Training in progress, step 16000, checkpoint
Browse files- .gitattributes +1 -0
- checkpoint-16000/config.json +35 -0
- checkpoint-16000/model.safetensors +3 -0
- checkpoint-16000/optimizer.pt +3 -0
- checkpoint-16000/rng_state.pth +3 -0
- checkpoint-16000/scheduler.pt +3 -0
- checkpoint-16000/sentencepiece.bpe.model +3 -0
- checkpoint-16000/special_tokens_map.json +51 -0
- checkpoint-16000/tokenizer.json +3 -0
- checkpoint-16000/tokenizer_config.json +59 -0
- checkpoint-16000/trainer_state.json +450 -0
- checkpoint-16000/training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -49,3 +49,4 @@ checkpoint-12000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
| 49 |
checkpoint-13000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 50 |
checkpoint-14000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 51 |
checkpoint-15000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 49 |
checkpoint-13000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 50 |
checkpoint-14000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 51 |
checkpoint-15000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
checkpoint-16000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
checkpoint-16000/config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"XLMRobertaForTokenClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "B",
|
| 15 |
+
"1": "I"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"B": 0,
|
| 21 |
+
"I": 1
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_eps": 1e-05,
|
| 24 |
+
"max_position_embeddings": 514,
|
| 25 |
+
"model_type": "xlm-roberta",
|
| 26 |
+
"num_attention_heads": 12,
|
| 27 |
+
"num_hidden_layers": 12,
|
| 28 |
+
"output_past": true,
|
| 29 |
+
"pad_token_id": 1,
|
| 30 |
+
"position_embedding_type": "absolute",
|
| 31 |
+
"transformers_version": "4.57.1",
|
| 32 |
+
"type_vocab_size": 1,
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 250002
|
| 35 |
+
}
|
checkpoint-16000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cea1dd8e11260782e239ce9c61eedfd61a8d9e74dc45b804dabe9e626c086f8a
|
| 3 |
+
size 1109842416
|
checkpoint-16000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04c27a25ef91489a6fdf62ffb6236d3543c2055112ade73266c3df8f9fa92a80
|
| 3 |
+
size 2219806475
|
checkpoint-16000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fccfeef076ba4d048a3286a7d11dd305869fc33d4b3d1c3c623496609ede0c4
|
| 3 |
+
size 14645
|
checkpoint-16000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25e159b2c3bf5df5f7d85d74ec2b07d12ecdc6702eb8a79ed7981cd18a70cca1
|
| 3 |
+
size 1465
|
checkpoint-16000/sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
checkpoint-16000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-16000/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
|
| 3 |
+
size 17082832
|
checkpoint-16000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"250001": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"max_length": 512,
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"stride": 0,
|
| 55 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 56 |
+
"truncation_side": "right",
|
| 57 |
+
"truncation_strategy": "longest_first",
|
| 58 |
+
"unk_token": "<unk>"
|
| 59 |
+
}
|
checkpoint-16000/trainer_state.json
ADDED
|
@@ -0,0 +1,450 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 16000,
|
| 3 |
+
"best_metric": 0.10620830953121185,
|
| 4 |
+
"best_model_checkpoint": "myanmar_text_segmentation_model/checkpoint-16000",
|
| 5 |
+
"epoch": 1.4701828539924653,
|
| 6 |
+
"eval_steps": 1000,
|
| 7 |
+
"global_step": 16000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.04594321418726454,
|
| 14 |
+
"grad_norm": 0.577109158039093,
|
| 15 |
+
"learning_rate": 1.9816594688964442e-05,
|
| 16 |
+
"loss": 0.1144,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.09188642837452908,
|
| 21 |
+
"grad_norm": 0.8819814324378967,
|
| 22 |
+
"learning_rate": 1.9632821832215383e-05,
|
| 23 |
+
"loss": 0.1133,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.09188642837452908,
|
| 28 |
+
"eval_accuracy": 0.9564004775738034,
|
| 29 |
+
"eval_f1": 0.7581789101913106,
|
| 30 |
+
"eval_loss": 0.11448723077774048,
|
| 31 |
+
"eval_precision": 0.7703745996379334,
|
| 32 |
+
"eval_recall": 0.7463633395484631,
|
| 33 |
+
"eval_runtime": 465.4607,
|
| 34 |
+
"eval_samples_per_second": 61.528,
|
| 35 |
+
"eval_steps_per_second": 1.231,
|
| 36 |
+
"step": 1000
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.1378296425617936,
|
| 40 |
+
"grad_norm": 0.5137984156608582,
|
| 41 |
+
"learning_rate": 1.9449048975466325e-05,
|
| 42 |
+
"loss": 0.1119,
|
| 43 |
+
"step": 1500
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.18377285674905816,
|
| 47 |
+
"grad_norm": 0.6753482222557068,
|
| 48 |
+
"learning_rate": 1.9265276118717266e-05,
|
| 49 |
+
"loss": 0.1115,
|
| 50 |
+
"step": 2000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.18377285674905816,
|
| 54 |
+
"eval_accuracy": 0.9565513036953667,
|
| 55 |
+
"eval_f1": 0.7631813253052621,
|
| 56 |
+
"eval_loss": 0.11509840190410614,
|
| 57 |
+
"eval_precision": 0.7619568901058112,
|
| 58 |
+
"eval_recall": 0.7644097020785157,
|
| 59 |
+
"eval_runtime": 471.4797,
|
| 60 |
+
"eval_samples_per_second": 60.743,
|
| 61 |
+
"eval_steps_per_second": 1.215,
|
| 62 |
+
"step": 2000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.2297160709363227,
|
| 66 |
+
"grad_norm": 0.46862444281578064,
|
| 67 |
+
"learning_rate": 1.9081503261968207e-05,
|
| 68 |
+
"loss": 0.1083,
|
| 69 |
+
"step": 2500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.2756592851235872,
|
| 73 |
+
"grad_norm": 0.6514066457748413,
|
| 74 |
+
"learning_rate": 1.889773040521915e-05,
|
| 75 |
+
"loss": 0.1085,
|
| 76 |
+
"step": 3000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.2756592851235872,
|
| 80 |
+
"eval_accuracy": 0.955793370748351,
|
| 81 |
+
"eval_f1": 0.7617613129080717,
|
| 82 |
+
"eval_loss": 0.11627302318811417,
|
| 83 |
+
"eval_precision": 0.7514122514122514,
|
| 84 |
+
"eval_recall": 0.7723994268768838,
|
| 85 |
+
"eval_runtime": 464.541,
|
| 86 |
+
"eval_samples_per_second": 61.65,
|
| 87 |
+
"eval_steps_per_second": 1.233,
|
| 88 |
+
"step": 3000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.3216024993108518,
|
| 92 |
+
"grad_norm": 0.5837205052375793,
|
| 93 |
+
"learning_rate": 1.8713957548470093e-05,
|
| 94 |
+
"loss": 0.1068,
|
| 95 |
+
"step": 3500
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.3675457134981163,
|
| 99 |
+
"grad_norm": 0.590044379234314,
|
| 100 |
+
"learning_rate": 1.8530184691721034e-05,
|
| 101 |
+
"loss": 0.1076,
|
| 102 |
+
"step": 4000
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.3675457134981163,
|
| 106 |
+
"eval_accuracy": 0.9567566300121167,
|
| 107 |
+
"eval_f1": 0.7569129075628852,
|
| 108 |
+
"eval_loss": 0.11681018769741058,
|
| 109 |
+
"eval_precision": 0.7790560842692136,
|
| 110 |
+
"eval_recall": 0.7359936967250493,
|
| 111 |
+
"eval_runtime": 464.1614,
|
| 112 |
+
"eval_samples_per_second": 61.701,
|
| 113 |
+
"eval_steps_per_second": 1.234,
|
| 114 |
+
"step": 4000
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.41348892768538087,
|
| 118 |
+
"grad_norm": 0.43107616901397705,
|
| 119 |
+
"learning_rate": 1.8346411834971975e-05,
|
| 120 |
+
"loss": 0.1071,
|
| 121 |
+
"step": 4500
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.4594321418726454,
|
| 125 |
+
"grad_norm": 0.6132990121841431,
|
| 126 |
+
"learning_rate": 1.8162638978222916e-05,
|
| 127 |
+
"loss": 0.1056,
|
| 128 |
+
"step": 5000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.4594321418726454,
|
| 132 |
+
"eval_accuracy": 0.9576032842071108,
|
| 133 |
+
"eval_f1": 0.7661190672004459,
|
| 134 |
+
"eval_loss": 0.11183962970972061,
|
| 135 |
+
"eval_precision": 0.7719609680194174,
|
| 136 |
+
"eval_recall": 0.7603649207638403,
|
| 137 |
+
"eval_runtime": 473.1438,
|
| 138 |
+
"eval_samples_per_second": 60.529,
|
| 139 |
+
"eval_steps_per_second": 1.211,
|
| 140 |
+
"step": 5000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.5053753560599099,
|
| 144 |
+
"grad_norm": 0.4892466962337494,
|
| 145 |
+
"learning_rate": 1.7978866121473858e-05,
|
| 146 |
+
"loss": 0.1154,
|
| 147 |
+
"step": 5500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.5513185702471745,
|
| 151 |
+
"grad_norm": 0.8282744884490967,
|
| 152 |
+
"learning_rate": 1.7795093264724802e-05,
|
| 153 |
+
"loss": 0.1141,
|
| 154 |
+
"step": 6000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.5513185702471745,
|
| 158 |
+
"eval_accuracy": 0.9580804777765948,
|
| 159 |
+
"eval_f1": 0.7681685393564336,
|
| 160 |
+
"eval_loss": 0.11200755834579468,
|
| 161 |
+
"eval_precision": 0.7751412801894542,
|
| 162 |
+
"eval_recall": 0.7613201259575663,
|
| 163 |
+
"eval_runtime": 463.6002,
|
| 164 |
+
"eval_samples_per_second": 61.775,
|
| 165 |
+
"eval_steps_per_second": 1.236,
|
| 166 |
+
"step": 6000
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.597261784434439,
|
| 170 |
+
"grad_norm": 0.44782352447509766,
|
| 171 |
+
"learning_rate": 1.7611320407975743e-05,
|
| 172 |
+
"loss": 0.1135,
|
| 173 |
+
"step": 6500
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.6432049986217035,
|
| 177 |
+
"grad_norm": 0.5544679760932922,
|
| 178 |
+
"learning_rate": 1.7427547551226684e-05,
|
| 179 |
+
"loss": 0.1154,
|
| 180 |
+
"step": 7000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.6432049986217035,
|
| 184 |
+
"eval_accuracy": 0.9576146912247081,
|
| 185 |
+
"eval_f1": 0.7686338805157804,
|
| 186 |
+
"eval_loss": 0.11075501888990402,
|
| 187 |
+
"eval_precision": 0.7656366294168357,
|
| 188 |
+
"eval_recall": 0.7716546906241484,
|
| 189 |
+
"eval_runtime": 472.6577,
|
| 190 |
+
"eval_samples_per_second": 60.591,
|
| 191 |
+
"eval_steps_per_second": 1.212,
|
| 192 |
+
"step": 7000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.6891482128089681,
|
| 196 |
+
"grad_norm": 0.4101652503013611,
|
| 197 |
+
"learning_rate": 1.7243774694477626e-05,
|
| 198 |
+
"loss": 0.1123,
|
| 199 |
+
"step": 7500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.7350914269962326,
|
| 203 |
+
"grad_norm": 0.5032928586006165,
|
| 204 |
+
"learning_rate": 1.7060001837728567e-05,
|
| 205 |
+
"loss": 0.1128,
|
| 206 |
+
"step": 8000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.7350914269962326,
|
| 210 |
+
"eval_accuracy": 0.9583707230021242,
|
| 211 |
+
"eval_f1": 0.7702898098589065,
|
| 212 |
+
"eval_loss": 0.10922538489103317,
|
| 213 |
+
"eval_precision": 0.7744496660220761,
|
| 214 |
+
"eval_recall": 0.7661744031991279,
|
| 215 |
+
"eval_runtime": 465.4833,
|
| 216 |
+
"eval_samples_per_second": 61.525,
|
| 217 |
+
"eval_steps_per_second": 1.231,
|
| 218 |
+
"step": 8000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.7810346411834972,
|
| 222 |
+
"grad_norm": 0.5559138059616089,
|
| 223 |
+
"learning_rate": 1.687622898097951e-05,
|
| 224 |
+
"loss": 0.112,
|
| 225 |
+
"step": 8500
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.8269778553707617,
|
| 229 |
+
"grad_norm": 0.7113578915596008,
|
| 230 |
+
"learning_rate": 1.6692456124230453e-05,
|
| 231 |
+
"loss": 0.1082,
|
| 232 |
+
"step": 9000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.8269778553707617,
|
| 236 |
+
"eval_accuracy": 0.9588998818739956,
|
| 237 |
+
"eval_f1": 0.7713698035177239,
|
| 238 |
+
"eval_loss": 0.10946337133646011,
|
| 239 |
+
"eval_precision": 0.78099547261026,
|
| 240 |
+
"eval_recall": 0.7619785159781004,
|
| 241 |
+
"eval_runtime": 477.2564,
|
| 242 |
+
"eval_samples_per_second": 60.008,
|
| 243 |
+
"eval_steps_per_second": 1.201,
|
| 244 |
+
"step": 9000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.8729210695580263,
|
| 248 |
+
"grad_norm": 0.4333978593349457,
|
| 249 |
+
"learning_rate": 1.6508683267481394e-05,
|
| 250 |
+
"loss": 0.1116,
|
| 251 |
+
"step": 9500
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.9188642837452908,
|
| 255 |
+
"grad_norm": 0.3579271137714386,
|
| 256 |
+
"learning_rate": 1.6324910410732335e-05,
|
| 257 |
+
"loss": 0.1101,
|
| 258 |
+
"step": 10000
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.9188642837452908,
|
| 262 |
+
"eval_accuracy": 0.9590893651107495,
|
| 263 |
+
"eval_f1": 0.7721416651417115,
|
| 264 |
+
"eval_loss": 0.10736154764890671,
|
| 265 |
+
"eval_precision": 0.7816850586599052,
|
| 266 |
+
"eval_recall": 0.7628284867013311,
|
| 267 |
+
"eval_runtime": 478.6898,
|
| 268 |
+
"eval_samples_per_second": 59.828,
|
| 269 |
+
"eval_steps_per_second": 1.197,
|
| 270 |
+
"step": 10000
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.9648074979325554,
|
| 274 |
+
"grad_norm": 0.4602518677711487,
|
| 275 |
+
"learning_rate": 1.6141137553983276e-05,
|
| 276 |
+
"loss": 0.1101,
|
| 277 |
+
"step": 10500
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 1.0107507121198198,
|
| 281 |
+
"grad_norm": 0.5322664976119995,
|
| 282 |
+
"learning_rate": 1.5957364697234217e-05,
|
| 283 |
+
"loss": 0.1101,
|
| 284 |
+
"step": 11000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.0107507121198198,
|
| 288 |
+
"eval_accuracy": 0.9591349931811384,
|
| 289 |
+
"eval_f1": 0.7744744313952638,
|
| 290 |
+
"eval_loss": 0.10792569071054459,
|
| 291 |
+
"eval_precision": 0.7768799906601179,
|
| 292 |
+
"eval_recall": 0.7720837234653981,
|
| 293 |
+
"eval_runtime": 477.7344,
|
| 294 |
+
"eval_samples_per_second": 59.948,
|
| 295 |
+
"eval_steps_per_second": 1.199,
|
| 296 |
+
"step": 11000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.0566939263070845,
|
| 300 |
+
"grad_norm": 0.5673955678939819,
|
| 301 |
+
"learning_rate": 1.5773591840485162e-05,
|
| 302 |
+
"loss": 0.1071,
|
| 303 |
+
"step": 11500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.102637140494349,
|
| 307 |
+
"grad_norm": 0.42657607793807983,
|
| 308 |
+
"learning_rate": 1.5589818983736103e-05,
|
| 309 |
+
"loss": 0.1058,
|
| 310 |
+
"step": 12000
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.102637140494349,
|
| 314 |
+
"eval_accuracy": 0.9584847931780965,
|
| 315 |
+
"eval_f1": 0.7735292150015388,
|
| 316 |
+
"eval_loss": 0.10933595150709152,
|
| 317 |
+
"eval_precision": 0.7671773857517072,
|
| 318 |
+
"eval_recall": 0.779987102031565,
|
| 319 |
+
"eval_runtime": 475.9965,
|
| 320 |
+
"eval_samples_per_second": 60.166,
|
| 321 |
+
"eval_steps_per_second": 1.204,
|
| 322 |
+
"step": 12000
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.1485803546816136,
|
| 326 |
+
"grad_norm": 0.4599572718143463,
|
| 327 |
+
"learning_rate": 1.5406046126987044e-05,
|
| 328 |
+
"loss": 0.107,
|
| 329 |
+
"step": 12500
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.194523568868878,
|
| 333 |
+
"grad_norm": 0.4379059970378876,
|
| 334 |
+
"learning_rate": 1.5222273270237986e-05,
|
| 335 |
+
"loss": 0.107,
|
| 336 |
+
"step": 13000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.194523568868878,
|
| 340 |
+
"eval_accuracy": 0.959601413456225,
|
| 341 |
+
"eval_f1": 0.7737560775183182,
|
| 342 |
+
"eval_loss": 0.1075456365942955,
|
| 343 |
+
"eval_precision": 0.7856481314090709,
|
| 344 |
+
"eval_recall": 0.76221866643641,
|
| 345 |
+
"eval_runtime": 478.1835,
|
| 346 |
+
"eval_samples_per_second": 59.891,
|
| 347 |
+
"eval_steps_per_second": 1.198,
|
| 348 |
+
"step": 13000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.2404667830561427,
|
| 352 |
+
"grad_norm": 0.43774718046188354,
|
| 353 |
+
"learning_rate": 1.5038500413488928e-05,
|
| 354 |
+
"loss": 0.1055,
|
| 355 |
+
"step": 13500
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 1.286409997243407,
|
| 359 |
+
"grad_norm": 0.4196317195892334,
|
| 360 |
+
"learning_rate": 1.485472755673987e-05,
|
| 361 |
+
"loss": 0.1055,
|
| 362 |
+
"step": 14000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.286409997243407,
|
| 366 |
+
"eval_accuracy": 0.959860606244962,
|
| 367 |
+
"eval_f1": 0.7768597287158228,
|
| 368 |
+
"eval_loss": 0.10658087581396103,
|
| 369 |
+
"eval_precision": 0.7824100936011823,
|
| 370 |
+
"eval_recall": 0.7713875569682759,
|
| 371 |
+
"eval_runtime": 464.4067,
|
| 372 |
+
"eval_samples_per_second": 61.668,
|
| 373 |
+
"eval_steps_per_second": 1.234,
|
| 374 |
+
"step": 14000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.3323532114306718,
|
| 378 |
+
"grad_norm": 0.36208856105804443,
|
| 379 |
+
"learning_rate": 1.467095469999081e-05,
|
| 380 |
+
"loss": 0.1035,
|
| 381 |
+
"step": 14500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.3782964256179362,
|
| 385 |
+
"grad_norm": 0.5692697763442993,
|
| 386 |
+
"learning_rate": 1.4487181843241755e-05,
|
| 387 |
+
"loss": 0.1054,
|
| 388 |
+
"step": 15000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.3782964256179362,
|
| 392 |
+
"eval_accuracy": 0.9593396857746885,
|
| 393 |
+
"eval_f1": 0.7750922296908528,
|
| 394 |
+
"eval_loss": 0.10651089251041412,
|
| 395 |
+
"eval_precision": 0.7777847213920075,
|
| 396 |
+
"eval_recall": 0.7724183151151778,
|
| 397 |
+
"eval_runtime": 484.7629,
|
| 398 |
+
"eval_samples_per_second": 59.078,
|
| 399 |
+
"eval_steps_per_second": 1.182,
|
| 400 |
+
"step": 15000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.4242396398052009,
|
| 404 |
+
"grad_norm": 0.4805659055709839,
|
| 405 |
+
"learning_rate": 1.4303408986492697e-05,
|
| 406 |
+
"loss": 0.1043,
|
| 407 |
+
"step": 15500
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 1.4701828539924653,
|
| 411 |
+
"grad_norm": 0.5373257994651794,
|
| 412 |
+
"learning_rate": 1.411963612974364e-05,
|
| 413 |
+
"loss": 0.1038,
|
| 414 |
+
"step": 16000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.4701828539924653,
|
| 418 |
+
"eval_accuracy": 0.9594822734946539,
|
| 419 |
+
"eval_f1": 0.77620383584155,
|
| 420 |
+
"eval_loss": 0.10620830953121185,
|
| 421 |
+
"eval_precision": 0.7775004264051742,
|
| 422 |
+
"eval_recall": 0.7749115625699877,
|
| 423 |
+
"eval_runtime": 484.6548,
|
| 424 |
+
"eval_samples_per_second": 59.092,
|
| 425 |
+
"eval_steps_per_second": 1.182,
|
| 426 |
+
"step": 16000
|
| 427 |
+
}
|
| 428 |
+
],
|
| 429 |
+
"logging_steps": 500,
|
| 430 |
+
"max_steps": 54415,
|
| 431 |
+
"num_input_tokens_seen": 0,
|
| 432 |
+
"num_train_epochs": 5,
|
| 433 |
+
"save_steps": 1000,
|
| 434 |
+
"stateful_callbacks": {
|
| 435 |
+
"TrainerControl": {
|
| 436 |
+
"args": {
|
| 437 |
+
"should_epoch_stop": false,
|
| 438 |
+
"should_evaluate": false,
|
| 439 |
+
"should_log": false,
|
| 440 |
+
"should_save": true,
|
| 441 |
+
"should_training_stop": false
|
| 442 |
+
},
|
| 443 |
+
"attributes": {}
|
| 444 |
+
}
|
| 445 |
+
},
|
| 446 |
+
"total_flos": 1.8607586715262573e+17,
|
| 447 |
+
"train_batch_size": 50,
|
| 448 |
+
"trial_name": null,
|
| 449 |
+
"trial_params": null
|
| 450 |
+
}
|
checkpoint-16000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00b4b9762ccfa84b11343caf9dc8e425d1fff34876d44d47e49b5c8a90f64236
|
| 3 |
+
size 5841
|