Upload folder using huggingface_hub
Browse files- config.json +39 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +633 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gpt2",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 50256,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 1024,
|
| 15 |
+
"n_embd": 768,
|
| 16 |
+
"n_head": 12,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 12,
|
| 19 |
+
"n_positions": 1024,
|
| 20 |
+
"reorder_and_upcast_attn": false,
|
| 21 |
+
"resid_pdrop": 0.1,
|
| 22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 23 |
+
"scale_attn_weights": true,
|
| 24 |
+
"summary_activation": null,
|
| 25 |
+
"summary_first_dropout": 0.1,
|
| 26 |
+
"summary_proj_to_labels": true,
|
| 27 |
+
"summary_type": "cls_index",
|
| 28 |
+
"summary_use_proj": true,
|
| 29 |
+
"task_specific_params": {
|
| 30 |
+
"text-generation": {
|
| 31 |
+
"do_sample": true,
|
| 32 |
+
"max_length": 50
|
| 33 |
+
}
|
| 34 |
+
},
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.46.3",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50257
|
| 39 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.46.3"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32e1c292adb4571bcaa540df997b7c0994c85f8419f91bb4efad4442f0634536
|
| 3 |
+
size 497774208
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00fd9310f86fbfb542d904f836dc8bd2b7ead76be499b38f559436d9efe5bc7a
|
| 3 |
+
size 995642298
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2bd98c522c8acadc7236c4dec9a6d7f2c45122d9cdb2534e9e6ca864d9b22d54
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7efd851823c41e299dc26218b34ebe2f67e3f195ba01b8ffc6443fa63eb93a3
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,633 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.416276407534603,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 4000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.010406910188365074,
|
| 13 |
+
"grad_norm": 17.59031867980957,
|
| 14 |
+
"learning_rate": 4.982655149686058e-05,
|
| 15 |
+
"loss": 4.0667,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.010406910188365074,
|
| 20 |
+
"eval_loss": 3.950298309326172,
|
| 21 |
+
"eval_runtime": 3517.0273,
|
| 22 |
+
"eval_samples_per_second": 11.923,
|
| 23 |
+
"eval_steps_per_second": 1.49,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.020813820376730147,
|
| 28 |
+
"grad_norm": 12.363835334777832,
|
| 29 |
+
"learning_rate": 4.965310299372117e-05,
|
| 30 |
+
"loss": 3.6567,
|
| 31 |
+
"step": 200
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.020813820376730147,
|
| 35 |
+
"eval_loss": 3.9310147762298584,
|
| 36 |
+
"eval_runtime": 3451.7016,
|
| 37 |
+
"eval_samples_per_second": 12.148,
|
| 38 |
+
"eval_steps_per_second": 1.519,
|
| 39 |
+
"step": 200
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.031220730565095223,
|
| 43 |
+
"grad_norm": 9.739866256713867,
|
| 44 |
+
"learning_rate": 4.947965449058175e-05,
|
| 45 |
+
"loss": 3.6612,
|
| 46 |
+
"step": 300
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.031220730565095223,
|
| 50 |
+
"eval_loss": 3.9458096027374268,
|
| 51 |
+
"eval_runtime": 3450.7573,
|
| 52 |
+
"eval_samples_per_second": 12.152,
|
| 53 |
+
"eval_steps_per_second": 1.519,
|
| 54 |
+
"step": 300
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.041627640753460295,
|
| 58 |
+
"grad_norm": 7.430461406707764,
|
| 59 |
+
"learning_rate": 4.930620598744233e-05,
|
| 60 |
+
"loss": 3.6409,
|
| 61 |
+
"step": 400
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.041627640753460295,
|
| 65 |
+
"eval_loss": 3.928576707839966,
|
| 66 |
+
"eval_runtime": 3466.9688,
|
| 67 |
+
"eval_samples_per_second": 12.095,
|
| 68 |
+
"eval_steps_per_second": 1.512,
|
| 69 |
+
"step": 400
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.052034550941825373,
|
| 73 |
+
"grad_norm": 9.64016056060791,
|
| 74 |
+
"learning_rate": 4.913275748430291e-05,
|
| 75 |
+
"loss": 3.5862,
|
| 76 |
+
"step": 500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.052034550941825373,
|
| 80 |
+
"eval_loss": 3.9448041915893555,
|
| 81 |
+
"eval_runtime": 3452.0797,
|
| 82 |
+
"eval_samples_per_second": 12.147,
|
| 83 |
+
"eval_steps_per_second": 1.519,
|
| 84 |
+
"step": 500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.062441461130190445,
|
| 88 |
+
"grad_norm": 8.797385215759277,
|
| 89 |
+
"learning_rate": 4.8959308981163494e-05,
|
| 90 |
+
"loss": 3.5627,
|
| 91 |
+
"step": 600
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.062441461130190445,
|
| 95 |
+
"eval_loss": 3.925294876098633,
|
| 96 |
+
"eval_runtime": 3449.9288,
|
| 97 |
+
"eval_samples_per_second": 12.154,
|
| 98 |
+
"eval_steps_per_second": 1.519,
|
| 99 |
+
"step": 600
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.07284837131855552,
|
| 103 |
+
"grad_norm": 7.623824596405029,
|
| 104 |
+
"learning_rate": 4.8785860478024074e-05,
|
| 105 |
+
"loss": 3.5507,
|
| 106 |
+
"step": 700
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.07284837131855552,
|
| 110 |
+
"eval_loss": 3.9132120609283447,
|
| 111 |
+
"eval_runtime": 3475.0918,
|
| 112 |
+
"eval_samples_per_second": 12.066,
|
| 113 |
+
"eval_steps_per_second": 1.508,
|
| 114 |
+
"step": 700
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.08325528150692059,
|
| 118 |
+
"grad_norm": 7.819701671600342,
|
| 119 |
+
"learning_rate": 4.861241197488466e-05,
|
| 120 |
+
"loss": 3.4453,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.08325528150692059,
|
| 125 |
+
"eval_loss": 3.9031147956848145,
|
| 126 |
+
"eval_runtime": 3466.7274,
|
| 127 |
+
"eval_samples_per_second": 12.096,
|
| 128 |
+
"eval_steps_per_second": 1.512,
|
| 129 |
+
"step": 800
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.09366219169528567,
|
| 133 |
+
"grad_norm": 7.915994167327881,
|
| 134 |
+
"learning_rate": 4.843896347174524e-05,
|
| 135 |
+
"loss": 3.4908,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.09366219169528567,
|
| 140 |
+
"eval_loss": 3.922236442565918,
|
| 141 |
+
"eval_runtime": 3474.1465,
|
| 142 |
+
"eval_samples_per_second": 12.07,
|
| 143 |
+
"eval_steps_per_second": 1.509,
|
| 144 |
+
"step": 900
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.10406910188365075,
|
| 148 |
+
"grad_norm": 6.398956775665283,
|
| 149 |
+
"learning_rate": 4.826551496860582e-05,
|
| 150 |
+
"loss": 3.4467,
|
| 151 |
+
"step": 1000
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.10406910188365075,
|
| 155 |
+
"eval_loss": 3.9016082286834717,
|
| 156 |
+
"eval_runtime": 3439.9815,
|
| 157 |
+
"eval_samples_per_second": 12.19,
|
| 158 |
+
"eval_steps_per_second": 1.524,
|
| 159 |
+
"step": 1000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.11447601207201581,
|
| 163 |
+
"grad_norm": 5.43521785736084,
|
| 164 |
+
"learning_rate": 4.8092066465466404e-05,
|
| 165 |
+
"loss": 3.4598,
|
| 166 |
+
"step": 1100
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.11447601207201581,
|
| 170 |
+
"eval_loss": 3.9063823223114014,
|
| 171 |
+
"eval_runtime": 3446.7857,
|
| 172 |
+
"eval_samples_per_second": 12.166,
|
| 173 |
+
"eval_steps_per_second": 1.521,
|
| 174 |
+
"step": 1100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.12488292226038089,
|
| 178 |
+
"grad_norm": 5.717388153076172,
|
| 179 |
+
"learning_rate": 4.791861796232699e-05,
|
| 180 |
+
"loss": 3.4359,
|
| 181 |
+
"step": 1200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.12488292226038089,
|
| 185 |
+
"eval_loss": 3.881629705429077,
|
| 186 |
+
"eval_runtime": 3449.577,
|
| 187 |
+
"eval_samples_per_second": 12.156,
|
| 188 |
+
"eval_steps_per_second": 1.52,
|
| 189 |
+
"step": 1200
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.13528983244874596,
|
| 193 |
+
"grad_norm": 5.882245063781738,
|
| 194 |
+
"learning_rate": 4.774516945918757e-05,
|
| 195 |
+
"loss": 3.425,
|
| 196 |
+
"step": 1300
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.13528983244874596,
|
| 200 |
+
"eval_loss": 3.883547782897949,
|
| 201 |
+
"eval_runtime": 3446.1151,
|
| 202 |
+
"eval_samples_per_second": 12.168,
|
| 203 |
+
"eval_steps_per_second": 1.521,
|
| 204 |
+
"step": 1300
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.14569674263711105,
|
| 208 |
+
"grad_norm": 7.307028293609619,
|
| 209 |
+
"learning_rate": 4.7571720956048146e-05,
|
| 210 |
+
"loss": 3.4218,
|
| 211 |
+
"step": 1400
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.14569674263711105,
|
| 215 |
+
"eval_loss": 3.8712680339813232,
|
| 216 |
+
"eval_runtime": 3438.5402,
|
| 217 |
+
"eval_samples_per_second": 12.195,
|
| 218 |
+
"eval_steps_per_second": 1.524,
|
| 219 |
+
"step": 1400
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.1561036528254761,
|
| 223 |
+
"grad_norm": 7.0670485496521,
|
| 224 |
+
"learning_rate": 4.7398272452908734e-05,
|
| 225 |
+
"loss": 3.3977,
|
| 226 |
+
"step": 1500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.1561036528254761,
|
| 230 |
+
"eval_loss": 3.8845202922821045,
|
| 231 |
+
"eval_runtime": 3441.119,
|
| 232 |
+
"eval_samples_per_second": 12.186,
|
| 233 |
+
"eval_steps_per_second": 1.523,
|
| 234 |
+
"step": 1500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.16651056301384118,
|
| 238 |
+
"grad_norm": 5.122912883758545,
|
| 239 |
+
"learning_rate": 4.7224823949769314e-05,
|
| 240 |
+
"loss": 3.4539,
|
| 241 |
+
"step": 1600
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.16651056301384118,
|
| 245 |
+
"eval_loss": 3.8676364421844482,
|
| 246 |
+
"eval_runtime": 3435.2798,
|
| 247 |
+
"eval_samples_per_second": 12.206,
|
| 248 |
+
"eval_steps_per_second": 1.526,
|
| 249 |
+
"step": 1600
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.17691747320220627,
|
| 253 |
+
"grad_norm": 8.177063941955566,
|
| 254 |
+
"learning_rate": 4.7051375446629895e-05,
|
| 255 |
+
"loss": 3.4278,
|
| 256 |
+
"step": 1700
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.17691747320220627,
|
| 260 |
+
"eval_loss": 3.8678488731384277,
|
| 261 |
+
"eval_runtime": 3414.3552,
|
| 262 |
+
"eval_samples_per_second": 12.281,
|
| 263 |
+
"eval_steps_per_second": 1.535,
|
| 264 |
+
"step": 1700
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.18732438339057134,
|
| 268 |
+
"grad_norm": 5.061961650848389,
|
| 269 |
+
"learning_rate": 4.687792694349048e-05,
|
| 270 |
+
"loss": 3.4475,
|
| 271 |
+
"step": 1800
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.18732438339057134,
|
| 275 |
+
"eval_loss": 3.8584587574005127,
|
| 276 |
+
"eval_runtime": 3487.8876,
|
| 277 |
+
"eval_samples_per_second": 12.022,
|
| 278 |
+
"eval_steps_per_second": 1.503,
|
| 279 |
+
"step": 1800
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.1977312935789364,
|
| 283 |
+
"grad_norm": 5.108020305633545,
|
| 284 |
+
"learning_rate": 4.670447844035106e-05,
|
| 285 |
+
"loss": 3.4618,
|
| 286 |
+
"step": 1900
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.1977312935789364,
|
| 290 |
+
"eval_loss": 3.869356155395508,
|
| 291 |
+
"eval_runtime": 3642.3755,
|
| 292 |
+
"eval_samples_per_second": 11.512,
|
| 293 |
+
"eval_steps_per_second": 1.439,
|
| 294 |
+
"step": 1900
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.2081382037673015,
|
| 298 |
+
"grad_norm": 5.9767351150512695,
|
| 299 |
+
"learning_rate": 4.6531029937211644e-05,
|
| 300 |
+
"loss": 3.3986,
|
| 301 |
+
"step": 2000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.2081382037673015,
|
| 305 |
+
"eval_loss": 3.8760101795196533,
|
| 306 |
+
"eval_runtime": 3500.4112,
|
| 307 |
+
"eval_samples_per_second": 11.979,
|
| 308 |
+
"eval_steps_per_second": 1.498,
|
| 309 |
+
"step": 2000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.21854511395566656,
|
| 313 |
+
"grad_norm": 7.525568008422852,
|
| 314 |
+
"learning_rate": 4.6357581434072225e-05,
|
| 315 |
+
"loss": 3.3452,
|
| 316 |
+
"step": 2100
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.21854511395566656,
|
| 320 |
+
"eval_loss": 3.8635501861572266,
|
| 321 |
+
"eval_runtime": 3434.6174,
|
| 322 |
+
"eval_samples_per_second": 12.209,
|
| 323 |
+
"eval_steps_per_second": 1.526,
|
| 324 |
+
"step": 2100
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.22895202414403162,
|
| 328 |
+
"grad_norm": 6.358871936798096,
|
| 329 |
+
"learning_rate": 4.618413293093281e-05,
|
| 330 |
+
"loss": 3.3387,
|
| 331 |
+
"step": 2200
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.22895202414403162,
|
| 335 |
+
"eval_loss": 3.85604190826416,
|
| 336 |
+
"eval_runtime": 3437.498,
|
| 337 |
+
"eval_samples_per_second": 12.198,
|
| 338 |
+
"eval_steps_per_second": 1.525,
|
| 339 |
+
"step": 2200
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.23935893433239672,
|
| 343 |
+
"grad_norm": 7.322586536407471,
|
| 344 |
+
"learning_rate": 4.6010684427793386e-05,
|
| 345 |
+
"loss": 3.3527,
|
| 346 |
+
"step": 2300
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.23935893433239672,
|
| 350 |
+
"eval_loss": 3.867178440093994,
|
| 351 |
+
"eval_runtime": 3435.5675,
|
| 352 |
+
"eval_samples_per_second": 12.205,
|
| 353 |
+
"eval_steps_per_second": 1.526,
|
| 354 |
+
"step": 2300
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.24976584452076178,
|
| 358 |
+
"grad_norm": 8.45722770690918,
|
| 359 |
+
"learning_rate": 4.5837235924653974e-05,
|
| 360 |
+
"loss": 3.4033,
|
| 361 |
+
"step": 2400
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.24976584452076178,
|
| 365 |
+
"eval_loss": 3.8560798168182373,
|
| 366 |
+
"eval_runtime": 3565.6947,
|
| 367 |
+
"eval_samples_per_second": 11.76,
|
| 368 |
+
"eval_steps_per_second": 1.47,
|
| 369 |
+
"step": 2400
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.2601727547091269,
|
| 373 |
+
"grad_norm": 5.179561614990234,
|
| 374 |
+
"learning_rate": 4.5663787421514554e-05,
|
| 375 |
+
"loss": 3.4205,
|
| 376 |
+
"step": 2500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.2601727547091269,
|
| 380 |
+
"eval_loss": 3.8475325107574463,
|
| 381 |
+
"eval_runtime": 3647.5472,
|
| 382 |
+
"eval_samples_per_second": 11.496,
|
| 383 |
+
"eval_steps_per_second": 1.437,
|
| 384 |
+
"step": 2500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.2705796648974919,
|
| 388 |
+
"grad_norm": 5.7942399978637695,
|
| 389 |
+
"learning_rate": 4.5490338918375135e-05,
|
| 390 |
+
"loss": 3.2885,
|
| 391 |
+
"step": 2600
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.2705796648974919,
|
| 395 |
+
"eval_loss": 3.8502981662750244,
|
| 396 |
+
"eval_runtime": 3640.4425,
|
| 397 |
+
"eval_samples_per_second": 11.518,
|
| 398 |
+
"eval_steps_per_second": 1.44,
|
| 399 |
+
"step": 2600
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.280986575085857,
|
| 403 |
+
"grad_norm": 6.213371753692627,
|
| 404 |
+
"learning_rate": 4.5316890415235716e-05,
|
| 405 |
+
"loss": 3.3147,
|
| 406 |
+
"step": 2700
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.280986575085857,
|
| 410 |
+
"eval_loss": 3.856261730194092,
|
| 411 |
+
"eval_runtime": 3643.059,
|
| 412 |
+
"eval_samples_per_second": 11.51,
|
| 413 |
+
"eval_steps_per_second": 1.439,
|
| 414 |
+
"step": 2700
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.2913934852742221,
|
| 418 |
+
"grad_norm": 4.848277568817139,
|
| 419 |
+
"learning_rate": 4.5143441912096303e-05,
|
| 420 |
+
"loss": 3.3275,
|
| 421 |
+
"step": 2800
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.2913934852742221,
|
| 425 |
+
"eval_loss": 3.8547070026397705,
|
| 426 |
+
"eval_runtime": 3641.446,
|
| 427 |
+
"eval_samples_per_second": 11.515,
|
| 428 |
+
"eval_steps_per_second": 1.44,
|
| 429 |
+
"step": 2800
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.30180039546258713,
|
| 433 |
+
"grad_norm": 6.599040508270264,
|
| 434 |
+
"learning_rate": 4.4969993408956884e-05,
|
| 435 |
+
"loss": 3.3368,
|
| 436 |
+
"step": 2900
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.30180039546258713,
|
| 440 |
+
"eval_loss": 3.8605613708496094,
|
| 441 |
+
"eval_runtime": 3525.3985,
|
| 442 |
+
"eval_samples_per_second": 11.894,
|
| 443 |
+
"eval_steps_per_second": 1.487,
|
| 444 |
+
"step": 2900
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.3122073056509522,
|
| 448 |
+
"grad_norm": 7.062480449676514,
|
| 449 |
+
"learning_rate": 4.4796544905817465e-05,
|
| 450 |
+
"loss": 3.3218,
|
| 451 |
+
"step": 3000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.3122073056509522,
|
| 455 |
+
"eval_loss": 3.8569867610931396,
|
| 456 |
+
"eval_runtime": 3438.6282,
|
| 457 |
+
"eval_samples_per_second": 12.194,
|
| 458 |
+
"eval_steps_per_second": 1.524,
|
| 459 |
+
"step": 3000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.3226142158393173,
|
| 463 |
+
"grad_norm": 5.044654846191406,
|
| 464 |
+
"learning_rate": 4.462309640267805e-05,
|
| 465 |
+
"loss": 3.2919,
|
| 466 |
+
"step": 3100
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.3226142158393173,
|
| 470 |
+
"eval_loss": 3.857635974884033,
|
| 471 |
+
"eval_runtime": 3422.615,
|
| 472 |
+
"eval_samples_per_second": 12.251,
|
| 473 |
+
"eval_steps_per_second": 1.532,
|
| 474 |
+
"step": 3100
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.33302112602768236,
|
| 478 |
+
"grad_norm": 4.636962413787842,
|
| 479 |
+
"learning_rate": 4.4449647899538626e-05,
|
| 480 |
+
"loss": 3.2528,
|
| 481 |
+
"step": 3200
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.33302112602768236,
|
| 485 |
+
"eval_loss": 3.860072612762451,
|
| 486 |
+
"eval_runtime": 3427.8634,
|
| 487 |
+
"eval_samples_per_second": 12.233,
|
| 488 |
+
"eval_steps_per_second": 1.529,
|
| 489 |
+
"step": 3200
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.34342803621604745,
|
| 493 |
+
"grad_norm": 6.344686985015869,
|
| 494 |
+
"learning_rate": 4.427619939639921e-05,
|
| 495 |
+
"loss": 3.3591,
|
| 496 |
+
"step": 3300
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.34342803621604745,
|
| 500 |
+
"eval_loss": 3.8569118976593018,
|
| 501 |
+
"eval_runtime": 3432.7441,
|
| 502 |
+
"eval_samples_per_second": 12.215,
|
| 503 |
+
"eval_steps_per_second": 1.527,
|
| 504 |
+
"step": 3300
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.35383494640441254,
|
| 508 |
+
"grad_norm": 5.941151142120361,
|
| 509 |
+
"learning_rate": 4.4102750893259795e-05,
|
| 510 |
+
"loss": 3.3384,
|
| 511 |
+
"step": 3400
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.35383494640441254,
|
| 515 |
+
"eval_loss": 3.851085901260376,
|
| 516 |
+
"eval_runtime": 3432.068,
|
| 517 |
+
"eval_samples_per_second": 12.218,
|
| 518 |
+
"eval_steps_per_second": 1.527,
|
| 519 |
+
"step": 3400
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.3642418565927776,
|
| 523 |
+
"grad_norm": 6.193995475769043,
|
| 524 |
+
"learning_rate": 4.3929302390120375e-05,
|
| 525 |
+
"loss": 3.2801,
|
| 526 |
+
"step": 3500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.3642418565927776,
|
| 530 |
+
"eval_loss": 3.843860387802124,
|
| 531 |
+
"eval_runtime": 3429.2875,
|
| 532 |
+
"eval_samples_per_second": 12.228,
|
| 533 |
+
"eval_steps_per_second": 1.529,
|
| 534 |
+
"step": 3500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.3746487667811427,
|
| 538 |
+
"grad_norm": 7.5851545333862305,
|
| 539 |
+
"learning_rate": 4.3755853886980956e-05,
|
| 540 |
+
"loss": 3.2912,
|
| 541 |
+
"step": 3600
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.3746487667811427,
|
| 545 |
+
"eval_loss": 3.851679563522339,
|
| 546 |
+
"eval_runtime": 3429.968,
|
| 547 |
+
"eval_samples_per_second": 12.225,
|
| 548 |
+
"eval_steps_per_second": 1.528,
|
| 549 |
+
"step": 3600
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.38505567696950777,
|
| 553 |
+
"grad_norm": 5.366103172302246,
|
| 554 |
+
"learning_rate": 4.3582405383841544e-05,
|
| 555 |
+
"loss": 3.2847,
|
| 556 |
+
"step": 3700
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.38505567696950777,
|
| 560 |
+
"eval_loss": 3.847703218460083,
|
| 561 |
+
"eval_runtime": 3435.5138,
|
| 562 |
+
"eval_samples_per_second": 12.205,
|
| 563 |
+
"eval_steps_per_second": 1.526,
|
| 564 |
+
"step": 3700
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.3954625871578728,
|
| 568 |
+
"grad_norm": 5.834432125091553,
|
| 569 |
+
"learning_rate": 4.3408956880702124e-05,
|
| 570 |
+
"loss": 3.3753,
|
| 571 |
+
"step": 3800
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.3954625871578728,
|
| 575 |
+
"eval_loss": 3.8320815563201904,
|
| 576 |
+
"eval_runtime": 3440.1983,
|
| 577 |
+
"eval_samples_per_second": 12.189,
|
| 578 |
+
"eval_steps_per_second": 1.524,
|
| 579 |
+
"step": 3800
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.4058694973462379,
|
| 583 |
+
"grad_norm": 4.3302178382873535,
|
| 584 |
+
"learning_rate": 4.3235508377562705e-05,
|
| 585 |
+
"loss": 3.2613,
|
| 586 |
+
"step": 3900
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.4058694973462379,
|
| 590 |
+
"eval_loss": 3.8347744941711426,
|
| 591 |
+
"eval_runtime": 3475.7623,
|
| 592 |
+
"eval_samples_per_second": 12.064,
|
| 593 |
+
"eval_steps_per_second": 1.508,
|
| 594 |
+
"step": 3900
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.416276407534603,
|
| 598 |
+
"grad_norm": 10.435820579528809,
|
| 599 |
+
"learning_rate": 4.3062059874423286e-05,
|
| 600 |
+
"loss": 3.2497,
|
| 601 |
+
"step": 4000
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.416276407534603,
|
| 605 |
+
"eval_loss": 3.835855484008789,
|
| 606 |
+
"eval_runtime": 3464.7097,
|
| 607 |
+
"eval_samples_per_second": 12.103,
|
| 608 |
+
"eval_steps_per_second": 1.513,
|
| 609 |
+
"step": 4000
|
| 610 |
+
}
|
| 611 |
+
],
|
| 612 |
+
"logging_steps": 100,
|
| 613 |
+
"max_steps": 28827,
|
| 614 |
+
"num_input_tokens_seen": 0,
|
| 615 |
+
"num_train_epochs": 3,
|
| 616 |
+
"save_steps": 1000,
|
| 617 |
+
"stateful_callbacks": {
|
| 618 |
+
"TrainerControl": {
|
| 619 |
+
"args": {
|
| 620 |
+
"should_epoch_stop": false,
|
| 621 |
+
"should_evaluate": false,
|
| 622 |
+
"should_log": false,
|
| 623 |
+
"should_save": true,
|
| 624 |
+
"should_training_stop": false
|
| 625 |
+
},
|
| 626 |
+
"attributes": {}
|
| 627 |
+
}
|
| 628 |
+
},
|
| 629 |
+
"total_flos": 8361345024000000.0,
|
| 630 |
+
"train_batch_size": 8,
|
| 631 |
+
"trial_name": null,
|
| 632 |
+
"trial_params": null
|
| 633 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb2b7751bf88069e3f5e27f7b384b70086817ae9e5abb6834b165efd62f841cb
|
| 3 |
+
size 5240
|