Upload folder using huggingface_hub
Browse files- checkpoint-1250/config.json +31 -0
- checkpoint-1250/model.safetensors +3 -0
- checkpoint-1250/optimizer.pt +3 -0
- checkpoint-1250/rng_state.pth +3 -0
- checkpoint-1250/scheduler.pt +3 -0
- checkpoint-1250/tokenizer.json +0 -0
- checkpoint-1250/tokenizer_config.json +14 -0
- checkpoint-1250/trainer_state.json +925 -0
- checkpoint-1250/training_args.bin +3 -0
checkpoint-1250/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": null,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"is_decoder": false,
|
| 18 |
+
"layer_norm_eps": 1e-12,
|
| 19 |
+
"max_position_embeddings": 512,
|
| 20 |
+
"model_type": "bert",
|
| 21 |
+
"num_attention_heads": 12,
|
| 22 |
+
"num_hidden_layers": 12,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"position_embedding_type": "absolute",
|
| 25 |
+
"problem_type": "single_label_classification",
|
| 26 |
+
"tie_word_embeddings": true,
|
| 27 |
+
"transformers_version": "5.0.0",
|
| 28 |
+
"type_vocab_size": 2,
|
| 29 |
+
"use_cache": false,
|
| 30 |
+
"vocab_size": 30522
|
| 31 |
+
}
|
checkpoint-1250/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ad520f45e6ff47e61cab924778eacbcf197a8d584c31de5105035ff89dcb251
|
| 3 |
+
size 437958624
|
checkpoint-1250/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5073bb78ceedac0cf6a790a1e98dbd72396a814c53f406d3218778bc18830e43
|
| 3 |
+
size 876041611
|
checkpoint-1250/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f12010f20317a3d6b54079480443fc12d8839bd48304a8ef98d61b1c53a7e76
|
| 3 |
+
size 14645
|
checkpoint-1250/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ad1f24bf2246b019e5c4979ace691aa118b7de7cc84ddd0aa9224068c0079d8
|
| 3 |
+
size 1465
|
checkpoint-1250/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1250/tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"is_local": false,
|
| 6 |
+
"mask_token": "[MASK]",
|
| 7 |
+
"model_max_length": 512,
|
| 8 |
+
"pad_token": "[PAD]",
|
| 9 |
+
"sep_token": "[SEP]",
|
| 10 |
+
"strip_accents": null,
|
| 11 |
+
"tokenize_chinese_chars": true,
|
| 12 |
+
"tokenizer_class": "BertTokenizer",
|
| 13 |
+
"unk_token": "[UNK]"
|
| 14 |
+
}
|
checkpoint-1250/trainer_state.json
ADDED
|
@@ -0,0 +1,925 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 625,
|
| 3 |
+
"best_metric": 0.18495811522006989,
|
| 4 |
+
"best_model_checkpoint": "./results/checkpoint-625",
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1250,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.016,
|
| 14 |
+
"grad_norm": 19.218093872070312,
|
| 15 |
+
"learning_rate": 4.9640000000000006e-05,
|
| 16 |
+
"loss": 0.09028505682945251,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.032,
|
| 21 |
+
"grad_norm": 1.0261529684066772,
|
| 22 |
+
"learning_rate": 4.924e-05,
|
| 23 |
+
"loss": 0.15324625968933106,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.048,
|
| 28 |
+
"grad_norm": 21.003023147583008,
|
| 29 |
+
"learning_rate": 4.884e-05,
|
| 30 |
+
"loss": 0.22774670124053956,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.064,
|
| 35 |
+
"grad_norm": 7.388162612915039,
|
| 36 |
+
"learning_rate": 4.8440000000000004e-05,
|
| 37 |
+
"loss": 0.4121945858001709,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.08,
|
| 42 |
+
"grad_norm": 4.979572296142578,
|
| 43 |
+
"learning_rate": 4.804e-05,
|
| 44 |
+
"loss": 0.38861570358276365,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.096,
|
| 49 |
+
"grad_norm": 5.862935543060303,
|
| 50 |
+
"learning_rate": 4.7640000000000005e-05,
|
| 51 |
+
"loss": 0.29872808456420896,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.112,
|
| 56 |
+
"grad_norm": 8.852452278137207,
|
| 57 |
+
"learning_rate": 4.724e-05,
|
| 58 |
+
"loss": 0.3256639242172241,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.128,
|
| 63 |
+
"grad_norm": 3.3186402320861816,
|
| 64 |
+
"learning_rate": 4.684e-05,
|
| 65 |
+
"loss": 0.3397534847259521,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.144,
|
| 70 |
+
"grad_norm": 5.926950931549072,
|
| 71 |
+
"learning_rate": 4.644e-05,
|
| 72 |
+
"loss": 0.19672555923461915,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.16,
|
| 77 |
+
"grad_norm": 9.196661949157715,
|
| 78 |
+
"learning_rate": 4.604e-05,
|
| 79 |
+
"loss": 0.2907862663269043,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.176,
|
| 84 |
+
"grad_norm": 5.412224292755127,
|
| 85 |
+
"learning_rate": 4.564e-05,
|
| 86 |
+
"loss": 0.2230736255645752,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.192,
|
| 91 |
+
"grad_norm": 2.8200976848602295,
|
| 92 |
+
"learning_rate": 4.524000000000001e-05,
|
| 93 |
+
"loss": 0.3943183422088623,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.208,
|
| 98 |
+
"grad_norm": 11.510780334472656,
|
| 99 |
+
"learning_rate": 4.4840000000000004e-05,
|
| 100 |
+
"loss": 0.28646397590637207,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.224,
|
| 105 |
+
"grad_norm": 3.909830093383789,
|
| 106 |
+
"learning_rate": 4.444e-05,
|
| 107 |
+
"loss": 0.346493124961853,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.24,
|
| 112 |
+
"grad_norm": 3.446835517883301,
|
| 113 |
+
"learning_rate": 4.4040000000000005e-05,
|
| 114 |
+
"loss": 0.2555964946746826,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.256,
|
| 119 |
+
"grad_norm": 8.182538032531738,
|
| 120 |
+
"learning_rate": 4.364e-05,
|
| 121 |
+
"loss": 0.24913170337677001,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.272,
|
| 126 |
+
"grad_norm": 4.328517913818359,
|
| 127 |
+
"learning_rate": 4.324e-05,
|
| 128 |
+
"loss": 0.3257677316665649,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.288,
|
| 133 |
+
"grad_norm": 4.964771270751953,
|
| 134 |
+
"learning_rate": 4.284e-05,
|
| 135 |
+
"loss": 0.28899221420288085,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.304,
|
| 140 |
+
"grad_norm": 9.758742332458496,
|
| 141 |
+
"learning_rate": 4.244e-05,
|
| 142 |
+
"loss": 0.2279355764389038,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.32,
|
| 147 |
+
"grad_norm": 4.366827964782715,
|
| 148 |
+
"learning_rate": 4.2040000000000004e-05,
|
| 149 |
+
"loss": 0.31453232765197753,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.336,
|
| 154 |
+
"grad_norm": 2.277212381362915,
|
| 155 |
+
"learning_rate": 4.164e-05,
|
| 156 |
+
"loss": 0.20993876457214355,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.352,
|
| 161 |
+
"grad_norm": 4.816099166870117,
|
| 162 |
+
"learning_rate": 4.124e-05,
|
| 163 |
+
"loss": 0.27517788410186766,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.368,
|
| 168 |
+
"grad_norm": 3.51198673248291,
|
| 169 |
+
"learning_rate": 4.084e-05,
|
| 170 |
+
"loss": 0.22087533473968507,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.384,
|
| 175 |
+
"grad_norm": 5.840693950653076,
|
| 176 |
+
"learning_rate": 4.044e-05,
|
| 177 |
+
"loss": 0.20846953392028808,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.4,
|
| 182 |
+
"grad_norm": 3.9098050594329834,
|
| 183 |
+
"learning_rate": 4.004e-05,
|
| 184 |
+
"loss": 0.26031317710876467,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.416,
|
| 189 |
+
"grad_norm": 3.918344020843506,
|
| 190 |
+
"learning_rate": 3.964e-05,
|
| 191 |
+
"loss": 0.2516783714294434,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.432,
|
| 196 |
+
"grad_norm": 8.892339706420898,
|
| 197 |
+
"learning_rate": 3.9240000000000004e-05,
|
| 198 |
+
"loss": 0.2795307159423828,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.448,
|
| 203 |
+
"grad_norm": 4.103593826293945,
|
| 204 |
+
"learning_rate": 3.884e-05,
|
| 205 |
+
"loss": 0.23137011528015136,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.464,
|
| 210 |
+
"grad_norm": 6.328890800476074,
|
| 211 |
+
"learning_rate": 3.8440000000000005e-05,
|
| 212 |
+
"loss": 0.22461700439453125,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.48,
|
| 217 |
+
"grad_norm": 6.5414719581604,
|
| 218 |
+
"learning_rate": 3.804e-05,
|
| 219 |
+
"loss": 0.21610186100006104,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.496,
|
| 224 |
+
"grad_norm": 3.691993474960327,
|
| 225 |
+
"learning_rate": 3.7640000000000006e-05,
|
| 226 |
+
"loss": 0.24925684928894043,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.512,
|
| 231 |
+
"grad_norm": 4.344432353973389,
|
| 232 |
+
"learning_rate": 3.724e-05,
|
| 233 |
+
"loss": 0.21005148887634278,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.528,
|
| 238 |
+
"grad_norm": 7.790218353271484,
|
| 239 |
+
"learning_rate": 3.684e-05,
|
| 240 |
+
"loss": 0.17650561332702636,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.544,
|
| 245 |
+
"grad_norm": 7.356423854827881,
|
| 246 |
+
"learning_rate": 3.6440000000000003e-05,
|
| 247 |
+
"loss": 0.2985139131546021,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.56,
|
| 252 |
+
"grad_norm": 2.8463327884674072,
|
| 253 |
+
"learning_rate": 3.604e-05,
|
| 254 |
+
"loss": 0.20631999969482423,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.576,
|
| 259 |
+
"grad_norm": 7.239101409912109,
|
| 260 |
+
"learning_rate": 3.5640000000000004e-05,
|
| 261 |
+
"loss": 0.2260190486907959,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.592,
|
| 266 |
+
"grad_norm": 6.864079475402832,
|
| 267 |
+
"learning_rate": 3.524e-05,
|
| 268 |
+
"loss": 0.29787819385528563,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.608,
|
| 273 |
+
"grad_norm": 4.634511947631836,
|
| 274 |
+
"learning_rate": 3.484e-05,
|
| 275 |
+
"loss": 0.2093559741973877,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.624,
|
| 280 |
+
"grad_norm": 8.057502746582031,
|
| 281 |
+
"learning_rate": 3.444e-05,
|
| 282 |
+
"loss": 0.23704848289489747,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.64,
|
| 287 |
+
"grad_norm": 2.670377731323242,
|
| 288 |
+
"learning_rate": 3.404e-05,
|
| 289 |
+
"loss": 0.20256345272064208,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.656,
|
| 294 |
+
"grad_norm": 5.436578273773193,
|
| 295 |
+
"learning_rate": 3.3639999999999996e-05,
|
| 296 |
+
"loss": 0.2178948402404785,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.672,
|
| 301 |
+
"grad_norm": 2.7397665977478027,
|
| 302 |
+
"learning_rate": 3.324e-05,
|
| 303 |
+
"loss": 0.28787732124328613,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.688,
|
| 308 |
+
"grad_norm": 7.691206455230713,
|
| 309 |
+
"learning_rate": 3.2840000000000004e-05,
|
| 310 |
+
"loss": 0.2569857358932495,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.704,
|
| 315 |
+
"grad_norm": 2.859588623046875,
|
| 316 |
+
"learning_rate": 3.244e-05,
|
| 317 |
+
"loss": 0.21177470684051514,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.72,
|
| 322 |
+
"grad_norm": 8.864638328552246,
|
| 323 |
+
"learning_rate": 3.2040000000000005e-05,
|
| 324 |
+
"loss": 0.21835825443267823,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.736,
|
| 329 |
+
"grad_norm": 3.5713469982147217,
|
| 330 |
+
"learning_rate": 3.164e-05,
|
| 331 |
+
"loss": 0.18327864408493041,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.752,
|
| 336 |
+
"grad_norm": 4.1505351066589355,
|
| 337 |
+
"learning_rate": 3.1240000000000006e-05,
|
| 338 |
+
"loss": 0.23397378921508788,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.768,
|
| 343 |
+
"grad_norm": 7.102250099182129,
|
| 344 |
+
"learning_rate": 3.084e-05,
|
| 345 |
+
"loss": 0.2387765645980835,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.784,
|
| 350 |
+
"grad_norm": 2.268003225326538,
|
| 351 |
+
"learning_rate": 3.0440000000000003e-05,
|
| 352 |
+
"loss": 0.24410586357116698,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.8,
|
| 357 |
+
"grad_norm": 7.200525760650635,
|
| 358 |
+
"learning_rate": 3.004e-05,
|
| 359 |
+
"loss": 0.22940239906311036,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.816,
|
| 364 |
+
"grad_norm": 6.109457015991211,
|
| 365 |
+
"learning_rate": 2.964e-05,
|
| 366 |
+
"loss": 0.23941683769226074,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.832,
|
| 371 |
+
"grad_norm": 2.041025400161743,
|
| 372 |
+
"learning_rate": 2.924e-05,
|
| 373 |
+
"loss": 0.2272693157196045,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.848,
|
| 378 |
+
"grad_norm": 3.117744207382202,
|
| 379 |
+
"learning_rate": 2.8840000000000002e-05,
|
| 380 |
+
"loss": 0.3034891843795776,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.864,
|
| 385 |
+
"grad_norm": 3.5636343955993652,
|
| 386 |
+
"learning_rate": 2.844e-05,
|
| 387 |
+
"loss": 0.22543411254882811,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.88,
|
| 392 |
+
"grad_norm": 5.813530921936035,
|
| 393 |
+
"learning_rate": 2.804e-05,
|
| 394 |
+
"loss": 0.15515211820602418,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.896,
|
| 399 |
+
"grad_norm": 3.961332082748413,
|
| 400 |
+
"learning_rate": 2.764e-05,
|
| 401 |
+
"loss": 0.18014708757400513,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.912,
|
| 406 |
+
"grad_norm": 4.513957500457764,
|
| 407 |
+
"learning_rate": 2.724e-05,
|
| 408 |
+
"loss": 0.15350849628448487,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.928,
|
| 413 |
+
"grad_norm": 4.664239406585693,
|
| 414 |
+
"learning_rate": 2.6840000000000004e-05,
|
| 415 |
+
"loss": 0.17080495357513428,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.944,
|
| 420 |
+
"grad_norm": 4.640005588531494,
|
| 421 |
+
"learning_rate": 2.6440000000000004e-05,
|
| 422 |
+
"loss": 0.2014240026473999,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.96,
|
| 427 |
+
"grad_norm": 4.601800441741943,
|
| 428 |
+
"learning_rate": 2.6040000000000005e-05,
|
| 429 |
+
"loss": 0.14860270023345948,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.976,
|
| 434 |
+
"grad_norm": 3.3365046977996826,
|
| 435 |
+
"learning_rate": 2.5640000000000002e-05,
|
| 436 |
+
"loss": 0.16999433040618897,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.992,
|
| 441 |
+
"grad_norm": 11.081926345825195,
|
| 442 |
+
"learning_rate": 2.5240000000000002e-05,
|
| 443 |
+
"loss": 0.2594302177429199,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.0,
|
| 448 |
+
"eval_loss": 0.18495811522006989,
|
| 449 |
+
"eval_runtime": 154.2281,
|
| 450 |
+
"eval_samples_per_second": 32.42,
|
| 451 |
+
"eval_steps_per_second": 1.018,
|
| 452 |
+
"step": 625
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.008,
|
| 456 |
+
"grad_norm": 1.409481406211853,
|
| 457 |
+
"learning_rate": 2.4840000000000003e-05,
|
| 458 |
+
"loss": 0.23080673217773437,
|
| 459 |
+
"step": 630
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.024,
|
| 463 |
+
"grad_norm": 3.118706703186035,
|
| 464 |
+
"learning_rate": 2.4440000000000003e-05,
|
| 465 |
+
"loss": 0.12968307733535767,
|
| 466 |
+
"step": 640
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.04,
|
| 470 |
+
"grad_norm": 4.754483699798584,
|
| 471 |
+
"learning_rate": 2.404e-05,
|
| 472 |
+
"loss": 0.11642718315124512,
|
| 473 |
+
"step": 650
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.056,
|
| 477 |
+
"grad_norm": 8.341479301452637,
|
| 478 |
+
"learning_rate": 2.364e-05,
|
| 479 |
+
"loss": 0.13068459033966065,
|
| 480 |
+
"step": 660
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.072,
|
| 484 |
+
"grad_norm": 4.099249362945557,
|
| 485 |
+
"learning_rate": 2.324e-05,
|
| 486 |
+
"loss": 0.16937563419342042,
|
| 487 |
+
"step": 670
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 1.088,
|
| 491 |
+
"grad_norm": 4.4017720222473145,
|
| 492 |
+
"learning_rate": 2.284e-05,
|
| 493 |
+
"loss": 0.1266240119934082,
|
| 494 |
+
"step": 680
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.104,
|
| 498 |
+
"grad_norm": 5.481026649475098,
|
| 499 |
+
"learning_rate": 2.244e-05,
|
| 500 |
+
"loss": 0.08416222333908081,
|
| 501 |
+
"step": 690
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.12,
|
| 505 |
+
"grad_norm": 4.0869140625,
|
| 506 |
+
"learning_rate": 2.2040000000000002e-05,
|
| 507 |
+
"loss": 0.13754202127456666,
|
| 508 |
+
"step": 700
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 1.1360000000000001,
|
| 512 |
+
"grad_norm": 12.687203407287598,
|
| 513 |
+
"learning_rate": 2.1640000000000003e-05,
|
| 514 |
+
"loss": 0.07033992409706116,
|
| 515 |
+
"step": 710
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.152,
|
| 519 |
+
"grad_norm": 2.744762897491455,
|
| 520 |
+
"learning_rate": 2.124e-05,
|
| 521 |
+
"loss": 0.10703094005584717,
|
| 522 |
+
"step": 720
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.168,
|
| 526 |
+
"grad_norm": 7.220569133758545,
|
| 527 |
+
"learning_rate": 2.084e-05,
|
| 528 |
+
"loss": 0.13606520891189575,
|
| 529 |
+
"step": 730
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 1.184,
|
| 533 |
+
"grad_norm": 6.549191474914551,
|
| 534 |
+
"learning_rate": 2.044e-05,
|
| 535 |
+
"loss": 0.13524794578552246,
|
| 536 |
+
"step": 740
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.2,
|
| 540 |
+
"grad_norm": 4.867711067199707,
|
| 541 |
+
"learning_rate": 2.004e-05,
|
| 542 |
+
"loss": 0.10759615898132324,
|
| 543 |
+
"step": 750
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.216,
|
| 547 |
+
"grad_norm": 4.896305561065674,
|
| 548 |
+
"learning_rate": 1.9640000000000002e-05,
|
| 549 |
+
"loss": 0.10973103046417236,
|
| 550 |
+
"step": 760
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 1.232,
|
| 554 |
+
"grad_norm": 10.444025039672852,
|
| 555 |
+
"learning_rate": 1.924e-05,
|
| 556 |
+
"loss": 0.05662683844566345,
|
| 557 |
+
"step": 770
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 1.248,
|
| 561 |
+
"grad_norm": 15.567150115966797,
|
| 562 |
+
"learning_rate": 1.8840000000000003e-05,
|
| 563 |
+
"loss": 0.11076383590698242,
|
| 564 |
+
"step": 780
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.264,
|
| 568 |
+
"grad_norm": 2.87619948387146,
|
| 569 |
+
"learning_rate": 1.8440000000000003e-05,
|
| 570 |
+
"loss": 0.09802154898643493,
|
| 571 |
+
"step": 790
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.28,
|
| 575 |
+
"grad_norm": 9.998023986816406,
|
| 576 |
+
"learning_rate": 1.804e-05,
|
| 577 |
+
"loss": 0.1250164270401001,
|
| 578 |
+
"step": 800
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.296,
|
| 582 |
+
"grad_norm": 7.159102439880371,
|
| 583 |
+
"learning_rate": 1.764e-05,
|
| 584 |
+
"loss": 0.09611091613769532,
|
| 585 |
+
"step": 810
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.312,
|
| 589 |
+
"grad_norm": 8.660289764404297,
|
| 590 |
+
"learning_rate": 1.724e-05,
|
| 591 |
+
"loss": 0.1441337823867798,
|
| 592 |
+
"step": 820
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 1.328,
|
| 596 |
+
"grad_norm": 5.77480936050415,
|
| 597 |
+
"learning_rate": 1.684e-05,
|
| 598 |
+
"loss": 0.15176002979278563,
|
| 599 |
+
"step": 830
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 1.3439999999999999,
|
| 603 |
+
"grad_norm": 4.082831382751465,
|
| 604 |
+
"learning_rate": 1.644e-05,
|
| 605 |
+
"loss": 0.08848962783813477,
|
| 606 |
+
"step": 840
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 1.3599999999999999,
|
| 610 |
+
"grad_norm": 2.577115774154663,
|
| 611 |
+
"learning_rate": 1.604e-05,
|
| 612 |
+
"loss": 0.10309876203536987,
|
| 613 |
+
"step": 850
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 1.376,
|
| 617 |
+
"grad_norm": 3.0724472999572754,
|
| 618 |
+
"learning_rate": 1.5640000000000003e-05,
|
| 619 |
+
"loss": 0.10082556009292602,
|
| 620 |
+
"step": 860
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 1.392,
|
| 624 |
+
"grad_norm": 3.345585584640503,
|
| 625 |
+
"learning_rate": 1.5240000000000001e-05,
|
| 626 |
+
"loss": 0.0675260603427887,
|
| 627 |
+
"step": 870
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 1.408,
|
| 631 |
+
"grad_norm": 1.7632936239242554,
|
| 632 |
+
"learning_rate": 1.4840000000000002e-05,
|
| 633 |
+
"loss": 0.11104966402053833,
|
| 634 |
+
"step": 880
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 1.424,
|
| 638 |
+
"grad_norm": 9.795392990112305,
|
| 639 |
+
"learning_rate": 1.444e-05,
|
| 640 |
+
"loss": 0.1164703130722046,
|
| 641 |
+
"step": 890
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 1.44,
|
| 645 |
+
"grad_norm": 0.41051211953163147,
|
| 646 |
+
"learning_rate": 1.4040000000000001e-05,
|
| 647 |
+
"loss": 0.09447898268699646,
|
| 648 |
+
"step": 900
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 1.456,
|
| 652 |
+
"grad_norm": 4.203612804412842,
|
| 653 |
+
"learning_rate": 1.364e-05,
|
| 654 |
+
"loss": 0.14231808185577394,
|
| 655 |
+
"step": 910
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 1.472,
|
| 659 |
+
"grad_norm": 7.408661842346191,
|
| 660 |
+
"learning_rate": 1.324e-05,
|
| 661 |
+
"loss": 0.06679580807685852,
|
| 662 |
+
"step": 920
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 1.488,
|
| 666 |
+
"grad_norm": 7.812554359436035,
|
| 667 |
+
"learning_rate": 1.2839999999999999e-05,
|
| 668 |
+
"loss": 0.08085909485816956,
|
| 669 |
+
"step": 930
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.504,
|
| 673 |
+
"grad_norm": 8.036355972290039,
|
| 674 |
+
"learning_rate": 1.244e-05,
|
| 675 |
+
"loss": 0.14998269081115723,
|
| 676 |
+
"step": 940
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.52,
|
| 680 |
+
"grad_norm": 2.2026758193969727,
|
| 681 |
+
"learning_rate": 1.204e-05,
|
| 682 |
+
"loss": 0.09423889517784119,
|
| 683 |
+
"step": 950
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 1.536,
|
| 687 |
+
"grad_norm": 7.581295490264893,
|
| 688 |
+
"learning_rate": 1.164e-05,
|
| 689 |
+
"loss": 0.07243572473526001,
|
| 690 |
+
"step": 960
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 1.552,
|
| 694 |
+
"grad_norm": 7.5626935958862305,
|
| 695 |
+
"learning_rate": 1.124e-05,
|
| 696 |
+
"loss": 0.1211039662361145,
|
| 697 |
+
"step": 970
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 1.568,
|
| 701 |
+
"grad_norm": 8.267356872558594,
|
| 702 |
+
"learning_rate": 1.084e-05,
|
| 703 |
+
"loss": 0.0996507465839386,
|
| 704 |
+
"step": 980
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 1.584,
|
| 708 |
+
"grad_norm": 0.8569573760032654,
|
| 709 |
+
"learning_rate": 1.0440000000000002e-05,
|
| 710 |
+
"loss": 0.036824467778205874,
|
| 711 |
+
"step": 990
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.6,
|
| 715 |
+
"grad_norm": 2.5389115810394287,
|
| 716 |
+
"learning_rate": 1.004e-05,
|
| 717 |
+
"loss": 0.11773452758789063,
|
| 718 |
+
"step": 1000
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 1.616,
|
| 722 |
+
"grad_norm": 2.706822156906128,
|
| 723 |
+
"learning_rate": 9.640000000000001e-06,
|
| 724 |
+
"loss": 0.19166380167007446,
|
| 725 |
+
"step": 1010
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 1.6320000000000001,
|
| 729 |
+
"grad_norm": 9.506473541259766,
|
| 730 |
+
"learning_rate": 9.24e-06,
|
| 731 |
+
"loss": 0.16758540868759156,
|
| 732 |
+
"step": 1020
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 1.6480000000000001,
|
| 736 |
+
"grad_norm": 0.3241702616214752,
|
| 737 |
+
"learning_rate": 8.840000000000002e-06,
|
| 738 |
+
"loss": 0.1203872561454773,
|
| 739 |
+
"step": 1030
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 1.6640000000000001,
|
| 743 |
+
"grad_norm": 3.3109052181243896,
|
| 744 |
+
"learning_rate": 8.44e-06,
|
| 745 |
+
"loss": 0.0420354425907135,
|
| 746 |
+
"step": 1040
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 1.6800000000000002,
|
| 750 |
+
"grad_norm": 8.419422149658203,
|
| 751 |
+
"learning_rate": 8.040000000000001e-06,
|
| 752 |
+
"loss": 0.10436058044433594,
|
| 753 |
+
"step": 1050
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 1.696,
|
| 757 |
+
"grad_norm": 1.2641408443450928,
|
| 758 |
+
"learning_rate": 7.64e-06,
|
| 759 |
+
"loss": 0.09875598549842834,
|
| 760 |
+
"step": 1060
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 1.712,
|
| 764 |
+
"grad_norm": 1.592099666595459,
|
| 765 |
+
"learning_rate": 7.240000000000001e-06,
|
| 766 |
+
"loss": 0.07384807467460633,
|
| 767 |
+
"step": 1070
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 1.728,
|
| 771 |
+
"grad_norm": 2.490544557571411,
|
| 772 |
+
"learning_rate": 6.840000000000001e-06,
|
| 773 |
+
"loss": 0.1242129921913147,
|
| 774 |
+
"step": 1080
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 1.744,
|
| 778 |
+
"grad_norm": 5.5718889236450195,
|
| 779 |
+
"learning_rate": 6.44e-06,
|
| 780 |
+
"loss": 0.11525803804397583,
|
| 781 |
+
"step": 1090
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 1.76,
|
| 785 |
+
"grad_norm": 6.5801520347595215,
|
| 786 |
+
"learning_rate": 6.040000000000001e-06,
|
| 787 |
+
"loss": 0.0572867214679718,
|
| 788 |
+
"step": 1100
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 1.776,
|
| 792 |
+
"grad_norm": 0.25566336512565613,
|
| 793 |
+
"learning_rate": 5.64e-06,
|
| 794 |
+
"loss": 0.06712960004806519,
|
| 795 |
+
"step": 1110
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 1.792,
|
| 799 |
+
"grad_norm": 5.010447978973389,
|
| 800 |
+
"learning_rate": 5.240000000000001e-06,
|
| 801 |
+
"loss": 0.09681461453437805,
|
| 802 |
+
"step": 1120
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 1.808,
|
| 806 |
+
"grad_norm": 7.9100751876831055,
|
| 807 |
+
"learning_rate": 4.84e-06,
|
| 808 |
+
"loss": 0.07983118295669556,
|
| 809 |
+
"step": 1130
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 1.8239999999999998,
|
| 813 |
+
"grad_norm": 2.053251028060913,
|
| 814 |
+
"learning_rate": 4.440000000000001e-06,
|
| 815 |
+
"loss": 0.05444978475570679,
|
| 816 |
+
"step": 1140
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 1.8399999999999999,
|
| 820 |
+
"grad_norm": 1.8897933959960938,
|
| 821 |
+
"learning_rate": 4.04e-06,
|
| 822 |
+
"loss": 0.10996910333633422,
|
| 823 |
+
"step": 1150
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 1.8559999999999999,
|
| 827 |
+
"grad_norm": 7.506521224975586,
|
| 828 |
+
"learning_rate": 3.6400000000000003e-06,
|
| 829 |
+
"loss": 0.10293327569961548,
|
| 830 |
+
"step": 1160
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 1.8719999999999999,
|
| 834 |
+
"grad_norm": 7.165153980255127,
|
| 835 |
+
"learning_rate": 3.24e-06,
|
| 836 |
+
"loss": 0.13498435020446778,
|
| 837 |
+
"step": 1170
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 1.888,
|
| 841 |
+
"grad_norm": 5.471543312072754,
|
| 842 |
+
"learning_rate": 2.8400000000000003e-06,
|
| 843 |
+
"loss": 0.14159295558929444,
|
| 844 |
+
"step": 1180
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 1.904,
|
| 848 |
+
"grad_norm": 1.521297574043274,
|
| 849 |
+
"learning_rate": 2.4400000000000004e-06,
|
| 850 |
+
"loss": 0.12328060865402221,
|
| 851 |
+
"step": 1190
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 1.92,
|
| 855 |
+
"grad_norm": 5.420016288757324,
|
| 856 |
+
"learning_rate": 2.0400000000000004e-06,
|
| 857 |
+
"loss": 0.0512222945690155,
|
| 858 |
+
"step": 1200
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 1.936,
|
| 862 |
+
"grad_norm": 4.897031784057617,
|
| 863 |
+
"learning_rate": 1.6400000000000002e-06,
|
| 864 |
+
"loss": 0.09001591801643372,
|
| 865 |
+
"step": 1210
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 1.952,
|
| 869 |
+
"grad_norm": 2.213510036468506,
|
| 870 |
+
"learning_rate": 1.24e-06,
|
| 871 |
+
"loss": 0.11251969337463379,
|
| 872 |
+
"step": 1220
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 1.968,
|
| 876 |
+
"grad_norm": 0.9154443740844727,
|
| 877 |
+
"learning_rate": 8.4e-07,
|
| 878 |
+
"loss": 0.12515219449996948,
|
| 879 |
+
"step": 1230
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.984,
|
| 883 |
+
"grad_norm": 13.852690696716309,
|
| 884 |
+
"learning_rate": 4.4e-07,
|
| 885 |
+
"loss": 0.07310597896575928,
|
| 886 |
+
"step": 1240
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 2.0,
|
| 890 |
+
"grad_norm": 2.5578453540802,
|
| 891 |
+
"learning_rate": 4e-08,
|
| 892 |
+
"loss": 0.132768714427948,
|
| 893 |
+
"step": 1250
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 2.0,
|
| 897 |
+
"eval_loss": 0.18955644965171814,
|
| 898 |
+
"eval_runtime": 154.3037,
|
| 899 |
+
"eval_samples_per_second": 32.404,
|
| 900 |
+
"eval_steps_per_second": 1.017,
|
| 901 |
+
"step": 1250
|
| 902 |
+
}
|
| 903 |
+
],
|
| 904 |
+
"logging_steps": 10,
|
| 905 |
+
"max_steps": 1250,
|
| 906 |
+
"num_input_tokens_seen": 0,
|
| 907 |
+
"num_train_epochs": 2,
|
| 908 |
+
"save_steps": 500,
|
| 909 |
+
"stateful_callbacks": {
|
| 910 |
+
"TrainerControl": {
|
| 911 |
+
"args": {
|
| 912 |
+
"should_epoch_stop": false,
|
| 913 |
+
"should_evaluate": false,
|
| 914 |
+
"should_log": false,
|
| 915 |
+
"should_save": true,
|
| 916 |
+
"should_training_stop": true
|
| 917 |
+
},
|
| 918 |
+
"attributes": {}
|
| 919 |
+
}
|
| 920 |
+
},
|
| 921 |
+
"total_flos": 1.05244422144e+16,
|
| 922 |
+
"train_batch_size": 32,
|
| 923 |
+
"trial_name": null,
|
| 924 |
+
"trial_params": null
|
| 925 |
+
}
|
checkpoint-1250/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a1c344e29edd7edf7d1a6b8ac205353a4129831994c51891c82a541b7d2dc8d
|
| 3 |
+
size 5201
|