End of training
Browse files- README.md +2 -1
- all_results.json +12 -0
- eval_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +766 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: mistralai/Mistral-7B-v0.1
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: hp_ablations_grid_mistral_bsz1024_lr5e-6_scheduler-cosine-warmup0.15
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# hp_ablations_grid_mistral_bsz1024_lr5e-6_scheduler-cosine-warmup0.15
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.0575
|
| 21 |
|
|
|
|
| 4 |
base_model: mistralai/Mistral-7B-v0.1
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: hp_ablations_grid_mistral_bsz1024_lr5e-6_scheduler-cosine-warmup0.15
|
|
|
|
| 16 |
|
| 17 |
# hp_ablations_grid_mistral_bsz1024_lr5e-6_scheduler-cosine-warmup0.15
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the mlfoundations-dev/oh-dcft-v3-llama3.1-nemotron-70b_shareGPT_format dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.0575
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.057458870112895966,
|
| 4 |
+
"eval_runtime": 227.0083,
|
| 5 |
+
"eval_samples_per_second": 79.746,
|
| 6 |
+
"eval_steps_per_second": 0.626,
|
| 7 |
+
"total_flos": 3376456327495680.0,
|
| 8 |
+
"train_loss": 0.4351037277115716,
|
| 9 |
+
"train_runtime": 33019.7588,
|
| 10 |
+
"train_samples_per_second": 31.25,
|
| 11 |
+
"train_steps_per_second": 0.031
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.057458870112895966,
|
| 4 |
+
"eval_runtime": 227.0083,
|
| 5 |
+
"eval_samples_per_second": 79.746,
|
| 6 |
+
"eval_steps_per_second": 0.626
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 3376456327495680.0,
|
| 4 |
+
"train_loss": 0.4351037277115716,
|
| 5 |
+
"train_runtime": 33019.7588,
|
| 6 |
+
"train_samples_per_second": 31.25,
|
| 7 |
+
"train_steps_per_second": 0.031
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,766 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1008,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02976190476190476,
|
| 13 |
+
"grad_norm": 9.855416467128451,
|
| 14 |
+
"learning_rate": 3.2894736842105264e-07,
|
| 15 |
+
"loss": 0.8831,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05952380952380952,
|
| 20 |
+
"grad_norm": 4.058333207297266,
|
| 21 |
+
"learning_rate": 6.578947368421053e-07,
|
| 22 |
+
"loss": 0.7946,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.08928571428571429,
|
| 27 |
+
"grad_norm": 1.7570375433828875,
|
| 28 |
+
"learning_rate": 9.86842105263158e-07,
|
| 29 |
+
"loss": 0.7122,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.11904761904761904,
|
| 34 |
+
"grad_norm": 1.1575290406793173,
|
| 35 |
+
"learning_rate": 1.3157894736842106e-06,
|
| 36 |
+
"loss": 0.6601,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.1488095238095238,
|
| 41 |
+
"grad_norm": 1.1945148190883437,
|
| 42 |
+
"learning_rate": 1.6447368421052635e-06,
|
| 43 |
+
"loss": 0.6275,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.17857142857142858,
|
| 48 |
+
"grad_norm": 1.221041026154983,
|
| 49 |
+
"learning_rate": 1.973684210526316e-06,
|
| 50 |
+
"loss": 0.6052,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.20833333333333334,
|
| 55 |
+
"grad_norm": 3.3209006702030646,
|
| 56 |
+
"learning_rate": 2.3026315789473684e-06,
|
| 57 |
+
"loss": 0.586,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.23809523809523808,
|
| 62 |
+
"grad_norm": 3.6681811496303838,
|
| 63 |
+
"learning_rate": 2.631578947368421e-06,
|
| 64 |
+
"loss": 0.5798,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.26785714285714285,
|
| 69 |
+
"grad_norm": 3.2185752709902724,
|
| 70 |
+
"learning_rate": 2.960526315789474e-06,
|
| 71 |
+
"loss": 0.5666,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.2976190476190476,
|
| 76 |
+
"grad_norm": 3.4706862638119795,
|
| 77 |
+
"learning_rate": 3.289473684210527e-06,
|
| 78 |
+
"loss": 0.5638,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3273809523809524,
|
| 83 |
+
"grad_norm": 3.6113112350238055,
|
| 84 |
+
"learning_rate": 3.618421052631579e-06,
|
| 85 |
+
"loss": 0.5522,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.35714285714285715,
|
| 90 |
+
"grad_norm": 3.2305389516520107,
|
| 91 |
+
"learning_rate": 3.947368421052632e-06,
|
| 92 |
+
"loss": 0.5463,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.3869047619047619,
|
| 97 |
+
"grad_norm": 3.038105776417889,
|
| 98 |
+
"learning_rate": 4.276315789473684e-06,
|
| 99 |
+
"loss": 0.5435,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.4166666666666667,
|
| 104 |
+
"grad_norm": 2.8452115838960004,
|
| 105 |
+
"learning_rate": 4.605263157894737e-06,
|
| 106 |
+
"loss": 0.5368,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.44642857142857145,
|
| 111 |
+
"grad_norm": 2.885654936231309,
|
| 112 |
+
"learning_rate": 4.9342105263157895e-06,
|
| 113 |
+
"loss": 0.5371,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.47619047619047616,
|
| 118 |
+
"grad_norm": 2.4395389590432695,
|
| 119 |
+
"learning_rate": 4.998922515567496e-06,
|
| 120 |
+
"loss": 0.5311,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5059523809523809,
|
| 125 |
+
"grad_norm": 3.316027131916539,
|
| 126 |
+
"learning_rate": 4.994546826814266e-06,
|
| 127 |
+
"loss": 0.5306,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.5357142857142857,
|
| 132 |
+
"grad_norm": 2.1091015101835064,
|
| 133 |
+
"learning_rate": 4.986811479610213e-06,
|
| 134 |
+
"loss": 0.5235,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.5654761904761905,
|
| 139 |
+
"grad_norm": 3.105111788839091,
|
| 140 |
+
"learning_rate": 4.975726891929585e-06,
|
| 141 |
+
"loss": 0.5172,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.5952380952380952,
|
| 146 |
+
"grad_norm": 2.4351797747389288,
|
| 147 |
+
"learning_rate": 4.9613079925074435e-06,
|
| 148 |
+
"loss": 0.5127,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.625,
|
| 153 |
+
"grad_norm": 2.058969332069431,
|
| 154 |
+
"learning_rate": 4.943574200733625e-06,
|
| 155 |
+
"loss": 0.5135,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.6547619047619048,
|
| 160 |
+
"grad_norm": 1.777838918535288,
|
| 161 |
+
"learning_rate": 4.922549400498685e-06,
|
| 162 |
+
"loss": 0.5089,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.6845238095238095,
|
| 167 |
+
"grad_norm": 2.7154588748327986,
|
| 168 |
+
"learning_rate": 4.89826190802705e-06,
|
| 169 |
+
"loss": 0.5037,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.7142857142857143,
|
| 174 |
+
"grad_norm": 1.5679948903593761,
|
| 175 |
+
"learning_rate": 4.870744433740688e-06,
|
| 176 |
+
"loss": 0.4986,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.7440476190476191,
|
| 181 |
+
"grad_norm": 1.4962958992598898,
|
| 182 |
+
"learning_rate": 4.840034038204687e-06,
|
| 183 |
+
"loss": 0.4972,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.7738095238095238,
|
| 188 |
+
"grad_norm": 2.122366808210638,
|
| 189 |
+
"learning_rate": 4.806172082214032e-06,
|
| 190 |
+
"loss": 0.4989,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.8035714285714286,
|
| 195 |
+
"grad_norm": 2.0302822908345153,
|
| 196 |
+
"learning_rate": 4.7692041710888495e-06,
|
| 197 |
+
"loss": 0.4901,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.8333333333333334,
|
| 202 |
+
"grad_norm": 3.5745905459632543,
|
| 203 |
+
"learning_rate": 4.729180093253106e-06,
|
| 204 |
+
"loss": 0.4916,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.8630952380952381,
|
| 209 |
+
"grad_norm": 1.8908937013266554,
|
| 210 |
+
"learning_rate": 4.6861537531795095e-06,
|
| 211 |
+
"loss": 0.4883,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.8928571428571429,
|
| 216 |
+
"grad_norm": 2.6221469442693652,
|
| 217 |
+
"learning_rate": 4.640183098790896e-06,
|
| 218 |
+
"loss": 0.4867,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.9226190476190477,
|
| 223 |
+
"grad_norm": 2.112945737548425,
|
| 224 |
+
"learning_rate": 4.5913300434159095e-06,
|
| 225 |
+
"loss": 0.4808,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.9523809523809523,
|
| 230 |
+
"grad_norm": 2.167157341115666,
|
| 231 |
+
"learning_rate": 4.53966038240406e-06,
|
| 232 |
+
"loss": 0.4829,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.9821428571428571,
|
| 237 |
+
"grad_norm": 1.7665074082761922,
|
| 238 |
+
"learning_rate": 4.485243704512474e-06,
|
| 239 |
+
"loss": 0.4775,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.0,
|
| 244 |
+
"eval_loss": 0.05986911430954933,
|
| 245 |
+
"eval_runtime": 228.6618,
|
| 246 |
+
"eval_samples_per_second": 79.169,
|
| 247 |
+
"eval_steps_per_second": 0.621,
|
| 248 |
+
"step": 336
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.0119047619047619,
|
| 252 |
+
"grad_norm": 2.7005444699805397,
|
| 253 |
+
"learning_rate": 4.428153298183676e-06,
|
| 254 |
+
"loss": 0.4615,
|
| 255 |
+
"step": 340
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.0416666666666667,
|
| 259 |
+
"grad_norm": 2.1637697857642766,
|
| 260 |
+
"learning_rate": 4.368466052840636e-06,
|
| 261 |
+
"loss": 0.4222,
|
| 262 |
+
"step": 350
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.0714285714285714,
|
| 266 |
+
"grad_norm": 2.1155220244099318,
|
| 267 |
+
"learning_rate": 4.306262355332006e-06,
|
| 268 |
+
"loss": 0.4226,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.1011904761904763,
|
| 273 |
+
"grad_norm": 2.9522060556993805,
|
| 274 |
+
"learning_rate": 4.2416259816670235e-06,
|
| 275 |
+
"loss": 0.4231,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.130952380952381,
|
| 280 |
+
"grad_norm": 3.069829782500402,
|
| 281 |
+
"learning_rate": 4.17464398418589e-06,
|
| 282 |
+
"loss": 0.424,
|
| 283 |
+
"step": 380
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.1607142857142858,
|
| 287 |
+
"grad_norm": 3.0267979137491263,
|
| 288 |
+
"learning_rate": 4.105406574317579e-06,
|
| 289 |
+
"loss": 0.4244,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.1904761904761905,
|
| 294 |
+
"grad_norm": 2.1977669399883695,
|
| 295 |
+
"learning_rate": 4.034007001082985e-06,
|
| 296 |
+
"loss": 0.418,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.2202380952380953,
|
| 301 |
+
"grad_norm": 2.697858786471712,
|
| 302 |
+
"learning_rate": 3.960541425507039e-06,
|
| 303 |
+
"loss": 0.4233,
|
| 304 |
+
"step": 410
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.25,
|
| 308 |
+
"grad_norm": 2.493946030937562,
|
| 309 |
+
"learning_rate": 3.8851087911089315e-06,
|
| 310 |
+
"loss": 0.4198,
|
| 311 |
+
"step": 420
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.2797619047619047,
|
| 315 |
+
"grad_norm": 2.2545695426043544,
|
| 316 |
+
"learning_rate": 3.8078106906448684e-06,
|
| 317 |
+
"loss": 0.4183,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.3095238095238095,
|
| 322 |
+
"grad_norm": 2.375162881348148,
|
| 323 |
+
"learning_rate": 3.7287512292828364e-06,
|
| 324 |
+
"loss": 0.4168,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.3392857142857144,
|
| 329 |
+
"grad_norm": 1.5621396833558368,
|
| 330 |
+
"learning_rate": 3.6480368843936463e-06,
|
| 331 |
+
"loss": 0.4163,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.369047619047619,
|
| 336 |
+
"grad_norm": 1.3598263826513288,
|
| 337 |
+
"learning_rate": 3.5657763621470905e-06,
|
| 338 |
+
"loss": 0.4197,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.3988095238095237,
|
| 343 |
+
"grad_norm": 1.6629757133775533,
|
| 344 |
+
"learning_rate": 3.48208045110635e-06,
|
| 345 |
+
"loss": 0.4187,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.4285714285714286,
|
| 350 |
+
"grad_norm": 2.2093813175502968,
|
| 351 |
+
"learning_rate": 3.39706187301784e-06,
|
| 352 |
+
"loss": 0.4166,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.4583333333333333,
|
| 357 |
+
"grad_norm": 1.884934841996157,
|
| 358 |
+
"learning_rate": 3.3108351309974286e-06,
|
| 359 |
+
"loss": 0.4154,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.4880952380952381,
|
| 364 |
+
"grad_norm": 1.5082137043399462,
|
| 365 |
+
"learning_rate": 3.2235163553175174e-06,
|
| 366 |
+
"loss": 0.417,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.5178571428571428,
|
| 371 |
+
"grad_norm": 1.3657040531080291,
|
| 372 |
+
"learning_rate": 3.1352231470026583e-06,
|
| 373 |
+
"loss": 0.416,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.5476190476190477,
|
| 378 |
+
"grad_norm": 1.2254626355269007,
|
| 379 |
+
"learning_rate": 3.0460744194443658e-06,
|
| 380 |
+
"loss": 0.4142,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.5773809523809523,
|
| 385 |
+
"grad_norm": 1.1398076994088004,
|
| 386 |
+
"learning_rate": 2.956190238248425e-06,
|
| 387 |
+
"loss": 0.4149,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.6071428571428572,
|
| 392 |
+
"grad_norm": 1.1825076561434265,
|
| 393 |
+
"learning_rate": 2.8656916595304026e-06,
|
| 394 |
+
"loss": 0.4133,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.6369047619047619,
|
| 399 |
+
"grad_norm": 1.5151800119422074,
|
| 400 |
+
"learning_rate": 2.7747005668771293e-06,
|
| 401 |
+
"loss": 0.4173,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.6666666666666665,
|
| 406 |
+
"grad_norm": 1.4847041684984181,
|
| 407 |
+
"learning_rate": 2.68333950719376e-06,
|
| 408 |
+
"loss": 0.4122,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.6964285714285714,
|
| 413 |
+
"grad_norm": 1.4926221075919288,
|
| 414 |
+
"learning_rate": 2.5917315256574543e-06,
|
| 415 |
+
"loss": 0.4138,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.7261904761904763,
|
| 420 |
+
"grad_norm": 1.4851596357393222,
|
| 421 |
+
"learning_rate": 2.5e-06,
|
| 422 |
+
"loss": 0.4146,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.755952380952381,
|
| 427 |
+
"grad_norm": 1.4494102675836165,
|
| 428 |
+
"learning_rate": 2.4082684743425457e-06,
|
| 429 |
+
"loss": 0.41,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.7857142857142856,
|
| 434 |
+
"grad_norm": 1.096907686976151,
|
| 435 |
+
"learning_rate": 2.3166604928062407e-06,
|
| 436 |
+
"loss": 0.4083,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.8154761904761905,
|
| 441 |
+
"grad_norm": 1.1069324511062155,
|
| 442 |
+
"learning_rate": 2.2252994331228715e-06,
|
| 443 |
+
"loss": 0.4092,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.8452380952380953,
|
| 448 |
+
"grad_norm": 1.5676344586960804,
|
| 449 |
+
"learning_rate": 2.1343083404695987e-06,
|
| 450 |
+
"loss": 0.4071,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.875,
|
| 455 |
+
"grad_norm": 1.5244672991700199,
|
| 456 |
+
"learning_rate": 2.0438097617515744e-06,
|
| 457 |
+
"loss": 0.4092,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.9047619047619047,
|
| 462 |
+
"grad_norm": 1.1711984219863045,
|
| 463 |
+
"learning_rate": 1.9539255805556346e-06,
|
| 464 |
+
"loss": 0.4056,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.9345238095238095,
|
| 469 |
+
"grad_norm": 1.2364277364431069,
|
| 470 |
+
"learning_rate": 1.8647768529973426e-06,
|
| 471 |
+
"loss": 0.4065,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.9642857142857144,
|
| 476 |
+
"grad_norm": 1.173689997741917,
|
| 477 |
+
"learning_rate": 1.7764836446824835e-06,
|
| 478 |
+
"loss": 0.4066,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.994047619047619,
|
| 483 |
+
"grad_norm": 1.0429379558488223,
|
| 484 |
+
"learning_rate": 1.689164869002572e-06,
|
| 485 |
+
"loss": 0.4039,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 2.0,
|
| 490 |
+
"eval_loss": 0.05654621869325638,
|
| 491 |
+
"eval_runtime": 233.1622,
|
| 492 |
+
"eval_samples_per_second": 77.641,
|
| 493 |
+
"eval_steps_per_second": 0.609,
|
| 494 |
+
"step": 672
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.0238095238095237,
|
| 498 |
+
"grad_norm": 1.8042620783640224,
|
| 499 |
+
"learning_rate": 1.6029381269821607e-06,
|
| 500 |
+
"loss": 0.355,
|
| 501 |
+
"step": 680
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.0535714285714284,
|
| 505 |
+
"grad_norm": 1.3103423601245003,
|
| 506 |
+
"learning_rate": 1.5179195488936505e-06,
|
| 507 |
+
"loss": 0.342,
|
| 508 |
+
"step": 690
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 2.0833333333333335,
|
| 512 |
+
"grad_norm": 1.1981284388735467,
|
| 513 |
+
"learning_rate": 1.4342236378529106e-06,
|
| 514 |
+
"loss": 0.3394,
|
| 515 |
+
"step": 700
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.113095238095238,
|
| 519 |
+
"grad_norm": 1.3227357738839063,
|
| 520 |
+
"learning_rate": 1.351963115606354e-06,
|
| 521 |
+
"loss": 0.3363,
|
| 522 |
+
"step": 710
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 2.142857142857143,
|
| 526 |
+
"grad_norm": 1.0826862483712594,
|
| 527 |
+
"learning_rate": 1.2712487707171645e-06,
|
| 528 |
+
"loss": 0.3378,
|
| 529 |
+
"step": 720
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.1726190476190474,
|
| 533 |
+
"grad_norm": 1.2571941714304598,
|
| 534 |
+
"learning_rate": 1.1921893093551324e-06,
|
| 535 |
+
"loss": 0.338,
|
| 536 |
+
"step": 730
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.2023809523809526,
|
| 540 |
+
"grad_norm": 1.168368127805181,
|
| 541 |
+
"learning_rate": 1.1148912088910687e-06,
|
| 542 |
+
"loss": 0.3363,
|
| 543 |
+
"step": 740
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.232142857142857,
|
| 547 |
+
"grad_norm": 1.1226203835961706,
|
| 548 |
+
"learning_rate": 1.0394585744929605e-06,
|
| 549 |
+
"loss": 0.3393,
|
| 550 |
+
"step": 750
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.261904761904762,
|
| 554 |
+
"grad_norm": 1.0656940582932617,
|
| 555 |
+
"learning_rate": 9.659929989170156e-07,
|
| 556 |
+
"loss": 0.3401,
|
| 557 |
+
"step": 760
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 2.2916666666666665,
|
| 561 |
+
"grad_norm": 1.074973225972827,
|
| 562 |
+
"learning_rate": 8.945934256824218e-07,
|
| 563 |
+
"loss": 0.3356,
|
| 564 |
+
"step": 770
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.3214285714285716,
|
| 568 |
+
"grad_norm": 1.1457434350978388,
|
| 569 |
+
"learning_rate": 8.253560158141111e-07,
|
| 570 |
+
"loss": 0.3372,
|
| 571 |
+
"step": 780
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.3511904761904763,
|
| 575 |
+
"grad_norm": 1.0748233318983023,
|
| 576 |
+
"learning_rate": 7.583740183329769e-07,
|
| 577 |
+
"loss": 0.3339,
|
| 578 |
+
"step": 790
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.380952380952381,
|
| 582 |
+
"grad_norm": 1.0162550586451078,
|
| 583 |
+
"learning_rate": 6.93737644667995e-07,
|
| 584 |
+
"loss": 0.3366,
|
| 585 |
+
"step": 800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.4107142857142856,
|
| 589 |
+
"grad_norm": 1.0398744748365716,
|
| 590 |
+
"learning_rate": 6.315339471593646e-07,
|
| 591 |
+
"loss": 0.3359,
|
| 592 |
+
"step": 810
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.4404761904761907,
|
| 596 |
+
"grad_norm": 1.0255604222182617,
|
| 597 |
+
"learning_rate": 5.718467018163243e-07,
|
| 598 |
+
"loss": 0.3344,
|
| 599 |
+
"step": 820
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.4702380952380953,
|
| 603 |
+
"grad_norm": 0.9872536325493508,
|
| 604 |
+
"learning_rate": 5.147562954875269e-07,
|
| 605 |
+
"loss": 0.3362,
|
| 606 |
+
"step": 830
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.5,
|
| 610 |
+
"grad_norm": 1.0132034371898346,
|
| 611 |
+
"learning_rate": 4.6033961759594045e-07,
|
| 612 |
+
"loss": 0.3337,
|
| 613 |
+
"step": 840
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.5297619047619047,
|
| 617 |
+
"grad_norm": 1.0177216034721577,
|
| 618 |
+
"learning_rate": 4.0866995658409155e-07,
|
| 619 |
+
"loss": 0.3363,
|
| 620 |
+
"step": 850
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.5595238095238093,
|
| 624 |
+
"grad_norm": 0.9981956934484016,
|
| 625 |
+
"learning_rate": 3.598169012091049e-07,
|
| 626 |
+
"loss": 0.3362,
|
| 627 |
+
"step": 860
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.5892857142857144,
|
| 631 |
+
"grad_norm": 0.9529369028261363,
|
| 632 |
+
"learning_rate": 3.1384624682049144e-07,
|
| 633 |
+
"loss": 0.3394,
|
| 634 |
+
"step": 870
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.619047619047619,
|
| 638 |
+
"grad_norm": 0.9766851469747638,
|
| 639 |
+
"learning_rate": 2.708199067468939e-07,
|
| 640 |
+
"loss": 0.3343,
|
| 641 |
+
"step": 880
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.6488095238095237,
|
| 645 |
+
"grad_norm": 0.9534173170238686,
|
| 646 |
+
"learning_rate": 2.3079582891115144e-07,
|
| 647 |
+
"loss": 0.3358,
|
| 648 |
+
"step": 890
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.678571428571429,
|
| 652 |
+
"grad_norm": 0.9571473294443575,
|
| 653 |
+
"learning_rate": 1.9382791778596864e-07,
|
| 654 |
+
"loss": 0.3343,
|
| 655 |
+
"step": 900
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.7083333333333335,
|
| 659 |
+
"grad_norm": 0.9382822776109654,
|
| 660 |
+
"learning_rate": 1.5996596179531365e-07,
|
| 661 |
+
"loss": 0.3348,
|
| 662 |
+
"step": 910
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.738095238095238,
|
| 666 |
+
"grad_norm": 0.9309707054846061,
|
| 667 |
+
"learning_rate": 1.2925556625931174e-07,
|
| 668 |
+
"loss": 0.3375,
|
| 669 |
+
"step": 920
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.767857142857143,
|
| 673 |
+
"grad_norm": 0.9621376118686727,
|
| 674 |
+
"learning_rate": 1.0173809197295075e-07,
|
| 675 |
+
"loss": 0.336,
|
| 676 |
+
"step": 930
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.7976190476190474,
|
| 680 |
+
"grad_norm": 0.9169046599509947,
|
| 681 |
+
"learning_rate": 7.7450599501315e-08,
|
| 682 |
+
"loss": 0.3339,
|
| 683 |
+
"step": 940
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.8273809523809526,
|
| 687 |
+
"grad_norm": 0.9398290467609749,
|
| 688 |
+
"learning_rate": 5.6425799266375534e-08,
|
| 689 |
+
"loss": 0.335,
|
| 690 |
+
"step": 950
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.857142857142857,
|
| 694 |
+
"grad_norm": 0.9100820752220524,
|
| 695 |
+
"learning_rate": 3.869200749255703e-08,
|
| 696 |
+
"loss": 0.334,
|
| 697 |
+
"step": 960
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.886904761904762,
|
| 701 |
+
"grad_norm": 0.904751932290303,
|
| 702 |
+
"learning_rate": 2.427310807041561e-08,
|
| 703 |
+
"loss": 0.3327,
|
| 704 |
+
"step": 970
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.9166666666666665,
|
| 708 |
+
"grad_norm": 0.913682536330684,
|
| 709 |
+
"learning_rate": 1.3188520389787462e-08,
|
| 710 |
+
"loss": 0.3313,
|
| 711 |
+
"step": 980
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.946428571428571,
|
| 715 |
+
"grad_norm": 0.9340585620250436,
|
| 716 |
+
"learning_rate": 5.453173185734073e-09,
|
| 717 |
+
"loss": 0.336,
|
| 718 |
+
"step": 990
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.9761904761904763,
|
| 722 |
+
"grad_norm": 0.9406350686317787,
|
| 723 |
+
"learning_rate": 1.0774844325039946e-09,
|
| 724 |
+
"loss": 0.3325,
|
| 725 |
+
"step": 1000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 3.0,
|
| 729 |
+
"eval_loss": 0.057458870112895966,
|
| 730 |
+
"eval_runtime": 228.1192,
|
| 731 |
+
"eval_samples_per_second": 79.358,
|
| 732 |
+
"eval_steps_per_second": 0.622,
|
| 733 |
+
"step": 1008
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 3.0,
|
| 737 |
+
"step": 1008,
|
| 738 |
+
"total_flos": 3376456327495680.0,
|
| 739 |
+
"train_loss": 0.4351037277115716,
|
| 740 |
+
"train_runtime": 33019.7588,
|
| 741 |
+
"train_samples_per_second": 31.25,
|
| 742 |
+
"train_steps_per_second": 0.031
|
| 743 |
+
}
|
| 744 |
+
],
|
| 745 |
+
"logging_steps": 10,
|
| 746 |
+
"max_steps": 1008,
|
| 747 |
+
"num_input_tokens_seen": 0,
|
| 748 |
+
"num_train_epochs": 3,
|
| 749 |
+
"save_steps": 500,
|
| 750 |
+
"stateful_callbacks": {
|
| 751 |
+
"TrainerControl": {
|
| 752 |
+
"args": {
|
| 753 |
+
"should_epoch_stop": false,
|
| 754 |
+
"should_evaluate": false,
|
| 755 |
+
"should_log": false,
|
| 756 |
+
"should_save": true,
|
| 757 |
+
"should_training_stop": true
|
| 758 |
+
},
|
| 759 |
+
"attributes": {}
|
| 760 |
+
}
|
| 761 |
+
},
|
| 762 |
+
"total_flos": 3376456327495680.0,
|
| 763 |
+
"train_batch_size": 8,
|
| 764 |
+
"trial_name": null,
|
| 765 |
+
"trial_params": null
|
| 766 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|