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 +745 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: llama3.1
|
|
| 4 |
base_model: meta-llama/Meta-Llama-3.1-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: oh-dcft-v1.2_no-curation_gpt-4o-mini_wo_airoboros
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# oh-dcft-v1.2_no-curation_gpt-4o-mini_wo_airoboros
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.6514
|
| 21 |
|
|
|
|
| 4 |
base_model: meta-llama/Meta-Llama-3.1-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: oh-dcft-v1.2_no-curation_gpt-4o-mini_wo_airoboros
|
|
|
|
| 16 |
|
| 17 |
# oh-dcft-v1.2_no-curation_gpt-4o-mini_wo_airoboros
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/oh-dcft-v1.2_no-curation_gpt-4o-mini_wo_airoboros dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.6514
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.6513996720314026,
|
| 4 |
+
"eval_runtime": 31.2805,
|
| 5 |
+
"eval_samples_per_second": 278.608,
|
| 6 |
+
"eval_steps_per_second": 1.119,
|
| 7 |
+
"total_flos": 1628136202567680.0,
|
| 8 |
+
"train_loss": 0.6230609294318368,
|
| 9 |
+
"train_runtime": 6074.7502,
|
| 10 |
+
"train_samples_per_second": 81.773,
|
| 11 |
+
"train_steps_per_second": 0.16
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.6513996720314026,
|
| 4 |
+
"eval_runtime": 31.2805,
|
| 5 |
+
"eval_samples_per_second": 278.608,
|
| 6 |
+
"eval_steps_per_second": 1.119
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1628136202567680.0,
|
| 4 |
+
"train_loss": 0.6230609294318368,
|
| 5 |
+
"train_runtime": 6074.7502,
|
| 6 |
+
"train_samples_per_second": 81.773,
|
| 7 |
+
"train_steps_per_second": 0.16
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,745 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 972,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.030864197530864196,
|
| 13 |
+
"grad_norm": 5.446850666927686,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 0.9199,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06172839506172839,
|
| 20 |
+
"grad_norm": 2.663126142630872,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.821,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.09259259259259259,
|
| 27 |
+
"grad_norm": 1.1642696107304236,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.7706,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.12345679012345678,
|
| 34 |
+
"grad_norm": 4.280110588222716,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.7596,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.15432098765432098,
|
| 41 |
+
"grad_norm": 4.412787627263132,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.746,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.18518518518518517,
|
| 48 |
+
"grad_norm": 1.5711972402992538,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.7267,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.21604938271604937,
|
| 55 |
+
"grad_norm": 0.9451756673135364,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.7186,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.24691358024691357,
|
| 62 |
+
"grad_norm": 0.9020860720269491,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.7099,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.2777777777777778,
|
| 69 |
+
"grad_norm": 0.7223983788610128,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.7001,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.30864197530864196,
|
| 76 |
+
"grad_norm": 0.8632286972903407,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.6965,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3395061728395062,
|
| 83 |
+
"grad_norm": 0.6600509272889379,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.6878,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.37037037037037035,
|
| 90 |
+
"grad_norm": 0.8445466577407515,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.685,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.4012345679012346,
|
| 97 |
+
"grad_norm": 0.7606146778204088,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.6826,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.43209876543209874,
|
| 104 |
+
"grad_norm": 0.6093510086614801,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.6828,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.46296296296296297,
|
| 111 |
+
"grad_norm": 0.7249517817925787,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.6808,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.49382716049382713,
|
| 118 |
+
"grad_norm": 0.559508936091321,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.6806,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5246913580246914,
|
| 125 |
+
"grad_norm": 0.6485112723957187,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.6755,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.5555555555555556,
|
| 132 |
+
"grad_norm": 0.5734053780909245,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.6676,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.5864197530864198,
|
| 139 |
+
"grad_norm": 0.7330429838481911,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.6695,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.6172839506172839,
|
| 146 |
+
"grad_norm": 0.7031639101048125,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.669,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.6481481481481481,
|
| 153 |
+
"grad_norm": 0.5618292117245931,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.6759,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.6790123456790124,
|
| 160 |
+
"grad_norm": 0.5384920681614226,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.6626,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.7098765432098766,
|
| 167 |
+
"grad_norm": 0.8695843119793333,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.6613,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.7407407407407407,
|
| 174 |
+
"grad_norm": 0.8530303198305609,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.6622,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.7716049382716049,
|
| 181 |
+
"grad_norm": 0.7246183829809985,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.6585,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.8024691358024691,
|
| 188 |
+
"grad_norm": 0.6467615123805251,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.6663,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.8333333333333334,
|
| 195 |
+
"grad_norm": 0.6051023696593527,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.6578,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.8641975308641975,
|
| 202 |
+
"grad_norm": 0.5325735601636417,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.6628,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.8950617283950617,
|
| 209 |
+
"grad_norm": 0.5624534504885511,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.6551,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.9259259259259259,
|
| 216 |
+
"grad_norm": 0.5105392081865389,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.6585,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.9567901234567902,
|
| 223 |
+
"grad_norm": 0.7882251080908214,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.6578,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.9876543209876543,
|
| 230 |
+
"grad_norm": 0.7218610961797266,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.6542,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.0,
|
| 237 |
+
"eval_loss": 0.6550179123878479,
|
| 238 |
+
"eval_runtime": 31.8484,
|
| 239 |
+
"eval_samples_per_second": 273.641,
|
| 240 |
+
"eval_steps_per_second": 1.099,
|
| 241 |
+
"step": 324
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.0185185185185186,
|
| 245 |
+
"grad_norm": 0.7148119037457841,
|
| 246 |
+
"learning_rate": 5e-06,
|
| 247 |
+
"loss": 0.624,
|
| 248 |
+
"step": 330
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.0493827160493827,
|
| 252 |
+
"grad_norm": 0.8285481607039845,
|
| 253 |
+
"learning_rate": 5e-06,
|
| 254 |
+
"loss": 0.6138,
|
| 255 |
+
"step": 340
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.0802469135802468,
|
| 259 |
+
"grad_norm": 0.5405908730469038,
|
| 260 |
+
"learning_rate": 5e-06,
|
| 261 |
+
"loss": 0.6154,
|
| 262 |
+
"step": 350
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.1111111111111112,
|
| 266 |
+
"grad_norm": 0.6837013751545337,
|
| 267 |
+
"learning_rate": 5e-06,
|
| 268 |
+
"loss": 0.613,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.1419753086419753,
|
| 273 |
+
"grad_norm": 0.8086734597067436,
|
| 274 |
+
"learning_rate": 5e-06,
|
| 275 |
+
"loss": 0.6051,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.1728395061728394,
|
| 280 |
+
"grad_norm": 0.6168727254851533,
|
| 281 |
+
"learning_rate": 5e-06,
|
| 282 |
+
"loss": 0.6047,
|
| 283 |
+
"step": 380
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.2037037037037037,
|
| 287 |
+
"grad_norm": 0.6222564529681911,
|
| 288 |
+
"learning_rate": 5e-06,
|
| 289 |
+
"loss": 0.6135,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.2345679012345678,
|
| 294 |
+
"grad_norm": 0.6502199448782471,
|
| 295 |
+
"learning_rate": 5e-06,
|
| 296 |
+
"loss": 0.6092,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.2654320987654322,
|
| 301 |
+
"grad_norm": 0.642957942043697,
|
| 302 |
+
"learning_rate": 5e-06,
|
| 303 |
+
"loss": 0.6151,
|
| 304 |
+
"step": 410
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.2962962962962963,
|
| 308 |
+
"grad_norm": 0.6973190504371732,
|
| 309 |
+
"learning_rate": 5e-06,
|
| 310 |
+
"loss": 0.6087,
|
| 311 |
+
"step": 420
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.3271604938271606,
|
| 315 |
+
"grad_norm": 0.5681720826825847,
|
| 316 |
+
"learning_rate": 5e-06,
|
| 317 |
+
"loss": 0.6058,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.3580246913580247,
|
| 322 |
+
"grad_norm": 0.5560347945291988,
|
| 323 |
+
"learning_rate": 5e-06,
|
| 324 |
+
"loss": 0.6152,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.3888888888888888,
|
| 329 |
+
"grad_norm": 0.5202152575422632,
|
| 330 |
+
"learning_rate": 5e-06,
|
| 331 |
+
"loss": 0.6112,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.4197530864197532,
|
| 336 |
+
"grad_norm": 0.6652453548193578,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.6084,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.4506172839506173,
|
| 343 |
+
"grad_norm": 0.5959726615804369,
|
| 344 |
+
"learning_rate": 5e-06,
|
| 345 |
+
"loss": 0.611,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.4814814814814814,
|
| 350 |
+
"grad_norm": 0.5753042580268376,
|
| 351 |
+
"learning_rate": 5e-06,
|
| 352 |
+
"loss": 0.6099,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.5123456790123457,
|
| 357 |
+
"grad_norm": 0.5657589973831328,
|
| 358 |
+
"learning_rate": 5e-06,
|
| 359 |
+
"loss": 0.6158,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.5432098765432098,
|
| 364 |
+
"grad_norm": 0.48962281372551314,
|
| 365 |
+
"learning_rate": 5e-06,
|
| 366 |
+
"loss": 0.612,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.574074074074074,
|
| 371 |
+
"grad_norm": 0.5867122795097997,
|
| 372 |
+
"learning_rate": 5e-06,
|
| 373 |
+
"loss": 0.6092,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.6049382716049383,
|
| 378 |
+
"grad_norm": 0.567887162579392,
|
| 379 |
+
"learning_rate": 5e-06,
|
| 380 |
+
"loss": 0.6049,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.6358024691358026,
|
| 385 |
+
"grad_norm": 0.5846370116192817,
|
| 386 |
+
"learning_rate": 5e-06,
|
| 387 |
+
"loss": 0.6102,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.6666666666666665,
|
| 392 |
+
"grad_norm": 0.7372794706158421,
|
| 393 |
+
"learning_rate": 5e-06,
|
| 394 |
+
"loss": 0.6121,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.6975308641975309,
|
| 399 |
+
"grad_norm": 0.5679832644741175,
|
| 400 |
+
"learning_rate": 5e-06,
|
| 401 |
+
"loss": 0.6039,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.7283950617283952,
|
| 406 |
+
"grad_norm": 0.4951982048137007,
|
| 407 |
+
"learning_rate": 5e-06,
|
| 408 |
+
"loss": 0.6097,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.7592592592592593,
|
| 413 |
+
"grad_norm": 0.5947044750562988,
|
| 414 |
+
"learning_rate": 5e-06,
|
| 415 |
+
"loss": 0.6108,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.7901234567901234,
|
| 420 |
+
"grad_norm": 0.5672737096963988,
|
| 421 |
+
"learning_rate": 5e-06,
|
| 422 |
+
"loss": 0.6095,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.8209876543209877,
|
| 427 |
+
"grad_norm": 0.5215432816515835,
|
| 428 |
+
"learning_rate": 5e-06,
|
| 429 |
+
"loss": 0.6096,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.8518518518518519,
|
| 434 |
+
"grad_norm": 0.5356125614039279,
|
| 435 |
+
"learning_rate": 5e-06,
|
| 436 |
+
"loss": 0.6037,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.882716049382716,
|
| 441 |
+
"grad_norm": 0.5290482585426443,
|
| 442 |
+
"learning_rate": 5e-06,
|
| 443 |
+
"loss": 0.6062,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.9135802469135803,
|
| 448 |
+
"grad_norm": 0.6241816332212873,
|
| 449 |
+
"learning_rate": 5e-06,
|
| 450 |
+
"loss": 0.6106,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.9444444444444444,
|
| 455 |
+
"grad_norm": 0.4959658493368521,
|
| 456 |
+
"learning_rate": 5e-06,
|
| 457 |
+
"loss": 0.6067,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.9753086419753085,
|
| 462 |
+
"grad_norm": 0.5282675010462219,
|
| 463 |
+
"learning_rate": 5e-06,
|
| 464 |
+
"loss": 0.6069,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.0,
|
| 469 |
+
"eval_loss": 0.6462317109107971,
|
| 470 |
+
"eval_runtime": 32.1855,
|
| 471 |
+
"eval_samples_per_second": 270.774,
|
| 472 |
+
"eval_steps_per_second": 1.087,
|
| 473 |
+
"step": 648
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 2.006172839506173,
|
| 477 |
+
"grad_norm": 0.7935581137695162,
|
| 478 |
+
"learning_rate": 5e-06,
|
| 479 |
+
"loss": 0.596,
|
| 480 |
+
"step": 650
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.037037037037037,
|
| 484 |
+
"grad_norm": 0.6261816641543,
|
| 485 |
+
"learning_rate": 5e-06,
|
| 486 |
+
"loss": 0.5645,
|
| 487 |
+
"step": 660
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 2.067901234567901,
|
| 491 |
+
"grad_norm": 0.5849160839297688,
|
| 492 |
+
"learning_rate": 5e-06,
|
| 493 |
+
"loss": 0.558,
|
| 494 |
+
"step": 670
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.0987654320987654,
|
| 498 |
+
"grad_norm": 0.6105130235265663,
|
| 499 |
+
"learning_rate": 5e-06,
|
| 500 |
+
"loss": 0.5591,
|
| 501 |
+
"step": 680
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.1296296296296298,
|
| 505 |
+
"grad_norm": 0.6033282280363377,
|
| 506 |
+
"learning_rate": 5e-06,
|
| 507 |
+
"loss": 0.5573,
|
| 508 |
+
"step": 690
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 2.1604938271604937,
|
| 512 |
+
"grad_norm": 0.7739145588445309,
|
| 513 |
+
"learning_rate": 5e-06,
|
| 514 |
+
"loss": 0.5571,
|
| 515 |
+
"step": 700
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.191358024691358,
|
| 519 |
+
"grad_norm": 0.626140801689634,
|
| 520 |
+
"learning_rate": 5e-06,
|
| 521 |
+
"loss": 0.56,
|
| 522 |
+
"step": 710
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 2.2222222222222223,
|
| 526 |
+
"grad_norm": 0.5916889343710152,
|
| 527 |
+
"learning_rate": 5e-06,
|
| 528 |
+
"loss": 0.5571,
|
| 529 |
+
"step": 720
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.253086419753086,
|
| 533 |
+
"grad_norm": 0.636584234517333,
|
| 534 |
+
"learning_rate": 5e-06,
|
| 535 |
+
"loss": 0.5638,
|
| 536 |
+
"step": 730
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.2839506172839505,
|
| 540 |
+
"grad_norm": 0.5507349524263677,
|
| 541 |
+
"learning_rate": 5e-06,
|
| 542 |
+
"loss": 0.5724,
|
| 543 |
+
"step": 740
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.314814814814815,
|
| 547 |
+
"grad_norm": 0.6732342797910674,
|
| 548 |
+
"learning_rate": 5e-06,
|
| 549 |
+
"loss": 0.567,
|
| 550 |
+
"step": 750
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.3456790123456788,
|
| 554 |
+
"grad_norm": 0.5395015214035337,
|
| 555 |
+
"learning_rate": 5e-06,
|
| 556 |
+
"loss": 0.5569,
|
| 557 |
+
"step": 760
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 2.376543209876543,
|
| 561 |
+
"grad_norm": 0.5992087208696053,
|
| 562 |
+
"learning_rate": 5e-06,
|
| 563 |
+
"loss": 0.5647,
|
| 564 |
+
"step": 770
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.4074074074074074,
|
| 568 |
+
"grad_norm": 0.5102699543572234,
|
| 569 |
+
"learning_rate": 5e-06,
|
| 570 |
+
"loss": 0.5622,
|
| 571 |
+
"step": 780
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.4382716049382718,
|
| 575 |
+
"grad_norm": 0.6025610989122395,
|
| 576 |
+
"learning_rate": 5e-06,
|
| 577 |
+
"loss": 0.5634,
|
| 578 |
+
"step": 790
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.4691358024691357,
|
| 582 |
+
"grad_norm": 0.6231368998767735,
|
| 583 |
+
"learning_rate": 5e-06,
|
| 584 |
+
"loss": 0.5594,
|
| 585 |
+
"step": 800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.5,
|
| 589 |
+
"grad_norm": 0.5707370285498646,
|
| 590 |
+
"learning_rate": 5e-06,
|
| 591 |
+
"loss": 0.5685,
|
| 592 |
+
"step": 810
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.5308641975308643,
|
| 596 |
+
"grad_norm": 0.5549089552658856,
|
| 597 |
+
"learning_rate": 5e-06,
|
| 598 |
+
"loss": 0.5629,
|
| 599 |
+
"step": 820
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.5617283950617287,
|
| 603 |
+
"grad_norm": 0.542471712528822,
|
| 604 |
+
"learning_rate": 5e-06,
|
| 605 |
+
"loss": 0.5681,
|
| 606 |
+
"step": 830
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.5925925925925926,
|
| 610 |
+
"grad_norm": 0.5566494869370542,
|
| 611 |
+
"learning_rate": 5e-06,
|
| 612 |
+
"loss": 0.5663,
|
| 613 |
+
"step": 840
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.623456790123457,
|
| 617 |
+
"grad_norm": 0.5552433471790524,
|
| 618 |
+
"learning_rate": 5e-06,
|
| 619 |
+
"loss": 0.5635,
|
| 620 |
+
"step": 850
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.6543209876543212,
|
| 624 |
+
"grad_norm": 0.5049248358370862,
|
| 625 |
+
"learning_rate": 5e-06,
|
| 626 |
+
"loss": 0.5654,
|
| 627 |
+
"step": 860
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.685185185185185,
|
| 631 |
+
"grad_norm": 0.6071017582058569,
|
| 632 |
+
"learning_rate": 5e-06,
|
| 633 |
+
"loss": 0.5669,
|
| 634 |
+
"step": 870
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.7160493827160495,
|
| 638 |
+
"grad_norm": 0.5625590442980464,
|
| 639 |
+
"learning_rate": 5e-06,
|
| 640 |
+
"loss": 0.5642,
|
| 641 |
+
"step": 880
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.746913580246914,
|
| 645 |
+
"grad_norm": 0.5506548153090438,
|
| 646 |
+
"learning_rate": 5e-06,
|
| 647 |
+
"loss": 0.5638,
|
| 648 |
+
"step": 890
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.7777777777777777,
|
| 652 |
+
"grad_norm": 0.6470830808425209,
|
| 653 |
+
"learning_rate": 5e-06,
|
| 654 |
+
"loss": 0.5629,
|
| 655 |
+
"step": 900
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.808641975308642,
|
| 659 |
+
"grad_norm": 0.6202475264816772,
|
| 660 |
+
"learning_rate": 5e-06,
|
| 661 |
+
"loss": 0.566,
|
| 662 |
+
"step": 910
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.8395061728395063,
|
| 666 |
+
"grad_norm": 0.6200010347166321,
|
| 667 |
+
"learning_rate": 5e-06,
|
| 668 |
+
"loss": 0.5672,
|
| 669 |
+
"step": 920
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.8703703703703702,
|
| 673 |
+
"grad_norm": 0.5382597238916978,
|
| 674 |
+
"learning_rate": 5e-06,
|
| 675 |
+
"loss": 0.5674,
|
| 676 |
+
"step": 930
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.9012345679012346,
|
| 680 |
+
"grad_norm": 0.6294871904049958,
|
| 681 |
+
"learning_rate": 5e-06,
|
| 682 |
+
"loss": 0.5714,
|
| 683 |
+
"step": 940
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.932098765432099,
|
| 687 |
+
"grad_norm": 0.5413425077416242,
|
| 688 |
+
"learning_rate": 5e-06,
|
| 689 |
+
"loss": 0.5677,
|
| 690 |
+
"step": 950
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.962962962962963,
|
| 694 |
+
"grad_norm": 0.5307261656256946,
|
| 695 |
+
"learning_rate": 5e-06,
|
| 696 |
+
"loss": 0.5674,
|
| 697 |
+
"step": 960
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.993827160493827,
|
| 701 |
+
"grad_norm": 0.519858507326187,
|
| 702 |
+
"learning_rate": 5e-06,
|
| 703 |
+
"loss": 0.5688,
|
| 704 |
+
"step": 970
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 3.0,
|
| 708 |
+
"eval_loss": 0.6513996720314026,
|
| 709 |
+
"eval_runtime": 31.4148,
|
| 710 |
+
"eval_samples_per_second": 277.417,
|
| 711 |
+
"eval_steps_per_second": 1.114,
|
| 712 |
+
"step": 972
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 3.0,
|
| 716 |
+
"step": 972,
|
| 717 |
+
"total_flos": 1628136202567680.0,
|
| 718 |
+
"train_loss": 0.6230609294318368,
|
| 719 |
+
"train_runtime": 6074.7502,
|
| 720 |
+
"train_samples_per_second": 81.773,
|
| 721 |
+
"train_steps_per_second": 0.16
|
| 722 |
+
}
|
| 723 |
+
],
|
| 724 |
+
"logging_steps": 10,
|
| 725 |
+
"max_steps": 972,
|
| 726 |
+
"num_input_tokens_seen": 0,
|
| 727 |
+
"num_train_epochs": 3,
|
| 728 |
+
"save_steps": 500,
|
| 729 |
+
"stateful_callbacks": {
|
| 730 |
+
"TrainerControl": {
|
| 731 |
+
"args": {
|
| 732 |
+
"should_epoch_stop": false,
|
| 733 |
+
"should_evaluate": false,
|
| 734 |
+
"should_log": false,
|
| 735 |
+
"should_save": true,
|
| 736 |
+
"should_training_stop": true
|
| 737 |
+
},
|
| 738 |
+
"attributes": {}
|
| 739 |
+
}
|
| 740 |
+
},
|
| 741 |
+
"total_flos": 1628136202567680.0,
|
| 742 |
+
"train_batch_size": 16,
|
| 743 |
+
"trial_name": null,
|
| 744 |
+
"trial_params": null
|
| 745 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|