Commit
•
ee39bd9
1
Parent(s):
4049904
Upload folder using huggingface_hub
Browse files- config.json +41 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +20 -0
- trainer_state.json +319 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/archive/turganbay/DPO/gpt_tuned_sft/checkpoint-10000/",
|
| 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": 1024,
|
| 16 |
+
"n_head": 16,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 24,
|
| 19 |
+
"n_positions": 1024,
|
| 20 |
+
"n_special": 0,
|
| 21 |
+
"predict_special_tokens": true,
|
| 22 |
+
"reorder_and_upcast_attn": false,
|
| 23 |
+
"resid_pdrop": 0.1,
|
| 24 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 25 |
+
"scale_attn_weights": true,
|
| 26 |
+
"summary_activation": null,
|
| 27 |
+
"summary_first_dropout": 0.1,
|
| 28 |
+
"summary_proj_to_labels": true,
|
| 29 |
+
"summary_type": "cls_index",
|
| 30 |
+
"summary_use_proj": true,
|
| 31 |
+
"task_specific_params": {
|
| 32 |
+
"text-generation": {
|
| 33 |
+
"do_sample": true,
|
| 34 |
+
"max_length": 50
|
| 35 |
+
}
|
| 36 |
+
},
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.35.0",
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 50257
|
| 41 |
+
}
|
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": "4.35.0"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6082eff10514a14c29369bee738da18027bd1a168686e2a07b6967fce26f210
|
| 3 |
+
size 1419322880
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebb48df631b8d56de847860943c3f8337e74eefb01126a3054c01b224cdd5f0a
|
| 3 |
+
size 2838759418
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f1a6cf8ac1cc50884e702dfffd082cc16c2e6bccabb3c9aab89deab1e40ee70
|
| 3 |
+
size 14768
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bed0efe94bd2535da8daa06213fbaee72834212832e963e090f5ec5f6548b4fe
|
| 3 |
+
size 14768
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d596c62ce4389f8f77ffe50f209963ab04eda6d6bf26f21dceb04326b3ae1021
|
| 3 |
+
size 14768
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c63fc8424fcb6db36631ca5e588b98557df3720423df8a9d4bafaf928f4152be
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
}
|
| 12 |
+
},
|
| 13 |
+
"bos_token": "<|endoftext|>",
|
| 14 |
+
"clean_up_tokenization_spaces": true,
|
| 15 |
+
"eos_token": "<|endoftext|>",
|
| 16 |
+
"model_max_length": 1024,
|
| 17 |
+
"pad_token": "<|endoftext|>",
|
| 18 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 19 |
+
"unk_token": "<|endoftext|>"
|
| 20 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,319 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 12.038221352795125,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 10000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.24,
|
| 13 |
+
"learning_rate": 1.2e-05,
|
| 14 |
+
"loss": 1.7974,
|
| 15 |
+
"step": 200
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.48,
|
| 19 |
+
"learning_rate": 2.4e-05,
|
| 20 |
+
"loss": 1.78,
|
| 21 |
+
"step": 400
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.72,
|
| 25 |
+
"learning_rate": 2.968421052631579e-05,
|
| 26 |
+
"loss": 1.7735,
|
| 27 |
+
"step": 600
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.96,
|
| 31 |
+
"learning_rate": 2.905263157894737e-05,
|
| 32 |
+
"loss": 1.7659,
|
| 33 |
+
"step": 800
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.2,
|
| 37 |
+
"learning_rate": 2.8421052631578946e-05,
|
| 38 |
+
"loss": 1.7449,
|
| 39 |
+
"step": 1000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.44,
|
| 43 |
+
"learning_rate": 2.7789473684210526e-05,
|
| 44 |
+
"loss": 1.7377,
|
| 45 |
+
"step": 1200
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.69,
|
| 49 |
+
"learning_rate": 2.7157894736842106e-05,
|
| 50 |
+
"loss": 1.7293,
|
| 51 |
+
"step": 1400
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.93,
|
| 55 |
+
"learning_rate": 2.6526315789473685e-05,
|
| 56 |
+
"loss": 1.7259,
|
| 57 |
+
"step": 1600
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 2.17,
|
| 61 |
+
"learning_rate": 2.5894736842105265e-05,
|
| 62 |
+
"loss": 1.705,
|
| 63 |
+
"step": 1800
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.41,
|
| 67 |
+
"learning_rate": 2.526315789473684e-05,
|
| 68 |
+
"loss": 1.6861,
|
| 69 |
+
"step": 2000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.65,
|
| 73 |
+
"learning_rate": 2.463157894736842e-05,
|
| 74 |
+
"loss": 1.6913,
|
| 75 |
+
"step": 2200
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 2.89,
|
| 79 |
+
"learning_rate": 2.4e-05,
|
| 80 |
+
"loss": 1.6857,
|
| 81 |
+
"step": 2400
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 3.13,
|
| 85 |
+
"learning_rate": 2.336842105263158e-05,
|
| 86 |
+
"loss": 1.6676,
|
| 87 |
+
"step": 2600
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 3.37,
|
| 91 |
+
"learning_rate": 2.273684210526316e-05,
|
| 92 |
+
"loss": 1.6573,
|
| 93 |
+
"step": 2800
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 3.61,
|
| 97 |
+
"learning_rate": 2.2105263157894736e-05,
|
| 98 |
+
"loss": 1.6504,
|
| 99 |
+
"step": 3000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 3.85,
|
| 103 |
+
"learning_rate": 2.1473684210526316e-05,
|
| 104 |
+
"loss": 1.6465,
|
| 105 |
+
"step": 3200
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 4.09,
|
| 109 |
+
"learning_rate": 2.0842105263157895e-05,
|
| 110 |
+
"loss": 1.6333,
|
| 111 |
+
"step": 3400
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 4.33,
|
| 115 |
+
"learning_rate": 2.0210526315789475e-05,
|
| 116 |
+
"loss": 1.6197,
|
| 117 |
+
"step": 3600
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 4.57,
|
| 121 |
+
"learning_rate": 1.9578947368421055e-05,
|
| 122 |
+
"loss": 1.6201,
|
| 123 |
+
"step": 3800
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 4.82,
|
| 127 |
+
"learning_rate": 1.894736842105263e-05,
|
| 128 |
+
"loss": 1.6179,
|
| 129 |
+
"step": 4000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 5.06,
|
| 133 |
+
"learning_rate": 1.831578947368421e-05,
|
| 134 |
+
"loss": 1.6134,
|
| 135 |
+
"step": 4200
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 5.3,
|
| 139 |
+
"learning_rate": 1.7684210526315787e-05,
|
| 140 |
+
"loss": 1.5945,
|
| 141 |
+
"step": 4400
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 5.54,
|
| 145 |
+
"learning_rate": 1.705263157894737e-05,
|
| 146 |
+
"loss": 1.588,
|
| 147 |
+
"step": 4600
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 5.78,
|
| 151 |
+
"learning_rate": 1.642105263157895e-05,
|
| 152 |
+
"loss": 1.5949,
|
| 153 |
+
"step": 4800
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 6.02,
|
| 157 |
+
"learning_rate": 1.5789473684210526e-05,
|
| 158 |
+
"loss": 1.585,
|
| 159 |
+
"step": 5000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 6.26,
|
| 163 |
+
"learning_rate": 1.5157894736842105e-05,
|
| 164 |
+
"loss": 1.5695,
|
| 165 |
+
"step": 5200
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 6.5,
|
| 169 |
+
"learning_rate": 1.4526315789473685e-05,
|
| 170 |
+
"loss": 1.5656,
|
| 171 |
+
"step": 5400
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 6.74,
|
| 175 |
+
"learning_rate": 1.3894736842105263e-05,
|
| 176 |
+
"loss": 1.5687,
|
| 177 |
+
"step": 5600
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 6.98,
|
| 181 |
+
"learning_rate": 1.3263157894736843e-05,
|
| 182 |
+
"loss": 1.5669,
|
| 183 |
+
"step": 5800
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 7.22,
|
| 187 |
+
"learning_rate": 1.263157894736842e-05,
|
| 188 |
+
"loss": 1.5511,
|
| 189 |
+
"step": 6000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 7.46,
|
| 193 |
+
"learning_rate": 1.2e-05,
|
| 194 |
+
"loss": 1.5488,
|
| 195 |
+
"step": 6200
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 7.7,
|
| 199 |
+
"learning_rate": 1.136842105263158e-05,
|
| 200 |
+
"loss": 1.5462,
|
| 201 |
+
"step": 6400
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 7.95,
|
| 205 |
+
"learning_rate": 1.0736842105263158e-05,
|
| 206 |
+
"loss": 1.5507,
|
| 207 |
+
"step": 6600
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 8.19,
|
| 211 |
+
"learning_rate": 1.0105263157894738e-05,
|
| 212 |
+
"loss": 1.5364,
|
| 213 |
+
"step": 6800
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 8.43,
|
| 217 |
+
"learning_rate": 9.473684210526315e-06,
|
| 218 |
+
"loss": 1.5352,
|
| 219 |
+
"step": 7000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 8.67,
|
| 223 |
+
"learning_rate": 8.842105263157893e-06,
|
| 224 |
+
"loss": 1.533,
|
| 225 |
+
"step": 7200
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 8.91,
|
| 229 |
+
"learning_rate": 8.210526315789475e-06,
|
| 230 |
+
"loss": 1.5292,
|
| 231 |
+
"step": 7400
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 9.15,
|
| 235 |
+
"learning_rate": 7.578947368421053e-06,
|
| 236 |
+
"loss": 1.5258,
|
| 237 |
+
"step": 7600
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 9.39,
|
| 241 |
+
"learning_rate": 6.9473684210526315e-06,
|
| 242 |
+
"loss": 1.5194,
|
| 243 |
+
"step": 7800
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 9.63,
|
| 247 |
+
"learning_rate": 6.31578947368421e-06,
|
| 248 |
+
"loss": 1.5205,
|
| 249 |
+
"step": 8000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 9.87,
|
| 253 |
+
"learning_rate": 5.68421052631579e-06,
|
| 254 |
+
"loss": 1.5163,
|
| 255 |
+
"step": 8200
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 10.11,
|
| 259 |
+
"learning_rate": 5.052631578947369e-06,
|
| 260 |
+
"loss": 1.5182,
|
| 261 |
+
"step": 8400
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 10.35,
|
| 265 |
+
"learning_rate": 4.421052631578947e-06,
|
| 266 |
+
"loss": 1.5126,
|
| 267 |
+
"step": 8600
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 10.59,
|
| 271 |
+
"learning_rate": 3.7894736842105264e-06,
|
| 272 |
+
"loss": 1.5102,
|
| 273 |
+
"step": 8800
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 10.83,
|
| 277 |
+
"learning_rate": 3.157894736842105e-06,
|
| 278 |
+
"loss": 1.5073,
|
| 279 |
+
"step": 9000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 11.08,
|
| 283 |
+
"learning_rate": 2.5263157894736844e-06,
|
| 284 |
+
"loss": 1.5104,
|
| 285 |
+
"step": 9200
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 11.32,
|
| 289 |
+
"learning_rate": 1.8947368421052632e-06,
|
| 290 |
+
"loss": 1.5033,
|
| 291 |
+
"step": 9400
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 11.56,
|
| 295 |
+
"learning_rate": 1.2631578947368422e-06,
|
| 296 |
+
"loss": 1.5055,
|
| 297 |
+
"step": 9600
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 11.8,
|
| 301 |
+
"learning_rate": 6.315789473684211e-07,
|
| 302 |
+
"loss": 1.5047,
|
| 303 |
+
"step": 9800
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 12.04,
|
| 307 |
+
"learning_rate": 0.0,
|
| 308 |
+
"loss": 1.5057,
|
| 309 |
+
"step": 10000
|
| 310 |
+
}
|
| 311 |
+
],
|
| 312 |
+
"logging_steps": 200,
|
| 313 |
+
"max_steps": 10000,
|
| 314 |
+
"num_train_epochs": 13,
|
| 315 |
+
"save_steps": 500,
|
| 316 |
+
"total_flos": 1.1107602523509228e+18,
|
| 317 |
+
"trial_name": null,
|
| 318 |
+
"trial_params": null
|
| 319 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6979520b26717047d67925b4572760c137c1a3b7fb9930790aa670ae5768595e
|
| 3 |
+
size 4536
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|