Commit
•
994883e
1
Parent(s):
20fbfc4
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 +738 -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_no-airoboros_gpt-4o-mini
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# oh-dcft-v1.2_no-curation_no-airoboros_gpt-4o-mini
|
| 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: 0.6511
|
| 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_no-airoboros_gpt-4o-mini
|
|
|
|
| 16 |
|
| 17 |
# oh-dcft-v1.2_no-curation_no-airoboros_gpt-4o-mini
|
| 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_no-airoboros_gpt-4o-mini dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.6511
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9953632148377123,
|
| 3 |
+
"eval_loss": 0.6511133909225464,
|
| 4 |
+
"eval_runtime": 110.4965,
|
| 5 |
+
"eval_samples_per_second": 78.871,
|
| 6 |
+
"eval_steps_per_second": 0.624,
|
| 7 |
+
"total_flos": 1622692331520000.0,
|
| 8 |
+
"train_loss": 0.6248709833166793,
|
| 9 |
+
"train_runtime": 16382.8374,
|
| 10 |
+
"train_samples_per_second": 30.32,
|
| 11 |
+
"train_steps_per_second": 0.059
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9953632148377123,
|
| 3 |
+
"eval_loss": 0.6511133909225464,
|
| 4 |
+
"eval_runtime": 110.4965,
|
| 5 |
+
"eval_samples_per_second": 78.871,
|
| 6 |
+
"eval_steps_per_second": 0.624
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9953632148377123,
|
| 3 |
+
"total_flos": 1622692331520000.0,
|
| 4 |
+
"train_loss": 0.6248709833166793,
|
| 5 |
+
"train_runtime": 16382.8374,
|
| 6 |
+
"train_samples_per_second": 30.32,
|
| 7 |
+
"train_steps_per_second": 0.059
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,738 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9953632148377123,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 969,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.030911901081916538,
|
| 13 |
+
"grad_norm": 2.0187587823402606,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 0.9224,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.061823802163833076,
|
| 20 |
+
"grad_norm": 5.23374455774046,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.8169,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.09273570324574962,
|
| 27 |
+
"grad_norm": 1.1567925380600657,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.7799,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.12364760432766615,
|
| 34 |
+
"grad_norm": 1.3555247489499298,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.7536,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.1545595054095827,
|
| 41 |
+
"grad_norm": 0.8540206480635643,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.7412,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.18547140649149924,
|
| 48 |
+
"grad_norm": 1.0411208272577643,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.7188,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.21638330757341576,
|
| 55 |
+
"grad_norm": 0.772135725000269,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.7099,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.2472952086553323,
|
| 62 |
+
"grad_norm": 0.718962153128519,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.7044,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.2782071097372488,
|
| 69 |
+
"grad_norm": 0.9018851336703633,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.7042,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.3091190108191654,
|
| 76 |
+
"grad_norm": 0.5501975291936315,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.6898,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3400309119010819,
|
| 83 |
+
"grad_norm": 0.8644622620986302,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.6901,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.37094281298299847,
|
| 90 |
+
"grad_norm": 0.5948602458220357,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.6828,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.401854714064915,
|
| 97 |
+
"grad_norm": 0.720162590208508,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.6858,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.4327666151468315,
|
| 104 |
+
"grad_norm": 0.5833952154939747,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.6745,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.46367851622874806,
|
| 111 |
+
"grad_norm": 0.6768653844503261,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.6764,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.4945904173106646,
|
| 118 |
+
"grad_norm": 0.5707017440465438,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.6734,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5255023183925811,
|
| 125 |
+
"grad_norm": 0.52632417149709,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.6746,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.5564142194744977,
|
| 132 |
+
"grad_norm": 0.5660566537871714,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.6654,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.5873261205564142,
|
| 139 |
+
"grad_norm": 0.6150804490960232,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.6669,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.6182380216383307,
|
| 146 |
+
"grad_norm": 0.5523983219898584,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.6722,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.6491499227202473,
|
| 153 |
+
"grad_norm": 0.7211222999715671,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.6689,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.6800618238021638,
|
| 160 |
+
"grad_norm": 0.7196378524123959,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.6685,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.7109737248840804,
|
| 167 |
+
"grad_norm": 0.7400759740386526,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.6637,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.7418856259659969,
|
| 174 |
+
"grad_norm": 0.5515081055008348,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.6602,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.7727975270479135,
|
| 181 |
+
"grad_norm": 0.5306297630685508,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.6641,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.80370942812983,
|
| 188 |
+
"grad_norm": 0.5220389228174283,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.657,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.8346213292117465,
|
| 195 |
+
"grad_norm": 0.5736057539218636,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.6606,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.865533230293663,
|
| 202 |
+
"grad_norm": 0.6831384912164588,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.6604,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.8964451313755796,
|
| 209 |
+
"grad_norm": 0.6555441815061606,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.6617,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.9273570324574961,
|
| 216 |
+
"grad_norm": 0.5107130356234296,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.6577,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.9582689335394127,
|
| 223 |
+
"grad_norm": 0.5294921581221994,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.6554,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.9891808346213292,
|
| 230 |
+
"grad_norm": 0.5933706977854671,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.6662,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.9984544049459042,
|
| 237 |
+
"eval_loss": 0.6590365171432495,
|
| 238 |
+
"eval_runtime": 113.7467,
|
| 239 |
+
"eval_samples_per_second": 76.618,
|
| 240 |
+
"eval_steps_per_second": 0.607,
|
| 241 |
+
"step": 323
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.0200927357032457,
|
| 245 |
+
"grad_norm": 0.6466092267278452,
|
| 246 |
+
"learning_rate": 5e-06,
|
| 247 |
+
"loss": 0.6283,
|
| 248 |
+
"step": 330
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.0510046367851622,
|
| 252 |
+
"grad_norm": 0.5455963224340917,
|
| 253 |
+
"learning_rate": 5e-06,
|
| 254 |
+
"loss": 0.6142,
|
| 255 |
+
"step": 340
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.0819165378670788,
|
| 259 |
+
"grad_norm": 0.5457563493460516,
|
| 260 |
+
"learning_rate": 5e-06,
|
| 261 |
+
"loss": 0.6136,
|
| 262 |
+
"step": 350
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.1128284389489953,
|
| 266 |
+
"grad_norm": 0.5123524043102256,
|
| 267 |
+
"learning_rate": 5e-06,
|
| 268 |
+
"loss": 0.6186,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.1437403400309119,
|
| 273 |
+
"grad_norm": 0.6133162659271869,
|
| 274 |
+
"learning_rate": 5e-06,
|
| 275 |
+
"loss": 0.612,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.1746522411128284,
|
| 280 |
+
"grad_norm": 0.531392662924999,
|
| 281 |
+
"learning_rate": 5e-06,
|
| 282 |
+
"loss": 0.6093,
|
| 283 |
+
"step": 380
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.205564142194745,
|
| 287 |
+
"grad_norm": 0.5434898390306484,
|
| 288 |
+
"learning_rate": 5e-06,
|
| 289 |
+
"loss": 0.6031,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.2364760432766615,
|
| 294 |
+
"grad_norm": 0.665502589919703,
|
| 295 |
+
"learning_rate": 5e-06,
|
| 296 |
+
"loss": 0.6153,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.267387944358578,
|
| 301 |
+
"grad_norm": 0.5263248988074614,
|
| 302 |
+
"learning_rate": 5e-06,
|
| 303 |
+
"loss": 0.6154,
|
| 304 |
+
"step": 410
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.2982998454404946,
|
| 308 |
+
"grad_norm": 0.6348966883540149,
|
| 309 |
+
"learning_rate": 5e-06,
|
| 310 |
+
"loss": 0.6112,
|
| 311 |
+
"step": 420
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.3292117465224111,
|
| 315 |
+
"grad_norm": 0.5230511187445398,
|
| 316 |
+
"learning_rate": 5e-06,
|
| 317 |
+
"loss": 0.6121,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.3601236476043277,
|
| 322 |
+
"grad_norm": 0.5500625021812695,
|
| 323 |
+
"learning_rate": 5e-06,
|
| 324 |
+
"loss": 0.6109,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.3910355486862442,
|
| 329 |
+
"grad_norm": 0.7153093571149675,
|
| 330 |
+
"learning_rate": 5e-06,
|
| 331 |
+
"loss": 0.6123,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.4219474497681608,
|
| 336 |
+
"grad_norm": 0.6382419366334218,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.6188,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.4528593508500773,
|
| 343 |
+
"grad_norm": 0.5471481346135804,
|
| 344 |
+
"learning_rate": 5e-06,
|
| 345 |
+
"loss": 0.6179,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.4837712519319939,
|
| 350 |
+
"grad_norm": 0.5409301526875265,
|
| 351 |
+
"learning_rate": 5e-06,
|
| 352 |
+
"loss": 0.6121,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.5146831530139102,
|
| 357 |
+
"grad_norm": 0.5070509983871482,
|
| 358 |
+
"learning_rate": 5e-06,
|
| 359 |
+
"loss": 0.6081,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.545595054095827,
|
| 364 |
+
"grad_norm": 0.6049383227511866,
|
| 365 |
+
"learning_rate": 5e-06,
|
| 366 |
+
"loss": 0.6111,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.5765069551777433,
|
| 371 |
+
"grad_norm": 0.5173228367317094,
|
| 372 |
+
"learning_rate": 5e-06,
|
| 373 |
+
"loss": 0.6088,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.60741885625966,
|
| 378 |
+
"grad_norm": 0.5087487433614813,
|
| 379 |
+
"learning_rate": 5e-06,
|
| 380 |
+
"loss": 0.6077,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.6383307573415764,
|
| 385 |
+
"grad_norm": 0.6681086881393504,
|
| 386 |
+
"learning_rate": 5e-06,
|
| 387 |
+
"loss": 0.6073,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.6692426584234932,
|
| 392 |
+
"grad_norm": 0.9262470601774611,
|
| 393 |
+
"learning_rate": 5e-06,
|
| 394 |
+
"loss": 0.6088,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.7001545595054095,
|
| 399 |
+
"grad_norm": 0.5528042557953681,
|
| 400 |
+
"learning_rate": 5e-06,
|
| 401 |
+
"loss": 0.6163,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.7310664605873263,
|
| 406 |
+
"grad_norm": 0.5064527021504606,
|
| 407 |
+
"learning_rate": 5e-06,
|
| 408 |
+
"loss": 0.6064,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.7619783616692426,
|
| 413 |
+
"grad_norm": 0.5307893550951357,
|
| 414 |
+
"learning_rate": 5e-06,
|
| 415 |
+
"loss": 0.6132,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.7928902627511591,
|
| 420 |
+
"grad_norm": 0.5363288571581243,
|
| 421 |
+
"learning_rate": 5e-06,
|
| 422 |
+
"loss": 0.6142,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.8238021638330757,
|
| 427 |
+
"grad_norm": 0.4985720023183297,
|
| 428 |
+
"learning_rate": 5e-06,
|
| 429 |
+
"loss": 0.6176,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.8547140649149922,
|
| 434 |
+
"grad_norm": 0.5256325470444526,
|
| 435 |
+
"learning_rate": 5e-06,
|
| 436 |
+
"loss": 0.6126,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.8856259659969088,
|
| 441 |
+
"grad_norm": 0.6274813396972104,
|
| 442 |
+
"learning_rate": 5e-06,
|
| 443 |
+
"loss": 0.612,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.9165378670788253,
|
| 448 |
+
"grad_norm": 0.5789315780747083,
|
| 449 |
+
"learning_rate": 5e-06,
|
| 450 |
+
"loss": 0.6125,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.947449768160742,
|
| 455 |
+
"grad_norm": 0.5907958566056928,
|
| 456 |
+
"learning_rate": 5e-06,
|
| 457 |
+
"loss": 0.6062,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.9783616692426584,
|
| 462 |
+
"grad_norm": 0.5292904118235623,
|
| 463 |
+
"learning_rate": 5e-06,
|
| 464 |
+
"loss": 0.6121,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.0,
|
| 469 |
+
"eval_loss": 0.6483988761901855,
|
| 470 |
+
"eval_runtime": 114.5876,
|
| 471 |
+
"eval_samples_per_second": 76.055,
|
| 472 |
+
"eval_steps_per_second": 0.602,
|
| 473 |
+
"step": 647
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 2.009273570324575,
|
| 477 |
+
"grad_norm": 1.0140873239994894,
|
| 478 |
+
"learning_rate": 5e-06,
|
| 479 |
+
"loss": 0.597,
|
| 480 |
+
"step": 650
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.0401854714064913,
|
| 484 |
+
"grad_norm": 0.630334813080006,
|
| 485 |
+
"learning_rate": 5e-06,
|
| 486 |
+
"loss": 0.5614,
|
| 487 |
+
"step": 660
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 2.071097372488408,
|
| 491 |
+
"grad_norm": 0.7038598022498512,
|
| 492 |
+
"learning_rate": 5e-06,
|
| 493 |
+
"loss": 0.5613,
|
| 494 |
+
"step": 670
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.1020092735703244,
|
| 498 |
+
"grad_norm": 0.625422416199728,
|
| 499 |
+
"learning_rate": 5e-06,
|
| 500 |
+
"loss": 0.5652,
|
| 501 |
+
"step": 680
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.132921174652241,
|
| 505 |
+
"grad_norm": 0.6504517407003202,
|
| 506 |
+
"learning_rate": 5e-06,
|
| 507 |
+
"loss": 0.5646,
|
| 508 |
+
"step": 690
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 2.1638330757341575,
|
| 512 |
+
"grad_norm": 0.6005779084691315,
|
| 513 |
+
"learning_rate": 5e-06,
|
| 514 |
+
"loss": 0.5635,
|
| 515 |
+
"step": 700
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.1947449768160743,
|
| 519 |
+
"grad_norm": 0.5153825857145766,
|
| 520 |
+
"learning_rate": 5e-06,
|
| 521 |
+
"loss": 0.5642,
|
| 522 |
+
"step": 710
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 2.2256568778979906,
|
| 526 |
+
"grad_norm": 0.6609026821979475,
|
| 527 |
+
"learning_rate": 5e-06,
|
| 528 |
+
"loss": 0.5636,
|
| 529 |
+
"step": 720
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.2565687789799074,
|
| 533 |
+
"grad_norm": 0.7763886247938674,
|
| 534 |
+
"learning_rate": 5e-06,
|
| 535 |
+
"loss": 0.5646,
|
| 536 |
+
"step": 730
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.2874806800618237,
|
| 540 |
+
"grad_norm": 0.5940744564359401,
|
| 541 |
+
"learning_rate": 5e-06,
|
| 542 |
+
"loss": 0.566,
|
| 543 |
+
"step": 740
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.3183925811437405,
|
| 547 |
+
"grad_norm": 0.8987915044882564,
|
| 548 |
+
"learning_rate": 5e-06,
|
| 549 |
+
"loss": 0.5639,
|
| 550 |
+
"step": 750
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.349304482225657,
|
| 554 |
+
"grad_norm": 0.7853307481543791,
|
| 555 |
+
"learning_rate": 5e-06,
|
| 556 |
+
"loss": 0.5652,
|
| 557 |
+
"step": 760
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 2.3802163833075736,
|
| 561 |
+
"grad_norm": 0.5555357862981527,
|
| 562 |
+
"learning_rate": 5e-06,
|
| 563 |
+
"loss": 0.5695,
|
| 564 |
+
"step": 770
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.41112828438949,
|
| 568 |
+
"grad_norm": 0.5858397000016529,
|
| 569 |
+
"learning_rate": 5e-06,
|
| 570 |
+
"loss": 0.5674,
|
| 571 |
+
"step": 780
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.4420401854714067,
|
| 575 |
+
"grad_norm": 0.5809649704126684,
|
| 576 |
+
"learning_rate": 5e-06,
|
| 577 |
+
"loss": 0.5666,
|
| 578 |
+
"step": 790
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.472952086553323,
|
| 582 |
+
"grad_norm": 0.6079171026499909,
|
| 583 |
+
"learning_rate": 5e-06,
|
| 584 |
+
"loss": 0.5662,
|
| 585 |
+
"step": 800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.5038639876352393,
|
| 589 |
+
"grad_norm": 0.6460104668614653,
|
| 590 |
+
"learning_rate": 5e-06,
|
| 591 |
+
"loss": 0.5724,
|
| 592 |
+
"step": 810
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.534775888717156,
|
| 596 |
+
"grad_norm": 0.5036700308469926,
|
| 597 |
+
"learning_rate": 5e-06,
|
| 598 |
+
"loss": 0.5689,
|
| 599 |
+
"step": 820
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.565687789799073,
|
| 603 |
+
"grad_norm": 0.5720133645014428,
|
| 604 |
+
"learning_rate": 5e-06,
|
| 605 |
+
"loss": 0.5694,
|
| 606 |
+
"step": 830
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.596599690880989,
|
| 610 |
+
"grad_norm": 0.4978320121327588,
|
| 611 |
+
"learning_rate": 5e-06,
|
| 612 |
+
"loss": 0.5688,
|
| 613 |
+
"step": 840
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.6275115919629055,
|
| 617 |
+
"grad_norm": 0.5742589206659079,
|
| 618 |
+
"learning_rate": 5e-06,
|
| 619 |
+
"loss": 0.5677,
|
| 620 |
+
"step": 850
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.6584234930448223,
|
| 624 |
+
"grad_norm": 0.8122081568789994,
|
| 625 |
+
"learning_rate": 5e-06,
|
| 626 |
+
"loss": 0.5685,
|
| 627 |
+
"step": 860
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.689335394126739,
|
| 631 |
+
"grad_norm": 0.5964179415080593,
|
| 632 |
+
"learning_rate": 5e-06,
|
| 633 |
+
"loss": 0.5695,
|
| 634 |
+
"step": 870
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.7202472952086554,
|
| 638 |
+
"grad_norm": 0.5560894480978509,
|
| 639 |
+
"learning_rate": 5e-06,
|
| 640 |
+
"loss": 0.5718,
|
| 641 |
+
"step": 880
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.7511591962905717,
|
| 645 |
+
"grad_norm": 0.5757117113268359,
|
| 646 |
+
"learning_rate": 5e-06,
|
| 647 |
+
"loss": 0.5696,
|
| 648 |
+
"step": 890
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.7820710973724885,
|
| 652 |
+
"grad_norm": 0.5435787690358811,
|
| 653 |
+
"learning_rate": 5e-06,
|
| 654 |
+
"loss": 0.5676,
|
| 655 |
+
"step": 900
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.812982998454405,
|
| 659 |
+
"grad_norm": 0.6300976369973321,
|
| 660 |
+
"learning_rate": 5e-06,
|
| 661 |
+
"loss": 0.5725,
|
| 662 |
+
"step": 910
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.8438948995363216,
|
| 666 |
+
"grad_norm": 0.6341460273574823,
|
| 667 |
+
"learning_rate": 5e-06,
|
| 668 |
+
"loss": 0.5699,
|
| 669 |
+
"step": 920
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.874806800618238,
|
| 673 |
+
"grad_norm": 0.6961502333247155,
|
| 674 |
+
"learning_rate": 5e-06,
|
| 675 |
+
"loss": 0.5694,
|
| 676 |
+
"step": 930
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.9057187017001547,
|
| 680 |
+
"grad_norm": 0.5370380886104864,
|
| 681 |
+
"learning_rate": 5e-06,
|
| 682 |
+
"loss": 0.5712,
|
| 683 |
+
"step": 940
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.936630602782071,
|
| 687 |
+
"grad_norm": 0.595358378564684,
|
| 688 |
+
"learning_rate": 5e-06,
|
| 689 |
+
"loss": 0.5691,
|
| 690 |
+
"step": 950
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.9675425038639878,
|
| 694 |
+
"grad_norm": 0.5413573519766721,
|
| 695 |
+
"learning_rate": 5e-06,
|
| 696 |
+
"loss": 0.5679,
|
| 697 |
+
"step": 960
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.9953632148377123,
|
| 701 |
+
"eval_loss": 0.6511133909225464,
|
| 702 |
+
"eval_runtime": 110.2332,
|
| 703 |
+
"eval_samples_per_second": 79.06,
|
| 704 |
+
"eval_steps_per_second": 0.626,
|
| 705 |
+
"step": 969
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 2.9953632148377123,
|
| 709 |
+
"step": 969,
|
| 710 |
+
"total_flos": 1622692331520000.0,
|
| 711 |
+
"train_loss": 0.6248709833166793,
|
| 712 |
+
"train_runtime": 16382.8374,
|
| 713 |
+
"train_samples_per_second": 30.32,
|
| 714 |
+
"train_steps_per_second": 0.059
|
| 715 |
+
}
|
| 716 |
+
],
|
| 717 |
+
"logging_steps": 10,
|
| 718 |
+
"max_steps": 969,
|
| 719 |
+
"num_input_tokens_seen": 0,
|
| 720 |
+
"num_train_epochs": 3,
|
| 721 |
+
"save_steps": 500,
|
| 722 |
+
"stateful_callbacks": {
|
| 723 |
+
"TrainerControl": {
|
| 724 |
+
"args": {
|
| 725 |
+
"should_epoch_stop": false,
|
| 726 |
+
"should_evaluate": false,
|
| 727 |
+
"should_log": false,
|
| 728 |
+
"should_save": true,
|
| 729 |
+
"should_training_stop": true
|
| 730 |
+
},
|
| 731 |
+
"attributes": {}
|
| 732 |
+
}
|
| 733 |
+
},
|
| 734 |
+
"total_flos": 1622692331520000.0,
|
| 735 |
+
"train_batch_size": 8,
|
| 736 |
+
"trial_name": null,
|
| 737 |
+
"trial_params": null
|
| 738 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|