Commit
•
01bec19
1
Parent(s):
d25b2f2
Upload 12 files
Browse files- config.json +38 -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.json +0 -0
- tokenizer_config.json +34 -0
- trainer_state.json +392 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/DialoGPT-small",
|
| 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 |
+
"conversational": {
|
| 31 |
+
"max_length": 1000
|
| 32 |
+
}
|
| 33 |
+
},
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.20.1",
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 50257
|
| 38 |
+
}
|
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 sha256:3d0e0c11268337047739237b4ae303ac1599137fdf68773bda1b4e4b819c3cb0
|
| 3 |
+
size 995605189
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:869815815761674452cd74b1bb540811a0c18c2f8cea93f16e99becd9b14bf25
|
| 3 |
+
size 510398013
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbe5e283396137e317863f844e873bad92b94ac2debac912ac23b5d179ae6a4d
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fd6684a6785c23792ac83d3d5eef471d30b3413d3d1a4eb6c06af6b143c6a5f
|
| 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.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"eos_token": {
|
| 13 |
+
"__type": "AddedToken",
|
| 14 |
+
"content": "<|endoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"errors": "replace",
|
| 21 |
+
"model_max_length": 1024,
|
| 22 |
+
"name_or_path": "microsoft/DialoGPT-small",
|
| 23 |
+
"pad_token": null,
|
| 24 |
+
"special_tokens_map_file": null,
|
| 25 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 26 |
+
"unk_token": {
|
| 27 |
+
"__type": "AddedToken",
|
| 28 |
+
"content": "<|endoftext|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false
|
| 33 |
+
}
|
| 34 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,392 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 28210,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.09,
|
| 12 |
+
"learning_rate": 9.822757887274017e-05,
|
| 13 |
+
"loss": 0.1767,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.18,
|
| 18 |
+
"learning_rate": 9.645515774548033e-05,
|
| 19 |
+
"loss": 0.1359,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.27,
|
| 24 |
+
"learning_rate": 9.46827366182205e-05,
|
| 25 |
+
"loss": 0.133,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.35,
|
| 30 |
+
"learning_rate": 9.291031549096066e-05,
|
| 31 |
+
"loss": 0.1302,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.44,
|
| 36 |
+
"learning_rate": 9.113789436370082e-05,
|
| 37 |
+
"loss": 0.1302,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.53,
|
| 42 |
+
"learning_rate": 8.936547323644098e-05,
|
| 43 |
+
"loss": 0.1298,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.62,
|
| 48 |
+
"learning_rate": 8.759305210918115e-05,
|
| 49 |
+
"loss": 0.1253,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.71,
|
| 54 |
+
"learning_rate": 8.582063098192131e-05,
|
| 55 |
+
"loss": 0.1288,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.8,
|
| 60 |
+
"learning_rate": 8.404820985466147e-05,
|
| 61 |
+
"loss": 0.1206,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.89,
|
| 66 |
+
"learning_rate": 8.227578872740164e-05,
|
| 67 |
+
"loss": 0.1224,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.97,
|
| 72 |
+
"learning_rate": 8.05033676001418e-05,
|
| 73 |
+
"loss": 0.1237,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.0,
|
| 78 |
+
"eval_loss": 0.114857017993927,
|
| 79 |
+
"eval_runtime": 83.1109,
|
| 80 |
+
"eval_samples_per_second": 33.943,
|
| 81 |
+
"eval_steps_per_second": 8.495,
|
| 82 |
+
"step": 5642
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.06,
|
| 86 |
+
"learning_rate": 7.873094647288196e-05,
|
| 87 |
+
"loss": 0.1154,
|
| 88 |
+
"step": 6000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.15,
|
| 92 |
+
"learning_rate": 7.695852534562212e-05,
|
| 93 |
+
"loss": 0.1071,
|
| 94 |
+
"step": 6500
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.24,
|
| 98 |
+
"learning_rate": 7.518610421836229e-05,
|
| 99 |
+
"loss": 0.1059,
|
| 100 |
+
"step": 7000
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.33,
|
| 104 |
+
"learning_rate": 7.341368309110245e-05,
|
| 105 |
+
"loss": 0.1057,
|
| 106 |
+
"step": 7500
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.42,
|
| 110 |
+
"learning_rate": 7.164126196384261e-05,
|
| 111 |
+
"loss": 0.1067,
|
| 112 |
+
"step": 8000
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.51,
|
| 116 |
+
"learning_rate": 6.986884083658278e-05,
|
| 117 |
+
"loss": 0.1116,
|
| 118 |
+
"step": 8500
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.6,
|
| 122 |
+
"learning_rate": 6.809641970932294e-05,
|
| 123 |
+
"loss": 0.1056,
|
| 124 |
+
"step": 9000
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.68,
|
| 128 |
+
"learning_rate": 6.632399858206309e-05,
|
| 129 |
+
"loss": 0.1061,
|
| 130 |
+
"step": 9500
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.77,
|
| 134 |
+
"learning_rate": 6.455157745480327e-05,
|
| 135 |
+
"loss": 0.104,
|
| 136 |
+
"step": 10000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.86,
|
| 140 |
+
"learning_rate": 6.277915632754343e-05,
|
| 141 |
+
"loss": 0.1036,
|
| 142 |
+
"step": 10500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.95,
|
| 146 |
+
"learning_rate": 6.100673520028359e-05,
|
| 147 |
+
"loss": 0.1085,
|
| 148 |
+
"step": 11000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 2.0,
|
| 152 |
+
"eval_loss": 0.10869502276182175,
|
| 153 |
+
"eval_runtime": 83.1785,
|
| 154 |
+
"eval_samples_per_second": 33.915,
|
| 155 |
+
"eval_steps_per_second": 8.488,
|
| 156 |
+
"step": 11284
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 2.04,
|
| 160 |
+
"learning_rate": 5.9234314073023755e-05,
|
| 161 |
+
"loss": 0.0972,
|
| 162 |
+
"step": 11500
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.13,
|
| 166 |
+
"learning_rate": 5.746189294576392e-05,
|
| 167 |
+
"loss": 0.0905,
|
| 168 |
+
"step": 12000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.22,
|
| 172 |
+
"learning_rate": 5.568947181850408e-05,
|
| 173 |
+
"loss": 0.0906,
|
| 174 |
+
"step": 12500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.3,
|
| 178 |
+
"learning_rate": 5.3917050691244244e-05,
|
| 179 |
+
"loss": 0.0918,
|
| 180 |
+
"step": 13000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 2.39,
|
| 184 |
+
"learning_rate": 5.21446295639844e-05,
|
| 185 |
+
"loss": 0.0916,
|
| 186 |
+
"step": 13500
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.48,
|
| 190 |
+
"learning_rate": 5.0372208436724564e-05,
|
| 191 |
+
"loss": 0.088,
|
| 192 |
+
"step": 14000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 2.57,
|
| 196 |
+
"learning_rate": 4.8599787309464734e-05,
|
| 197 |
+
"loss": 0.0928,
|
| 198 |
+
"step": 14500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.66,
|
| 202 |
+
"learning_rate": 4.68273661822049e-05,
|
| 203 |
+
"loss": 0.0917,
|
| 204 |
+
"step": 15000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 2.75,
|
| 208 |
+
"learning_rate": 4.505494505494506e-05,
|
| 209 |
+
"loss": 0.0883,
|
| 210 |
+
"step": 15500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 2.84,
|
| 214 |
+
"learning_rate": 4.328252392768522e-05,
|
| 215 |
+
"loss": 0.0946,
|
| 216 |
+
"step": 16000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.92,
|
| 220 |
+
"learning_rate": 4.151010280042538e-05,
|
| 221 |
+
"loss": 0.0936,
|
| 222 |
+
"step": 16500
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 3.0,
|
| 226 |
+
"eval_loss": 0.10643293708562851,
|
| 227 |
+
"eval_runtime": 83.1131,
|
| 228 |
+
"eval_samples_per_second": 33.942,
|
| 229 |
+
"eval_steps_per_second": 8.494,
|
| 230 |
+
"step": 16926
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 3.01,
|
| 234 |
+
"learning_rate": 3.973768167316554e-05,
|
| 235 |
+
"loss": 0.0888,
|
| 236 |
+
"step": 17000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 3.1,
|
| 240 |
+
"learning_rate": 3.7965260545905705e-05,
|
| 241 |
+
"loss": 0.0783,
|
| 242 |
+
"step": 17500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 3.19,
|
| 246 |
+
"learning_rate": 3.6192839418645875e-05,
|
| 247 |
+
"loss": 0.079,
|
| 248 |
+
"step": 18000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 3.28,
|
| 252 |
+
"learning_rate": 3.442041829138604e-05,
|
| 253 |
+
"loss": 0.0813,
|
| 254 |
+
"step": 18500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.37,
|
| 258 |
+
"learning_rate": 3.26479971641262e-05,
|
| 259 |
+
"loss": 0.0792,
|
| 260 |
+
"step": 19000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.46,
|
| 264 |
+
"learning_rate": 3.087557603686636e-05,
|
| 265 |
+
"loss": 0.079,
|
| 266 |
+
"step": 19500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 3.54,
|
| 270 |
+
"learning_rate": 2.9103154909606524e-05,
|
| 271 |
+
"loss": 0.0777,
|
| 272 |
+
"step": 20000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.63,
|
| 276 |
+
"learning_rate": 2.7330733782346684e-05,
|
| 277 |
+
"loss": 0.08,
|
| 278 |
+
"step": 20500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 3.72,
|
| 282 |
+
"learning_rate": 2.5558312655086853e-05,
|
| 283 |
+
"loss": 0.0795,
|
| 284 |
+
"step": 21000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.81,
|
| 288 |
+
"learning_rate": 2.3785891527827013e-05,
|
| 289 |
+
"loss": 0.0807,
|
| 290 |
+
"step": 21500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 3.9,
|
| 294 |
+
"learning_rate": 2.2013470400567176e-05,
|
| 295 |
+
"loss": 0.0807,
|
| 296 |
+
"step": 22000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.99,
|
| 300 |
+
"learning_rate": 2.024104927330734e-05,
|
| 301 |
+
"loss": 0.0765,
|
| 302 |
+
"step": 22500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 4.0,
|
| 306 |
+
"eval_loss": 0.10565190017223358,
|
| 307 |
+
"eval_runtime": 83.1461,
|
| 308 |
+
"eval_samples_per_second": 33.928,
|
| 309 |
+
"eval_steps_per_second": 8.491,
|
| 310 |
+
"step": 22568
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 4.08,
|
| 314 |
+
"learning_rate": 1.8468628146047502e-05,
|
| 315 |
+
"loss": 0.0742,
|
| 316 |
+
"step": 23000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 4.17,
|
| 320 |
+
"learning_rate": 1.6696207018787665e-05,
|
| 321 |
+
"loss": 0.0711,
|
| 322 |
+
"step": 23500
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 4.25,
|
| 326 |
+
"learning_rate": 1.4923785891527828e-05,
|
| 327 |
+
"loss": 0.0724,
|
| 328 |
+
"step": 24000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 4.34,
|
| 332 |
+
"learning_rate": 1.315136476426799e-05,
|
| 333 |
+
"loss": 0.0689,
|
| 334 |
+
"step": 24500
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 4.43,
|
| 338 |
+
"learning_rate": 1.1378943637008153e-05,
|
| 339 |
+
"loss": 0.07,
|
| 340 |
+
"step": 25000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 4.52,
|
| 344 |
+
"learning_rate": 9.606522509748318e-06,
|
| 345 |
+
"loss": 0.071,
|
| 346 |
+
"step": 25500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 4.61,
|
| 350 |
+
"learning_rate": 7.834101382488479e-06,
|
| 351 |
+
"loss": 0.0713,
|
| 352 |
+
"step": 26000
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 4.7,
|
| 356 |
+
"learning_rate": 6.061680255228642e-06,
|
| 357 |
+
"loss": 0.0707,
|
| 358 |
+
"step": 26500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 4.79,
|
| 362 |
+
"learning_rate": 4.289259127968805e-06,
|
| 363 |
+
"loss": 0.0751,
|
| 364 |
+
"step": 27000
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 4.87,
|
| 368 |
+
"learning_rate": 2.5168380007089687e-06,
|
| 369 |
+
"loss": 0.0696,
|
| 370 |
+
"step": 27500
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 4.96,
|
| 374 |
+
"learning_rate": 7.444168734491315e-07,
|
| 375 |
+
"loss": 0.0698,
|
| 376 |
+
"step": 28000
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 5.0,
|
| 380 |
+
"eval_loss": 0.1071661189198494,
|
| 381 |
+
"eval_runtime": 83.1775,
|
| 382 |
+
"eval_samples_per_second": 33.915,
|
| 383 |
+
"eval_steps_per_second": 8.488,
|
| 384 |
+
"step": 28210
|
| 385 |
+
}
|
| 386 |
+
],
|
| 387 |
+
"max_steps": 28210,
|
| 388 |
+
"num_train_epochs": 5,
|
| 389 |
+
"total_flos": 5.89605470208e+16,
|
| 390 |
+
"trial_name": null,
|
| 391 |
+
"trial_params": null
|
| 392 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e00836b179c13b91a569353ea2df52bb750bf3fbca32cfd46068da0e8378bc75
|
| 3 |
+
size 3387
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|