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 +646 -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: hp_ablations_llama3_epoch2
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# hp_ablations_llama3_epoch2
|
| 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: 0.6399
|
| 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: hp_ablations_llama3_epoch2
|
|
|
|
| 16 |
|
| 17 |
# hp_ablations_llama3_epoch2
|
| 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-v3.1-gpt-4o-mini dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.6399
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.9973380656610469,
|
| 3 |
+
"eval_loss": 0.6398828029632568,
|
| 4 |
+
"eval_runtime": 450.1392,
|
| 5 |
+
"eval_samples_per_second": 25.301,
|
| 6 |
+
"eval_steps_per_second": 0.395,
|
| 7 |
+
"total_flos": 1413522055495680.0,
|
| 8 |
+
"train_loss": 0.645099672378522,
|
| 9 |
+
"train_runtime": 50035.9585,
|
| 10 |
+
"train_samples_per_second": 8.649,
|
| 11 |
+
"train_steps_per_second": 0.017
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.9973380656610469,
|
| 3 |
+
"eval_loss": 0.6398828029632568,
|
| 4 |
+
"eval_runtime": 450.1392,
|
| 5 |
+
"eval_samples_per_second": 25.301,
|
| 6 |
+
"eval_steps_per_second": 0.395
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.9973380656610469,
|
| 3 |
+
"total_flos": 1413522055495680.0,
|
| 4 |
+
"train_loss": 0.645099672378522,
|
| 5 |
+
"train_runtime": 50035.9585,
|
| 6 |
+
"train_samples_per_second": 8.649,
|
| 7 |
+
"train_steps_per_second": 0.017
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,646 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9973380656610469,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 844,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.023661638568470866,
|
| 13 |
+
"grad_norm": 1.2408271523327399,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 0.8878,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.04732327713694173,
|
| 20 |
+
"grad_norm": 10.221763472546659,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.7989,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0709849157054126,
|
| 27 |
+
"grad_norm": 1.2230059638293505,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.773,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.09464655427388347,
|
| 34 |
+
"grad_norm": 2.6694221939382583,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.7466,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.11830819284235433,
|
| 41 |
+
"grad_norm": 0.7655921008659343,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.7308,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1419698314108252,
|
| 48 |
+
"grad_norm": 0.6751841899446792,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.7178,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.16563146997929606,
|
| 55 |
+
"grad_norm": 0.545261037277831,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.7116,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.18929310854776693,
|
| 62 |
+
"grad_norm": 0.8030523103589834,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.7017,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.2129547471162378,
|
| 69 |
+
"grad_norm": 0.8014531123871866,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.6861,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.23661638568470866,
|
| 76 |
+
"grad_norm": 0.4918470297754101,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.6852,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.26027802425317953,
|
| 83 |
+
"grad_norm": 0.69215978679395,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.69,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.2839396628216504,
|
| 90 |
+
"grad_norm": 0.8786435457825235,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.6773,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.30760130139012126,
|
| 97 |
+
"grad_norm": 0.49069358486584114,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.6737,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.33126293995859213,
|
| 104 |
+
"grad_norm": 0.7921488279977867,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.6821,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.354924578527063,
|
| 111 |
+
"grad_norm": 0.77230991386959,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.6648,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.37858621709553386,
|
| 118 |
+
"grad_norm": 0.47987920788300265,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.669,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.4022478556640047,
|
| 125 |
+
"grad_norm": 0.5618200809563821,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.6668,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.4259094942324756,
|
| 132 |
+
"grad_norm": 0.7304782642194491,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.6737,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.44957113280094646,
|
| 139 |
+
"grad_norm": 0.46280184605813207,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.6697,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.4732327713694173,
|
| 146 |
+
"grad_norm": 0.7079097684721737,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.6686,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.4968944099378882,
|
| 153 |
+
"grad_norm": 0.774761573498746,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.6694,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.5205560485063591,
|
| 160 |
+
"grad_norm": 0.576730626392715,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.6677,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.54421768707483,
|
| 167 |
+
"grad_norm": 0.5744988270185307,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.6602,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.5678793256433008,
|
| 174 |
+
"grad_norm": 0.5394481930250411,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.6644,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.5915409642117717,
|
| 181 |
+
"grad_norm": 0.5182952984171931,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.6615,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.6152026027802425,
|
| 188 |
+
"grad_norm": 0.6364320156443367,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.6519,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.6388642413487134,
|
| 195 |
+
"grad_norm": 0.6324207034276161,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.6639,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.6625258799171843,
|
| 202 |
+
"grad_norm": 0.6620182705762153,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.6651,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.6861875184856552,
|
| 209 |
+
"grad_norm": 0.46128169756980925,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.6596,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.709849157054126,
|
| 216 |
+
"grad_norm": 0.622188372470794,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.6534,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.7335107956225969,
|
| 223 |
+
"grad_norm": 0.4904698615453566,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.6618,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.7571724341910677,
|
| 230 |
+
"grad_norm": 0.4555806118897353,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.6554,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.7808340727595386,
|
| 237 |
+
"grad_norm": 0.5273034701797177,
|
| 238 |
+
"learning_rate": 5e-06,
|
| 239 |
+
"loss": 0.654,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.8044957113280095,
|
| 244 |
+
"grad_norm": 0.5442233535066454,
|
| 245 |
+
"learning_rate": 5e-06,
|
| 246 |
+
"loss": 0.6537,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.8281573498964804,
|
| 251 |
+
"grad_norm": 0.6380409398524519,
|
| 252 |
+
"learning_rate": 5e-06,
|
| 253 |
+
"loss": 0.6601,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.8518189884649512,
|
| 258 |
+
"grad_norm": 0.4389996927828098,
|
| 259 |
+
"learning_rate": 5e-06,
|
| 260 |
+
"loss": 0.6537,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.8754806270334221,
|
| 265 |
+
"grad_norm": 0.4608268531740333,
|
| 266 |
+
"learning_rate": 5e-06,
|
| 267 |
+
"loss": 0.6565,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.8991422656018929,
|
| 272 |
+
"grad_norm": 0.5330723429667825,
|
| 273 |
+
"learning_rate": 5e-06,
|
| 274 |
+
"loss": 0.6477,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.9228039041703638,
|
| 279 |
+
"grad_norm": 0.5929849990200475,
|
| 280 |
+
"learning_rate": 5e-06,
|
| 281 |
+
"loss": 0.6552,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.9464655427388347,
|
| 286 |
+
"grad_norm": 0.4773172047297779,
|
| 287 |
+
"learning_rate": 5e-06,
|
| 288 |
+
"loss": 0.6464,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.9701271813073056,
|
| 293 |
+
"grad_norm": 0.4606137860127268,
|
| 294 |
+
"learning_rate": 5e-06,
|
| 295 |
+
"loss": 0.6489,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.9937888198757764,
|
| 300 |
+
"grad_norm": 0.526120099445913,
|
| 301 |
+
"learning_rate": 5e-06,
|
| 302 |
+
"loss": 0.6478,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.9985211475894705,
|
| 307 |
+
"eval_loss": 0.6501929759979248,
|
| 308 |
+
"eval_runtime": 449.6535,
|
| 309 |
+
"eval_samples_per_second": 25.328,
|
| 310 |
+
"eval_steps_per_second": 0.396,
|
| 311 |
+
"step": 422
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.0177462289263532,
|
| 315 |
+
"grad_norm": 0.5143362353922324,
|
| 316 |
+
"learning_rate": 5e-06,
|
| 317 |
+
"loss": 0.6515,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.041407867494824,
|
| 322 |
+
"grad_norm": 0.5162162401792869,
|
| 323 |
+
"learning_rate": 5e-06,
|
| 324 |
+
"loss": 0.605,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.0650695060632949,
|
| 329 |
+
"grad_norm": 0.7393357078452915,
|
| 330 |
+
"learning_rate": 5e-06,
|
| 331 |
+
"loss": 0.603,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.0887311446317658,
|
| 336 |
+
"grad_norm": 0.649426932177774,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.6134,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.1123927832002367,
|
| 343 |
+
"grad_norm": 0.5705639188659947,
|
| 344 |
+
"learning_rate": 5e-06,
|
| 345 |
+
"loss": 0.6106,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.1360544217687074,
|
| 350 |
+
"grad_norm": 0.7543562567579628,
|
| 351 |
+
"learning_rate": 5e-06,
|
| 352 |
+
"loss": 0.611,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.1597160603371783,
|
| 357 |
+
"grad_norm": 0.5499597181388575,
|
| 358 |
+
"learning_rate": 5e-06,
|
| 359 |
+
"loss": 0.6079,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.1833776989056493,
|
| 364 |
+
"grad_norm": 0.5262121393467482,
|
| 365 |
+
"learning_rate": 5e-06,
|
| 366 |
+
"loss": 0.6036,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.2070393374741202,
|
| 371 |
+
"grad_norm": 0.5683114548160128,
|
| 372 |
+
"learning_rate": 5e-06,
|
| 373 |
+
"loss": 0.6034,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.2307009760425909,
|
| 378 |
+
"grad_norm": 0.6610172663362014,
|
| 379 |
+
"learning_rate": 5e-06,
|
| 380 |
+
"loss": 0.6099,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.2543626146110618,
|
| 385 |
+
"grad_norm": 0.6007955010537178,
|
| 386 |
+
"learning_rate": 5e-06,
|
| 387 |
+
"loss": 0.6125,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.2780242531795327,
|
| 392 |
+
"grad_norm": 0.5585264375543114,
|
| 393 |
+
"learning_rate": 5e-06,
|
| 394 |
+
"loss": 0.6121,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.3016858917480034,
|
| 399 |
+
"grad_norm": 0.4689366084615487,
|
| 400 |
+
"learning_rate": 5e-06,
|
| 401 |
+
"loss": 0.6089,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.3253475303164743,
|
| 406 |
+
"grad_norm": 0.443719906754886,
|
| 407 |
+
"learning_rate": 5e-06,
|
| 408 |
+
"loss": 0.6073,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.3490091688849453,
|
| 413 |
+
"grad_norm": 0.8624897115990705,
|
| 414 |
+
"learning_rate": 5e-06,
|
| 415 |
+
"loss": 0.6084,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.3726708074534162,
|
| 420 |
+
"grad_norm": 0.5498793437391156,
|
| 421 |
+
"learning_rate": 5e-06,
|
| 422 |
+
"loss": 0.611,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.396332446021887,
|
| 427 |
+
"grad_norm": 0.44457160894446396,
|
| 428 |
+
"learning_rate": 5e-06,
|
| 429 |
+
"loss": 0.6115,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.4199940845903578,
|
| 434 |
+
"grad_norm": 0.5196837986130378,
|
| 435 |
+
"learning_rate": 5e-06,
|
| 436 |
+
"loss": 0.6008,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.4436557231588287,
|
| 441 |
+
"grad_norm": 0.40806642647037533,
|
| 442 |
+
"learning_rate": 5e-06,
|
| 443 |
+
"loss": 0.6002,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.4673173617272997,
|
| 448 |
+
"grad_norm": 0.449778520265882,
|
| 449 |
+
"learning_rate": 5e-06,
|
| 450 |
+
"loss": 0.6037,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.4909790002957704,
|
| 455 |
+
"grad_norm": 0.46760792115141014,
|
| 456 |
+
"learning_rate": 5e-06,
|
| 457 |
+
"loss": 0.6157,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.5146406388642415,
|
| 462 |
+
"grad_norm": 0.4490152450206069,
|
| 463 |
+
"learning_rate": 5e-06,
|
| 464 |
+
"loss": 0.6101,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.5383022774327122,
|
| 469 |
+
"grad_norm": 0.42442779950583953,
|
| 470 |
+
"learning_rate": 5e-06,
|
| 471 |
+
"loss": 0.6042,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.5619639160011831,
|
| 476 |
+
"grad_norm": 0.5976128445381751,
|
| 477 |
+
"learning_rate": 5e-06,
|
| 478 |
+
"loss": 0.609,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.585625554569654,
|
| 483 |
+
"grad_norm": 0.7381067199080075,
|
| 484 |
+
"learning_rate": 5e-06,
|
| 485 |
+
"loss": 0.6015,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.6092871931381247,
|
| 490 |
+
"grad_norm": 0.4692365896477618,
|
| 491 |
+
"learning_rate": 5e-06,
|
| 492 |
+
"loss": 0.6098,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.6329488317065957,
|
| 497 |
+
"grad_norm": 0.5475052095467955,
|
| 498 |
+
"learning_rate": 5e-06,
|
| 499 |
+
"loss": 0.601,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.6566104702750666,
|
| 504 |
+
"grad_norm": 0.5706027825471482,
|
| 505 |
+
"learning_rate": 5e-06,
|
| 506 |
+
"loss": 0.6107,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.6802721088435373,
|
| 511 |
+
"grad_norm": 0.5270197331562642,
|
| 512 |
+
"learning_rate": 5e-06,
|
| 513 |
+
"loss": 0.609,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.7039337474120084,
|
| 518 |
+
"grad_norm": 0.6598391343305342,
|
| 519 |
+
"learning_rate": 5e-06,
|
| 520 |
+
"loss": 0.6118,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.7275953859804791,
|
| 525 |
+
"grad_norm": 0.5570434796027114,
|
| 526 |
+
"learning_rate": 5e-06,
|
| 527 |
+
"loss": 0.6116,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.75125702454895,
|
| 532 |
+
"grad_norm": 0.4955844130516369,
|
| 533 |
+
"learning_rate": 5e-06,
|
| 534 |
+
"loss": 0.6039,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.774918663117421,
|
| 539 |
+
"grad_norm": 0.47770168087128073,
|
| 540 |
+
"learning_rate": 5e-06,
|
| 541 |
+
"loss": 0.6101,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.7985803016858917,
|
| 546 |
+
"grad_norm": 0.4667370666965365,
|
| 547 |
+
"learning_rate": 5e-06,
|
| 548 |
+
"loss": 0.614,
|
| 549 |
+
"step": 760
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.8222419402543626,
|
| 553 |
+
"grad_norm": 0.4616819567056668,
|
| 554 |
+
"learning_rate": 5e-06,
|
| 555 |
+
"loss": 0.6158,
|
| 556 |
+
"step": 770
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.8459035788228335,
|
| 560 |
+
"grad_norm": 0.43467879051005953,
|
| 561 |
+
"learning_rate": 5e-06,
|
| 562 |
+
"loss": 0.6067,
|
| 563 |
+
"step": 780
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.8695652173913042,
|
| 567 |
+
"grad_norm": 0.48362881437134725,
|
| 568 |
+
"learning_rate": 5e-06,
|
| 569 |
+
"loss": 0.6054,
|
| 570 |
+
"step": 790
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.8932268559597754,
|
| 574 |
+
"grad_norm": 0.49747648081112666,
|
| 575 |
+
"learning_rate": 5e-06,
|
| 576 |
+
"loss": 0.6137,
|
| 577 |
+
"step": 800
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.916888494528246,
|
| 581 |
+
"grad_norm": 0.4097820122920606,
|
| 582 |
+
"learning_rate": 5e-06,
|
| 583 |
+
"loss": 0.6114,
|
| 584 |
+
"step": 810
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.940550133096717,
|
| 588 |
+
"grad_norm": 0.47535675742314604,
|
| 589 |
+
"learning_rate": 5e-06,
|
| 590 |
+
"loss": 0.5996,
|
| 591 |
+
"step": 820
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.964211771665188,
|
| 595 |
+
"grad_norm": 0.49949616004506914,
|
| 596 |
+
"learning_rate": 5e-06,
|
| 597 |
+
"loss": 0.6108,
|
| 598 |
+
"step": 830
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.9878734102336586,
|
| 602 |
+
"grad_norm": 0.4387152081138621,
|
| 603 |
+
"learning_rate": 5e-06,
|
| 604 |
+
"loss": 0.5981,
|
| 605 |
+
"step": 840
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.9973380656610469,
|
| 609 |
+
"eval_loss": 0.6398828029632568,
|
| 610 |
+
"eval_runtime": 449.4321,
|
| 611 |
+
"eval_samples_per_second": 25.341,
|
| 612 |
+
"eval_steps_per_second": 0.396,
|
| 613 |
+
"step": 844
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 1.9973380656610469,
|
| 617 |
+
"step": 844,
|
| 618 |
+
"total_flos": 1413522055495680.0,
|
| 619 |
+
"train_loss": 0.645099672378522,
|
| 620 |
+
"train_runtime": 50035.9585,
|
| 621 |
+
"train_samples_per_second": 8.649,
|
| 622 |
+
"train_steps_per_second": 0.017
|
| 623 |
+
}
|
| 624 |
+
],
|
| 625 |
+
"logging_steps": 10,
|
| 626 |
+
"max_steps": 844,
|
| 627 |
+
"num_input_tokens_seen": 0,
|
| 628 |
+
"num_train_epochs": 2,
|
| 629 |
+
"save_steps": 500,
|
| 630 |
+
"stateful_callbacks": {
|
| 631 |
+
"TrainerControl": {
|
| 632 |
+
"args": {
|
| 633 |
+
"should_epoch_stop": false,
|
| 634 |
+
"should_evaluate": false,
|
| 635 |
+
"should_log": false,
|
| 636 |
+
"should_save": true,
|
| 637 |
+
"should_training_stop": true
|
| 638 |
+
},
|
| 639 |
+
"attributes": {}
|
| 640 |
+
}
|
| 641 |
+
},
|
| 642 |
+
"total_flos": 1413522055495680.0,
|
| 643 |
+
"train_batch_size": 8,
|
| 644 |
+
"trial_name": null,
|
| 645 |
+
"trial_params": null
|
| 646 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|