Commit
•
ae41a95
1
Parent(s):
f5c69c6
Upload 14 files
Browse filesadd model and tokenizer
- added_tokens.json +3 -0
- config.json +39 -0
- generation_config.json +6 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- trainer_state.json +548 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 21128
|
| 3 |
+
}
|
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": 21128,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 21128,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 512,
|
| 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": "4.26.0",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 21129
|
| 39 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 21128,
|
| 4 |
+
"eos_token_id": 21128,
|
| 5 |
+
"transformers_version": "4.26.0"
|
| 6 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ec79853f0858fe90ac33227941a021cc4f1bbbcbfe5d3931db78c9e17f181bd
|
| 3 |
+
size 816643013
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:216a85ade9b9880f3914f8571cf9b05fd5213e494e7dd43f7e980b5c1f7cf32e
|
| 3 |
+
size 420916797
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d12b26084aef2f02e657466a44c88be0208e604843f9984d2d6edcfd7f02ce9
|
| 3 |
+
size 14575
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1231db49e3fa352487e4e459a5cc7b62189afa85071441604846c5c806c86339
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d773b3d7b7116e07c33947243fe4224e9e610e97cafc4b76abd601fd700ca23a
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "<|endoftext|>",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "<|endoftext|>",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": "<|endoftext|>"
|
| 9 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"do_lower_case": false,
|
| 4 |
+
"mask_token": "[MASK]",
|
| 5 |
+
"model_max_length": 512,
|
| 6 |
+
"name_or_path": "bert-base-chinese",
|
| 7 |
+
"pad_token": "[PAD]",
|
| 8 |
+
"sep_token": "[SEP]",
|
| 9 |
+
"special_tokens_map_file": null,
|
| 10 |
+
"strip_accents": null,
|
| 11 |
+
"tokenize_chinese_chars": true,
|
| 12 |
+
"tokenizer_class": "BertTokenizer",
|
| 13 |
+
"unk_token": "[UNK]"
|
| 14 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,548 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9839005449146736,
|
| 5 |
+
"global_step": 76000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 0.0004997842653586619,
|
| 13 |
+
"loss": 4.023,
|
| 14 |
+
"step": 2000
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"eval_loss": 2.9591097831726074,
|
| 19 |
+
"eval_runtime": 235.529,
|
| 20 |
+
"eval_samples_per_second": 167.083,
|
| 21 |
+
"eval_steps_per_second": 10.445,
|
| 22 |
+
"step": 2000
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.1,
|
| 26 |
+
"learning_rate": 0.0004980606215742609,
|
| 27 |
+
"loss": 2.9094,
|
| 28 |
+
"step": 4000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.1,
|
| 32 |
+
"eval_loss": 2.7322702407836914,
|
| 33 |
+
"eval_runtime": 235.6062,
|
| 34 |
+
"eval_samples_per_second": 167.029,
|
| 35 |
+
"eval_steps_per_second": 10.441,
|
| 36 |
+
"step": 4000
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.16,
|
| 40 |
+
"learning_rate": 0.0004946252280608798,
|
| 41 |
+
"loss": 2.7599,
|
| 42 |
+
"step": 6000
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.16,
|
| 46 |
+
"eval_loss": 2.633601665496826,
|
| 47 |
+
"eval_runtime": 235.5566,
|
| 48 |
+
"eval_samples_per_second": 167.064,
|
| 49 |
+
"eval_steps_per_second": 10.443,
|
| 50 |
+
"step": 6000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.21,
|
| 54 |
+
"learning_rate": 0.0004895017908540765,
|
| 55 |
+
"loss": 2.6821,
|
| 56 |
+
"step": 8000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.21,
|
| 60 |
+
"eval_loss": 2.571882724761963,
|
| 61 |
+
"eval_runtime": 235.5446,
|
| 62 |
+
"eval_samples_per_second": 167.072,
|
| 63 |
+
"eval_steps_per_second": 10.444,
|
| 64 |
+
"step": 8000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.26,
|
| 68 |
+
"learning_rate": 0.0004827332514022428,
|
| 69 |
+
"loss": 2.6301,
|
| 70 |
+
"step": 10000
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.26,
|
| 74 |
+
"eval_loss": 2.5301053524017334,
|
| 75 |
+
"eval_runtime": 236.1109,
|
| 76 |
+
"eval_samples_per_second": 166.672,
|
| 77 |
+
"eval_steps_per_second": 10.419,
|
| 78 |
+
"step": 10000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.31,
|
| 82 |
+
"learning_rate": 0.0004743573557450783,
|
| 83 |
+
"loss": 2.5918,
|
| 84 |
+
"step": 12000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.31,
|
| 88 |
+
"eval_loss": 2.4954473972320557,
|
| 89 |
+
"eval_runtime": 235.5537,
|
| 90 |
+
"eval_samples_per_second": 167.066,
|
| 91 |
+
"eval_steps_per_second": 10.443,
|
| 92 |
+
"step": 12000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.37,
|
| 96 |
+
"learning_rate": 0.00046442948254696206,
|
| 97 |
+
"loss": 2.5616,
|
| 98 |
+
"step": 14000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.37,
|
| 102 |
+
"eval_loss": 2.4691474437713623,
|
| 103 |
+
"eval_runtime": 235.6133,
|
| 104 |
+
"eval_samples_per_second": 167.024,
|
| 105 |
+
"eval_steps_per_second": 10.441,
|
| 106 |
+
"step": 14000
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.42,
|
| 110 |
+
"learning_rate": 0.00045302193229931784,
|
| 111 |
+
"loss": 2.5361,
|
| 112 |
+
"step": 16000
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.42,
|
| 116 |
+
"eval_loss": 2.4461960792541504,
|
| 117 |
+
"eval_runtime": 235.5392,
|
| 118 |
+
"eval_samples_per_second": 167.076,
|
| 119 |
+
"eval_steps_per_second": 10.444,
|
| 120 |
+
"step": 16000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.47,
|
| 124 |
+
"learning_rate": 0.00044023364212028847,
|
| 125 |
+
"loss": 2.5158,
|
| 126 |
+
"step": 18000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.47,
|
| 130 |
+
"eval_loss": 2.4347801208496094,
|
| 131 |
+
"eval_runtime": 235.4954,
|
| 132 |
+
"eval_samples_per_second": 167.107,
|
| 133 |
+
"eval_steps_per_second": 10.446,
|
| 134 |
+
"step": 18000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.52,
|
| 138 |
+
"learning_rate": 0.0004261144576270032,
|
| 139 |
+
"loss": 2.4993,
|
| 140 |
+
"step": 20000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.52,
|
| 144 |
+
"eval_loss": 2.412471294403076,
|
| 145 |
+
"eval_runtime": 235.4551,
|
| 146 |
+
"eval_samples_per_second": 167.136,
|
| 147 |
+
"eval_steps_per_second": 10.448,
|
| 148 |
+
"step": 20000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.57,
|
| 152 |
+
"learning_rate": 0.00041077999005815623,
|
| 153 |
+
"loss": 2.4848,
|
| 154 |
+
"step": 22000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.57,
|
| 158 |
+
"eval_loss": 2.3976333141326904,
|
| 159 |
+
"eval_runtime": 236.1174,
|
| 160 |
+
"eval_samples_per_second": 166.667,
|
| 161 |
+
"eval_steps_per_second": 10.419,
|
| 162 |
+
"step": 22000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.63,
|
| 166 |
+
"learning_rate": 0.00039433605536526187,
|
| 167 |
+
"loss": 2.4689,
|
| 168 |
+
"step": 24000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.63,
|
| 172 |
+
"eval_loss": 2.3828279972076416,
|
| 173 |
+
"eval_runtime": 235.5611,
|
| 174 |
+
"eval_samples_per_second": 167.061,
|
| 175 |
+
"eval_steps_per_second": 10.443,
|
| 176 |
+
"step": 24000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.68,
|
| 180 |
+
"learning_rate": 0.00037690507447365334,
|
| 181 |
+
"loss": 2.4562,
|
| 182 |
+
"step": 26000
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.68,
|
| 186 |
+
"eval_loss": 2.3714354038238525,
|
| 187 |
+
"eval_runtime": 237.177,
|
| 188 |
+
"eval_samples_per_second": 165.923,
|
| 189 |
+
"eval_steps_per_second": 10.372,
|
| 190 |
+
"step": 26000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.73,
|
| 194 |
+
"learning_rate": 0.00035860861171489625,
|
| 195 |
+
"loss": 2.4415,
|
| 196 |
+
"step": 28000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.73,
|
| 200 |
+
"eval_loss": 2.3587660789489746,
|
| 201 |
+
"eval_runtime": 235.9789,
|
| 202 |
+
"eval_samples_per_second": 166.765,
|
| 203 |
+
"eval_steps_per_second": 10.425,
|
| 204 |
+
"step": 28000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.78,
|
| 208 |
+
"learning_rate": 0.0003395447945183574,
|
| 209 |
+
"loss": 2.4321,
|
| 210 |
+
"step": 30000
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.78,
|
| 214 |
+
"eval_loss": 2.3464348316192627,
|
| 215 |
+
"eval_runtime": 235.9733,
|
| 216 |
+
"eval_samples_per_second": 166.769,
|
| 217 |
+
"eval_steps_per_second": 10.425,
|
| 218 |
+
"step": 30000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.84,
|
| 222 |
+
"learning_rate": 0.0003198730435893789,
|
| 223 |
+
"loss": 2.4217,
|
| 224 |
+
"step": 32000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.84,
|
| 228 |
+
"eval_loss": 2.3358864784240723,
|
| 229 |
+
"eval_runtime": 235.8391,
|
| 230 |
+
"eval_samples_per_second": 166.864,
|
| 231 |
+
"eval_steps_per_second": 10.431,
|
| 232 |
+
"step": 32000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.89,
|
| 236 |
+
"learning_rate": 0.00029970943417239666,
|
| 237 |
+
"loss": 2.4062,
|
| 238 |
+
"step": 34000
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.89,
|
| 242 |
+
"eval_loss": 2.3258254528045654,
|
| 243 |
+
"eval_runtime": 235.6751,
|
| 244 |
+
"eval_samples_per_second": 166.98,
|
| 245 |
+
"eval_steps_per_second": 10.438,
|
| 246 |
+
"step": 34000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.94,
|
| 250 |
+
"learning_rate": 0.00027922343434053505,
|
| 251 |
+
"loss": 2.3968,
|
| 252 |
+
"step": 36000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.94,
|
| 256 |
+
"eval_loss": 2.3131136894226074,
|
| 257 |
+
"eval_runtime": 235.4005,
|
| 258 |
+
"eval_samples_per_second": 167.175,
|
| 259 |
+
"eval_steps_per_second": 10.45,
|
| 260 |
+
"step": 36000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.99,
|
| 264 |
+
"learning_rate": 0.000258556941398551,
|
| 265 |
+
"loss": 2.3882,
|
| 266 |
+
"step": 38000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.99,
|
| 270 |
+
"eval_loss": 2.3022758960723877,
|
| 271 |
+
"eval_runtime": 234.8551,
|
| 272 |
+
"eval_samples_per_second": 167.563,
|
| 273 |
+
"eval_steps_per_second": 10.475,
|
| 274 |
+
"step": 38000
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.04,
|
| 278 |
+
"learning_rate": 0.00023779013959131367,
|
| 279 |
+
"loss": 2.3708,
|
| 280 |
+
"step": 40000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.04,
|
| 284 |
+
"eval_loss": 2.292479991912842,
|
| 285 |
+
"eval_runtime": 234.8376,
|
| 286 |
+
"eval_samples_per_second": 167.575,
|
| 287 |
+
"eval_steps_per_second": 10.475,
|
| 288 |
+
"step": 40000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.1,
|
| 292 |
+
"learning_rate": 0.00021710759229054673,
|
| 293 |
+
"loss": 2.3597,
|
| 294 |
+
"step": 42000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.1,
|
| 298 |
+
"eval_loss": 2.2818188667297363,
|
| 299 |
+
"eval_runtime": 234.9302,
|
| 300 |
+
"eval_samples_per_second": 167.509,
|
| 301 |
+
"eval_steps_per_second": 10.471,
|
| 302 |
+
"step": 42000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.15,
|
| 306 |
+
"learning_rate": 0.0001966520200317064,
|
| 307 |
+
"loss": 2.3516,
|
| 308 |
+
"step": 44000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.15,
|
| 312 |
+
"eval_loss": 2.271631956100464,
|
| 313 |
+
"eval_runtime": 234.8493,
|
| 314 |
+
"eval_samples_per_second": 167.567,
|
| 315 |
+
"eval_steps_per_second": 10.475,
|
| 316 |
+
"step": 44000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.2,
|
| 320 |
+
"learning_rate": 0.00017656457710219216,
|
| 321 |
+
"loss": 2.3402,
|
| 322 |
+
"step": 46000
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.2,
|
| 326 |
+
"eval_loss": 2.262141466140747,
|
| 327 |
+
"eval_runtime": 234.8012,
|
| 328 |
+
"eval_samples_per_second": 167.601,
|
| 329 |
+
"eval_steps_per_second": 10.477,
|
| 330 |
+
"step": 46000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.25,
|
| 334 |
+
"learning_rate": 0.0001569838775019702,
|
| 335 |
+
"loss": 2.3317,
|
| 336 |
+
"step": 48000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.25,
|
| 340 |
+
"eval_loss": 2.250854730606079,
|
| 341 |
+
"eval_runtime": 234.8456,
|
| 342 |
+
"eval_samples_per_second": 167.57,
|
| 343 |
+
"eval_steps_per_second": 10.475,
|
| 344 |
+
"step": 48000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.31,
|
| 348 |
+
"learning_rate": 0.00013804503843352594,
|
| 349 |
+
"loss": 2.3208,
|
| 350 |
+
"step": 50000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.31,
|
| 354 |
+
"eval_loss": 2.2419745922088623,
|
| 355 |
+
"eval_runtime": 235.4331,
|
| 356 |
+
"eval_samples_per_second": 167.151,
|
| 357 |
+
"eval_steps_per_second": 10.449,
|
| 358 |
+
"step": 50000
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.36,
|
| 362 |
+
"learning_rate": 0.00011988761690506509,
|
| 363 |
+
"loss": 2.3129,
|
| 364 |
+
"step": 52000
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 1.36,
|
| 368 |
+
"eval_loss": 2.232053518295288,
|
| 369 |
+
"eval_runtime": 235.1368,
|
| 370 |
+
"eval_samples_per_second": 167.362,
|
| 371 |
+
"eval_steps_per_second": 10.462,
|
| 372 |
+
"step": 52000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.41,
|
| 376 |
+
"learning_rate": 0.00010262714265881779,
|
| 377 |
+
"loss": 2.3034,
|
| 378 |
+
"step": 54000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.41,
|
| 382 |
+
"eval_loss": 2.223116874694824,
|
| 383 |
+
"eval_runtime": 235.501,
|
| 384 |
+
"eval_samples_per_second": 167.103,
|
| 385 |
+
"eval_steps_per_second": 10.446,
|
| 386 |
+
"step": 54000
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.46,
|
| 390 |
+
"learning_rate": 8.638260310471869e-05,
|
| 391 |
+
"loss": 2.2944,
|
| 392 |
+
"step": 56000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.46,
|
| 396 |
+
"eval_loss": 2.215869188308716,
|
| 397 |
+
"eval_runtime": 235.4682,
|
| 398 |
+
"eval_samples_per_second": 167.127,
|
| 399 |
+
"eval_steps_per_second": 10.447,
|
| 400 |
+
"step": 56000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.51,
|
| 404 |
+
"learning_rate": 7.126598216971828e-05,
|
| 405 |
+
"loss": 2.2867,
|
| 406 |
+
"step": 58000
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.51,
|
| 410 |
+
"eval_loss": 2.2056751251220703,
|
| 411 |
+
"eval_runtime": 235.5179,
|
| 412 |
+
"eval_samples_per_second": 167.091,
|
| 413 |
+
"eval_steps_per_second": 10.445,
|
| 414 |
+
"step": 58000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.57,
|
| 418 |
+
"learning_rate": 5.737486728530572e-05,
|
| 419 |
+
"loss": 2.2775,
|
| 420 |
+
"step": 60000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.57,
|
| 424 |
+
"eval_loss": 2.19879150390625,
|
| 425 |
+
"eval_runtime": 235.4838,
|
| 426 |
+
"eval_samples_per_second": 167.116,
|
| 427 |
+
"eval_steps_per_second": 10.447,
|
| 428 |
+
"step": 60000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.62,
|
| 432 |
+
"learning_rate": 4.481890186103055e-05,
|
| 433 |
+
"loss": 2.2706,
|
| 434 |
+
"step": 62000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.62,
|
| 438 |
+
"eval_loss": 2.191859006881714,
|
| 439 |
+
"eval_runtime": 235.3807,
|
| 440 |
+
"eval_samples_per_second": 167.189,
|
| 441 |
+
"eval_steps_per_second": 10.451,
|
| 442 |
+
"step": 62000
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 1.67,
|
| 446 |
+
"learning_rate": 3.36825867617602e-05,
|
| 447 |
+
"loss": 2.2653,
|
| 448 |
+
"step": 64000
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.67,
|
| 452 |
+
"eval_loss": 2.185826301574707,
|
| 453 |
+
"eval_runtime": 235.8171,
|
| 454 |
+
"eval_samples_per_second": 166.879,
|
| 455 |
+
"eval_steps_per_second": 10.432,
|
| 456 |
+
"step": 64000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.72,
|
| 460 |
+
"learning_rate": 2.4031550628330818e-05,
|
| 461 |
+
"loss": 2.2595,
|
| 462 |
+
"step": 66000
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.72,
|
| 466 |
+
"eval_loss": 2.1810295581817627,
|
| 467 |
+
"eval_runtime": 235.6965,
|
| 468 |
+
"eval_samples_per_second": 166.965,
|
| 469 |
+
"eval_steps_per_second": 10.437,
|
| 470 |
+
"step": 66000
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.78,
|
| 474 |
+
"learning_rate": 1.5934609437343344e-05,
|
| 475 |
+
"loss": 2.2546,
|
| 476 |
+
"step": 68000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.78,
|
| 480 |
+
"eval_loss": 2.1772620677948,
|
| 481 |
+
"eval_runtime": 234.5679,
|
| 482 |
+
"eval_samples_per_second": 167.768,
|
| 483 |
+
"eval_steps_per_second": 10.487,
|
| 484 |
+
"step": 68000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 1.83,
|
| 488 |
+
"learning_rate": 9.452843465689393e-06,
|
| 489 |
+
"loss": 2.2515,
|
| 490 |
+
"step": 70000
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.83,
|
| 494 |
+
"eval_loss": 2.174480676651001,
|
| 495 |
+
"eval_runtime": 234.8677,
|
| 496 |
+
"eval_samples_per_second": 167.554,
|
| 497 |
+
"eval_steps_per_second": 10.474,
|
| 498 |
+
"step": 70000
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.88,
|
| 502 |
+
"learning_rate": 4.632970471463188e-06,
|
| 503 |
+
"loss": 2.25,
|
| 504 |
+
"step": 72000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.88,
|
| 508 |
+
"eval_loss": 2.1722278594970703,
|
| 509 |
+
"eval_runtime": 234.8936,
|
| 510 |
+
"eval_samples_per_second": 167.535,
|
| 511 |
+
"eval_steps_per_second": 10.473,
|
| 512 |
+
"step": 72000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.93,
|
| 516 |
+
"learning_rate": 1.504568227717773e-06,
|
| 517 |
+
"loss": 2.2491,
|
| 518 |
+
"step": 74000
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.93,
|
| 522 |
+
"eval_loss": 2.1710853576660156,
|
| 523 |
+
"eval_runtime": 234.9822,
|
| 524 |
+
"eval_samples_per_second": 167.472,
|
| 525 |
+
"eval_steps_per_second": 10.469,
|
| 526 |
+
"step": 74000
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.98,
|
| 530 |
+
"learning_rate": 8.920279775520568e-08,
|
| 531 |
+
"loss": 2.2505,
|
| 532 |
+
"step": 76000
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 1.98,
|
| 536 |
+
"eval_loss": 2.1710739135742188,
|
| 537 |
+
"eval_runtime": 234.8578,
|
| 538 |
+
"eval_samples_per_second": 167.561,
|
| 539 |
+
"eval_steps_per_second": 10.474,
|
| 540 |
+
"step": 76000
|
| 541 |
+
}
|
| 542 |
+
],
|
| 543 |
+
"max_steps": 76616,
|
| 544 |
+
"num_train_epochs": 2,
|
| 545 |
+
"total_flos": 3.177337760907264e+18,
|
| 546 |
+
"trial_name": null,
|
| 547 |
+
"trial_params": null
|
| 548 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59194af74faab562c30fcc55278599f9df4210f390441d92720ecda313a87ef0
|
| 3 |
+
size 3451
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|