Initial
Browse files- config.json +40 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- trainer_state.json +755 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ElectraForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"embedding_size": 128,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 256,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0",
|
| 14 |
+
"1": "LABEL_1",
|
| 15 |
+
"2": "LABEL_2"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 1024,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"LABEL_0": 0,
|
| 21 |
+
"LABEL_1": 1,
|
| 22 |
+
"LABEL_2": 2
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "electra",
|
| 27 |
+
"num_attention_heads": 4,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"position_embedding_type": "absolute",
|
| 31 |
+
"problem_type": "single_label_classification",
|
| 32 |
+
"summary_activation": "gelu",
|
| 33 |
+
"summary_last_dropout": 0.1,
|
| 34 |
+
"summary_type": "first",
|
| 35 |
+
"summary_use_proj": true,
|
| 36 |
+
"transformers_version": "4.57.2",
|
| 37 |
+
"type_vocab_size": 2,
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 30522
|
| 40 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab16cc1e3aaae8d065c3dc80be77afcb39c620ba04adbecffe5be7356eaa9b62
|
| 3 |
+
size 16777216
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08537a156c50f44d493a9e63573a65692dd1ab39e2ecfeb90a9e2ce4fc567714
|
| 3 |
+
size 16777216
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d3f19bc849d895ca9a0758650109d5bd3e5979db276cf56daab9cbeec109fed
|
| 3 |
+
size 14645
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a31a0a4b517581a787056bd0f21d4413f9cea2984c61fcc406d0572000abe68
|
| 3 |
+
size 1465
|
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 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "ElectraTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,755 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 51504,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.029123951537744643,
|
| 14 |
+
"grad_norm": 6.774685382843018,
|
| 15 |
+
"learning_rate": 4.951557160608885e-05,
|
| 16 |
+
"loss": 0.8291,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.058247903075489285,
|
| 21 |
+
"grad_norm": 6.7878875732421875,
|
| 22 |
+
"learning_rate": 4.9030172413793105e-05,
|
| 23 |
+
"loss": 0.6161,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.08737185461323392,
|
| 28 |
+
"grad_norm": 4.789400577545166,
|
| 29 |
+
"learning_rate": 4.854477322149736e-05,
|
| 30 |
+
"loss": 0.5785,
|
| 31 |
+
"step": 1500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.11649580615097857,
|
| 35 |
+
"grad_norm": 8.038426399230957,
|
| 36 |
+
"learning_rate": 4.805937402920162e-05,
|
| 37 |
+
"loss": 0.546,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1456197576887232,
|
| 42 |
+
"grad_norm": 5.627825736999512,
|
| 43 |
+
"learning_rate": 4.757397483690587e-05,
|
| 44 |
+
"loss": 0.5363,
|
| 45 |
+
"step": 2500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.17474370922646784,
|
| 49 |
+
"grad_norm": 4.209435939788818,
|
| 50 |
+
"learning_rate": 4.7088575644610125e-05,
|
| 51 |
+
"loss": 0.5225,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.20386766076421248,
|
| 56 |
+
"grad_norm": 6.513331890106201,
|
| 57 |
+
"learning_rate": 4.660317645231438e-05,
|
| 58 |
+
"loss": 0.5104,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.23299161230195714,
|
| 63 |
+
"grad_norm": 8.145315170288086,
|
| 64 |
+
"learning_rate": 4.611777726001864e-05,
|
| 65 |
+
"loss": 0.4894,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.26211556383970175,
|
| 70 |
+
"grad_norm": 5.720129489898682,
|
| 71 |
+
"learning_rate": 4.56323780677229e-05,
|
| 72 |
+
"loss": 0.483,
|
| 73 |
+
"step": 4500
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.2912395153774464,
|
| 77 |
+
"grad_norm": 4.3693718910217285,
|
| 78 |
+
"learning_rate": 4.514697887542715e-05,
|
| 79 |
+
"loss": 0.4747,
|
| 80 |
+
"step": 5000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.3203634669151911,
|
| 84 |
+
"grad_norm": 5.498645305633545,
|
| 85 |
+
"learning_rate": 4.466157968313141e-05,
|
| 86 |
+
"loss": 0.4686,
|
| 87 |
+
"step": 5500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.3494874184529357,
|
| 91 |
+
"grad_norm": 4.044460296630859,
|
| 92 |
+
"learning_rate": 4.417618049083567e-05,
|
| 93 |
+
"loss": 0.4679,
|
| 94 |
+
"step": 6000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.37861136999068035,
|
| 98 |
+
"grad_norm": 6.850383758544922,
|
| 99 |
+
"learning_rate": 4.369078129853993e-05,
|
| 100 |
+
"loss": 0.4632,
|
| 101 |
+
"step": 6500
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.40773532152842495,
|
| 105 |
+
"grad_norm": 6.392009258270264,
|
| 106 |
+
"learning_rate": 4.320538210624418e-05,
|
| 107 |
+
"loss": 0.4521,
|
| 108 |
+
"step": 7000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.4368592730661696,
|
| 112 |
+
"grad_norm": 4.33333683013916,
|
| 113 |
+
"learning_rate": 4.271998291394843e-05,
|
| 114 |
+
"loss": 0.447,
|
| 115 |
+
"step": 7500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.4659832246039143,
|
| 119 |
+
"grad_norm": 3.611548662185669,
|
| 120 |
+
"learning_rate": 4.223458372165269e-05,
|
| 121 |
+
"loss": 0.4465,
|
| 122 |
+
"step": 8000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.4951071761416589,
|
| 126 |
+
"grad_norm": 5.756487846374512,
|
| 127 |
+
"learning_rate": 4.1749184529356947e-05,
|
| 128 |
+
"loss": 0.4354,
|
| 129 |
+
"step": 8500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.5242311276794035,
|
| 133 |
+
"grad_norm": 5.3887786865234375,
|
| 134 |
+
"learning_rate": 4.12637853370612e-05,
|
| 135 |
+
"loss": 0.4395,
|
| 136 |
+
"step": 9000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.5533550792171482,
|
| 140 |
+
"grad_norm": 4.947877883911133,
|
| 141 |
+
"learning_rate": 4.0778386144765457e-05,
|
| 142 |
+
"loss": 0.4431,
|
| 143 |
+
"step": 9500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.5824790307548928,
|
| 147 |
+
"grad_norm": 6.60713529586792,
|
| 148 |
+
"learning_rate": 4.0292986952469715e-05,
|
| 149 |
+
"loss": 0.4355,
|
| 150 |
+
"step": 10000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.6116029822926374,
|
| 154 |
+
"grad_norm": 4.627679347991943,
|
| 155 |
+
"learning_rate": 3.980758776017397e-05,
|
| 156 |
+
"loss": 0.4317,
|
| 157 |
+
"step": 10500
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.6407269338303822,
|
| 161 |
+
"grad_norm": 4.922262668609619,
|
| 162 |
+
"learning_rate": 3.9322188567878225e-05,
|
| 163 |
+
"loss": 0.4247,
|
| 164 |
+
"step": 11000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.6698508853681268,
|
| 168 |
+
"grad_norm": 3.914152145385742,
|
| 169 |
+
"learning_rate": 3.883678937558248e-05,
|
| 170 |
+
"loss": 0.4334,
|
| 171 |
+
"step": 11500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.6989748369058714,
|
| 175 |
+
"grad_norm": 4.864943027496338,
|
| 176 |
+
"learning_rate": 3.835139018328674e-05,
|
| 177 |
+
"loss": 0.4185,
|
| 178 |
+
"step": 12000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.7280987884436161,
|
| 182 |
+
"grad_norm": 10.3380708694458,
|
| 183 |
+
"learning_rate": 3.786599099099099e-05,
|
| 184 |
+
"loss": 0.4223,
|
| 185 |
+
"step": 12500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.7572227399813607,
|
| 189 |
+
"grad_norm": 4.065073490142822,
|
| 190 |
+
"learning_rate": 3.7380591798695245e-05,
|
| 191 |
+
"loss": 0.4086,
|
| 192 |
+
"step": 13000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.7863466915191053,
|
| 196 |
+
"grad_norm": 4.190847873687744,
|
| 197 |
+
"learning_rate": 3.68951926063995e-05,
|
| 198 |
+
"loss": 0.4156,
|
| 199 |
+
"step": 13500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.8154706430568499,
|
| 203 |
+
"grad_norm": 5.804997444152832,
|
| 204 |
+
"learning_rate": 3.640979341410376e-05,
|
| 205 |
+
"loss": 0.4052,
|
| 206 |
+
"step": 14000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.8445945945945946,
|
| 210 |
+
"grad_norm": 7.701807975769043,
|
| 211 |
+
"learning_rate": 3.592439422180802e-05,
|
| 212 |
+
"loss": 0.4133,
|
| 213 |
+
"step": 14500
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.8737185461323392,
|
| 217 |
+
"grad_norm": 17.949703216552734,
|
| 218 |
+
"learning_rate": 3.543899502951227e-05,
|
| 219 |
+
"loss": 0.4076,
|
| 220 |
+
"step": 15000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.9028424976700838,
|
| 224 |
+
"grad_norm": 5.222975254058838,
|
| 225 |
+
"learning_rate": 3.495359583721653e-05,
|
| 226 |
+
"loss": 0.4201,
|
| 227 |
+
"step": 15500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.9319664492078286,
|
| 231 |
+
"grad_norm": 4.896594047546387,
|
| 232 |
+
"learning_rate": 3.446819664492079e-05,
|
| 233 |
+
"loss": 0.4035,
|
| 234 |
+
"step": 16000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.9610904007455732,
|
| 238 |
+
"grad_norm": 5.599170207977295,
|
| 239 |
+
"learning_rate": 3.398279745262504e-05,
|
| 240 |
+
"loss": 0.4065,
|
| 241 |
+
"step": 16500
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.9902143522833178,
|
| 245 |
+
"grad_norm": 3.4558660984039307,
|
| 246 |
+
"learning_rate": 3.34973982603293e-05,
|
| 247 |
+
"loss": 0.413,
|
| 248 |
+
"step": 17000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.0193383038210624,
|
| 252 |
+
"grad_norm": 6.404013156890869,
|
| 253 |
+
"learning_rate": 3.301199906803355e-05,
|
| 254 |
+
"loss": 0.3758,
|
| 255 |
+
"step": 17500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.048462255358807,
|
| 259 |
+
"grad_norm": 5.1876420974731445,
|
| 260 |
+
"learning_rate": 3.252659987573781e-05,
|
| 261 |
+
"loss": 0.3567,
|
| 262 |
+
"step": 18000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.0775862068965518,
|
| 266 |
+
"grad_norm": 3.246553421020508,
|
| 267 |
+
"learning_rate": 3.204120068344206e-05,
|
| 268 |
+
"loss": 0.362,
|
| 269 |
+
"step": 18500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.1067101584342964,
|
| 273 |
+
"grad_norm": 5.665416240692139,
|
| 274 |
+
"learning_rate": 3.155580149114632e-05,
|
| 275 |
+
"loss": 0.3639,
|
| 276 |
+
"step": 19000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.135834109972041,
|
| 280 |
+
"grad_norm": 4.938392162322998,
|
| 281 |
+
"learning_rate": 3.1070402298850576e-05,
|
| 282 |
+
"loss": 0.3649,
|
| 283 |
+
"step": 19500
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.1649580615097856,
|
| 287 |
+
"grad_norm": 4.021746635437012,
|
| 288 |
+
"learning_rate": 3.0585003106554835e-05,
|
| 289 |
+
"loss": 0.3688,
|
| 290 |
+
"step": 20000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.1940820130475303,
|
| 294 |
+
"grad_norm": 5.639608860015869,
|
| 295 |
+
"learning_rate": 3.009960391425909e-05,
|
| 296 |
+
"loss": 0.357,
|
| 297 |
+
"step": 20500
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.2232059645852749,
|
| 301 |
+
"grad_norm": 5.954344272613525,
|
| 302 |
+
"learning_rate": 2.9614204721963345e-05,
|
| 303 |
+
"loss": 0.3614,
|
| 304 |
+
"step": 21000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.2523299161230197,
|
| 308 |
+
"grad_norm": 4.498464107513428,
|
| 309 |
+
"learning_rate": 2.9128805529667603e-05,
|
| 310 |
+
"loss": 0.3592,
|
| 311 |
+
"step": 21500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.281453867660764,
|
| 315 |
+
"grad_norm": 7.547128200531006,
|
| 316 |
+
"learning_rate": 2.8643406337371858e-05,
|
| 317 |
+
"loss": 0.3597,
|
| 318 |
+
"step": 22000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.310577819198509,
|
| 322 |
+
"grad_norm": 6.078393459320068,
|
| 323 |
+
"learning_rate": 2.815800714507611e-05,
|
| 324 |
+
"loss": 0.3643,
|
| 325 |
+
"step": 22500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.3397017707362535,
|
| 329 |
+
"grad_norm": 5.5143303871154785,
|
| 330 |
+
"learning_rate": 2.7672607952780365e-05,
|
| 331 |
+
"loss": 0.359,
|
| 332 |
+
"step": 23000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.3688257222739981,
|
| 336 |
+
"grad_norm": 5.585659027099609,
|
| 337 |
+
"learning_rate": 2.7187208760484623e-05,
|
| 338 |
+
"loss": 0.3647,
|
| 339 |
+
"step": 23500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.3979496738117427,
|
| 343 |
+
"grad_norm": 6.159289836883545,
|
| 344 |
+
"learning_rate": 2.6701809568188878e-05,
|
| 345 |
+
"loss": 0.3525,
|
| 346 |
+
"step": 24000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.4270736253494873,
|
| 350 |
+
"grad_norm": 4.410373687744141,
|
| 351 |
+
"learning_rate": 2.6216410375893136e-05,
|
| 352 |
+
"loss": 0.3518,
|
| 353 |
+
"step": 24500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.4561975768872322,
|
| 357 |
+
"grad_norm": 4.7880754470825195,
|
| 358 |
+
"learning_rate": 2.573101118359739e-05,
|
| 359 |
+
"loss": 0.3568,
|
| 360 |
+
"step": 25000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.4853215284249768,
|
| 364 |
+
"grad_norm": 4.985711097717285,
|
| 365 |
+
"learning_rate": 2.524561199130165e-05,
|
| 366 |
+
"loss": 0.3566,
|
| 367 |
+
"step": 25500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.5144454799627214,
|
| 371 |
+
"grad_norm": 7.0648088455200195,
|
| 372 |
+
"learning_rate": 2.47602127990059e-05,
|
| 373 |
+
"loss": 0.3634,
|
| 374 |
+
"step": 26000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.543569431500466,
|
| 378 |
+
"grad_norm": 5.251628875732422,
|
| 379 |
+
"learning_rate": 2.427481360671016e-05,
|
| 380 |
+
"loss": 0.3526,
|
| 381 |
+
"step": 26500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.5726933830382106,
|
| 385 |
+
"grad_norm": 8.0952787399292,
|
| 386 |
+
"learning_rate": 2.3789414414414415e-05,
|
| 387 |
+
"loss": 0.3489,
|
| 388 |
+
"step": 27000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.6018173345759554,
|
| 392 |
+
"grad_norm": 3.6345725059509277,
|
| 393 |
+
"learning_rate": 2.3304015222118673e-05,
|
| 394 |
+
"loss": 0.3591,
|
| 395 |
+
"step": 27500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.6309412861136998,
|
| 399 |
+
"grad_norm": 6.777653217315674,
|
| 400 |
+
"learning_rate": 2.2818616029822928e-05,
|
| 401 |
+
"loss": 0.3566,
|
| 402 |
+
"step": 28000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.6600652376514446,
|
| 406 |
+
"grad_norm": 5.334507465362549,
|
| 407 |
+
"learning_rate": 2.2333216837527183e-05,
|
| 408 |
+
"loss": 0.3506,
|
| 409 |
+
"step": 28500
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.689189189189189,
|
| 413 |
+
"grad_norm": 5.431693077087402,
|
| 414 |
+
"learning_rate": 2.1847817645231438e-05,
|
| 415 |
+
"loss": 0.358,
|
| 416 |
+
"step": 29000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.7183131407269339,
|
| 420 |
+
"grad_norm": 8.189932823181152,
|
| 421 |
+
"learning_rate": 2.1362418452935696e-05,
|
| 422 |
+
"loss": 0.3535,
|
| 423 |
+
"step": 29500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.7474370922646785,
|
| 427 |
+
"grad_norm": 6.549941062927246,
|
| 428 |
+
"learning_rate": 2.087701926063995e-05,
|
| 429 |
+
"loss": 0.3502,
|
| 430 |
+
"step": 30000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.776561043802423,
|
| 434 |
+
"grad_norm": 5.226093292236328,
|
| 435 |
+
"learning_rate": 2.039162006834421e-05,
|
| 436 |
+
"loss": 0.3509,
|
| 437 |
+
"step": 30500
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.805684995340168,
|
| 441 |
+
"grad_norm": 4.530932426452637,
|
| 442 |
+
"learning_rate": 1.990622087604846e-05,
|
| 443 |
+
"loss": 0.3439,
|
| 444 |
+
"step": 31000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.8348089468779123,
|
| 448 |
+
"grad_norm": 2.6704397201538086,
|
| 449 |
+
"learning_rate": 1.942082168375272e-05,
|
| 450 |
+
"loss": 0.3417,
|
| 451 |
+
"step": 31500
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.8639328984156571,
|
| 455 |
+
"grad_norm": 4.931678295135498,
|
| 456 |
+
"learning_rate": 1.8935422491456975e-05,
|
| 457 |
+
"loss": 0.3489,
|
| 458 |
+
"step": 32000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.8930568499534017,
|
| 462 |
+
"grad_norm": 3.0061357021331787,
|
| 463 |
+
"learning_rate": 1.8450023299161233e-05,
|
| 464 |
+
"loss": 0.3478,
|
| 465 |
+
"step": 32500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.9221808014911463,
|
| 469 |
+
"grad_norm": 5.605920314788818,
|
| 470 |
+
"learning_rate": 1.7964624106865488e-05,
|
| 471 |
+
"loss": 0.3469,
|
| 472 |
+
"step": 33000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.951304753028891,
|
| 476 |
+
"grad_norm": 8.776355743408203,
|
| 477 |
+
"learning_rate": 1.7479224914569743e-05,
|
| 478 |
+
"loss": 0.3479,
|
| 479 |
+
"step": 33500
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.9804287045666356,
|
| 483 |
+
"grad_norm": 6.094631671905518,
|
| 484 |
+
"learning_rate": 1.6993825722273998e-05,
|
| 485 |
+
"loss": 0.3465,
|
| 486 |
+
"step": 34000
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 2.0095526561043804,
|
| 490 |
+
"grad_norm": 3.9695520401000977,
|
| 491 |
+
"learning_rate": 1.6508426529978256e-05,
|
| 492 |
+
"loss": 0.337,
|
| 493 |
+
"step": 34500
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 2.0386766076421248,
|
| 497 |
+
"grad_norm": 9.629318237304688,
|
| 498 |
+
"learning_rate": 1.602302733768251e-05,
|
| 499 |
+
"loss": 0.2991,
|
| 500 |
+
"step": 35000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 2.0678005591798696,
|
| 504 |
+
"grad_norm": 5.794491767883301,
|
| 505 |
+
"learning_rate": 1.5537628145386766e-05,
|
| 506 |
+
"loss": 0.3049,
|
| 507 |
+
"step": 35500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 2.096924510717614,
|
| 511 |
+
"grad_norm": 3.9909379482269287,
|
| 512 |
+
"learning_rate": 1.5052228953091021e-05,
|
| 513 |
+
"loss": 0.307,
|
| 514 |
+
"step": 36000
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 2.126048462255359,
|
| 518 |
+
"grad_norm": 5.097212314605713,
|
| 519 |
+
"learning_rate": 1.4566829760795278e-05,
|
| 520 |
+
"loss": 0.3108,
|
| 521 |
+
"step": 36500
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.1551724137931036,
|
| 525 |
+
"grad_norm": 4.131860733032227,
|
| 526 |
+
"learning_rate": 1.4081430568499535e-05,
|
| 527 |
+
"loss": 0.308,
|
| 528 |
+
"step": 37000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 2.184296365330848,
|
| 532 |
+
"grad_norm": 5.7827372550964355,
|
| 533 |
+
"learning_rate": 1.3596031376203791e-05,
|
| 534 |
+
"loss": 0.3022,
|
| 535 |
+
"step": 37500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 2.213420316868593,
|
| 539 |
+
"grad_norm": 5.650452613830566,
|
| 540 |
+
"learning_rate": 1.3110632183908048e-05,
|
| 541 |
+
"loss": 0.3084,
|
| 542 |
+
"step": 38000
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 2.2425442684063372,
|
| 546 |
+
"grad_norm": 7.3451151847839355,
|
| 547 |
+
"learning_rate": 1.2625232991612301e-05,
|
| 548 |
+
"loss": 0.2974,
|
| 549 |
+
"step": 38500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.271668219944082,
|
| 553 |
+
"grad_norm": 6.839465141296387,
|
| 554 |
+
"learning_rate": 1.2139833799316558e-05,
|
| 555 |
+
"loss": 0.2978,
|
| 556 |
+
"step": 39000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 2.3007921714818265,
|
| 560 |
+
"grad_norm": 3.4287917613983154,
|
| 561 |
+
"learning_rate": 1.1654434607020815e-05,
|
| 562 |
+
"loss": 0.3137,
|
| 563 |
+
"step": 39500
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 2.3299161230195713,
|
| 567 |
+
"grad_norm": 7.438332557678223,
|
| 568 |
+
"learning_rate": 1.1169035414725071e-05,
|
| 569 |
+
"loss": 0.3032,
|
| 570 |
+
"step": 40000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.359040074557316,
|
| 574 |
+
"grad_norm": 4.485251426696777,
|
| 575 |
+
"learning_rate": 1.0683636222429326e-05,
|
| 576 |
+
"loss": 0.31,
|
| 577 |
+
"step": 40500
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 2.3881640260950605,
|
| 581 |
+
"grad_norm": 4.613361835479736,
|
| 582 |
+
"learning_rate": 1.0198237030133583e-05,
|
| 583 |
+
"loss": 0.3076,
|
| 584 |
+
"step": 41000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.4172879776328053,
|
| 588 |
+
"grad_norm": 3.4650862216949463,
|
| 589 |
+
"learning_rate": 9.712837837837838e-06,
|
| 590 |
+
"loss": 0.2925,
|
| 591 |
+
"step": 41500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 2.4464119291705497,
|
| 595 |
+
"grad_norm": 2.9402899742126465,
|
| 596 |
+
"learning_rate": 9.227438645542095e-06,
|
| 597 |
+
"loss": 0.3019,
|
| 598 |
+
"step": 42000
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 2.4755358807082946,
|
| 602 |
+
"grad_norm": 3.6428680419921875,
|
| 603 |
+
"learning_rate": 8.742039453246351e-06,
|
| 604 |
+
"loss": 0.3148,
|
| 605 |
+
"step": 42500
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 2.5046598322460394,
|
| 609 |
+
"grad_norm": 4.835502624511719,
|
| 610 |
+
"learning_rate": 8.256640260950606e-06,
|
| 611 |
+
"loss": 0.2923,
|
| 612 |
+
"step": 43000
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 2.5337837837837838,
|
| 616 |
+
"grad_norm": 6.484007835388184,
|
| 617 |
+
"learning_rate": 7.771241068654863e-06,
|
| 618 |
+
"loss": 0.2889,
|
| 619 |
+
"step": 43500
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 2.562907735321528,
|
| 623 |
+
"grad_norm": 7.5975565910339355,
|
| 624 |
+
"learning_rate": 7.285841876359117e-06,
|
| 625 |
+
"loss": 0.2909,
|
| 626 |
+
"step": 44000
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 2.592031686859273,
|
| 630 |
+
"grad_norm": 5.18363094329834,
|
| 631 |
+
"learning_rate": 6.800442684063374e-06,
|
| 632 |
+
"loss": 0.3019,
|
| 633 |
+
"step": 44500
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.621155638397018,
|
| 637 |
+
"grad_norm": 9.518139839172363,
|
| 638 |
+
"learning_rate": 6.31504349176763e-06,
|
| 639 |
+
"loss": 0.3029,
|
| 640 |
+
"step": 45000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.650279589934762,
|
| 644 |
+
"grad_norm": 3.660771369934082,
|
| 645 |
+
"learning_rate": 5.829644299471886e-06,
|
| 646 |
+
"loss": 0.301,
|
| 647 |
+
"step": 45500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.679403541472507,
|
| 651 |
+
"grad_norm": 6.393496036529541,
|
| 652 |
+
"learning_rate": 5.344245107176142e-06,
|
| 653 |
+
"loss": 0.3006,
|
| 654 |
+
"step": 46000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.7085274930102514,
|
| 658 |
+
"grad_norm": 5.712442398071289,
|
| 659 |
+
"learning_rate": 4.858845914880398e-06,
|
| 660 |
+
"loss": 0.315,
|
| 661 |
+
"step": 46500
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 2.7376514445479962,
|
| 665 |
+
"grad_norm": 7.901050090789795,
|
| 666 |
+
"learning_rate": 4.373446722584654e-06,
|
| 667 |
+
"loss": 0.3021,
|
| 668 |
+
"step": 47000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 2.766775396085741,
|
| 672 |
+
"grad_norm": 6.925070762634277,
|
| 673 |
+
"learning_rate": 3.8880475302889095e-06,
|
| 674 |
+
"loss": 0.2989,
|
| 675 |
+
"step": 47500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 2.7958993476234855,
|
| 679 |
+
"grad_norm": 2.2326674461364746,
|
| 680 |
+
"learning_rate": 3.402648337993166e-06,
|
| 681 |
+
"loss": 0.3024,
|
| 682 |
+
"step": 48000
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 2.8250232991612303,
|
| 686 |
+
"grad_norm": 7.3733320236206055,
|
| 687 |
+
"learning_rate": 2.917249145697422e-06,
|
| 688 |
+
"loss": 0.3078,
|
| 689 |
+
"step": 48500
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 2.8541472506989747,
|
| 693 |
+
"grad_norm": 5.280145645141602,
|
| 694 |
+
"learning_rate": 2.431849953401678e-06,
|
| 695 |
+
"loss": 0.2995,
|
| 696 |
+
"step": 49000
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 2.8832712022367195,
|
| 700 |
+
"grad_norm": 5.809254169464111,
|
| 701 |
+
"learning_rate": 1.9464507611059337e-06,
|
| 702 |
+
"loss": 0.3008,
|
| 703 |
+
"step": 49500
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 2.9123951537744643,
|
| 707 |
+
"grad_norm": 6.8635430335998535,
|
| 708 |
+
"learning_rate": 1.4610515688101895e-06,
|
| 709 |
+
"loss": 0.2995,
|
| 710 |
+
"step": 50000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 2.9415191053122087,
|
| 714 |
+
"grad_norm": 6.390039920806885,
|
| 715 |
+
"learning_rate": 9.756523765144455e-07,
|
| 716 |
+
"loss": 0.301,
|
| 717 |
+
"step": 50500
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 2.9706430568499536,
|
| 721 |
+
"grad_norm": 7.5721964836120605,
|
| 722 |
+
"learning_rate": 4.902531842187015e-07,
|
| 723 |
+
"loss": 0.305,
|
| 724 |
+
"step": 51000
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 2.999767008387698,
|
| 728 |
+
"grad_norm": 6.955125331878662,
|
| 729 |
+
"learning_rate": 4.85399192295744e-09,
|
| 730 |
+
"loss": 0.3002,
|
| 731 |
+
"step": 51500
|
| 732 |
+
}
|
| 733 |
+
],
|
| 734 |
+
"logging_steps": 500,
|
| 735 |
+
"max_steps": 51504,
|
| 736 |
+
"num_input_tokens_seen": 0,
|
| 737 |
+
"num_train_epochs": 3,
|
| 738 |
+
"save_steps": 500,
|
| 739 |
+
"stateful_callbacks": {
|
| 740 |
+
"TrainerControl": {
|
| 741 |
+
"args": {
|
| 742 |
+
"should_epoch_stop": false,
|
| 743 |
+
"should_evaluate": false,
|
| 744 |
+
"should_log": false,
|
| 745 |
+
"should_save": true,
|
| 746 |
+
"should_training_stop": true
|
| 747 |
+
},
|
| 748 |
+
"attributes": {}
|
| 749 |
+
}
|
| 750 |
+
},
|
| 751 |
+
"total_flos": 1.2121938098975232e+16,
|
| 752 |
+
"train_batch_size": 32,
|
| 753 |
+
"trial_name": null,
|
| 754 |
+
"trial_params": null
|
| 755 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:396c778375460b94889a30cd65b23395cb853b096525839df3355d65da7a326e
|
| 3 |
+
size 5841
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|