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 +696 -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_v1.3_camel_chemistry_x4
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# oh_v1.3_camel_chemistry_x4
|
| 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: 0.7374
|
| 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_v1.3_camel_chemistry_x4
|
|
|
|
| 16 |
|
| 17 |
# oh_v1.3_camel_chemistry_x4
|
| 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_v1.3_camel_chemistry_x4 dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.7374
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9987628865979383,
|
| 3 |
+
"eval_loss": 0.737443208694458,
|
| 4 |
+
"eval_runtime": 323.8922,
|
| 5 |
+
"eval_samples_per_second": 25.218,
|
| 6 |
+
"eval_steps_per_second": 0.395,
|
| 7 |
+
"total_flos": 1522399476449280.0,
|
| 8 |
+
"train_loss": 0.7216839113644641,
|
| 9 |
+
"train_runtime": 53747.0627,
|
| 10 |
+
"train_samples_per_second": 8.662,
|
| 11 |
+
"train_steps_per_second": 0.017
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9987628865979383,
|
| 3 |
+
"eval_loss": 0.737443208694458,
|
| 4 |
+
"eval_runtime": 323.8922,
|
| 5 |
+
"eval_samples_per_second": 25.218,
|
| 6 |
+
"eval_steps_per_second": 0.395
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9987628865979383,
|
| 3 |
+
"total_flos": 1522399476449280.0,
|
| 4 |
+
"train_loss": 0.7216839113644641,
|
| 5 |
+
"train_runtime": 53747.0627,
|
| 6 |
+
"train_samples_per_second": 8.662,
|
| 7 |
+
"train_steps_per_second": 0.017
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,696 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9987628865979383,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 909,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.032989690721649485,
|
| 13 |
+
"grad_norm": 3.190283465974621,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 1.0361,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06597938144329897,
|
| 20 |
+
"grad_norm": 1.2412136578455273,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.9152,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.09896907216494845,
|
| 27 |
+
"grad_norm": 0.9937983329085553,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.8771,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.13195876288659794,
|
| 34 |
+
"grad_norm": 0.9565722646796444,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.855,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.16494845360824742,
|
| 41 |
+
"grad_norm": 0.8422015410274669,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.834,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1979381443298969,
|
| 48 |
+
"grad_norm": 0.9927761059685116,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.8249,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.2309278350515464,
|
| 55 |
+
"grad_norm": 1.0124625468461579,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.8092,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.2639175257731959,
|
| 62 |
+
"grad_norm": 0.9162707322543721,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.8002,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.29690721649484536,
|
| 69 |
+
"grad_norm": 0.7438936667406614,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.7953,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.32989690721649484,
|
| 76 |
+
"grad_norm": 0.74943987165883,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.7912,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3628865979381443,
|
| 83 |
+
"grad_norm": 0.6393536784375358,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.7835,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.3958762886597938,
|
| 90 |
+
"grad_norm": 0.6732184370236527,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.7846,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.4288659793814433,
|
| 97 |
+
"grad_norm": 0.675715599863121,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.7835,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.4618556701030928,
|
| 104 |
+
"grad_norm": 0.638472159519646,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.7797,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.4948453608247423,
|
| 111 |
+
"grad_norm": 1.1212007213917934,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.7759,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.5278350515463918,
|
| 118 |
+
"grad_norm": 0.5929058650136099,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.7758,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5608247422680412,
|
| 125 |
+
"grad_norm": 0.7325664578284696,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.7746,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.5938144329896907,
|
| 132 |
+
"grad_norm": 0.7146407893100764,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.772,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.6268041237113402,
|
| 139 |
+
"grad_norm": 0.6297828498939105,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.7686,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.6597938144329897,
|
| 146 |
+
"grad_norm": 0.650337063259678,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.7668,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.6927835051546392,
|
| 153 |
+
"grad_norm": 0.577352278155154,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.7633,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.7257731958762886,
|
| 160 |
+
"grad_norm": 0.6351053699389445,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.7606,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.7587628865979381,
|
| 167 |
+
"grad_norm": 0.6179445706530043,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.7644,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.7917525773195876,
|
| 174 |
+
"grad_norm": 0.7772047208925177,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.7585,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.8247422680412371,
|
| 181 |
+
"grad_norm": 0.6393400921262609,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.7597,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.8577319587628865,
|
| 188 |
+
"grad_norm": 0.5366628092052804,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.7559,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.8907216494845361,
|
| 195 |
+
"grad_norm": 0.6897451596502111,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.757,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.9237113402061856,
|
| 202 |
+
"grad_norm": 0.683076031456689,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.7595,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.9567010309278351,
|
| 209 |
+
"grad_norm": 0.6342586759859082,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.7576,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.9896907216494846,
|
| 216 |
+
"grad_norm": 0.6339977397184522,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.7548,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.9995876288659794,
|
| 223 |
+
"eval_loss": 0.7519278526306152,
|
| 224 |
+
"eval_runtime": 322.6674,
|
| 225 |
+
"eval_samples_per_second": 25.314,
|
| 226 |
+
"eval_steps_per_second": 0.397,
|
| 227 |
+
"step": 303
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.022680412371134,
|
| 231 |
+
"grad_norm": 0.810990287818241,
|
| 232 |
+
"learning_rate": 5e-06,
|
| 233 |
+
"loss": 0.7934,
|
| 234 |
+
"step": 310
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.0556701030927835,
|
| 238 |
+
"grad_norm": 0.5989713675220099,
|
| 239 |
+
"learning_rate": 5e-06,
|
| 240 |
+
"loss": 0.7044,
|
| 241 |
+
"step": 320
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.088659793814433,
|
| 245 |
+
"grad_norm": 0.584782182855064,
|
| 246 |
+
"learning_rate": 5e-06,
|
| 247 |
+
"loss": 0.7115,
|
| 248 |
+
"step": 330
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.1216494845360825,
|
| 252 |
+
"grad_norm": 0.7858920415247334,
|
| 253 |
+
"learning_rate": 5e-06,
|
| 254 |
+
"loss": 0.7094,
|
| 255 |
+
"step": 340
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.1546391752577319,
|
| 259 |
+
"grad_norm": 0.9401995798606461,
|
| 260 |
+
"learning_rate": 5e-06,
|
| 261 |
+
"loss": 0.7079,
|
| 262 |
+
"step": 350
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.1876288659793814,
|
| 266 |
+
"grad_norm": 0.6150009311102699,
|
| 267 |
+
"learning_rate": 5e-06,
|
| 268 |
+
"loss": 0.7073,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.220618556701031,
|
| 273 |
+
"grad_norm": 0.6009149100944755,
|
| 274 |
+
"learning_rate": 5e-06,
|
| 275 |
+
"loss": 0.7096,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.2536082474226804,
|
| 280 |
+
"grad_norm": 0.6115518108906659,
|
| 281 |
+
"learning_rate": 5e-06,
|
| 282 |
+
"loss": 0.7066,
|
| 283 |
+
"step": 380
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.2865979381443298,
|
| 287 |
+
"grad_norm": 0.7496882281145417,
|
| 288 |
+
"learning_rate": 5e-06,
|
| 289 |
+
"loss": 0.7076,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.3195876288659794,
|
| 294 |
+
"grad_norm": 0.6685224897984725,
|
| 295 |
+
"learning_rate": 5e-06,
|
| 296 |
+
"loss": 0.7062,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.352577319587629,
|
| 301 |
+
"grad_norm": 0.641185927057492,
|
| 302 |
+
"learning_rate": 5e-06,
|
| 303 |
+
"loss": 0.7117,
|
| 304 |
+
"step": 410
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.3855670103092783,
|
| 308 |
+
"grad_norm": 0.5361388827305237,
|
| 309 |
+
"learning_rate": 5e-06,
|
| 310 |
+
"loss": 0.7094,
|
| 311 |
+
"step": 420
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.418556701030928,
|
| 315 |
+
"grad_norm": 1.002359631516242,
|
| 316 |
+
"learning_rate": 5e-06,
|
| 317 |
+
"loss": 0.7054,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.4515463917525773,
|
| 322 |
+
"grad_norm": 0.8431450479727091,
|
| 323 |
+
"learning_rate": 5e-06,
|
| 324 |
+
"loss": 0.7075,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.4845360824742269,
|
| 329 |
+
"grad_norm": 0.6447323729739957,
|
| 330 |
+
"learning_rate": 5e-06,
|
| 331 |
+
"loss": 0.7099,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.5175257731958762,
|
| 336 |
+
"grad_norm": 0.8431314429320579,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.7018,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.5505154639175258,
|
| 343 |
+
"grad_norm": 0.6273662519128372,
|
| 344 |
+
"learning_rate": 5e-06,
|
| 345 |
+
"loss": 0.7051,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.5835051546391754,
|
| 350 |
+
"grad_norm": 0.8396735090007554,
|
| 351 |
+
"learning_rate": 5e-06,
|
| 352 |
+
"loss": 0.7106,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.6164948453608248,
|
| 357 |
+
"grad_norm": 0.5802654475284174,
|
| 358 |
+
"learning_rate": 5e-06,
|
| 359 |
+
"loss": 0.7043,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.6494845360824741,
|
| 364 |
+
"grad_norm": 0.6224806599884348,
|
| 365 |
+
"learning_rate": 5e-06,
|
| 366 |
+
"loss": 0.7086,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.6824742268041237,
|
| 371 |
+
"grad_norm": 0.6154446076130442,
|
| 372 |
+
"learning_rate": 5e-06,
|
| 373 |
+
"loss": 0.7026,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.7154639175257733,
|
| 378 |
+
"grad_norm": 0.5857753449684375,
|
| 379 |
+
"learning_rate": 5e-06,
|
| 380 |
+
"loss": 0.7037,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.7484536082474227,
|
| 385 |
+
"grad_norm": 0.5716099691987403,
|
| 386 |
+
"learning_rate": 5e-06,
|
| 387 |
+
"loss": 0.7066,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.781443298969072,
|
| 392 |
+
"grad_norm": 0.6774790897099987,
|
| 393 |
+
"learning_rate": 5e-06,
|
| 394 |
+
"loss": 0.707,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.8144329896907216,
|
| 399 |
+
"grad_norm": 0.6117062221128381,
|
| 400 |
+
"learning_rate": 5e-06,
|
| 401 |
+
"loss": 0.6996,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.8474226804123712,
|
| 406 |
+
"grad_norm": 0.5362825787566358,
|
| 407 |
+
"learning_rate": 5e-06,
|
| 408 |
+
"loss": 0.7036,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.8804123711340206,
|
| 413 |
+
"grad_norm": 0.7851595485494056,
|
| 414 |
+
"learning_rate": 5e-06,
|
| 415 |
+
"loss": 0.7066,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.91340206185567,
|
| 420 |
+
"grad_norm": 0.642752104749906,
|
| 421 |
+
"learning_rate": 5e-06,
|
| 422 |
+
"loss": 0.705,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.9463917525773196,
|
| 427 |
+
"grad_norm": 0.6663997639727156,
|
| 428 |
+
"learning_rate": 5e-06,
|
| 429 |
+
"loss": 0.7051,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.9793814432989691,
|
| 434 |
+
"grad_norm": 0.6435653630361237,
|
| 435 |
+
"learning_rate": 5e-06,
|
| 436 |
+
"loss": 0.7026,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.9991752577319588,
|
| 441 |
+
"eval_loss": 0.7376570701599121,
|
| 442 |
+
"eval_runtime": 321.676,
|
| 443 |
+
"eval_samples_per_second": 25.392,
|
| 444 |
+
"eval_steps_per_second": 0.398,
|
| 445 |
+
"step": 606
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 2.0123711340206185,
|
| 449 |
+
"grad_norm": 0.7966992322635892,
|
| 450 |
+
"learning_rate": 5e-06,
|
| 451 |
+
"loss": 0.7418,
|
| 452 |
+
"step": 610
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 2.045360824742268,
|
| 456 |
+
"grad_norm": 0.5919842716689093,
|
| 457 |
+
"learning_rate": 5e-06,
|
| 458 |
+
"loss": 0.6581,
|
| 459 |
+
"step": 620
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.0783505154639177,
|
| 463 |
+
"grad_norm": 0.6225831303900108,
|
| 464 |
+
"learning_rate": 5e-06,
|
| 465 |
+
"loss": 0.6494,
|
| 466 |
+
"step": 630
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 2.111340206185567,
|
| 470 |
+
"grad_norm": 0.5720666970317613,
|
| 471 |
+
"learning_rate": 5e-06,
|
| 472 |
+
"loss": 0.6557,
|
| 473 |
+
"step": 640
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 2.1443298969072164,
|
| 477 |
+
"grad_norm": 0.625621284764116,
|
| 478 |
+
"learning_rate": 5e-06,
|
| 479 |
+
"loss": 0.6562,
|
| 480 |
+
"step": 650
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.177319587628866,
|
| 484 |
+
"grad_norm": 0.722621026378947,
|
| 485 |
+
"learning_rate": 5e-06,
|
| 486 |
+
"loss": 0.6592,
|
| 487 |
+
"step": 660
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 2.2103092783505156,
|
| 491 |
+
"grad_norm": 0.6611874958125228,
|
| 492 |
+
"learning_rate": 5e-06,
|
| 493 |
+
"loss": 0.6576,
|
| 494 |
+
"step": 670
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.243298969072165,
|
| 498 |
+
"grad_norm": 0.624720046082098,
|
| 499 |
+
"learning_rate": 5e-06,
|
| 500 |
+
"loss": 0.6534,
|
| 501 |
+
"step": 680
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.2762886597938143,
|
| 505 |
+
"grad_norm": 0.6227890769590231,
|
| 506 |
+
"learning_rate": 5e-06,
|
| 507 |
+
"loss": 0.6561,
|
| 508 |
+
"step": 690
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 2.3092783505154637,
|
| 512 |
+
"grad_norm": 0.6353543358518403,
|
| 513 |
+
"learning_rate": 5e-06,
|
| 514 |
+
"loss": 0.6564,
|
| 515 |
+
"step": 700
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.3422680412371135,
|
| 519 |
+
"grad_norm": 0.616682251013517,
|
| 520 |
+
"learning_rate": 5e-06,
|
| 521 |
+
"loss": 0.6558,
|
| 522 |
+
"step": 710
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 2.375257731958763,
|
| 526 |
+
"grad_norm": 0.5785627398529801,
|
| 527 |
+
"learning_rate": 5e-06,
|
| 528 |
+
"loss": 0.6579,
|
| 529 |
+
"step": 720
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.4082474226804123,
|
| 533 |
+
"grad_norm": 0.7087632640527876,
|
| 534 |
+
"learning_rate": 5e-06,
|
| 535 |
+
"loss": 0.6578,
|
| 536 |
+
"step": 730
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.441237113402062,
|
| 540 |
+
"grad_norm": 0.7221097669514308,
|
| 541 |
+
"learning_rate": 5e-06,
|
| 542 |
+
"loss": 0.6555,
|
| 543 |
+
"step": 740
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.4742268041237114,
|
| 547 |
+
"grad_norm": 0.6845092133296887,
|
| 548 |
+
"learning_rate": 5e-06,
|
| 549 |
+
"loss": 0.6589,
|
| 550 |
+
"step": 750
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.507216494845361,
|
| 554 |
+
"grad_norm": 0.6131735355128494,
|
| 555 |
+
"learning_rate": 5e-06,
|
| 556 |
+
"loss": 0.6597,
|
| 557 |
+
"step": 760
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 2.54020618556701,
|
| 561 |
+
"grad_norm": 0.74499117668607,
|
| 562 |
+
"learning_rate": 5e-06,
|
| 563 |
+
"loss": 0.6604,
|
| 564 |
+
"step": 770
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.5731958762886595,
|
| 568 |
+
"grad_norm": 0.6953072761863929,
|
| 569 |
+
"learning_rate": 5e-06,
|
| 570 |
+
"loss": 0.6599,
|
| 571 |
+
"step": 780
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.6061855670103093,
|
| 575 |
+
"grad_norm": 0.7683634702318719,
|
| 576 |
+
"learning_rate": 5e-06,
|
| 577 |
+
"loss": 0.6584,
|
| 578 |
+
"step": 790
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.6391752577319587,
|
| 582 |
+
"grad_norm": 0.9202931242949187,
|
| 583 |
+
"learning_rate": 5e-06,
|
| 584 |
+
"loss": 0.6599,
|
| 585 |
+
"step": 800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.6721649484536085,
|
| 589 |
+
"grad_norm": 0.6785534766587453,
|
| 590 |
+
"learning_rate": 5e-06,
|
| 591 |
+
"loss": 0.6605,
|
| 592 |
+
"step": 810
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.705154639175258,
|
| 596 |
+
"grad_norm": 0.9373759072613878,
|
| 597 |
+
"learning_rate": 5e-06,
|
| 598 |
+
"loss": 0.6633,
|
| 599 |
+
"step": 820
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.7381443298969073,
|
| 603 |
+
"grad_norm": 0.5316447851690145,
|
| 604 |
+
"learning_rate": 5e-06,
|
| 605 |
+
"loss": 0.6582,
|
| 606 |
+
"step": 830
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.7711340206185566,
|
| 610 |
+
"grad_norm": 0.7810499110998566,
|
| 611 |
+
"learning_rate": 5e-06,
|
| 612 |
+
"loss": 0.6638,
|
| 613 |
+
"step": 840
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.804123711340206,
|
| 617 |
+
"grad_norm": 0.5581690358208933,
|
| 618 |
+
"learning_rate": 5e-06,
|
| 619 |
+
"loss": 0.6572,
|
| 620 |
+
"step": 850
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.837113402061856,
|
| 624 |
+
"grad_norm": 0.5757480690524878,
|
| 625 |
+
"learning_rate": 5e-06,
|
| 626 |
+
"loss": 0.6629,
|
| 627 |
+
"step": 860
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.870103092783505,
|
| 631 |
+
"grad_norm": 0.6570394054126519,
|
| 632 |
+
"learning_rate": 5e-06,
|
| 633 |
+
"loss": 0.6603,
|
| 634 |
+
"step": 870
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.9030927835051545,
|
| 638 |
+
"grad_norm": 0.5532161107989387,
|
| 639 |
+
"learning_rate": 5e-06,
|
| 640 |
+
"loss": 0.6596,
|
| 641 |
+
"step": 880
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.9360824742268044,
|
| 645 |
+
"grad_norm": 0.6779485831959426,
|
| 646 |
+
"learning_rate": 5e-06,
|
| 647 |
+
"loss": 0.6615,
|
| 648 |
+
"step": 890
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.9690721649484537,
|
| 652 |
+
"grad_norm": 0.6105580266011457,
|
| 653 |
+
"learning_rate": 5e-06,
|
| 654 |
+
"loss": 0.6573,
|
| 655 |
+
"step": 900
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.9987628865979383,
|
| 659 |
+
"eval_loss": 0.737443208694458,
|
| 660 |
+
"eval_runtime": 321.3627,
|
| 661 |
+
"eval_samples_per_second": 25.417,
|
| 662 |
+
"eval_steps_per_second": 0.398,
|
| 663 |
+
"step": 909
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 2.9987628865979383,
|
| 667 |
+
"step": 909,
|
| 668 |
+
"total_flos": 1522399476449280.0,
|
| 669 |
+
"train_loss": 0.7216839113644641,
|
| 670 |
+
"train_runtime": 53747.0627,
|
| 671 |
+
"train_samples_per_second": 8.662,
|
| 672 |
+
"train_steps_per_second": 0.017
|
| 673 |
+
}
|
| 674 |
+
],
|
| 675 |
+
"logging_steps": 10,
|
| 676 |
+
"max_steps": 909,
|
| 677 |
+
"num_input_tokens_seen": 0,
|
| 678 |
+
"num_train_epochs": 3,
|
| 679 |
+
"save_steps": 500,
|
| 680 |
+
"stateful_callbacks": {
|
| 681 |
+
"TrainerControl": {
|
| 682 |
+
"args": {
|
| 683 |
+
"should_epoch_stop": false,
|
| 684 |
+
"should_evaluate": false,
|
| 685 |
+
"should_log": false,
|
| 686 |
+
"should_save": true,
|
| 687 |
+
"should_training_stop": true
|
| 688 |
+
},
|
| 689 |
+
"attributes": {}
|
| 690 |
+
}
|
| 691 |
+
},
|
| 692 |
+
"total_flos": 1522399476449280.0,
|
| 693 |
+
"train_batch_size": 8,
|
| 694 |
+
"trial_name": null,
|
| 695 |
+
"trial_params": null
|
| 696 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|