EfficientRAG bilingual (en+ru) — trained on Necent/efficientrag-*-training-data
Browse files- added_tokens.json +3 -0
- config.json +35 -0
- model.safetensors +3 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer_config.json +58 -0
- trainer_state.json +382 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "model_cache/deberta-v3-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaV2ForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 1024,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 4096,
|
| 12 |
+
"layer_norm_eps": 1e-07,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"max_relative_positions": -1,
|
| 15 |
+
"model_type": "deberta-v2",
|
| 16 |
+
"norm_rel_ebd": "layer_norm",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 24,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"pooler_dropout": 0,
|
| 21 |
+
"pooler_hidden_act": "gelu",
|
| 22 |
+
"pooler_hidden_size": 1024,
|
| 23 |
+
"pos_att_type": [
|
| 24 |
+
"p2c",
|
| 25 |
+
"c2p"
|
| 26 |
+
],
|
| 27 |
+
"position_biased_input": false,
|
| 28 |
+
"position_buckets": 256,
|
| 29 |
+
"relative_attention": true,
|
| 30 |
+
"share_att_key": true,
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.40.2",
|
| 33 |
+
"type_vocab_size": 0,
|
| 34 |
+
"vocab_size": 128100
|
| 35 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:131af1d226e48a2ca246ddb8786e08219fca3edd02e38ea2916f56f95479af0d
|
| 3 |
+
size 1736105856
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": {
|
| 9 |
+
"content": "[UNK]",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 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": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128000": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "[SEP]",
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"sp_model_kwargs": {},
|
| 54 |
+
"split_by_punct": false,
|
| 55 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 56 |
+
"unk_token": "[UNK]",
|
| 57 |
+
"vocab_type": "spm"
|
| 58 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,382 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 878,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04555808656036447,
|
| 13 |
+
"grad_norm": 14.260233879089355,
|
| 14 |
+
"learning_rate": 5.000000000000001e-07,
|
| 15 |
+
"loss": 0.6404,
|
| 16 |
+
"step": 20
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.09111617312072894,
|
| 20 |
+
"grad_norm": 13.856605529785156,
|
| 21 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 22 |
+
"loss": 0.6072,
|
| 23 |
+
"step": 40
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.1366742596810934,
|
| 27 |
+
"grad_norm": 10.69395637512207,
|
| 28 |
+
"learning_rate": 1.5e-06,
|
| 29 |
+
"loss": 0.4863,
|
| 30 |
+
"step": 60
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.18223234624145787,
|
| 34 |
+
"grad_norm": 6.665396213531494,
|
| 35 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 36 |
+
"loss": 0.3266,
|
| 37 |
+
"step": 80
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.22779043280182232,
|
| 41 |
+
"grad_norm": 2.674818754196167,
|
| 42 |
+
"learning_rate": 2.5e-06,
|
| 43 |
+
"loss": 0.1972,
|
| 44 |
+
"step": 100
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.2733485193621868,
|
| 48 |
+
"grad_norm": 0.46903184056282043,
|
| 49 |
+
"learning_rate": 3e-06,
|
| 50 |
+
"loss": 0.0999,
|
| 51 |
+
"step": 120
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.31890660592255127,
|
| 55 |
+
"grad_norm": 0.6415174603462219,
|
| 56 |
+
"learning_rate": 3.5e-06,
|
| 57 |
+
"loss": 0.0698,
|
| 58 |
+
"step": 140
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.36446469248291574,
|
| 62 |
+
"grad_norm": 0.3701508343219757,
|
| 63 |
+
"learning_rate": 4.000000000000001e-06,
|
| 64 |
+
"loss": 0.0656,
|
| 65 |
+
"step": 160
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.41002277904328016,
|
| 69 |
+
"grad_norm": 0.4025450348854065,
|
| 70 |
+
"learning_rate": 4.5e-06,
|
| 71 |
+
"loss": 0.0574,
|
| 72 |
+
"step": 180
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.45558086560364464,
|
| 76 |
+
"grad_norm": 0.5695033073425293,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.0562,
|
| 79 |
+
"step": 200
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.45558086560364464,
|
| 83 |
+
"eval_accuracy": 0.8391241361293846,
|
| 84 |
+
"eval_f1": 0.8391241361293846,
|
| 85 |
+
"eval_f1_marco": 0.8249262659790968,
|
| 86 |
+
"eval_loss": 0.056919749826192856,
|
| 87 |
+
"eval_negative_f1": 0.8747828015823136,
|
| 88 |
+
"eval_positive_f1": 0.7750697303758799,
|
| 89 |
+
"eval_precision": 0.8391241361293846,
|
| 90 |
+
"eval_recall": 0.8391241361293846,
|
| 91 |
+
"eval_runtime": 9.3166,
|
| 92 |
+
"eval_samples_per_second": 79.106,
|
| 93 |
+
"eval_steps_per_second": 1.288,
|
| 94 |
+
"step": 200
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.5011389521640092,
|
| 98 |
+
"grad_norm": 0.527057945728302,
|
| 99 |
+
"learning_rate": 4.852507374631269e-06,
|
| 100 |
+
"loss": 0.0622,
|
| 101 |
+
"step": 220
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.5466970387243736,
|
| 105 |
+
"grad_norm": 0.47804608941078186,
|
| 106 |
+
"learning_rate": 4.705014749262537e-06,
|
| 107 |
+
"loss": 0.0527,
|
| 108 |
+
"step": 240
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.592255125284738,
|
| 112 |
+
"grad_norm": 0.3202660381793976,
|
| 113 |
+
"learning_rate": 4.557522123893805e-06,
|
| 114 |
+
"loss": 0.0555,
|
| 115 |
+
"step": 260
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.6378132118451025,
|
| 119 |
+
"grad_norm": 0.40933147072792053,
|
| 120 |
+
"learning_rate": 4.410029498525074e-06,
|
| 121 |
+
"loss": 0.0563,
|
| 122 |
+
"step": 280
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.683371298405467,
|
| 126 |
+
"grad_norm": 0.4464198648929596,
|
| 127 |
+
"learning_rate": 4.2625368731563425e-06,
|
| 128 |
+
"loss": 0.054,
|
| 129 |
+
"step": 300
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.7289293849658315,
|
| 133 |
+
"grad_norm": 0.5946183204650879,
|
| 134 |
+
"learning_rate": 4.115044247787611e-06,
|
| 135 |
+
"loss": 0.0543,
|
| 136 |
+
"step": 320
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.7744874715261959,
|
| 140 |
+
"grad_norm": 0.8823751211166382,
|
| 141 |
+
"learning_rate": 3.967551622418879e-06,
|
| 142 |
+
"loss": 0.0552,
|
| 143 |
+
"step": 340
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.8200455580865603,
|
| 147 |
+
"grad_norm": 0.29086050391197205,
|
| 148 |
+
"learning_rate": 3.820058997050148e-06,
|
| 149 |
+
"loss": 0.0556,
|
| 150 |
+
"step": 360
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.8656036446469249,
|
| 154 |
+
"grad_norm": 0.36109957098960876,
|
| 155 |
+
"learning_rate": 3.6725663716814163e-06,
|
| 156 |
+
"loss": 0.0547,
|
| 157 |
+
"step": 380
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.9111617312072893,
|
| 161 |
+
"grad_norm": 0.357105553150177,
|
| 162 |
+
"learning_rate": 3.5250737463126845e-06,
|
| 163 |
+
"loss": 0.054,
|
| 164 |
+
"step": 400
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.9111617312072893,
|
| 168 |
+
"eval_accuracy": 0.857600873963949,
|
| 169 |
+
"eval_f1": 0.857600873963949,
|
| 170 |
+
"eval_f1_marco": 0.8454311469742184,
|
| 171 |
+
"eval_loss": 0.05031890422105789,
|
| 172 |
+
"eval_negative_f1": 0.8888023441267016,
|
| 173 |
+
"eval_positive_f1": 0.8020599498217351,
|
| 174 |
+
"eval_precision": 0.857600873963949,
|
| 175 |
+
"eval_recall": 0.857600873963949,
|
| 176 |
+
"eval_runtime": 9.081,
|
| 177 |
+
"eval_samples_per_second": 81.158,
|
| 178 |
+
"eval_steps_per_second": 1.321,
|
| 179 |
+
"step": 400
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.9567198177676538,
|
| 183 |
+
"grad_norm": 0.3978097438812256,
|
| 184 |
+
"learning_rate": 3.3775811209439528e-06,
|
| 185 |
+
"loss": 0.0513,
|
| 186 |
+
"step": 420
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.0022779043280183,
|
| 190 |
+
"grad_norm": 0.327373206615448,
|
| 191 |
+
"learning_rate": 3.2300884955752214e-06,
|
| 192 |
+
"loss": 0.0527,
|
| 193 |
+
"step": 440
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.0478359908883828,
|
| 197 |
+
"grad_norm": 0.39979490637779236,
|
| 198 |
+
"learning_rate": 3.08259587020649e-06,
|
| 199 |
+
"loss": 0.0474,
|
| 200 |
+
"step": 460
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.0933940774487472,
|
| 204 |
+
"grad_norm": 0.37922340631484985,
|
| 205 |
+
"learning_rate": 2.935103244837758e-06,
|
| 206 |
+
"loss": 0.0501,
|
| 207 |
+
"step": 480
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.1389521640091116,
|
| 211 |
+
"grad_norm": 0.4099065363407135,
|
| 212 |
+
"learning_rate": 2.7876106194690266e-06,
|
| 213 |
+
"loss": 0.0461,
|
| 214 |
+
"step": 500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.184510250569476,
|
| 218 |
+
"grad_norm": 0.3328123390674591,
|
| 219 |
+
"learning_rate": 2.6401179941002952e-06,
|
| 220 |
+
"loss": 0.048,
|
| 221 |
+
"step": 520
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.2300683371298406,
|
| 225 |
+
"grad_norm": 0.647693932056427,
|
| 226 |
+
"learning_rate": 2.4926253687315635e-06,
|
| 227 |
+
"loss": 0.0495,
|
| 228 |
+
"step": 540
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.275626423690205,
|
| 232 |
+
"grad_norm": 0.6742229461669922,
|
| 233 |
+
"learning_rate": 2.345132743362832e-06,
|
| 234 |
+
"loss": 0.0496,
|
| 235 |
+
"step": 560
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.3211845102505695,
|
| 239 |
+
"grad_norm": 0.2932397425174713,
|
| 240 |
+
"learning_rate": 2.1976401179941004e-06,
|
| 241 |
+
"loss": 0.0479,
|
| 242 |
+
"step": 580
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.366742596810934,
|
| 246 |
+
"grad_norm": 0.32655268907546997,
|
| 247 |
+
"learning_rate": 2.050147492625369e-06,
|
| 248 |
+
"loss": 0.0472,
|
| 249 |
+
"step": 600
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.366742596810934,
|
| 253 |
+
"eval_accuracy": 0.8680504429192296,
|
| 254 |
+
"eval_f1": 0.8680504429192296,
|
| 255 |
+
"eval_f1_marco": 0.853667569896885,
|
| 256 |
+
"eval_loss": 0.04778573289513588,
|
| 257 |
+
"eval_negative_f1": 0.8995443697114341,
|
| 258 |
+
"eval_positive_f1": 0.8077907700823358,
|
| 259 |
+
"eval_precision": 0.8680504429192296,
|
| 260 |
+
"eval_recall": 0.8680504429192296,
|
| 261 |
+
"eval_runtime": 9.6373,
|
| 262 |
+
"eval_samples_per_second": 76.473,
|
| 263 |
+
"eval_steps_per_second": 1.245,
|
| 264 |
+
"step": 600
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.4123006833712983,
|
| 268 |
+
"grad_norm": 0.3308158814907074,
|
| 269 |
+
"learning_rate": 1.9026548672566373e-06,
|
| 270 |
+
"loss": 0.0455,
|
| 271 |
+
"step": 620
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.4578587699316627,
|
| 275 |
+
"grad_norm": 0.4326237738132477,
|
| 276 |
+
"learning_rate": 1.7551622418879058e-06,
|
| 277 |
+
"loss": 0.0476,
|
| 278 |
+
"step": 640
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.5034168564920274,
|
| 282 |
+
"grad_norm": 0.9873289465904236,
|
| 283 |
+
"learning_rate": 1.607669616519174e-06,
|
| 284 |
+
"loss": 0.0469,
|
| 285 |
+
"step": 660
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.5489749430523918,
|
| 289 |
+
"grad_norm": 0.4288870096206665,
|
| 290 |
+
"learning_rate": 1.4601769911504427e-06,
|
| 291 |
+
"loss": 0.0459,
|
| 292 |
+
"step": 680
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.5945330296127562,
|
| 296 |
+
"grad_norm": 0.4720146358013153,
|
| 297 |
+
"learning_rate": 1.312684365781711e-06,
|
| 298 |
+
"loss": 0.0494,
|
| 299 |
+
"step": 700
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.6400911161731209,
|
| 303 |
+
"grad_norm": 0.6934795379638672,
|
| 304 |
+
"learning_rate": 1.1651917404129796e-06,
|
| 305 |
+
"loss": 0.05,
|
| 306 |
+
"step": 720
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.6856492027334853,
|
| 310 |
+
"grad_norm": 0.3552420735359192,
|
| 311 |
+
"learning_rate": 1.017699115044248e-06,
|
| 312 |
+
"loss": 0.0499,
|
| 313 |
+
"step": 740
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.7312072892938497,
|
| 317 |
+
"grad_norm": 0.32909882068634033,
|
| 318 |
+
"learning_rate": 8.702064896755164e-07,
|
| 319 |
+
"loss": 0.0485,
|
| 320 |
+
"step": 760
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.7767653758542141,
|
| 324 |
+
"grad_norm": 0.2789745628833771,
|
| 325 |
+
"learning_rate": 7.227138643067848e-07,
|
| 326 |
+
"loss": 0.0468,
|
| 327 |
+
"step": 780
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.8223234624145785,
|
| 331 |
+
"grad_norm": 0.3232771158218384,
|
| 332 |
+
"learning_rate": 5.752212389380532e-07,
|
| 333 |
+
"loss": 0.0481,
|
| 334 |
+
"step": 800
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.8223234624145785,
|
| 338 |
+
"eval_accuracy": 0.8677417056546417,
|
| 339 |
+
"eval_f1": 0.8677417056546417,
|
| 340 |
+
"eval_f1_marco": 0.8536354633333805,
|
| 341 |
+
"eval_loss": 0.04745788872241974,
|
| 342 |
+
"eval_negative_f1": 0.8990739230504359,
|
| 343 |
+
"eval_positive_f1": 0.8081970036163251,
|
| 344 |
+
"eval_precision": 0.8677417056546417,
|
| 345 |
+
"eval_recall": 0.8677417056546417,
|
| 346 |
+
"eval_runtime": 8.8278,
|
| 347 |
+
"eval_samples_per_second": 83.487,
|
| 348 |
+
"eval_steps_per_second": 1.359,
|
| 349 |
+
"step": 800
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.867881548974943,
|
| 353 |
+
"grad_norm": 0.4403178095817566,
|
| 354 |
+
"learning_rate": 4.277286135693216e-07,
|
| 355 |
+
"loss": 0.0502,
|
| 356 |
+
"step": 820
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.9134396355353074,
|
| 360 |
+
"grad_norm": 0.4974011182785034,
|
| 361 |
+
"learning_rate": 2.8023598820059e-07,
|
| 362 |
+
"loss": 0.0453,
|
| 363 |
+
"step": 840
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.958997722095672,
|
| 367 |
+
"grad_norm": 0.3315702974796295,
|
| 368 |
+
"learning_rate": 1.327433628318584e-07,
|
| 369 |
+
"loss": 0.0494,
|
| 370 |
+
"step": 860
|
| 371 |
+
}
|
| 372 |
+
],
|
| 373 |
+
"logging_steps": 20,
|
| 374 |
+
"max_steps": 878,
|
| 375 |
+
"num_input_tokens_seen": 0,
|
| 376 |
+
"num_train_epochs": 2,
|
| 377 |
+
"save_steps": 500,
|
| 378 |
+
"total_flos": 1.952805421392077e+16,
|
| 379 |
+
"train_batch_size": 32,
|
| 380 |
+
"trial_name": null,
|
| 381 |
+
"trial_params": null
|
| 382 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9135590d65cb00c50950549f23d56d81b60980139131a596fec7e0b87769a4e0
|
| 3 |
+
size 5048
|