Added gpt2 model
Browse files- config.json +38 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer_config.json +33 -0
- trainer_state.json +324 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_ctx": 128,
|
| 14 |
+
"n_embd": 768,
|
| 15 |
+
"n_head": 12,
|
| 16 |
+
"n_inner": null,
|
| 17 |
+
"n_layer": 12,
|
| 18 |
+
"n_positions": 1024,
|
| 19 |
+
"reorder_and_upcast_attn": false,
|
| 20 |
+
"resid_pdrop": 0.1,
|
| 21 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 22 |
+
"scale_attn_weights": true,
|
| 23 |
+
"summary_activation": null,
|
| 24 |
+
"summary_first_dropout": 0.1,
|
| 25 |
+
"summary_proj_to_labels": true,
|
| 26 |
+
"summary_type": "cls_index",
|
| 27 |
+
"summary_use_proj": true,
|
| 28 |
+
"task_specific_params": {
|
| 29 |
+
"text-generation": {
|
| 30 |
+
"do_sample": true,
|
| 31 |
+
"max_length": 50
|
| 32 |
+
}
|
| 33 |
+
},
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.31.0",
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 50257
|
| 38 |
+
}
|
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": "4.31.0"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7821d0cbfa96cb9e3dc1a9d11c3798188549e0b60e98b2bf452a78a21fe9a701
|
| 3 |
+
size 995605189
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87039797eeee31fa3a1d10c2d523177194c55dc59f61f4e681b323a3ff27e3ac
|
| 3 |
+
size 497807197
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46ce6d1e3d7df661bdec831f2ccc0a92148db2766e8bae2d96b45ecc70cfa48d
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8015d3b05a1d6e704db23f7bbf89c9b1f626d36f6bdc05c31adde13e38374441
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"clean_up_tokenization_spaces": true,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "<|endoftext|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"errors": "replace",
|
| 22 |
+
"model_max_length": 1024,
|
| 23 |
+
"pad_token": null,
|
| 24 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 25 |
+
"unk_token": {
|
| 26 |
+
"__type": "AddedToken",
|
| 27 |
+
"content": "<|endoftext|>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": true,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,324 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.839419269687637,
|
| 5 |
+
"global_step": 11000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.22,
|
| 12 |
+
"learning_rate": 2.5e-05,
|
| 13 |
+
"loss": 7.2786,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.22,
|
| 18 |
+
"eval_loss": 4.886257171630859,
|
| 19 |
+
"eval_runtime": 81.5985,
|
| 20 |
+
"eval_samples_per_second": 190.972,
|
| 21 |
+
"eval_steps_per_second": 11.936,
|
| 22 |
+
"step": 500
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.44,
|
| 26 |
+
"learning_rate": 5e-05,
|
| 27 |
+
"loss": 4.3573,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.44,
|
| 32 |
+
"eval_loss": 3.8646771907806396,
|
| 33 |
+
"eval_runtime": 81.3815,
|
| 34 |
+
"eval_samples_per_second": 191.481,
|
| 35 |
+
"eval_steps_per_second": 11.968,
|
| 36 |
+
"step": 1000
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.66,
|
| 40 |
+
"learning_rate": 4.758803666184274e-05,
|
| 41 |
+
"loss": 3.6885,
|
| 42 |
+
"step": 1500
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.66,
|
| 46 |
+
"eval_loss": 3.40698504447937,
|
| 47 |
+
"eval_runtime": 81.4183,
|
| 48 |
+
"eval_samples_per_second": 191.394,
|
| 49 |
+
"eval_steps_per_second": 11.963,
|
| 50 |
+
"step": 1500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.88,
|
| 54 |
+
"learning_rate": 4.517607332368548e-05,
|
| 55 |
+
"loss": 3.3144,
|
| 56 |
+
"step": 2000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.88,
|
| 60 |
+
"eval_loss": 3.0980827808380127,
|
| 61 |
+
"eval_runtime": 81.5071,
|
| 62 |
+
"eval_samples_per_second": 191.186,
|
| 63 |
+
"eval_steps_per_second": 11.95,
|
| 64 |
+
"step": 2000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 1.1,
|
| 68 |
+
"learning_rate": 4.2764109985528225e-05,
|
| 69 |
+
"loss": 3.0218,
|
| 70 |
+
"step": 2500
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 1.1,
|
| 74 |
+
"eval_loss": 2.8812012672424316,
|
| 75 |
+
"eval_runtime": 81.6765,
|
| 76 |
+
"eval_samples_per_second": 190.789,
|
| 77 |
+
"eval_steps_per_second": 11.925,
|
| 78 |
+
"step": 2500
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 1.32,
|
| 82 |
+
"learning_rate": 4.0352146647370966e-05,
|
| 83 |
+
"loss": 2.832,
|
| 84 |
+
"step": 3000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.32,
|
| 88 |
+
"eval_loss": 2.730829954147339,
|
| 89 |
+
"eval_runtime": 81.679,
|
| 90 |
+
"eval_samples_per_second": 190.783,
|
| 91 |
+
"eval_steps_per_second": 11.925,
|
| 92 |
+
"step": 3000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.54,
|
| 96 |
+
"learning_rate": 3.79401833092137e-05,
|
| 97 |
+
"loss": 2.7159,
|
| 98 |
+
"step": 3500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.54,
|
| 102 |
+
"eval_loss": 2.6153135299682617,
|
| 103 |
+
"eval_runtime": 81.5642,
|
| 104 |
+
"eval_samples_per_second": 191.052,
|
| 105 |
+
"eval_steps_per_second": 11.942,
|
| 106 |
+
"step": 3500
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.76,
|
| 110 |
+
"learning_rate": 3.552821997105644e-05,
|
| 111 |
+
"loss": 2.6086,
|
| 112 |
+
"step": 4000
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.76,
|
| 116 |
+
"eval_loss": 2.522780418395996,
|
| 117 |
+
"eval_runtime": 81.5345,
|
| 118 |
+
"eval_samples_per_second": 191.122,
|
| 119 |
+
"eval_steps_per_second": 11.946,
|
| 120 |
+
"step": 4000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.98,
|
| 124 |
+
"learning_rate": 3.311625663289918e-05,
|
| 125 |
+
"loss": 2.52,
|
| 126 |
+
"step": 4500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.98,
|
| 130 |
+
"eval_loss": 2.446049451828003,
|
| 131 |
+
"eval_runtime": 81.2437,
|
| 132 |
+
"eval_samples_per_second": 191.806,
|
| 133 |
+
"eval_steps_per_second": 11.989,
|
| 134 |
+
"step": 4500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.2,
|
| 138 |
+
"learning_rate": 3.0704293294741923e-05,
|
| 139 |
+
"loss": 2.3734,
|
| 140 |
+
"step": 5000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.2,
|
| 144 |
+
"eval_loss": 2.3772902488708496,
|
| 145 |
+
"eval_runtime": 81.4154,
|
| 146 |
+
"eval_samples_per_second": 191.401,
|
| 147 |
+
"eval_steps_per_second": 11.963,
|
| 148 |
+
"step": 5000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 2.42,
|
| 152 |
+
"learning_rate": 2.829232995658466e-05,
|
| 153 |
+
"loss": 2.3257,
|
| 154 |
+
"step": 5500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 2.42,
|
| 158 |
+
"eval_loss": 2.322295904159546,
|
| 159 |
+
"eval_runtime": 81.2639,
|
| 160 |
+
"eval_samples_per_second": 191.758,
|
| 161 |
+
"eval_steps_per_second": 11.986,
|
| 162 |
+
"step": 5500
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.64,
|
| 166 |
+
"learning_rate": 2.58803666184274e-05,
|
| 167 |
+
"loss": 2.2788,
|
| 168 |
+
"step": 6000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.64,
|
| 172 |
+
"eval_loss": 2.274811267852783,
|
| 173 |
+
"eval_runtime": 81.4351,
|
| 174 |
+
"eval_samples_per_second": 191.355,
|
| 175 |
+
"eval_steps_per_second": 11.96,
|
| 176 |
+
"step": 6000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.86,
|
| 180 |
+
"learning_rate": 2.346840328027014e-05,
|
| 181 |
+
"loss": 2.2449,
|
| 182 |
+
"step": 6500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.86,
|
| 186 |
+
"eval_loss": 2.233612298965454,
|
| 187 |
+
"eval_runtime": 81.4361,
|
| 188 |
+
"eval_samples_per_second": 191.352,
|
| 189 |
+
"eval_steps_per_second": 11.96,
|
| 190 |
+
"step": 6500
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 3.08,
|
| 194 |
+
"learning_rate": 2.105643994211288e-05,
|
| 195 |
+
"loss": 2.1734,
|
| 196 |
+
"step": 7000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 3.08,
|
| 200 |
+
"eval_loss": 2.195352077484131,
|
| 201 |
+
"eval_runtime": 81.4409,
|
| 202 |
+
"eval_samples_per_second": 191.341,
|
| 203 |
+
"eval_steps_per_second": 11.96,
|
| 204 |
+
"step": 7000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 3.3,
|
| 208 |
+
"learning_rate": 1.864447660395562e-05,
|
| 209 |
+
"loss": 2.088,
|
| 210 |
+
"step": 7500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 3.3,
|
| 214 |
+
"eval_loss": 2.172189950942993,
|
| 215 |
+
"eval_runtime": 81.2625,
|
| 216 |
+
"eval_samples_per_second": 191.761,
|
| 217 |
+
"eval_steps_per_second": 11.986,
|
| 218 |
+
"step": 7500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.52,
|
| 222 |
+
"learning_rate": 1.623251326579836e-05,
|
| 223 |
+
"loss": 2.0633,
|
| 224 |
+
"step": 8000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 3.52,
|
| 228 |
+
"eval_loss": 2.1411869525909424,
|
| 229 |
+
"eval_runtime": 81.2032,
|
| 230 |
+
"eval_samples_per_second": 191.901,
|
| 231 |
+
"eval_steps_per_second": 11.995,
|
| 232 |
+
"step": 8000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 3.74,
|
| 236 |
+
"learning_rate": 1.3825373854317415e-05,
|
| 237 |
+
"loss": 2.0491,
|
| 238 |
+
"step": 8500
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 3.74,
|
| 242 |
+
"eval_loss": 2.117720127105713,
|
| 243 |
+
"eval_runtime": 81.4728,
|
| 244 |
+
"eval_samples_per_second": 191.266,
|
| 245 |
+
"eval_steps_per_second": 11.955,
|
| 246 |
+
"step": 8500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 3.96,
|
| 250 |
+
"learning_rate": 1.1413410516160154e-05,
|
| 251 |
+
"loss": 2.032,
|
| 252 |
+
"step": 9000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 3.96,
|
| 256 |
+
"eval_loss": 2.0970561504364014,
|
| 257 |
+
"eval_runtime": 81.4071,
|
| 258 |
+
"eval_samples_per_second": 191.421,
|
| 259 |
+
"eval_steps_per_second": 11.965,
|
| 260 |
+
"step": 9000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 4.18,
|
| 264 |
+
"learning_rate": 9.001447178002895e-06,
|
| 265 |
+
"loss": 1.9451,
|
| 266 |
+
"step": 9500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 4.18,
|
| 270 |
+
"eval_loss": 2.084089756011963,
|
| 271 |
+
"eval_runtime": 81.4657,
|
| 272 |
+
"eval_samples_per_second": 191.283,
|
| 273 |
+
"eval_steps_per_second": 11.956,
|
| 274 |
+
"step": 9500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 4.4,
|
| 278 |
+
"learning_rate": 6.589483839845635e-06,
|
| 279 |
+
"loss": 1.9275,
|
| 280 |
+
"step": 10000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 4.4,
|
| 284 |
+
"eval_loss": 2.0687994956970215,
|
| 285 |
+
"eval_runtime": 81.6182,
|
| 286 |
+
"eval_samples_per_second": 190.926,
|
| 287 |
+
"eval_steps_per_second": 11.934,
|
| 288 |
+
"step": 10000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 4.62,
|
| 292 |
+
"learning_rate": 4.18234442836469e-06,
|
| 293 |
+
"loss": 1.9138,
|
| 294 |
+
"step": 10500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 4.62,
|
| 298 |
+
"eval_loss": 2.0576138496398926,
|
| 299 |
+
"eval_runtime": 81.6062,
|
| 300 |
+
"eval_samples_per_second": 190.954,
|
| 301 |
+
"eval_steps_per_second": 11.935,
|
| 302 |
+
"step": 10500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 4.84,
|
| 306 |
+
"learning_rate": 1.7703810902074289e-06,
|
| 307 |
+
"loss": 1.9068,
|
| 308 |
+
"step": 11000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 4.84,
|
| 312 |
+
"eval_loss": 2.048520565032959,
|
| 313 |
+
"eval_runtime": 81.6161,
|
| 314 |
+
"eval_samples_per_second": 190.93,
|
| 315 |
+
"eval_steps_per_second": 11.934,
|
| 316 |
+
"step": 11000
|
| 317 |
+
}
|
| 318 |
+
],
|
| 319 |
+
"max_steps": 11365,
|
| 320 |
+
"num_train_epochs": 5,
|
| 321 |
+
"total_flos": 1.1494473283584e+16,
|
| 322 |
+
"trial_name": null,
|
| 323 |
+
"trial_params": null
|
| 324 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff4a22b53672fbc7f2d5cc3310f4e17058a7a012b48b927465d691e9f95a218b
|
| 3 |
+
size 3963
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|