Commit
·
287b37a
1
Parent(s):
7e110c4
electra_google/electra-small-generator_b32_50e
Browse files- config.json +30 -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 +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- trainer_state.json +702 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/electra-small-generator",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ElectraForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"embedding_size": 128,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 256,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 1024,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "electra",
|
| 17 |
+
"num_attention_heads": 4,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"summary_activation": "gelu",
|
| 22 |
+
"summary_last_dropout": 0.1,
|
| 23 |
+
"summary_type": "first",
|
| 24 |
+
"summary_use_proj": true,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.28.1",
|
| 27 |
+
"type_vocab_size": 2,
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 30522
|
| 30 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a41f3b11c84d7da4a9743ce8310e19901dc457aa737f4fc4e0dbeafe07c03c7
|
| 3 |
+
size 108493381
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39e43fb05f5efb970cf90a967a7751e994326d5f2685efd9a3b1e85036634221
|
| 3 |
+
size 54261249
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cea533a89b2544a3dd1251891c69b80a38083ac6e4a328a74fb9dcf37f83a3d6
|
| 3 |
+
size 14575
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50aea151c5f20e32891d48e17d25cb58a62ab96c29ad66fed893801a78352bd2
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a68a014ef7352c80af8f4bee88886be9fab2aaa62e4867fa274fd40142f3442
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"model_max_length": 512,
|
| 7 |
+
"pad_token": "[PAD]",
|
| 8 |
+
"sep_token": "[SEP]",
|
| 9 |
+
"strip_accents": null,
|
| 10 |
+
"tokenize_chinese_chars": true,
|
| 11 |
+
"tokenizer_class": "ElectraTokenizer",
|
| 12 |
+
"unk_token": "[UNK]"
|
| 13 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,702 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.3500477075576782,
|
| 3 |
+
"best_model_checkpoint": "./output_c/checkpoint-842163",
|
| 4 |
+
"epoch": 49.0,
|
| 5 |
+
"global_step": 842163,
|
| 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": 2.4473,
|
| 14 |
+
"step": 17186
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_loss": 2.0222833156585693,
|
| 19 |
+
"eval_runtime": 62.1889,
|
| 20 |
+
"eval_samples_per_second": 1104.941,
|
| 21 |
+
"eval_steps_per_second": 34.54,
|
| 22 |
+
"step": 17187
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 2.0,
|
| 26 |
+
"learning_rate": 1.920032582766044e-05,
|
| 27 |
+
"loss": 2.0795,
|
| 28 |
+
"step": 34372
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"eval_loss": 1.871239185333252,
|
| 33 |
+
"eval_runtime": 58.1601,
|
| 34 |
+
"eval_samples_per_second": 1181.481,
|
| 35 |
+
"eval_steps_per_second": 36.933,
|
| 36 |
+
"step": 34374
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 3.0,
|
| 40 |
+
"learning_rate": 1.880051201489498e-05,
|
| 41 |
+
"loss": 1.958,
|
| 42 |
+
"step": 51558
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.0,
|
| 46 |
+
"eval_loss": 1.781246542930603,
|
| 47 |
+
"eval_runtime": 54.7184,
|
| 48 |
+
"eval_samples_per_second": 1255.793,
|
| 49 |
+
"eval_steps_per_second": 39.256,
|
| 50 |
+
"step": 51561
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.0,
|
| 54 |
+
"learning_rate": 1.8400698202129518e-05,
|
| 55 |
+
"loss": 1.883,
|
| 56 |
+
"step": 68744
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.0,
|
| 60 |
+
"eval_loss": 1.7132632732391357,
|
| 61 |
+
"eval_runtime": 53.9408,
|
| 62 |
+
"eval_samples_per_second": 1273.896,
|
| 63 |
+
"eval_steps_per_second": 39.821,
|
| 64 |
+
"step": 68748
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 5.0,
|
| 68 |
+
"learning_rate": 1.8000884389364056e-05,
|
| 69 |
+
"loss": 1.8308,
|
| 70 |
+
"step": 85930
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 5.0,
|
| 74 |
+
"eval_loss": 1.6726739406585693,
|
| 75 |
+
"eval_runtime": 54.0625,
|
| 76 |
+
"eval_samples_per_second": 1271.03,
|
| 77 |
+
"eval_steps_per_second": 39.732,
|
| 78 |
+
"step": 85935
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 6.0,
|
| 82 |
+
"learning_rate": 1.7601047303194276e-05,
|
| 83 |
+
"loss": 1.7889,
|
| 84 |
+
"step": 103116
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 6.0,
|
| 88 |
+
"eval_loss": 1.6451952457427979,
|
| 89 |
+
"eval_runtime": 56.4005,
|
| 90 |
+
"eval_samples_per_second": 1218.341,
|
| 91 |
+
"eval_steps_per_second": 38.085,
|
| 92 |
+
"step": 103122
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 7.0,
|
| 96 |
+
"learning_rate": 1.7201256763833133e-05,
|
| 97 |
+
"loss": 1.7562,
|
| 98 |
+
"step": 120302
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 7.0,
|
| 102 |
+
"eval_loss": 1.6122530698776245,
|
| 103 |
+
"eval_runtime": 56.1664,
|
| 104 |
+
"eval_samples_per_second": 1223.419,
|
| 105 |
+
"eval_steps_per_second": 38.244,
|
| 106 |
+
"step": 120309
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 8.0,
|
| 110 |
+
"learning_rate": 1.6801442951067668e-05,
|
| 111 |
+
"loss": 1.7289,
|
| 112 |
+
"step": 137488
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 8.0,
|
| 116 |
+
"eval_loss": 1.5861868858337402,
|
| 117 |
+
"eval_runtime": 59.6521,
|
| 118 |
+
"eval_samples_per_second": 1151.929,
|
| 119 |
+
"eval_steps_per_second": 36.009,
|
| 120 |
+
"step": 137496
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 9.0,
|
| 124 |
+
"learning_rate": 1.6401652411706525e-05,
|
| 125 |
+
"loss": 1.7051,
|
| 126 |
+
"step": 154674
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 9.0,
|
| 130 |
+
"eval_loss": 1.5660465955734253,
|
| 131 |
+
"eval_runtime": 55.3868,
|
| 132 |
+
"eval_samples_per_second": 1240.638,
|
| 133 |
+
"eval_steps_per_second": 38.782,
|
| 134 |
+
"step": 154683
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 10.0,
|
| 138 |
+
"learning_rate": 1.6001838598941063e-05,
|
| 139 |
+
"loss": 1.6828,
|
| 140 |
+
"step": 171860
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 10.0,
|
| 144 |
+
"eval_loss": 1.551895022392273,
|
| 145 |
+
"eval_runtime": 56.8329,
|
| 146 |
+
"eval_samples_per_second": 1209.07,
|
| 147 |
+
"eval_steps_per_second": 37.795,
|
| 148 |
+
"step": 171870
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 11.0,
|
| 152 |
+
"learning_rate": 1.5602048059579917e-05,
|
| 153 |
+
"loss": 1.666,
|
| 154 |
+
"step": 189046
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 11.0,
|
| 158 |
+
"eval_loss": 1.5311487913131714,
|
| 159 |
+
"eval_runtime": 55.1299,
|
| 160 |
+
"eval_samples_per_second": 1246.419,
|
| 161 |
+
"eval_steps_per_second": 38.962,
|
| 162 |
+
"step": 189057
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 12.0,
|
| 166 |
+
"learning_rate": 1.5202234246814453e-05,
|
| 167 |
+
"loss": 1.65,
|
| 168 |
+
"step": 206232
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 12.0,
|
| 172 |
+
"eval_loss": 1.521924376487732,
|
| 173 |
+
"eval_runtime": 54.0055,
|
| 174 |
+
"eval_samples_per_second": 1272.369,
|
| 175 |
+
"eval_steps_per_second": 39.774,
|
| 176 |
+
"step": 206244
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 13.0,
|
| 180 |
+
"learning_rate": 1.4802443707453309e-05,
|
| 181 |
+
"loss": 1.6347,
|
| 182 |
+
"step": 223418
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 13.0,
|
| 186 |
+
"eval_loss": 1.5064960718154907,
|
| 187 |
+
"eval_runtime": 53.5728,
|
| 188 |
+
"eval_samples_per_second": 1282.647,
|
| 189 |
+
"eval_steps_per_second": 40.095,
|
| 190 |
+
"step": 223431
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 14.0,
|
| 194 |
+
"learning_rate": 1.4402629894687847e-05,
|
| 195 |
+
"loss": 1.6208,
|
| 196 |
+
"step": 240604
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 14.0,
|
| 200 |
+
"eval_loss": 1.4912291765213013,
|
| 201 |
+
"eval_runtime": 55.9464,
|
| 202 |
+
"eval_samples_per_second": 1228.23,
|
| 203 |
+
"eval_steps_per_second": 38.394,
|
| 204 |
+
"step": 240618
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 15.0,
|
| 208 |
+
"learning_rate": 1.4002816081922384e-05,
|
| 209 |
+
"loss": 1.6095,
|
| 210 |
+
"step": 257790
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 15.0,
|
| 214 |
+
"eval_loss": 1.4807928800582886,
|
| 215 |
+
"eval_runtime": 57.4004,
|
| 216 |
+
"eval_samples_per_second": 1197.116,
|
| 217 |
+
"eval_steps_per_second": 37.421,
|
| 218 |
+
"step": 257805
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 16.0,
|
| 222 |
+
"learning_rate": 1.3603002269156922e-05,
|
| 223 |
+
"loss": 1.6,
|
| 224 |
+
"step": 274976
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 16.0,
|
| 228 |
+
"eval_loss": 1.4743348360061646,
|
| 229 |
+
"eval_runtime": 56.4585,
|
| 230 |
+
"eval_samples_per_second": 1217.089,
|
| 231 |
+
"eval_steps_per_second": 38.046,
|
| 232 |
+
"step": 274992
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 17.0,
|
| 236 |
+
"learning_rate": 1.3203235003200094e-05,
|
| 237 |
+
"loss": 1.5898,
|
| 238 |
+
"step": 292162
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 17.0,
|
| 242 |
+
"eval_loss": 1.460829734802246,
|
| 243 |
+
"eval_runtime": 55.6267,
|
| 244 |
+
"eval_samples_per_second": 1235.289,
|
| 245 |
+
"eval_steps_per_second": 38.615,
|
| 246 |
+
"step": 292179
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 18.0,
|
| 250 |
+
"learning_rate": 1.2803397917030315e-05,
|
| 251 |
+
"loss": 1.5802,
|
| 252 |
+
"step": 309348
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 18.0,
|
| 256 |
+
"eval_loss": 1.455512523651123,
|
| 257 |
+
"eval_runtime": 55.4831,
|
| 258 |
+
"eval_samples_per_second": 1238.486,
|
| 259 |
+
"eval_steps_per_second": 38.715,
|
| 260 |
+
"step": 309366
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 19.0,
|
| 264 |
+
"learning_rate": 1.2403584104264852e-05,
|
| 265 |
+
"loss": 1.5711,
|
| 266 |
+
"step": 326534
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 19.0,
|
| 270 |
+
"eval_loss": 1.4483146667480469,
|
| 271 |
+
"eval_runtime": 55.2066,
|
| 272 |
+
"eval_samples_per_second": 1244.689,
|
| 273 |
+
"eval_steps_per_second": 38.908,
|
| 274 |
+
"step": 326553
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 20.0,
|
| 278 |
+
"learning_rate": 1.2003793564903707e-05,
|
| 279 |
+
"loss": 1.5638,
|
| 280 |
+
"step": 343720
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 20.0,
|
| 284 |
+
"eval_loss": 1.4421828985214233,
|
| 285 |
+
"eval_runtime": 53.3823,
|
| 286 |
+
"eval_samples_per_second": 1287.225,
|
| 287 |
+
"eval_steps_per_second": 40.238,
|
| 288 |
+
"step": 343740
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 21.0,
|
| 292 |
+
"learning_rate": 1.1603956478733929e-05,
|
| 293 |
+
"loss": 1.5577,
|
| 294 |
+
"step": 360906
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 21.0,
|
| 298 |
+
"eval_loss": 1.4301999807357788,
|
| 299 |
+
"eval_runtime": 52.0928,
|
| 300 |
+
"eval_samples_per_second": 1319.088,
|
| 301 |
+
"eval_steps_per_second": 41.234,
|
| 302 |
+
"step": 360927
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 22.0,
|
| 306 |
+
"learning_rate": 1.1204165939372782e-05,
|
| 307 |
+
"loss": 1.5494,
|
| 308 |
+
"step": 378092
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 22.0,
|
| 312 |
+
"eval_loss": 1.4282857179641724,
|
| 313 |
+
"eval_runtime": 51.7394,
|
| 314 |
+
"eval_samples_per_second": 1328.098,
|
| 315 |
+
"eval_steps_per_second": 41.516,
|
| 316 |
+
"step": 378114
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 23.0,
|
| 320 |
+
"learning_rate": 1.0804328853203004e-05,
|
| 321 |
+
"loss": 1.5437,
|
| 322 |
+
"step": 395278
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 23.0,
|
| 326 |
+
"eval_loss": 1.4197551012039185,
|
| 327 |
+
"eval_runtime": 56.4255,
|
| 328 |
+
"eval_samples_per_second": 1217.801,
|
| 329 |
+
"eval_steps_per_second": 38.068,
|
| 330 |
+
"step": 395301
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 24.0,
|
| 334 |
+
"learning_rate": 1.0404515040437542e-05,
|
| 335 |
+
"loss": 1.5377,
|
| 336 |
+
"step": 412464
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 24.0,
|
| 340 |
+
"eval_loss": 1.4187239408493042,
|
| 341 |
+
"eval_runtime": 57.0967,
|
| 342 |
+
"eval_samples_per_second": 1203.485,
|
| 343 |
+
"eval_steps_per_second": 37.62,
|
| 344 |
+
"step": 412488
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 25.0,
|
| 348 |
+
"learning_rate": 1.0004701227672077e-05,
|
| 349 |
+
"loss": 1.532,
|
| 350 |
+
"step": 429650
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 25.0,
|
| 354 |
+
"eval_loss": 1.407697319984436,
|
| 355 |
+
"eval_runtime": 57.5147,
|
| 356 |
+
"eval_samples_per_second": 1194.737,
|
| 357 |
+
"eval_steps_per_second": 37.347,
|
| 358 |
+
"step": 429675
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 26.0,
|
| 362 |
+
"learning_rate": 9.604887414906617e-06,
|
| 363 |
+
"loss": 1.5259,
|
| 364 |
+
"step": 446836
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 26.0,
|
| 368 |
+
"eval_loss": 1.406160593032837,
|
| 369 |
+
"eval_runtime": 57.387,
|
| 370 |
+
"eval_samples_per_second": 1197.396,
|
| 371 |
+
"eval_steps_per_second": 37.43,
|
| 372 |
+
"step": 446862
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 27.0,
|
| 376 |
+
"learning_rate": 9.205073602141154e-06,
|
| 377 |
+
"loss": 1.5202,
|
| 378 |
+
"step": 464022
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 27.0,
|
| 382 |
+
"eval_loss": 1.4006047248840332,
|
| 383 |
+
"eval_runtime": 57.8577,
|
| 384 |
+
"eval_samples_per_second": 1187.656,
|
| 385 |
+
"eval_steps_per_second": 37.126,
|
| 386 |
+
"step": 464049
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 28.0,
|
| 390 |
+
"learning_rate": 8.805283062780009e-06,
|
| 391 |
+
"loss": 1.5165,
|
| 392 |
+
"step": 481208
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 28.0,
|
| 396 |
+
"eval_loss": 1.401613473892212,
|
| 397 |
+
"eval_runtime": 57.2222,
|
| 398 |
+
"eval_samples_per_second": 1200.846,
|
| 399 |
+
"eval_steps_per_second": 37.538,
|
| 400 |
+
"step": 481236
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 29.0,
|
| 404 |
+
"learning_rate": 8.405469250014546e-06,
|
| 405 |
+
"loss": 1.5118,
|
| 406 |
+
"step": 498394
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 29.0,
|
| 410 |
+
"eval_loss": 1.3900607824325562,
|
| 411 |
+
"eval_runtime": 57.1887,
|
| 412 |
+
"eval_samples_per_second": 1201.549,
|
| 413 |
+
"eval_steps_per_second": 37.56,
|
| 414 |
+
"step": 498423
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 30.0,
|
| 418 |
+
"learning_rate": 8.005678710653402e-06,
|
| 419 |
+
"loss": 1.5079,
|
| 420 |
+
"step": 515580
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 30.0,
|
| 424 |
+
"eval_loss": 1.3925185203552246,
|
| 425 |
+
"eval_runtime": 57.0206,
|
| 426 |
+
"eval_samples_per_second": 1205.091,
|
| 427 |
+
"eval_steps_per_second": 37.671,
|
| 428 |
+
"step": 515610
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 31.0,
|
| 432 |
+
"learning_rate": 7.605864897887939e-06,
|
| 433 |
+
"loss": 1.5037,
|
| 434 |
+
"step": 532766
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 31.0,
|
| 438 |
+
"eval_loss": 1.3832355737686157,
|
| 439 |
+
"eval_runtime": 57.7842,
|
| 440 |
+
"eval_samples_per_second": 1189.166,
|
| 441 |
+
"eval_steps_per_second": 37.173,
|
| 442 |
+
"step": 532797
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 32.0,
|
| 446 |
+
"learning_rate": 7.206027811718159e-06,
|
| 447 |
+
"loss": 1.4998,
|
| 448 |
+
"step": 549952
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 32.0,
|
| 452 |
+
"eval_loss": 1.3857349157333374,
|
| 453 |
+
"eval_runtime": 57.6923,
|
| 454 |
+
"eval_samples_per_second": 1191.061,
|
| 455 |
+
"eval_steps_per_second": 37.232,
|
| 456 |
+
"step": 549984
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 33.0,
|
| 460 |
+
"learning_rate": 6.806213998952697e-06,
|
| 461 |
+
"loss": 1.4953,
|
| 462 |
+
"step": 567138
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 33.0,
|
| 466 |
+
"eval_loss": 1.3751457929611206,
|
| 467 |
+
"eval_runtime": 56.0689,
|
| 468 |
+
"eval_samples_per_second": 1225.545,
|
| 469 |
+
"eval_steps_per_second": 38.31,
|
| 470 |
+
"step": 567171
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 34.0,
|
| 474 |
+
"learning_rate": 6.406423459591552e-06,
|
| 475 |
+
"loss": 1.4924,
|
| 476 |
+
"step": 584324
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 34.0,
|
| 480 |
+
"eval_loss": 1.3691054582595825,
|
| 481 |
+
"eval_runtime": 57.9405,
|
| 482 |
+
"eval_samples_per_second": 1185.957,
|
| 483 |
+
"eval_steps_per_second": 37.072,
|
| 484 |
+
"step": 584358
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 35.0,
|
| 488 |
+
"learning_rate": 6.006586373421773e-06,
|
| 489 |
+
"loss": 1.489,
|
| 490 |
+
"step": 601510
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 35.0,
|
| 494 |
+
"eval_loss": 1.3761118650436401,
|
| 495 |
+
"eval_runtime": 57.9115,
|
| 496 |
+
"eval_samples_per_second": 1186.551,
|
| 497 |
+
"eval_steps_per_second": 37.091,
|
| 498 |
+
"step": 601545
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 36.0,
|
| 502 |
+
"learning_rate": 5.606749287251994e-06,
|
| 503 |
+
"loss": 1.4857,
|
| 504 |
+
"step": 618696
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 36.0,
|
| 508 |
+
"eval_loss": 1.3728961944580078,
|
| 509 |
+
"eval_runtime": 57.678,
|
| 510 |
+
"eval_samples_per_second": 1191.356,
|
| 511 |
+
"eval_steps_per_second": 37.241,
|
| 512 |
+
"step": 618732
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 37.0,
|
| 516 |
+
"learning_rate": 5.2069354744865304e-06,
|
| 517 |
+
"loss": 1.4836,
|
| 518 |
+
"step": 635882
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 37.0,
|
| 522 |
+
"eval_loss": 1.3688822984695435,
|
| 523 |
+
"eval_runtime": 57.411,
|
| 524 |
+
"eval_samples_per_second": 1196.896,
|
| 525 |
+
"eval_steps_per_second": 37.414,
|
| 526 |
+
"step": 635919
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 38.0,
|
| 530 |
+
"learning_rate": 4.807121661721069e-06,
|
| 531 |
+
"loss": 1.4814,
|
| 532 |
+
"step": 653068
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 38.0,
|
| 536 |
+
"eval_loss": 1.3645319938659668,
|
| 537 |
+
"eval_runtime": 57.5288,
|
| 538 |
+
"eval_samples_per_second": 1194.446,
|
| 539 |
+
"eval_steps_per_second": 37.338,
|
| 540 |
+
"step": 653106
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 39.0,
|
| 544 |
+
"learning_rate": 4.407284575551289e-06,
|
| 545 |
+
"loss": 1.4804,
|
| 546 |
+
"step": 670254
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 39.0,
|
| 550 |
+
"eval_loss": 1.3667703866958618,
|
| 551 |
+
"eval_runtime": 57.9227,
|
| 552 |
+
"eval_samples_per_second": 1186.322,
|
| 553 |
+
"eval_steps_per_second": 37.084,
|
| 554 |
+
"step": 670293
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 40.0,
|
| 558 |
+
"learning_rate": 4.007447489381509e-06,
|
| 559 |
+
"loss": 1.4773,
|
| 560 |
+
"step": 687440
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 40.0,
|
| 564 |
+
"eval_loss": 1.3591846227645874,
|
| 565 |
+
"eval_runtime": 57.728,
|
| 566 |
+
"eval_samples_per_second": 1190.324,
|
| 567 |
+
"eval_steps_per_second": 37.209,
|
| 568 |
+
"step": 687480
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 41.0,
|
| 572 |
+
"learning_rate": 3.6076569500203645e-06,
|
| 573 |
+
"loss": 1.4735,
|
| 574 |
+
"step": 704626
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 41.0,
|
| 578 |
+
"eval_loss": 1.3576593399047852,
|
| 579 |
+
"eval_runtime": 57.8776,
|
| 580 |
+
"eval_samples_per_second": 1187.247,
|
| 581 |
+
"eval_steps_per_second": 37.113,
|
| 582 |
+
"step": 704667
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 42.0,
|
| 586 |
+
"learning_rate": 3.2078664106592196e-06,
|
| 587 |
+
"loss": 1.473,
|
| 588 |
+
"step": 721812
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 42.0,
|
| 592 |
+
"eval_loss": 1.3613665103912354,
|
| 593 |
+
"eval_runtime": 57.6832,
|
| 594 |
+
"eval_samples_per_second": 1191.247,
|
| 595 |
+
"eval_steps_per_second": 37.238,
|
| 596 |
+
"step": 721854
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 43.0,
|
| 600 |
+
"learning_rate": 2.8080758712980744e-06,
|
| 601 |
+
"loss": 1.4715,
|
| 602 |
+
"step": 738998
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 43.0,
|
| 606 |
+
"eval_loss": 1.3575751781463623,
|
| 607 |
+
"eval_runtime": 58.5415,
|
| 608 |
+
"eval_samples_per_second": 1173.783,
|
| 609 |
+
"eval_steps_per_second": 36.692,
|
| 610 |
+
"step": 739041
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 44.0,
|
| 614 |
+
"learning_rate": 2.4082620585326123e-06,
|
| 615 |
+
"loss": 1.4696,
|
| 616 |
+
"step": 756184
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 44.0,
|
| 620 |
+
"eval_loss": 1.3553742170333862,
|
| 621 |
+
"eval_runtime": 57.9841,
|
| 622 |
+
"eval_samples_per_second": 1185.066,
|
| 623 |
+
"eval_steps_per_second": 37.045,
|
| 624 |
+
"step": 756228
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 45.0,
|
| 628 |
+
"learning_rate": 2.00844824576715e-06,
|
| 629 |
+
"loss": 1.4681,
|
| 630 |
+
"step": 773370
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 45.0,
|
| 634 |
+
"eval_loss": 1.3520816564559937,
|
| 635 |
+
"eval_runtime": 57.2264,
|
| 636 |
+
"eval_samples_per_second": 1200.757,
|
| 637 |
+
"eval_steps_per_second": 37.535,
|
| 638 |
+
"step": 773415
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 46.0,
|
| 642 |
+
"learning_rate": 1.6086111595973703e-06,
|
| 643 |
+
"loss": 1.4667,
|
| 644 |
+
"step": 790556
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 46.0,
|
| 648 |
+
"eval_loss": 1.3518463373184204,
|
| 649 |
+
"eval_runtime": 57.2812,
|
| 650 |
+
"eval_samples_per_second": 1199.609,
|
| 651 |
+
"eval_steps_per_second": 37.499,
|
| 652 |
+
"step": 790602
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 47.0,
|
| 656 |
+
"learning_rate": 1.2088206202362252e-06,
|
| 657 |
+
"loss": 1.465,
|
| 658 |
+
"step": 807742
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 47.0,
|
| 662 |
+
"eval_loss": 1.353028416633606,
|
| 663 |
+
"eval_runtime": 57.8145,
|
| 664 |
+
"eval_samples_per_second": 1188.543,
|
| 665 |
+
"eval_steps_per_second": 37.153,
|
| 666 |
+
"step": 807789
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 48.0,
|
| 670 |
+
"learning_rate": 8.090300808750801e-07,
|
| 671 |
+
"loss": 1.4637,
|
| 672 |
+
"step": 824928
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 48.0,
|
| 676 |
+
"eval_loss": 1.3512929677963257,
|
| 677 |
+
"eval_runtime": 57.6297,
|
| 678 |
+
"eval_samples_per_second": 1192.354,
|
| 679 |
+
"eval_steps_per_second": 37.272,
|
| 680 |
+
"step": 824976
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 49.0,
|
| 684 |
+
"learning_rate": 4.092162681096178e-07,
|
| 685 |
+
"loss": 1.462,
|
| 686 |
+
"step": 842114
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 49.0,
|
| 690 |
+
"eval_loss": 1.3500477075576782,
|
| 691 |
+
"eval_runtime": 58.0134,
|
| 692 |
+
"eval_samples_per_second": 1184.467,
|
| 693 |
+
"eval_steps_per_second": 37.026,
|
| 694 |
+
"step": 842163
|
| 695 |
+
}
|
| 696 |
+
],
|
| 697 |
+
"max_steps": 859350,
|
| 698 |
+
"num_train_epochs": 50,
|
| 699 |
+
"total_flos": 1.9815098644202803e+17,
|
| 700 |
+
"trial_name": null,
|
| 701 |
+
"trial_params": null
|
| 702 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89ca1ca3557d4150cb0d838160870f5330797f6b3f02ab04d02a6520f1b7cfed
|
| 3 |
+
size 3643
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|