Training in progress, step 1600, checkpoint
Browse files- checkpoint-1600/config.json +56 -0
- checkpoint-1600/model.safetensors +3 -0
- checkpoint-1600/optimizer.pt +3 -0
- checkpoint-1600/rng_state.pth +3 -0
- checkpoint-1600/scheduler.pt +3 -0
- checkpoint-1600/special_tokens_map.json +51 -0
- checkpoint-1600/tokenizer.json +3 -0
- checkpoint-1600/tokenizer_config.json +54 -0
- checkpoint-1600/trainer_state.json +246 -0
- checkpoint-1600/training_args.bin +3 -0
checkpoint-1600/config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "nielsr/lilt-xlm-roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LiltForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"channel_shrink_ratio": 4,
|
| 9 |
+
"classifier_dropout": null,
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "Caption",
|
| 16 |
+
"1": "Footnote",
|
| 17 |
+
"2": "Formula",
|
| 18 |
+
"3": "List-item",
|
| 19 |
+
"4": "Page-footer",
|
| 20 |
+
"5": "Page-header",
|
| 21 |
+
"6": "Picture",
|
| 22 |
+
"7": "Section-header",
|
| 23 |
+
"8": "Table",
|
| 24 |
+
"9": "Text",
|
| 25 |
+
"10": "Title"
|
| 26 |
+
},
|
| 27 |
+
"initializer_range": 0.02,
|
| 28 |
+
"intermediate_size": 3072,
|
| 29 |
+
"label2id": {
|
| 30 |
+
"Caption": 0,
|
| 31 |
+
"Footnote": 1,
|
| 32 |
+
"Formula": 2,
|
| 33 |
+
"List-item": 3,
|
| 34 |
+
"Page-footer": 4,
|
| 35 |
+
"Page-header": 5,
|
| 36 |
+
"Picture": 6,
|
| 37 |
+
"Section-header": 7,
|
| 38 |
+
"Table": 8,
|
| 39 |
+
"Text": 9,
|
| 40 |
+
"Title": 10
|
| 41 |
+
},
|
| 42 |
+
"layer_norm_eps": 1e-05,
|
| 43 |
+
"max_2d_position_embeddings": 1024,
|
| 44 |
+
"max_position_embeddings": 514,
|
| 45 |
+
"model_type": "lilt",
|
| 46 |
+
"num_attention_heads": 12,
|
| 47 |
+
"num_hidden_layers": 12,
|
| 48 |
+
"output_past": true,
|
| 49 |
+
"pad_token_id": 1,
|
| 50 |
+
"position_embedding_type": "absolute",
|
| 51 |
+
"torch_dtype": "float32",
|
| 52 |
+
"transformers_version": "4.41.2",
|
| 53 |
+
"type_vocab_size": 1,
|
| 54 |
+
"use_cache": true,
|
| 55 |
+
"vocab_size": 250002
|
| 56 |
+
}
|
checkpoint-1600/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3f06d493585d02543c0f85b3a4c8df185ce546121387fead04845213ae8598f
|
| 3 |
+
size 1134332228
|
checkpoint-1600/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab89706b6db32c79095b7b28eee5be3ab8cf12155def5844b4f181ec5eaa3d7d
|
| 3 |
+
size 2265924830
|
checkpoint-1600/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9af7c696d7d3613b57047f535219171e5e37d3344701ad987ff4224c53d3b144
|
| 3 |
+
size 14244
|
checkpoint-1600/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de1c16b862e71d299ea1dba2557e5bcbe7d2ea20d693fdbf60c63ec37bce0fe4
|
| 3 |
+
size 1064
|
checkpoint-1600/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-1600/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
|
| 3 |
+
size 17082734
|
checkpoint-1600/tokenizer_config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"mask_token": "<mask>",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "<pad>",
|
| 51 |
+
"sep_token": "</s>",
|
| 52 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 53 |
+
"unk_token": "<unk>"
|
| 54 |
+
}
|
checkpoint-1600/trainer_state.json
ADDED
|
@@ -0,0 +1,246 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8963138930200525,
|
| 3 |
+
"best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v1/checkpoint-1600",
|
| 4 |
+
"epoch": 0.8528784648187633,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 1600,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.053304904051172705,
|
| 13 |
+
"eval_accuracy": 0.6684599798377034,
|
| 14 |
+
"eval_f1": 0.6684599798377034,
|
| 15 |
+
"eval_loss": 0.9209221005439758,
|
| 16 |
+
"eval_precision": 0.6684599798377034,
|
| 17 |
+
"eval_recall": 0.6684599798377034,
|
| 18 |
+
"eval_runtime": 41.8743,
|
| 19 |
+
"eval_samples_per_second": 38.377,
|
| 20 |
+
"eval_steps_per_second": 2.412,
|
| 21 |
+
"step": 100
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.10660980810234541,
|
| 25 |
+
"eval_accuracy": 0.8154451176300318,
|
| 26 |
+
"eval_f1": 0.8154451176300318,
|
| 27 |
+
"eval_loss": 0.6488999724388123,
|
| 28 |
+
"eval_precision": 0.8154451176300318,
|
| 29 |
+
"eval_recall": 0.8154451176300318,
|
| 30 |
+
"eval_runtime": 44.2144,
|
| 31 |
+
"eval_samples_per_second": 36.346,
|
| 32 |
+
"eval_steps_per_second": 2.284,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.15991471215351813,
|
| 37 |
+
"eval_accuracy": 0.7420323994130975,
|
| 38 |
+
"eval_f1": 0.7420323994130975,
|
| 39 |
+
"eval_loss": 0.7198283076286316,
|
| 40 |
+
"eval_precision": 0.7420323994130975,
|
| 41 |
+
"eval_recall": 0.7420323994130975,
|
| 42 |
+
"eval_runtime": 41.064,
|
| 43 |
+
"eval_samples_per_second": 39.134,
|
| 44 |
+
"eval_steps_per_second": 2.46,
|
| 45 |
+
"step": 300
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.21321961620469082,
|
| 49 |
+
"eval_accuracy": 0.7961212532564105,
|
| 50 |
+
"eval_f1": 0.7961212532564104,
|
| 51 |
+
"eval_loss": 0.5486767292022705,
|
| 52 |
+
"eval_precision": 0.7961212532564105,
|
| 53 |
+
"eval_recall": 0.7961212532564105,
|
| 54 |
+
"eval_runtime": 43.0362,
|
| 55 |
+
"eval_samples_per_second": 37.341,
|
| 56 |
+
"eval_steps_per_second": 2.347,
|
| 57 |
+
"step": 400
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.26652452025586354,
|
| 61 |
+
"grad_norm": 8.946574211120605,
|
| 62 |
+
"learning_rate": 1.4722814498933904e-05,
|
| 63 |
+
"loss": 0.736,
|
| 64 |
+
"step": 500
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.26652452025586354,
|
| 68 |
+
"eval_accuracy": 0.8669088803936639,
|
| 69 |
+
"eval_f1": 0.8669088803936638,
|
| 70 |
+
"eval_loss": 0.44298624992370605,
|
| 71 |
+
"eval_precision": 0.8669088803936639,
|
| 72 |
+
"eval_recall": 0.8669088803936639,
|
| 73 |
+
"eval_runtime": 42.8219,
|
| 74 |
+
"eval_samples_per_second": 37.527,
|
| 75 |
+
"eval_steps_per_second": 2.359,
|
| 76 |
+
"step": 500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.31982942430703626,
|
| 80 |
+
"eval_accuracy": 0.8614091648617086,
|
| 81 |
+
"eval_f1": 0.8614091648617086,
|
| 82 |
+
"eval_loss": 0.4405972361564636,
|
| 83 |
+
"eval_precision": 0.8614091648617086,
|
| 84 |
+
"eval_recall": 0.8614091648617086,
|
| 85 |
+
"eval_runtime": 46.0068,
|
| 86 |
+
"eval_samples_per_second": 34.93,
|
| 87 |
+
"eval_steps_per_second": 2.195,
|
| 88 |
+
"step": 600
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.373134328358209,
|
| 92 |
+
"eval_accuracy": 0.865092277441185,
|
| 93 |
+
"eval_f1": 0.865092277441185,
|
| 94 |
+
"eval_loss": 0.41120249032974243,
|
| 95 |
+
"eval_precision": 0.865092277441185,
|
| 96 |
+
"eval_recall": 0.865092277441185,
|
| 97 |
+
"eval_runtime": 43.2183,
|
| 98 |
+
"eval_samples_per_second": 37.183,
|
| 99 |
+
"eval_steps_per_second": 2.337,
|
| 100 |
+
"step": 700
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.42643923240938164,
|
| 104 |
+
"eval_accuracy": 0.8710710970485193,
|
| 105 |
+
"eval_f1": 0.8710710970485193,
|
| 106 |
+
"eval_loss": 0.41007000207901,
|
| 107 |
+
"eval_precision": 0.8710710970485193,
|
| 108 |
+
"eval_recall": 0.8710710970485193,
|
| 109 |
+
"eval_runtime": 41.5981,
|
| 110 |
+
"eval_samples_per_second": 38.632,
|
| 111 |
+
"eval_steps_per_second": 2.428,
|
| 112 |
+
"step": 800
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.47974413646055436,
|
| 116 |
+
"eval_accuracy": 0.8397596494555182,
|
| 117 |
+
"eval_f1": 0.8397596494555181,
|
| 118 |
+
"eval_loss": 0.469059020280838,
|
| 119 |
+
"eval_precision": 0.8397596494555182,
|
| 120 |
+
"eval_recall": 0.8397596494555182,
|
| 121 |
+
"eval_runtime": 42.8271,
|
| 122 |
+
"eval_samples_per_second": 37.523,
|
| 123 |
+
"eval_steps_per_second": 2.358,
|
| 124 |
+
"step": 900
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.5330490405117271,
|
| 128 |
+
"grad_norm": 1.78385591506958,
|
| 129 |
+
"learning_rate": 9.392324093816631e-06,
|
| 130 |
+
"loss": 0.4575,
|
| 131 |
+
"step": 1000
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.5330490405117271,
|
| 135 |
+
"eval_accuracy": 0.8009322566800083,
|
| 136 |
+
"eval_f1": 0.8009322566800084,
|
| 137 |
+
"eval_loss": 0.4894373416900635,
|
| 138 |
+
"eval_precision": 0.8009322566800083,
|
| 139 |
+
"eval_recall": 0.8009322566800083,
|
| 140 |
+
"eval_runtime": 45.5517,
|
| 141 |
+
"eval_samples_per_second": 35.279,
|
| 142 |
+
"eval_steps_per_second": 2.217,
|
| 143 |
+
"step": 1000
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.5863539445628998,
|
| 147 |
+
"eval_accuracy": 0.8552706438959147,
|
| 148 |
+
"eval_f1": 0.8552706438959147,
|
| 149 |
+
"eval_loss": 0.427526593208313,
|
| 150 |
+
"eval_precision": 0.8552706438959147,
|
| 151 |
+
"eval_recall": 0.8552706438959147,
|
| 152 |
+
"eval_runtime": 41.1754,
|
| 153 |
+
"eval_samples_per_second": 39.028,
|
| 154 |
+
"eval_steps_per_second": 2.453,
|
| 155 |
+
"step": 1100
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.6396588486140725,
|
| 159 |
+
"eval_accuracy": 0.88568377134758,
|
| 160 |
+
"eval_f1": 0.88568377134758,
|
| 161 |
+
"eval_loss": 0.3613550066947937,
|
| 162 |
+
"eval_precision": 0.88568377134758,
|
| 163 |
+
"eval_recall": 0.88568377134758,
|
| 164 |
+
"eval_runtime": 43.3876,
|
| 165 |
+
"eval_samples_per_second": 37.038,
|
| 166 |
+
"eval_steps_per_second": 2.328,
|
| 167 |
+
"step": 1200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.6929637526652452,
|
| 171 |
+
"eval_accuracy": 0.8431832473274976,
|
| 172 |
+
"eval_f1": 0.8431832473274976,
|
| 173 |
+
"eval_loss": 0.45708218216896057,
|
| 174 |
+
"eval_precision": 0.8431832473274976,
|
| 175 |
+
"eval_recall": 0.8431832473274976,
|
| 176 |
+
"eval_runtime": 43.4109,
|
| 177 |
+
"eval_samples_per_second": 37.018,
|
| 178 |
+
"eval_steps_per_second": 2.327,
|
| 179 |
+
"step": 1300
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.746268656716418,
|
| 183 |
+
"eval_accuracy": 0.8377234571351573,
|
| 184 |
+
"eval_f1": 0.8377234571351573,
|
| 185 |
+
"eval_loss": 0.4477834701538086,
|
| 186 |
+
"eval_precision": 0.8377234571351573,
|
| 187 |
+
"eval_recall": 0.8377234571351573,
|
| 188 |
+
"eval_runtime": 41.9819,
|
| 189 |
+
"eval_samples_per_second": 38.278,
|
| 190 |
+
"eval_steps_per_second": 2.406,
|
| 191 |
+
"step": 1400
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.7995735607675906,
|
| 195 |
+
"grad_norm": 3.844151496887207,
|
| 196 |
+
"learning_rate": 4.061833688699361e-06,
|
| 197 |
+
"loss": 0.3718,
|
| 198 |
+
"step": 1500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.7995735607675906,
|
| 202 |
+
"eval_accuracy": 0.8324133869663729,
|
| 203 |
+
"eval_f1": 0.8324133869663729,
|
| 204 |
+
"eval_loss": 0.43807488679885864,
|
| 205 |
+
"eval_precision": 0.8324133869663729,
|
| 206 |
+
"eval_recall": 0.8324133869663729,
|
| 207 |
+
"eval_runtime": 44.8422,
|
| 208 |
+
"eval_samples_per_second": 35.837,
|
| 209 |
+
"eval_steps_per_second": 2.252,
|
| 210 |
+
"step": 1500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.8528784648187633,
|
| 214 |
+
"eval_accuracy": 0.8963138930200525,
|
| 215 |
+
"eval_f1": 0.8963138930200525,
|
| 216 |
+
"eval_loss": 0.3266744911670685,
|
| 217 |
+
"eval_precision": 0.8963138930200525,
|
| 218 |
+
"eval_recall": 0.8963138930200525,
|
| 219 |
+
"eval_runtime": 42.399,
|
| 220 |
+
"eval_samples_per_second": 37.902,
|
| 221 |
+
"eval_steps_per_second": 2.382,
|
| 222 |
+
"step": 1600
|
| 223 |
+
}
|
| 224 |
+
],
|
| 225 |
+
"logging_steps": 500,
|
| 226 |
+
"max_steps": 1876,
|
| 227 |
+
"num_input_tokens_seen": 0,
|
| 228 |
+
"num_train_epochs": 1,
|
| 229 |
+
"save_steps": 100,
|
| 230 |
+
"stateful_callbacks": {
|
| 231 |
+
"TrainerControl": {
|
| 232 |
+
"args": {
|
| 233 |
+
"should_epoch_stop": false,
|
| 234 |
+
"should_evaluate": false,
|
| 235 |
+
"should_log": false,
|
| 236 |
+
"should_save": true,
|
| 237 |
+
"should_training_stop": false
|
| 238 |
+
},
|
| 239 |
+
"attributes": {}
|
| 240 |
+
}
|
| 241 |
+
},
|
| 242 |
+
"total_flos": 3560604657254400.0,
|
| 243 |
+
"train_batch_size": 8,
|
| 244 |
+
"trial_name": null,
|
| 245 |
+
"trial_params": null
|
| 246 |
+
}
|
checkpoint-1600/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:310ed091c3918a1d9ebfef484979290e5f98817614fea477d6988c3c827bc379
|
| 3 |
+
size 5304
|