learning_rate": 0.0001,
|
| 303 |
+
"loss": 0.0031,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.43,
|
| 308 |
+
"grad_norm": 0.019575210288167,
|
| 309 |
+
"learning_rate": 0.0001,
|
| 310 |
+
"loss": 0.0026,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.44,
|
| 315 |
+
"grad_norm": 0.026317287236452103,
|
| 316 |
+
"learning_rate": 0.0001,
|
| 317 |
+
"loss": 0.0023,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.45,
|
| 322 |
+
"grad_norm": 0.040029872208833694,
|
| 323 |
+
"learning_rate": 0.0001,
|
| 324 |
+
"loss": 0.0026,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.46,
|
| 329 |
+
"grad_norm": 0.013975433073937893,
|
| 330 |
+
"learning_rate": 0.0001,
|
| 331 |
+
"loss": 0.0022,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.47,
|
| 336 |
+
"grad_norm": 0.03210354968905449,
|
| 337 |
+
"learning_rate": 0.0001,
|
| 338 |
+
"loss": 0.0017,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.48,
|
| 343 |
+
"grad_norm": 0.01889188587665558,
|
| 344 |
+
"learning_rate": 0.0001,
|
| 345 |
+
"loss": 0.0019,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.49,
|
| 350 |
+
"grad_norm": 0.013832672499120235,
|
| 351 |
+
"learning_rate": 0.0001,
|
| 352 |
+
"loss": 0.0016,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.5,
|
| 357 |
+
"grad_norm": 0.057756196707487106,
|
| 358 |
+
"learning_rate": 0.0001,
|
| 359 |
+
"loss": 0.0018,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.5,
|
| 364 |
+
"step": 500,
|
| 365 |
+
"total_flos": 6.856066495152128e+17,
|
| 366 |
+
"train_loss": 0.07727908698283135,
|
| 367 |
+
"train_runtime": 9003.3191,
|
| 368 |
+
"train_samples_per_second": 1.111,
|
| 369 |
+
"train_steps_per_second": 0.056
|
| 370 |
}
|
| 371 |
],
|
| 372 |
"logging_steps": 10,
|
| 373 |
+
"max_steps": 500,
|
| 374 |
"num_input_tokens_seen": 0,
|
| 375 |
+
"num_train_epochs": 1,
|
| 376 |
+
"save_steps": 1000,
|
| 377 |
"stateful_callbacks": {
|
| 378 |
"TrainerControl": {
|
| 379 |
"args": {
|
|
|
|
| 386 |
"attributes": {}
|
| 387 |
}
|
| 388 |
},
|
| 389 |
+
"total_flos": 6.856066495152128e+17,
|
| 390 |
"train_batch_size": 2,
|
| 391 |
"trial_name": null,
|
| 392 |
"trial_params": null
|