Commit
·
8ffa32c
1
Parent(s):
8e7e7cf
initial version (14) crawler 50e
Browse files- config.json +27 -0
- merges.txt +0 -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 +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- trainer_state.json +688 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.28.1",
|
| 24 |
+
"type_vocab_size": 1,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 50265
|
| 27 |
+
}
|
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 sha256:3d055aaf8019ae97cb747d57d1f1406dcdbea641658c099e9eee1f9a6fc9e415
|
| 3 |
+
size 997698309
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ff535386dcb7fcfaf04d6b5ef1bfca70090565bd49efd165b899b9d740e9806
|
| 3 |
+
size 498863417
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23c1900744d438376f402dc892ac28aad6c08c3d5a9a7035a5c18d3a2a06052a
|
| 3 |
+
size 14575
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35b7c99bc408ccfd0f83d4f99b185ad6437f6b4a9314b0a7a405ffcf7d69fc72
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60994a7e28a75d576312c32259242afc09b2561c1c6dc72ef0509e007e78bba1
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"cls_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"mask_token": "<mask>",
|
| 9 |
+
"model_max_length": 512,
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"sep_token": "</s>",
|
| 12 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 13 |
+
"trim_offsets": true,
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,688 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.012279748916626,
|
| 3 |
+
"best_model_checkpoint": "./output_c/checkpoint-824976",
|
| 4 |
+
"epoch": 48.0,
|
| 5 |
+
"global_step": 824976,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"learning_rate": 1.960020946063886e-05,
|
| 13 |
+
"loss": 3.5114,
|
| 14 |
+
"step": 17186
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_loss": 2.5249948501586914,
|
| 19 |
+
"eval_runtime": 71.153,
|
| 20 |
+
"eval_samples_per_second": 965.735,
|
| 21 |
+
"eval_steps_per_second": 30.188,
|
| 22 |
+
"step": 17187
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 2.0,
|
| 26 |
+
"learning_rate": 1.920034910106476e-05,
|
| 27 |
+
"loss": 2.4281,
|
| 28 |
+
"step": 34372
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"eval_loss": 2.0742549896240234,
|
| 33 |
+
"eval_runtime": 71.0702,
|
| 34 |
+
"eval_samples_per_second": 966.861,
|
| 35 |
+
"eval_steps_per_second": 30.224,
|
| 36 |
+
"step": 34374
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 3.0,
|
| 40 |
+
"learning_rate": 1.8800535288299298e-05,
|
| 41 |
+
"loss": 2.0989,
|
| 42 |
+
"step": 51558
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.0,
|
| 46 |
+
"eval_loss": 1.8547435998916626,
|
| 47 |
+
"eval_runtime": 71.5379,
|
| 48 |
+
"eval_samples_per_second": 960.54,
|
| 49 |
+
"eval_steps_per_second": 30.026,
|
| 50 |
+
"step": 51561
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.0,
|
| 54 |
+
"learning_rate": 1.8400698202129518e-05,
|
| 55 |
+
"loss": 1.9144,
|
| 56 |
+
"step": 68744
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.0,
|
| 60 |
+
"eval_loss": 1.7082182168960571,
|
| 61 |
+
"eval_runtime": 71.3486,
|
| 62 |
+
"eval_samples_per_second": 963.089,
|
| 63 |
+
"eval_steps_per_second": 30.106,
|
| 64 |
+
"step": 68748
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 5.0,
|
| 68 |
+
"learning_rate": 1.8000861115959738e-05,
|
| 69 |
+
"loss": 1.7926,
|
| 70 |
+
"step": 85930
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 5.0,
|
| 74 |
+
"eval_loss": 1.614298701286316,
|
| 75 |
+
"eval_runtime": 72.4304,
|
| 76 |
+
"eval_samples_per_second": 948.703,
|
| 77 |
+
"eval_steps_per_second": 29.656,
|
| 78 |
+
"step": 85935
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 6.0,
|
| 82 |
+
"learning_rate": 1.7601047303194276e-05,
|
| 83 |
+
"loss": 1.7014,
|
| 84 |
+
"step": 103116
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 6.0,
|
| 88 |
+
"eval_loss": 1.5449920892715454,
|
| 89 |
+
"eval_runtime": 71.3467,
|
| 90 |
+
"eval_samples_per_second": 963.114,
|
| 91 |
+
"eval_steps_per_second": 30.107,
|
| 92 |
+
"step": 103122
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 7.0,
|
| 96 |
+
"learning_rate": 1.7201210217024496e-05,
|
| 97 |
+
"loss": 1.6306,
|
| 98 |
+
"step": 120302
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 7.0,
|
| 102 |
+
"eval_loss": 1.4825724363327026,
|
| 103 |
+
"eval_runtime": 71.2883,
|
| 104 |
+
"eval_samples_per_second": 963.903,
|
| 105 |
+
"eval_steps_per_second": 30.131,
|
| 106 |
+
"step": 120309
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 8.0,
|
| 110 |
+
"learning_rate": 1.6801373130854716e-05,
|
| 111 |
+
"loss": 1.5745,
|
| 112 |
+
"step": 137488
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 8.0,
|
| 116 |
+
"eval_loss": 1.4376918077468872,
|
| 117 |
+
"eval_runtime": 72.4942,
|
| 118 |
+
"eval_samples_per_second": 947.869,
|
| 119 |
+
"eval_steps_per_second": 29.63,
|
| 120 |
+
"step": 137496
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 9.0,
|
| 124 |
+
"learning_rate": 1.6401559318089254e-05,
|
| 125 |
+
"loss": 1.5262,
|
| 126 |
+
"step": 154674
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 9.0,
|
| 130 |
+
"eval_loss": 1.3938175439834595,
|
| 131 |
+
"eval_runtime": 71.2189,
|
| 132 |
+
"eval_samples_per_second": 964.842,
|
| 133 |
+
"eval_steps_per_second": 30.161,
|
| 134 |
+
"step": 154683
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 10.0,
|
| 138 |
+
"learning_rate": 1.6001722231919474e-05,
|
| 139 |
+
"loss": 1.4839,
|
| 140 |
+
"step": 171860
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 10.0,
|
| 144 |
+
"eval_loss": 1.363573431968689,
|
| 145 |
+
"eval_runtime": 71.173,
|
| 146 |
+
"eval_samples_per_second": 965.465,
|
| 147 |
+
"eval_steps_per_second": 30.18,
|
| 148 |
+
"step": 171870
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 11.0,
|
| 152 |
+
"learning_rate": 1.5601908419154012e-05,
|
| 153 |
+
"loss": 1.4505,
|
| 154 |
+
"step": 189046
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 11.0,
|
| 158 |
+
"eval_loss": 1.3312129974365234,
|
| 159 |
+
"eval_runtime": 71.256,
|
| 160 |
+
"eval_samples_per_second": 964.339,
|
| 161 |
+
"eval_steps_per_second": 30.145,
|
| 162 |
+
"step": 189057
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 12.0,
|
| 166 |
+
"learning_rate": 1.5202071332984234e-05,
|
| 167 |
+
"loss": 1.4187,
|
| 168 |
+
"step": 206232
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 12.0,
|
| 172 |
+
"eval_loss": 1.3099381923675537,
|
| 173 |
+
"eval_runtime": 71.1495,
|
| 174 |
+
"eval_samples_per_second": 965.783,
|
| 175 |
+
"eval_steps_per_second": 30.19,
|
| 176 |
+
"step": 206244
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 13.0,
|
| 180 |
+
"learning_rate": 1.480225752021877e-05,
|
| 181 |
+
"loss": 1.39,
|
| 182 |
+
"step": 223418
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 13.0,
|
| 186 |
+
"eval_loss": 1.2823187112808228,
|
| 187 |
+
"eval_runtime": 69.4163,
|
| 188 |
+
"eval_samples_per_second": 989.898,
|
| 189 |
+
"eval_steps_per_second": 30.944,
|
| 190 |
+
"step": 223431
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 14.0,
|
| 194 |
+
"learning_rate": 1.4402420434048992e-05,
|
| 195 |
+
"loss": 1.3651,
|
| 196 |
+
"step": 240604
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 14.0,
|
| 200 |
+
"eval_loss": 1.2610409259796143,
|
| 201 |
+
"eval_runtime": 69.462,
|
| 202 |
+
"eval_samples_per_second": 989.246,
|
| 203 |
+
"eval_steps_per_second": 30.923,
|
| 204 |
+
"step": 240618
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 15.0,
|
| 208 |
+
"learning_rate": 1.4002583347879212e-05,
|
| 209 |
+
"loss": 1.3436,
|
| 210 |
+
"step": 257790
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 15.0,
|
| 214 |
+
"eval_loss": 1.2433568239212036,
|
| 215 |
+
"eval_runtime": 69.4357,
|
| 216 |
+
"eval_samples_per_second": 989.621,
|
| 217 |
+
"eval_steps_per_second": 30.935,
|
| 218 |
+
"step": 257805
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 16.0,
|
| 222 |
+
"learning_rate": 1.3602722988305115e-05,
|
| 223 |
+
"loss": 1.3245,
|
| 224 |
+
"step": 274976
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 16.0,
|
| 228 |
+
"eval_loss": 1.2258530855178833,
|
| 229 |
+
"eval_runtime": 69.4442,
|
| 230 |
+
"eval_samples_per_second": 989.499,
|
| 231 |
+
"eval_steps_per_second": 30.931,
|
| 232 |
+
"step": 274992
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 17.0,
|
| 236 |
+
"learning_rate": 1.3202885902135337e-05,
|
| 237 |
+
"loss": 1.305,
|
| 238 |
+
"step": 292162
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 17.0,
|
| 242 |
+
"eval_loss": 1.2092918157577515,
|
| 243 |
+
"eval_runtime": 69.4339,
|
| 244 |
+
"eval_samples_per_second": 989.646,
|
| 245 |
+
"eval_steps_per_second": 30.936,
|
| 246 |
+
"step": 292179
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 18.0,
|
| 250 |
+
"learning_rate": 1.2803072089369875e-05,
|
| 251 |
+
"loss": 1.2878,
|
| 252 |
+
"step": 309348
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 18.0,
|
| 256 |
+
"eval_loss": 1.1935821771621704,
|
| 257 |
+
"eval_runtime": 69.4288,
|
| 258 |
+
"eval_samples_per_second": 989.72,
|
| 259 |
+
"eval_steps_per_second": 30.938,
|
| 260 |
+
"step": 309366
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 19.0,
|
| 264 |
+
"learning_rate": 1.2403304823413045e-05,
|
| 265 |
+
"loss": 1.2716,
|
| 266 |
+
"step": 326534
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 19.0,
|
| 270 |
+
"eval_loss": 1.1804686784744263,
|
| 271 |
+
"eval_runtime": 69.4238,
|
| 272 |
+
"eval_samples_per_second": 989.791,
|
| 273 |
+
"eval_steps_per_second": 30.94,
|
| 274 |
+
"step": 326553
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 20.0,
|
| 278 |
+
"learning_rate": 1.2003421190434631e-05,
|
| 279 |
+
"loss": 1.2577,
|
| 280 |
+
"step": 343720
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 20.0,
|
| 284 |
+
"eval_loss": 1.170041799545288,
|
| 285 |
+
"eval_runtime": 69.4213,
|
| 286 |
+
"eval_samples_per_second": 989.826,
|
| 287 |
+
"eval_steps_per_second": 30.942,
|
| 288 |
+
"step": 343740
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 21.0,
|
| 292 |
+
"learning_rate": 1.1603584104264853e-05,
|
| 293 |
+
"loss": 1.2451,
|
| 294 |
+
"step": 360906
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 21.0,
|
| 298 |
+
"eval_loss": 1.1530039310455322,
|
| 299 |
+
"eval_runtime": 69.5559,
|
| 300 |
+
"eval_samples_per_second": 987.911,
|
| 301 |
+
"eval_steps_per_second": 30.882,
|
| 302 |
+
"step": 360927
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 22.0,
|
| 306 |
+
"learning_rate": 1.1203747018095073e-05,
|
| 307 |
+
"loss": 1.2312,
|
| 308 |
+
"step": 378092
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 22.0,
|
| 312 |
+
"eval_loss": 1.1468385457992554,
|
| 313 |
+
"eval_runtime": 70.6551,
|
| 314 |
+
"eval_samples_per_second": 972.542,
|
| 315 |
+
"eval_steps_per_second": 30.401,
|
| 316 |
+
"step": 378114
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 23.0,
|
| 320 |
+
"learning_rate": 1.0803933205329611e-05,
|
| 321 |
+
"loss": 1.2189,
|
| 322 |
+
"step": 395278
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 23.0,
|
| 326 |
+
"eval_loss": 1.1345593929290771,
|
| 327 |
+
"eval_runtime": 69.4572,
|
| 328 |
+
"eval_samples_per_second": 989.315,
|
| 329 |
+
"eval_steps_per_second": 30.926,
|
| 330 |
+
"step": 395301
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 24.0,
|
| 334 |
+
"learning_rate": 1.040411939256415e-05,
|
| 335 |
+
"loss": 1.2081,
|
| 336 |
+
"step": 412464
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 24.0,
|
| 340 |
+
"eval_loss": 1.1272401809692383,
|
| 341 |
+
"eval_runtime": 69.4251,
|
| 342 |
+
"eval_samples_per_second": 989.772,
|
| 343 |
+
"eval_steps_per_second": 30.94,
|
| 344 |
+
"step": 412488
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 25.0,
|
| 348 |
+
"learning_rate": 1.0004305579798686e-05,
|
| 349 |
+
"loss": 1.1972,
|
| 350 |
+
"step": 429650
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 25.0,
|
| 354 |
+
"eval_loss": 1.1170649528503418,
|
| 355 |
+
"eval_runtime": 69.594,
|
| 356 |
+
"eval_samples_per_second": 987.37,
|
| 357 |
+
"eval_steps_per_second": 30.865,
|
| 358 |
+
"step": 429675
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 26.0,
|
| 362 |
+
"learning_rate": 9.604491767033224e-06,
|
| 363 |
+
"loss": 1.187,
|
| 364 |
+
"step": 446836
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 26.0,
|
| 368 |
+
"eval_loss": 1.1084502935409546,
|
| 369 |
+
"eval_runtime": 69.4386,
|
| 370 |
+
"eval_samples_per_second": 989.579,
|
| 371 |
+
"eval_steps_per_second": 30.934,
|
| 372 |
+
"step": 446862
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 27.0,
|
| 376 |
+
"learning_rate": 9.204654680863444e-06,
|
| 377 |
+
"loss": 1.1777,
|
| 378 |
+
"step": 464022
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 27.0,
|
| 382 |
+
"eval_loss": 1.100696086883545,
|
| 383 |
+
"eval_runtime": 69.6537,
|
| 384 |
+
"eval_samples_per_second": 986.524,
|
| 385 |
+
"eval_steps_per_second": 30.838,
|
| 386 |
+
"step": 464049
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 28.0,
|
| 390 |
+
"learning_rate": 8.804840868097981e-06,
|
| 391 |
+
"loss": 1.1691,
|
| 392 |
+
"step": 481208
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 28.0,
|
| 396 |
+
"eval_loss": 1.0973334312438965,
|
| 397 |
+
"eval_runtime": 69.4707,
|
| 398 |
+
"eval_samples_per_second": 989.122,
|
| 399 |
+
"eval_steps_per_second": 30.92,
|
| 400 |
+
"step": 481236
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 29.0,
|
| 404 |
+
"learning_rate": 8.40502705533252e-06,
|
| 405 |
+
"loss": 1.1611,
|
| 406 |
+
"step": 498394
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 29.0,
|
| 410 |
+
"eval_loss": 1.0852068662643433,
|
| 411 |
+
"eval_runtime": 69.6222,
|
| 412 |
+
"eval_samples_per_second": 986.969,
|
| 413 |
+
"eval_steps_per_second": 30.852,
|
| 414 |
+
"step": 498423
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 30.0,
|
| 418 |
+
"learning_rate": 8.005189969162739e-06,
|
| 419 |
+
"loss": 1.1534,
|
| 420 |
+
"step": 515580
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 30.0,
|
| 424 |
+
"eval_loss": 1.082985520362854,
|
| 425 |
+
"eval_runtime": 69.4202,
|
| 426 |
+
"eval_samples_per_second": 989.842,
|
| 427 |
+
"eval_steps_per_second": 30.942,
|
| 428 |
+
"step": 515610
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 31.0,
|
| 432 |
+
"learning_rate": 7.6053761563972775e-06,
|
| 433 |
+
"loss": 1.1453,
|
| 434 |
+
"step": 532766
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 31.0,
|
| 438 |
+
"eval_loss": 1.0722641944885254,
|
| 439 |
+
"eval_runtime": 69.4459,
|
| 440 |
+
"eval_samples_per_second": 989.476,
|
| 441 |
+
"eval_steps_per_second": 30.931,
|
| 442 |
+
"step": 532797
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 32.0,
|
| 446 |
+
"learning_rate": 7.205539070227498e-06,
|
| 447 |
+
"loss": 1.1387,
|
| 448 |
+
"step": 549952
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 32.0,
|
| 452 |
+
"eval_loss": 1.0714243650436401,
|
| 453 |
+
"eval_runtime": 69.4689,
|
| 454 |
+
"eval_samples_per_second": 989.147,
|
| 455 |
+
"eval_steps_per_second": 30.92,
|
| 456 |
+
"step": 549984
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 33.0,
|
| 460 |
+
"learning_rate": 6.805678710653402e-06,
|
| 461 |
+
"loss": 1.1304,
|
| 462 |
+
"step": 567138
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 33.0,
|
| 466 |
+
"eval_loss": 1.0586808919906616,
|
| 467 |
+
"eval_runtime": 69.5198,
|
| 468 |
+
"eval_samples_per_second": 988.423,
|
| 469 |
+
"eval_steps_per_second": 30.898,
|
| 470 |
+
"step": 567171
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 34.0,
|
| 474 |
+
"learning_rate": 6.405864897887939e-06,
|
| 475 |
+
"loss": 1.1243,
|
| 476 |
+
"step": 584324
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 34.0,
|
| 480 |
+
"eval_loss": 1.0512875318527222,
|
| 481 |
+
"eval_runtime": 69.4412,
|
| 482 |
+
"eval_samples_per_second": 989.542,
|
| 483 |
+
"eval_steps_per_second": 30.933,
|
| 484 |
+
"step": 584358
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 35.0,
|
| 488 |
+
"learning_rate": 6.006051085122476e-06,
|
| 489 |
+
"loss": 1.1192,
|
| 490 |
+
"step": 601510
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 35.0,
|
| 494 |
+
"eval_loss": 1.0537949800491333,
|
| 495 |
+
"eval_runtime": 69.726,
|
| 496 |
+
"eval_samples_per_second": 985.5,
|
| 497 |
+
"eval_steps_per_second": 30.806,
|
| 498 |
+
"step": 601545
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 36.0,
|
| 502 |
+
"learning_rate": 5.606213998952698e-06,
|
| 503 |
+
"loss": 1.1126,
|
| 504 |
+
"step": 618696
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 36.0,
|
| 508 |
+
"eval_loss": 1.049811840057373,
|
| 509 |
+
"eval_runtime": 69.9084,
|
| 510 |
+
"eval_samples_per_second": 982.929,
|
| 511 |
+
"eval_steps_per_second": 30.726,
|
| 512 |
+
"step": 618732
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 37.0,
|
| 516 |
+
"learning_rate": 5.206446732995869e-06,
|
| 517 |
+
"loss": 1.1083,
|
| 518 |
+
"step": 635882
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 37.0,
|
| 522 |
+
"eval_loss": 1.0433541536331177,
|
| 523 |
+
"eval_runtime": 69.7631,
|
| 524 |
+
"eval_samples_per_second": 984.977,
|
| 525 |
+
"eval_steps_per_second": 30.79,
|
| 526 |
+
"step": 635919
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 38.0,
|
| 530 |
+
"learning_rate": 4.8066096468260895e-06,
|
| 531 |
+
"loss": 1.1037,
|
| 532 |
+
"step": 653068
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 38.0,
|
| 536 |
+
"eval_loss": 1.0362184047698975,
|
| 537 |
+
"eval_runtime": 69.5998,
|
| 538 |
+
"eval_samples_per_second": 987.287,
|
| 539 |
+
"eval_steps_per_second": 30.862,
|
| 540 |
+
"step": 653106
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 39.0,
|
| 544 |
+
"learning_rate": 4.4067492872519926e-06,
|
| 545 |
+
"loss": 1.0997,
|
| 546 |
+
"step": 670254
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 39.0,
|
| 550 |
+
"eval_loss": 1.037041187286377,
|
| 551 |
+
"eval_runtime": 69.6134,
|
| 552 |
+
"eval_samples_per_second": 987.095,
|
| 553 |
+
"eval_steps_per_second": 30.856,
|
| 554 |
+
"step": 670293
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 40.0,
|
| 558 |
+
"learning_rate": 4.006935474486531e-06,
|
| 559 |
+
"loss": 1.0952,
|
| 560 |
+
"step": 687440
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 40.0,
|
| 564 |
+
"eval_loss": 1.0285437107086182,
|
| 565 |
+
"eval_runtime": 69.7372,
|
| 566 |
+
"eval_samples_per_second": 985.341,
|
| 567 |
+
"eval_steps_per_second": 30.801,
|
| 568 |
+
"step": 687480
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 41.0,
|
| 572 |
+
"learning_rate": 3.6071216617210684e-06,
|
| 573 |
+
"loss": 1.0891,
|
| 574 |
+
"step": 704626
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 41.0,
|
| 578 |
+
"eval_loss": 1.0275565385818481,
|
| 579 |
+
"eval_runtime": 69.6129,
|
| 580 |
+
"eval_samples_per_second": 987.101,
|
| 581 |
+
"eval_steps_per_second": 30.856,
|
| 582 |
+
"step": 704667
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 42.0,
|
| 586 |
+
"learning_rate": 3.207261302146972e-06,
|
| 587 |
+
"loss": 1.086,
|
| 588 |
+
"step": 721812
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 42.0,
|
| 592 |
+
"eval_loss": 1.0269238948822021,
|
| 593 |
+
"eval_runtime": 69.6407,
|
| 594 |
+
"eval_samples_per_second": 986.708,
|
| 595 |
+
"eval_steps_per_second": 30.844,
|
| 596 |
+
"step": 721854
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 43.0,
|
| 600 |
+
"learning_rate": 2.8074707627858266e-06,
|
| 601 |
+
"loss": 1.0831,
|
| 602 |
+
"step": 738998
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 43.0,
|
| 606 |
+
"eval_loss": 1.0213665962219238,
|
| 607 |
+
"eval_runtime": 69.6166,
|
| 608 |
+
"eval_samples_per_second": 987.049,
|
| 609 |
+
"eval_steps_per_second": 30.855,
|
| 610 |
+
"step": 739041
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 44.0,
|
| 614 |
+
"learning_rate": 2.4076569500203645e-06,
|
| 615 |
+
"loss": 1.0791,
|
| 616 |
+
"step": 756184
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 44.0,
|
| 620 |
+
"eval_loss": 1.020618200302124,
|
| 621 |
+
"eval_runtime": 69.8024,
|
| 622 |
+
"eval_samples_per_second": 984.422,
|
| 623 |
+
"eval_steps_per_second": 30.773,
|
| 624 |
+
"step": 756228
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 45.0,
|
| 628 |
+
"learning_rate": 2.007819863850585e-06,
|
| 629 |
+
"loss": 1.077,
|
| 630 |
+
"step": 773370
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 45.0,
|
| 634 |
+
"eval_loss": 1.0169862508773804,
|
| 635 |
+
"eval_runtime": 69.6571,
|
| 636 |
+
"eval_samples_per_second": 986.475,
|
| 637 |
+
"eval_steps_per_second": 30.837,
|
| 638 |
+
"step": 773415
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 46.0,
|
| 642 |
+
"learning_rate": 1.608052597893757e-06,
|
| 643 |
+
"loss": 1.0739,
|
| 644 |
+
"step": 790556
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 46.0,
|
| 648 |
+
"eval_loss": 1.0156688690185547,
|
| 649 |
+
"eval_runtime": 69.7503,
|
| 650 |
+
"eval_samples_per_second": 985.157,
|
| 651 |
+
"eval_steps_per_second": 30.796,
|
| 652 |
+
"step": 790602
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 47.0,
|
| 656 |
+
"learning_rate": 1.2081922383196604e-06,
|
| 657 |
+
"loss": 1.0709,
|
| 658 |
+
"step": 807742
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 47.0,
|
| 662 |
+
"eval_loss": 1.0143157243728638,
|
| 663 |
+
"eval_runtime": 69.6201,
|
| 664 |
+
"eval_samples_per_second": 986.999,
|
| 665 |
+
"eval_steps_per_second": 30.853,
|
| 666 |
+
"step": 807789
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 48.0,
|
| 670 |
+
"learning_rate": 8.084249723628325e-07,
|
| 671 |
+
"loss": 1.0693,
|
| 672 |
+
"step": 824928
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 48.0,
|
| 676 |
+
"eval_loss": 1.012279748916626,
|
| 677 |
+
"eval_runtime": 69.6307,
|
| 678 |
+
"eval_samples_per_second": 986.849,
|
| 679 |
+
"eval_steps_per_second": 30.848,
|
| 680 |
+
"step": 824976
|
| 681 |
+
}
|
| 682 |
+
],
|
| 683 |
+
"max_steps": 859350,
|
| 684 |
+
"num_train_epochs": 50,
|
| 685 |
+
"total_flos": 1.7374699189290516e+18,
|
| 686 |
+
"trial_name": null,
|
| 687 |
+
"trial_params": null
|
| 688 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f945af00fe3c74d8f641dcaa014573093a4dcd241697dde5f347f6bb9c66d1b
|
| 3 |
+
size 3643
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|