Upload folder using huggingface_hub
Browse files- added_tokens.json +5 -0
- config.json +108 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +74 -0
- trainer_state.json +641 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<<LABEL>>": 128001,
|
| 3 |
+
"<<SEP>>": 128002,
|
| 4 |
+
"[MASK]": 128000
|
| 5 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GLiClassModel"
|
| 4 |
+
],
|
| 5 |
+
"class_token_index": 128001,
|
| 6 |
+
"encoder_config": {
|
| 7 |
+
"_name_or_path": "microsoft/deberta-v3-base",
|
| 8 |
+
"add_cross_attention": false,
|
| 9 |
+
"architectures": null,
|
| 10 |
+
"attention_probs_dropout_prob": 0.1,
|
| 11 |
+
"bad_words_ids": null,
|
| 12 |
+
"begin_suppress_tokens": null,
|
| 13 |
+
"bos_token_id": null,
|
| 14 |
+
"chunk_size_feed_forward": 0,
|
| 15 |
+
"cross_attention_hidden_size": null,
|
| 16 |
+
"decoder_start_token_id": null,
|
| 17 |
+
"diversity_penalty": 0.0,
|
| 18 |
+
"do_sample": false,
|
| 19 |
+
"early_stopping": false,
|
| 20 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 21 |
+
"eos_token_id": null,
|
| 22 |
+
"exponential_decay_length_penalty": null,
|
| 23 |
+
"finetuning_task": null,
|
| 24 |
+
"forced_bos_token_id": null,
|
| 25 |
+
"forced_eos_token_id": null,
|
| 26 |
+
"hidden_act": "gelu",
|
| 27 |
+
"hidden_dropout_prob": 0.1,
|
| 28 |
+
"hidden_size": 768,
|
| 29 |
+
"id2label": {
|
| 30 |
+
"0": "LABEL_0",
|
| 31 |
+
"1": "LABEL_1"
|
| 32 |
+
},
|
| 33 |
+
"initializer_range": 0.02,
|
| 34 |
+
"intermediate_size": 3072,
|
| 35 |
+
"is_decoder": false,
|
| 36 |
+
"is_encoder_decoder": false,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"LABEL_0": 0,
|
| 39 |
+
"LABEL_1": 1
|
| 40 |
+
},
|
| 41 |
+
"layer_norm_eps": 1e-07,
|
| 42 |
+
"length_penalty": 1.0,
|
| 43 |
+
"max_length": 20,
|
| 44 |
+
"max_position_embeddings": 512,
|
| 45 |
+
"max_relative_positions": -1,
|
| 46 |
+
"min_length": 0,
|
| 47 |
+
"model_type": "deberta-v2",
|
| 48 |
+
"no_repeat_ngram_size": 0,
|
| 49 |
+
"norm_rel_ebd": "layer_norm",
|
| 50 |
+
"num_attention_heads": 12,
|
| 51 |
+
"num_beam_groups": 1,
|
| 52 |
+
"num_beams": 1,
|
| 53 |
+
"num_hidden_layers": 12,
|
| 54 |
+
"num_return_sequences": 1,
|
| 55 |
+
"output_attentions": false,
|
| 56 |
+
"output_hidden_states": false,
|
| 57 |
+
"output_scores": false,
|
| 58 |
+
"pad_token_id": 0,
|
| 59 |
+
"pooler_dropout": 0,
|
| 60 |
+
"pooler_hidden_act": "gelu",
|
| 61 |
+
"pooler_hidden_size": 768,
|
| 62 |
+
"pos_att_type": [
|
| 63 |
+
"p2c",
|
| 64 |
+
"c2p"
|
| 65 |
+
],
|
| 66 |
+
"position_biased_input": false,
|
| 67 |
+
"position_buckets": 256,
|
| 68 |
+
"prefix": null,
|
| 69 |
+
"problem_type": null,
|
| 70 |
+
"pruned_heads": {},
|
| 71 |
+
"relative_attention": true,
|
| 72 |
+
"remove_invalid_values": false,
|
| 73 |
+
"repetition_penalty": 1.0,
|
| 74 |
+
"return_dict": true,
|
| 75 |
+
"return_dict_in_generate": false,
|
| 76 |
+
"sep_token_id": null,
|
| 77 |
+
"share_att_key": true,
|
| 78 |
+
"suppress_tokens": null,
|
| 79 |
+
"task_specific_params": null,
|
| 80 |
+
"temperature": 1.0,
|
| 81 |
+
"tf_legacy_loss": false,
|
| 82 |
+
"tie_encoder_decoder": false,
|
| 83 |
+
"tie_word_embeddings": true,
|
| 84 |
+
"tokenizer_class": null,
|
| 85 |
+
"top_k": 50,
|
| 86 |
+
"top_p": 1.0,
|
| 87 |
+
"torch_dtype": null,
|
| 88 |
+
"torchscript": false,
|
| 89 |
+
"type_vocab_size": 0,
|
| 90 |
+
"typical_p": 1.0,
|
| 91 |
+
"use_bfloat16": false,
|
| 92 |
+
"vocab_size": 128003
|
| 93 |
+
},
|
| 94 |
+
"encoder_model_name": "microsoft/deberta-v3-base",
|
| 95 |
+
"hidden_size": 768,
|
| 96 |
+
"ignore_index": -100,
|
| 97 |
+
"initializer_range": 0.03,
|
| 98 |
+
"max_num_classes": 25,
|
| 99 |
+
"model_type": "GLiClass",
|
| 100 |
+
"pooling_strategy": "first",
|
| 101 |
+
"problem_type": "multi_label_classification",
|
| 102 |
+
"projector_hidden_act": "gelu",
|
| 103 |
+
"scorer_type": "simple",
|
| 104 |
+
"torch_dtype": "bfloat16",
|
| 105 |
+
"transformers_version": "4.40.2",
|
| 106 |
+
"use_lstm": false,
|
| 107 |
+
"vocab_size": 128003
|
| 108 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a74089e637821bcc046ce0b45a16e0c45b9d12fc775d21274b516c3b23caa45
|
| 3 |
+
size 372265272
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ff788e493dd1f86f258427da20ed45ebae8aaa65c1274ea0867a706450cf565
|
| 3 |
+
size 744650362
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50efd9e038ed1d8fd02c3b897b8d6eb9c7ccc7ed56d4fb2693b64c68deb9ae11
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0dcdd51df27b6045f8c06f22c2ae42a1190b854eb7f7396adffb65879362f5b
|
| 3 |
+
size 1064
|
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.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"128001": {
|
| 44 |
+
"content": "<<LABEL>>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
"128002": {
|
| 52 |
+
"content": "<<SEP>>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": true,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": false
|
| 58 |
+
}
|
| 59 |
+
},
|
| 60 |
+
"bos_token": "[CLS]",
|
| 61 |
+
"clean_up_tokenization_spaces": true,
|
| 62 |
+
"cls_token": "[CLS]",
|
| 63 |
+
"do_lower_case": false,
|
| 64 |
+
"eos_token": "[SEP]",
|
| 65 |
+
"mask_token": "[MASK]",
|
| 66 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 67 |
+
"pad_token": "[PAD]",
|
| 68 |
+
"sep_token": "[SEP]",
|
| 69 |
+
"sp_model_kwargs": {},
|
| 70 |
+
"split_by_punct": false,
|
| 71 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 72 |
+
"unk_token": "[UNK]",
|
| 73 |
+
"vocab_type": "spm"
|
| 74 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,641 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.9988002399520095,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 40000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.07498500299940011,
|
| 13 |
+
"grad_norm": 32.0,
|
| 14 |
+
"learning_rate": 6.248437890527369e-06,
|
| 15 |
+
"loss": 1.2095,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.14997000599880023,
|
| 20 |
+
"grad_norm": 16.5,
|
| 21 |
+
"learning_rate": 1.2496875781054738e-05,
|
| 22 |
+
"loss": 0.8665,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.22495500899820037,
|
| 27 |
+
"grad_norm": 17.75,
|
| 28 |
+
"learning_rate": 1.8745313671582104e-05,
|
| 29 |
+
"loss": 0.6844,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.29994001199760045,
|
| 34 |
+
"grad_norm": 7.78125,
|
| 35 |
+
"learning_rate": 2.4993751562109475e-05,
|
| 36 |
+
"loss": 0.5099,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.3749250149970006,
|
| 41 |
+
"grad_norm": 7.375,
|
| 42 |
+
"learning_rate": 3.124218945263684e-05,
|
| 43 |
+
"loss": 0.2845,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.44991001799640074,
|
| 48 |
+
"grad_norm": 8.0,
|
| 49 |
+
"learning_rate": 3.749062734316421e-05,
|
| 50 |
+
"loss": 0.2251,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.5248950209958009,
|
| 55 |
+
"grad_norm": 6.1875,
|
| 56 |
+
"learning_rate": 4.373906523369158e-05,
|
| 57 |
+
"loss": 0.206,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.5998800239952009,
|
| 62 |
+
"grad_norm": 3.640625,
|
| 63 |
+
"learning_rate": 4.998750312421895e-05,
|
| 64 |
+
"loss": 0.1874,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.674865026994601,
|
| 69 |
+
"grad_norm": 4.8125,
|
| 70 |
+
"learning_rate": 4.997630981947256e-05,
|
| 71 |
+
"loss": 0.1793,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.7498500299940012,
|
| 76 |
+
"grad_norm": 3.953125,
|
| 77 |
+
"learning_rate": 4.9905094389741605e-05,
|
| 78 |
+
"loss": 0.1708,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.8248350329934013,
|
| 83 |
+
"grad_norm": 6.125,
|
| 84 |
+
"learning_rate": 4.978648912557427e-05,
|
| 85 |
+
"loss": 0.1614,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.8998200359928015,
|
| 90 |
+
"grad_norm": 3.15625,
|
| 91 |
+
"learning_rate": 4.962071971107133e-05,
|
| 92 |
+
"loss": 0.1581,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.9748050389922016,
|
| 97 |
+
"grad_norm": 3.984375,
|
| 98 |
+
"learning_rate": 4.940810157507576e-05,
|
| 99 |
+
"loss": 0.154,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.0,
|
| 104 |
+
"eval_accuracy": 0.6357488330240144,
|
| 105 |
+
"eval_f1": 0.5235656092218528,
|
| 106 |
+
"eval_loss": 0.1340431272983551,
|
| 107 |
+
"eval_precision": 0.4623448805170602,
|
| 108 |
+
"eval_recall": 0.6357488330240144,
|
| 109 |
+
"eval_runtime": 40.157,
|
| 110 |
+
"eval_samples_per_second": 295.191,
|
| 111 |
+
"eval_steps_per_second": 18.453,
|
| 112 |
+
"step": 6668
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.0497900419916018,
|
| 116 |
+
"grad_norm": 2.796875,
|
| 117 |
+
"learning_rate": 4.914903929096945e-05,
|
| 118 |
+
"loss": 0.1466,
|
| 119 |
+
"step": 7000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.124775044991002,
|
| 123 |
+
"grad_norm": 3.8125,
|
| 124 |
+
"learning_rate": 4.884402580684407e-05,
|
| 125 |
+
"loss": 0.1503,
|
| 126 |
+
"step": 7500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.1997600479904018,
|
| 130 |
+
"grad_norm": 2.90625,
|
| 131 |
+
"learning_rate": 4.8493641507511146e-05,
|
| 132 |
+
"loss": 0.1463,
|
| 133 |
+
"step": 8000
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.274745050989802,
|
| 137 |
+
"grad_norm": 5.15625,
|
| 138 |
+
"learning_rate": 4.809855311013604e-05,
|
| 139 |
+
"loss": 0.1473,
|
| 140 |
+
"step": 8500
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.349730053989202,
|
| 144 |
+
"grad_norm": 3.3125,
|
| 145 |
+
"learning_rate": 4.765951239559725e-05,
|
| 146 |
+
"loss": 0.1448,
|
| 147 |
+
"step": 9000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.4247150569886022,
|
| 151 |
+
"grad_norm": 5.125,
|
| 152 |
+
"learning_rate": 4.717735477798505e-05,
|
| 153 |
+
"loss": 0.1381,
|
| 154 |
+
"step": 9500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.4997000599880024,
|
| 158 |
+
"grad_norm": 3.046875,
|
| 159 |
+
"learning_rate": 4.665299771496145e-05,
|
| 160 |
+
"loss": 0.1413,
|
| 161 |
+
"step": 10000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.5746850629874025,
|
| 165 |
+
"grad_norm": 4.40625,
|
| 166 |
+
"learning_rate": 4.608743896200624e-05,
|
| 167 |
+
"loss": 0.1419,
|
| 168 |
+
"step": 10500
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.6496700659868027,
|
| 172 |
+
"grad_norm": 3.984375,
|
| 173 |
+
"learning_rate": 4.548175467387103e-05,
|
| 174 |
+
"loss": 0.1407,
|
| 175 |
+
"step": 11000
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.7246550689862028,
|
| 179 |
+
"grad_norm": 4.34375,
|
| 180 |
+
"learning_rate": 4.483709735685378e-05,
|
| 181 |
+
"loss": 0.1394,
|
| 182 |
+
"step": 11500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.799640071985603,
|
| 186 |
+
"grad_norm": 4.09375,
|
| 187 |
+
"learning_rate": 4.415469367579033e-05,
|
| 188 |
+
"loss": 0.1379,
|
| 189 |
+
"step": 12000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.874625074985003,
|
| 193 |
+
"grad_norm": 2.0,
|
| 194 |
+
"learning_rate": 4.343584211993589e-05,
|
| 195 |
+
"loss": 0.1377,
|
| 196 |
+
"step": 12500
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.9496100779844032,
|
| 200 |
+
"grad_norm": 2.96875,
|
| 201 |
+
"learning_rate": 4.268191053217765e-05,
|
| 202 |
+
"loss": 0.1357,
|
| 203 |
+
"step": 13000
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 2.0,
|
| 207 |
+
"eval_accuracy": 0.6386662729880209,
|
| 208 |
+
"eval_f1": 0.525822096019018,
|
| 209 |
+
"eval_loss": 0.12524983286857605,
|
| 210 |
+
"eval_precision": 0.463306913237047,
|
| 211 |
+
"eval_recall": 0.6386662729880209,
|
| 212 |
+
"eval_runtime": 40.1169,
|
| 213 |
+
"eval_samples_per_second": 295.487,
|
| 214 |
+
"eval_steps_per_second": 18.471,
|
| 215 |
+
"step": 13336
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 2.0245950809838034,
|
| 219 |
+
"grad_norm": 5.4375,
|
| 220 |
+
"learning_rate": 4.189433350628029e-05,
|
| 221 |
+
"loss": 0.1366,
|
| 222 |
+
"step": 13500
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 2.0995800839832035,
|
| 226 |
+
"grad_norm": 5.875,
|
| 227 |
+
"learning_rate": 4.10746096571167e-05,
|
| 228 |
+
"loss": 0.1329,
|
| 229 |
+
"step": 14000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 2.1745650869826036,
|
| 233 |
+
"grad_norm": 4.15625,
|
| 234 |
+
"learning_rate": 4.02242987690783e-05,
|
| 235 |
+
"loss": 0.1325,
|
| 236 |
+
"step": 14500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.249550089982004,
|
| 240 |
+
"grad_norm": 3.71875,
|
| 241 |
+
"learning_rate": 3.9345018828090864e-05,
|
| 242 |
+
"loss": 0.1321,
|
| 243 |
+
"step": 15000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.324535092981404,
|
| 247 |
+
"grad_norm": 2.796875,
|
| 248 |
+
"learning_rate": 3.843844294288368e-05,
|
| 249 |
+
"loss": 0.1332,
|
| 250 |
+
"step": 15500
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 2.3995200959808036,
|
| 254 |
+
"grad_norm": 3.203125,
|
| 255 |
+
"learning_rate": 3.750629616136989e-05,
|
| 256 |
+
"loss": 0.1281,
|
| 257 |
+
"step": 16000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 2.4745050989802038,
|
| 261 |
+
"grad_norm": 2.921875,
|
| 262 |
+
"learning_rate": 3.6550352188196244e-05,
|
| 263 |
+
"loss": 0.1307,
|
| 264 |
+
"step": 16500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.549490101979604,
|
| 268 |
+
"grad_norm": 4.34375,
|
| 269 |
+
"learning_rate": 3.557243000970787e-05,
|
| 270 |
+
"loss": 0.1345,
|
| 271 |
+
"step": 17000
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 2.624475104979004,
|
| 275 |
+
"grad_norm": 3.28125,
|
| 276 |
+
"learning_rate": 3.457439043275033e-05,
|
| 277 |
+
"loss": 0.129,
|
| 278 |
+
"step": 17500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.699460107978404,
|
| 282 |
+
"grad_norm": 3.703125,
|
| 283 |
+
"learning_rate": 3.355813254389495e-05,
|
| 284 |
+
"loss": 0.135,
|
| 285 |
+
"step": 18000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.7744451109778043,
|
| 289 |
+
"grad_norm": 2.96875,
|
| 290 |
+
"learning_rate": 3.252559009582478e-05,
|
| 291 |
+
"loss": 0.1336,
|
| 292 |
+
"step": 18500
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 2.8494301139772045,
|
| 296 |
+
"grad_norm": 3.6875,
|
| 297 |
+
"learning_rate": 3.14787278277573e-05,
|
| 298 |
+
"loss": 0.1327,
|
| 299 |
+
"step": 19000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.9244151169766046,
|
| 303 |
+
"grad_norm": 4.34375,
|
| 304 |
+
"learning_rate": 3.0419537726905434e-05,
|
| 305 |
+
"loss": 0.1326,
|
| 306 |
+
"step": 19500
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.9994001199760048,
|
| 310 |
+
"grad_norm": 4.28125,
|
| 311 |
+
"learning_rate": 2.9350035238090666e-05,
|
| 312 |
+
"loss": 0.1295,
|
| 313 |
+
"step": 20000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 3.0,
|
| 317 |
+
"eval_accuracy": 0.6393481806422586,
|
| 318 |
+
"eval_f1": 0.5262540403072158,
|
| 319 |
+
"eval_loss": 0.12466703355312347,
|
| 320 |
+
"eval_precision": 0.4630570055607114,
|
| 321 |
+
"eval_recall": 0.6393481806422586,
|
| 322 |
+
"eval_runtime": 40.1133,
|
| 323 |
+
"eval_samples_per_second": 295.513,
|
| 324 |
+
"eval_steps_per_second": 18.473,
|
| 325 |
+
"step": 20004
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 3.074385122975405,
|
| 329 |
+
"grad_norm": 4.625,
|
| 330 |
+
"learning_rate": 2.827225542872053e-05,
|
| 331 |
+
"loss": 0.1301,
|
| 332 |
+
"step": 20500
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 3.149370125974805,
|
| 336 |
+
"grad_norm": 3.4375,
|
| 337 |
+
"learning_rate": 2.7188249116427988e-05,
|
| 338 |
+
"loss": 0.1287,
|
| 339 |
+
"step": 21000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 3.224355128974205,
|
| 343 |
+
"grad_norm": 4.0625,
|
| 344 |
+
"learning_rate": 2.6100078966740953e-05,
|
| 345 |
+
"loss": 0.1314,
|
| 346 |
+
"step": 21500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 3.2993401319736053,
|
| 350 |
+
"grad_norm": 4.1875,
|
| 351 |
+
"learning_rate": 2.500981556820753e-05,
|
| 352 |
+
"loss": 0.1299,
|
| 353 |
+
"step": 22000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 3.3743251349730055,
|
| 357 |
+
"grad_norm": 4.3125,
|
| 358 |
+
"learning_rate": 2.3919533492445064e-05,
|
| 359 |
+
"loss": 0.1298,
|
| 360 |
+
"step": 22500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 3.4493101379724056,
|
| 364 |
+
"grad_norm": 4.25,
|
| 365 |
+
"learning_rate": 2.2831307346610255e-05,
|
| 366 |
+
"loss": 0.1293,
|
| 367 |
+
"step": 23000
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 3.5242951409718057,
|
| 371 |
+
"grad_norm": 3.640625,
|
| 372 |
+
"learning_rate": 2.17472078258016e-05,
|
| 373 |
+
"loss": 0.1261,
|
| 374 |
+
"step": 23500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 3.599280143971206,
|
| 378 |
+
"grad_norm": 3.75,
|
| 379 |
+
"learning_rate": 2.066929777290578e-05,
|
| 380 |
+
"loss": 0.1298,
|
| 381 |
+
"step": 24000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 3.674265146970606,
|
| 385 |
+
"grad_norm": 4.9375,
|
| 386 |
+
"learning_rate": 1.9599628253385327e-05,
|
| 387 |
+
"loss": 0.1302,
|
| 388 |
+
"step": 24500
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 3.749250149970006,
|
| 392 |
+
"grad_norm": 3.4375,
|
| 393 |
+
"learning_rate": 1.8540234652476617e-05,
|
| 394 |
+
"loss": 0.1295,
|
| 395 |
+
"step": 25000
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 3.824235152969406,
|
| 399 |
+
"grad_norm": 3.875,
|
| 400 |
+
"learning_rate": 1.7493132802224482e-05,
|
| 401 |
+
"loss": 0.1285,
|
| 402 |
+
"step": 25500
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 3.8992201559688064,
|
| 406 |
+
"grad_norm": 4.15625,
|
| 407 |
+
"learning_rate": 1.6460315145722894e-05,
|
| 408 |
+
"loss": 0.1272,
|
| 409 |
+
"step": 26000
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 3.974205158968206,
|
| 413 |
+
"grad_norm": 3.890625,
|
| 414 |
+
"learning_rate": 1.5443746945860566e-05,
|
| 415 |
+
"loss": 0.1294,
|
| 416 |
+
"step": 26500
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 4.0,
|
| 420 |
+
"eval_accuracy": 0.639137281367752,
|
| 421 |
+
"eval_f1": 0.5262984000216192,
|
| 422 |
+
"eval_loss": 0.12251855432987213,
|
| 423 |
+
"eval_precision": 0.4640513156681777,
|
| 424 |
+
"eval_recall": 0.639137281367752,
|
| 425 |
+
"eval_runtime": 40.1904,
|
| 426 |
+
"eval_samples_per_second": 294.946,
|
| 427 |
+
"eval_steps_per_second": 18.437,
|
| 428 |
+
"step": 26672
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 4.049190161967607,
|
| 432 |
+
"grad_norm": 3.1875,
|
| 433 |
+
"learning_rate": 1.4445362545785581e-05,
|
| 434 |
+
"loss": 0.1311,
|
| 435 |
+
"step": 27000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 4.124175164967006,
|
| 439 |
+
"grad_norm": 3.390625,
|
| 440 |
+
"learning_rate": 1.3467061688204524e-05,
|
| 441 |
+
"loss": 0.1289,
|
| 442 |
+
"step": 27500
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 4.199160167966407,
|
| 446 |
+
"grad_norm": 6.0625,
|
| 447 |
+
"learning_rate": 1.2510705900519926e-05,
|
| 448 |
+
"loss": 0.1263,
|
| 449 |
+
"step": 28000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 4.274145170965807,
|
| 453 |
+
"grad_norm": 4.15625,
|
| 454 |
+
"learning_rate": 1.1578114952684529e-05,
|
| 455 |
+
"loss": 0.1273,
|
| 456 |
+
"step": 28500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 4.349130173965207,
|
| 460 |
+
"grad_norm": 4.21875,
|
| 461 |
+
"learning_rate": 1.0671063394512279e-05,
|
| 462 |
+
"loss": 0.1339,
|
| 463 |
+
"step": 29000
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 4.424115176964607,
|
| 467 |
+
"grad_norm": 4.5,
|
| 468 |
+
"learning_rate": 9.791277179034853e-06,
|
| 469 |
+
"loss": 0.1286,
|
| 470 |
+
"step": 29500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 4.499100179964008,
|
| 474 |
+
"grad_norm": 3.921875,
|
| 475 |
+
"learning_rate": 8.940430378329174e-06,
|
| 476 |
+
"loss": 0.133,
|
| 477 |
+
"step": 30000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 4.574085182963407,
|
| 481 |
+
"grad_norm": 2.828125,
|
| 482 |
+
"learning_rate": 8.120141998064757e-06,
|
| 483 |
+
"loss": 0.1241,
|
| 484 |
+
"step": 30500
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 4.649070185962808,
|
| 488 |
+
"grad_norm": 3.203125,
|
| 489 |
+
"learning_rate": 7.331972896832292e-06,
|
| 490 |
+
"loss": 0.1269,
|
| 491 |
+
"step": 31000
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 4.7240551889622076,
|
| 495 |
+
"grad_norm": 6.40625,
|
| 496 |
+
"learning_rate": 6.577422816115633e-06,
|
| 497 |
+
"loss": 0.1303,
|
| 498 |
+
"step": 31500
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 4.799040191961607,
|
| 502 |
+
"grad_norm": 3.328125,
|
| 503 |
+
"learning_rate": 5.857927526558302e-06,
|
| 504 |
+
"loss": 0.1306,
|
| 505 |
+
"step": 32000
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 4.874025194961008,
|
| 509 |
+
"grad_norm": 2.96875,
|
| 510 |
+
"learning_rate": 5.174856095954883e-06,
|
| 511 |
+
"loss": 0.129,
|
| 512 |
+
"step": 32500
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 4.9490101979604075,
|
| 516 |
+
"grad_norm": 2.65625,
|
| 517 |
+
"learning_rate": 4.529508284165662e-06,
|
| 518 |
+
"loss": 0.1271,
|
| 519 |
+
"step": 33000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 5.0,
|
| 523 |
+
"eval_accuracy": 0.6391864911984703,
|
| 524 |
+
"eval_f1": 0.5263388946843862,
|
| 525 |
+
"eval_loss": 0.12287881225347519,
|
| 526 |
+
"eval_precision": 0.464080708996073,
|
| 527 |
+
"eval_recall": 0.6391864911984703,
|
| 528 |
+
"eval_runtime": 40.1821,
|
| 529 |
+
"eval_samples_per_second": 295.007,
|
| 530 |
+
"eval_steps_per_second": 18.441,
|
| 531 |
+
"step": 33340
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 5.023995200959808,
|
| 535 |
+
"grad_norm": 2.296875,
|
| 536 |
+
"learning_rate": 3.923112069911616e-06,
|
| 537 |
+
"loss": 0.1263,
|
| 538 |
+
"step": 33500
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 5.098980203959208,
|
| 542 |
+
"grad_norm": 8.375,
|
| 543 |
+
"learning_rate": 3.3568213141557586e-06,
|
| 544 |
+
"loss": 0.1289,
|
| 545 |
+
"step": 34000
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 5.173965206958608,
|
| 549 |
+
"grad_norm": 3.21875,
|
| 550 |
+
"learning_rate": 2.8317135645169912e-06,
|
| 551 |
+
"loss": 0.1291,
|
| 552 |
+
"step": 34500
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 5.248950209958008,
|
| 556 |
+
"grad_norm": 4.1875,
|
| 557 |
+
"learning_rate": 2.3487880048942728e-06,
|
| 558 |
+
"loss": 0.1271,
|
| 559 |
+
"step": 35000
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 5.323935212957409,
|
| 563 |
+
"grad_norm": 3.765625,
|
| 564 |
+
"learning_rate": 1.9089635542026586e-06,
|
| 565 |
+
"loss": 0.1306,
|
| 566 |
+
"step": 35500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 5.398920215956808,
|
| 570 |
+
"grad_norm": 6.21875,
|
| 571 |
+
"learning_rate": 1.5130771178388153e-06,
|
| 572 |
+
"loss": 0.1287,
|
| 573 |
+
"step": 36000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 5.473905218956209,
|
| 577 |
+
"grad_norm": 4.65625,
|
| 578 |
+
"learning_rate": 1.1618819952033066e-06,
|
| 579 |
+
"loss": 0.1268,
|
| 580 |
+
"step": 36500
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 5.548890221955609,
|
| 584 |
+
"grad_norm": 3.625,
|
| 585 |
+
"learning_rate": 8.560464463097773e-07,
|
| 586 |
+
"loss": 0.1293,
|
| 587 |
+
"step": 37000
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 5.623875224955009,
|
| 591 |
+
"grad_norm": 4.28125,
|
| 592 |
+
"learning_rate": 5.961524202084901e-07,
|
| 593 |
+
"loss": 0.1292,
|
| 594 |
+
"step": 37500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 5.698860227954409,
|
| 598 |
+
"grad_norm": 3.03125,
|
| 599 |
+
"learning_rate": 3.826944476438388e-07,
|
| 600 |
+
"loss": 0.1311,
|
| 601 |
+
"step": 38000
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 5.7738452309538095,
|
| 605 |
+
"grad_norm": 3.609375,
|
| 606 |
+
"learning_rate": 2.1607870005291575e-07,
|
| 607 |
+
"loss": 0.1269,
|
| 608 |
+
"step": 38500
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 5.848830233953209,
|
| 612 |
+
"grad_norm": 4.6875,
|
| 613 |
+
"learning_rate": 9.662221669560767e-08,
|
| 614 |
+
"loss": 0.1273,
|
| 615 |
+
"step": 39000
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 5.92381523695261,
|
| 619 |
+
"grad_norm": 3.15625,
|
| 620 |
+
"learning_rate": 2.4552301386951415e-08,
|
| 621 |
+
"loss": 0.1312,
|
| 622 |
+
"step": 39500
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 5.9988002399520095,
|
| 626 |
+
"grad_norm": 4.78125,
|
| 627 |
+
"learning_rate": 6.089979592838191e-12,
|
| 628 |
+
"loss": 0.1285,
|
| 629 |
+
"step": 40000
|
| 630 |
+
}
|
| 631 |
+
],
|
| 632 |
+
"logging_steps": 500,
|
| 633 |
+
"max_steps": 40008,
|
| 634 |
+
"num_input_tokens_seen": 0,
|
| 635 |
+
"num_train_epochs": 6,
|
| 636 |
+
"save_steps": 1000,
|
| 637 |
+
"total_flos": 1.7186915377741824e+17,
|
| 638 |
+
"train_batch_size": 16,
|
| 639 |
+
"trial_name": null,
|
| 640 |
+
"trial_params": null
|
| 641 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef50d79747e142d8f7a8a481db4201a6e5d9e5b873ac2f5107138330d013c9da
|
| 3 |
+
size 5048
|