Upload folder using huggingface_hub
Browse files- added_tokens.json +6 -0
- gliner_config.json +129 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +83 -0
- trainer_state.json +741 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<<ENT>>": 128002,
|
| 3 |
+
"<<SEP>>": 128003,
|
| 4 |
+
"[FLERT]": 128001,
|
| 5 |
+
"[MASK]": 128000
|
| 6 |
+
}
|
gliner_config.json
ADDED
|
@@ -0,0 +1,129 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"class_token_index": 128002,
|
| 3 |
+
"dropout": 0.4,
|
| 4 |
+
"embed_ent_token": true,
|
| 5 |
+
"encoder_config": {
|
| 6 |
+
"_attn_implementation_autoset": false,
|
| 7 |
+
"_name_or_path": "microsoft/deberta-v3-small",
|
| 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 |
+
"legacy": true,
|
| 43 |
+
"length_penalty": 1.0,
|
| 44 |
+
"max_length": 20,
|
| 45 |
+
"max_position_embeddings": 512,
|
| 46 |
+
"max_relative_positions": -1,
|
| 47 |
+
"min_length": 0,
|
| 48 |
+
"model_type": "deberta-v2",
|
| 49 |
+
"no_repeat_ngram_size": 0,
|
| 50 |
+
"norm_rel_ebd": "layer_norm",
|
| 51 |
+
"num_attention_heads": 12,
|
| 52 |
+
"num_beam_groups": 1,
|
| 53 |
+
"num_beams": 1,
|
| 54 |
+
"num_hidden_layers": 6,
|
| 55 |
+
"num_return_sequences": 1,
|
| 56 |
+
"output_attentions": false,
|
| 57 |
+
"output_hidden_states": false,
|
| 58 |
+
"output_scores": false,
|
| 59 |
+
"pad_token_id": 0,
|
| 60 |
+
"pooler_dropout": 0,
|
| 61 |
+
"pooler_hidden_act": "gelu",
|
| 62 |
+
"pooler_hidden_size": 768,
|
| 63 |
+
"pos_att_type": [
|
| 64 |
+
"p2c",
|
| 65 |
+
"c2p"
|
| 66 |
+
],
|
| 67 |
+
"position_biased_input": false,
|
| 68 |
+
"position_buckets": 256,
|
| 69 |
+
"prefix": null,
|
| 70 |
+
"problem_type": null,
|
| 71 |
+
"pruned_heads": {},
|
| 72 |
+
"relative_attention": true,
|
| 73 |
+
"remove_invalid_values": false,
|
| 74 |
+
"repetition_penalty": 1.0,
|
| 75 |
+
"return_dict": true,
|
| 76 |
+
"return_dict_in_generate": false,
|
| 77 |
+
"sep_token_id": null,
|
| 78 |
+
"share_att_key": true,
|
| 79 |
+
"suppress_tokens": null,
|
| 80 |
+
"task_specific_params": null,
|
| 81 |
+
"temperature": 1.0,
|
| 82 |
+
"tf_legacy_loss": false,
|
| 83 |
+
"tie_encoder_decoder": false,
|
| 84 |
+
"tie_word_embeddings": true,
|
| 85 |
+
"tokenizer_class": null,
|
| 86 |
+
"top_k": 50,
|
| 87 |
+
"top_p": 1.0,
|
| 88 |
+
"torch_dtype": null,
|
| 89 |
+
"torchscript": false,
|
| 90 |
+
"type_vocab_size": 0,
|
| 91 |
+
"typical_p": 1.0,
|
| 92 |
+
"use_bfloat16": false,
|
| 93 |
+
"vocab_size": 128004
|
| 94 |
+
},
|
| 95 |
+
"ent_token": "<<ENT>>",
|
| 96 |
+
"eval_every": 5000,
|
| 97 |
+
"fine_tune": true,
|
| 98 |
+
"fuse_layers": false,
|
| 99 |
+
"has_rnn": true,
|
| 100 |
+
"hidden_size": 512,
|
| 101 |
+
"labels_encoder": null,
|
| 102 |
+
"labels_encoder_config": null,
|
| 103 |
+
"labels_fusion_schema": "",
|
| 104 |
+
"lr_encoder": "1e-5",
|
| 105 |
+
"lr_others": "5e-5",
|
| 106 |
+
"max_len": 1024,
|
| 107 |
+
"max_neg_type_ratio": 1,
|
| 108 |
+
"max_types": 25,
|
| 109 |
+
"max_width": 12,
|
| 110 |
+
"model_name": "microsoft/deberta-v3-small",
|
| 111 |
+
"model_type": "gliner",
|
| 112 |
+
"name": "correct",
|
| 113 |
+
"num_post_fusion_layers": 1,
|
| 114 |
+
"num_rnns": 1,
|
| 115 |
+
"num_steps": 30000,
|
| 116 |
+
"post_fusion_schema": "",
|
| 117 |
+
"pre_fusion": false,
|
| 118 |
+
"random_drop": true,
|
| 119 |
+
"sep_token": "<<SEP>>",
|
| 120 |
+
"shuffle_types": true,
|
| 121 |
+
"size_sup": -1,
|
| 122 |
+
"span_mode": "markerV0",
|
| 123 |
+
"subtoken_pooling": "first",
|
| 124 |
+
"train_batch_size": 8,
|
| 125 |
+
"transformers_version": "4.49.0",
|
| 126 |
+
"vocab_size": 128004,
|
| 127 |
+
"warmup_ratio": 3000,
|
| 128 |
+
"words_splitter_type": "whitespace"
|
| 129 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41fcda39c303a5926cbb82fccb4ddddf3fec697cd45eb52062b29a71da2ab8b1
|
| 3 |
+
size 610640046
|
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 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "[FLERT]",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
"128002": {
|
| 52 |
+
"content": "<<ENT>>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": true,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": false
|
| 58 |
+
},
|
| 59 |
+
"128003": {
|
| 60 |
+
"content": "<<SEP>>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": true,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": false
|
| 66 |
+
}
|
| 67 |
+
},
|
| 68 |
+
"bos_token": "[CLS]",
|
| 69 |
+
"clean_up_tokenization_spaces": false,
|
| 70 |
+
"cls_token": "[CLS]",
|
| 71 |
+
"do_lower_case": false,
|
| 72 |
+
"eos_token": "[SEP]",
|
| 73 |
+
"extra_special_tokens": {},
|
| 74 |
+
"mask_token": "[MASK]",
|
| 75 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 76 |
+
"pad_token": "[PAD]",
|
| 77 |
+
"sep_token": "[SEP]",
|
| 78 |
+
"sp_model_kwargs": {},
|
| 79 |
+
"split_by_punct": false,
|
| 80 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 81 |
+
"unk_token": "[UNK]",
|
| 82 |
+
"vocab_type": "spm"
|
| 83 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,741 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.1060723371308483,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 10000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.011060723371308484,
|
| 13 |
+
"grad_norm": 31525.89453125,
|
| 14 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 15 |
+
"loss": 108.938,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.022121446742616967,
|
| 20 |
+
"grad_norm": 276.1221008300781,
|
| 21 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 22 |
+
"loss": 71.4733,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03318217011392545,
|
| 27 |
+
"grad_norm": 3096.194580078125,
|
| 28 |
+
"learning_rate": 3e-06,
|
| 29 |
+
"loss": 119.8372,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.044242893485233935,
|
| 34 |
+
"grad_norm": 715.627197265625,
|
| 35 |
+
"learning_rate": 4.000000000000001e-06,
|
| 36 |
+
"loss": 131.9085,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.05530361685654242,
|
| 41 |
+
"grad_norm": 8888.615234375,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 120.4494,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0663643402278509,
|
| 48 |
+
"grad_norm": 4452.72119140625,
|
| 49 |
+
"learning_rate": 6e-06,
|
| 50 |
+
"loss": 100.8797,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07742506359915939,
|
| 55 |
+
"grad_norm": 66307.34375,
|
| 56 |
+
"learning_rate": 7e-06,
|
| 57 |
+
"loss": 145.084,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.08848578697046787,
|
| 62 |
+
"grad_norm": 602.1884765625,
|
| 63 |
+
"learning_rate": 8.000000000000001e-06,
|
| 64 |
+
"loss": 68.911,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.09954651034177635,
|
| 69 |
+
"grad_norm": 1317.8251953125,
|
| 70 |
+
"learning_rate": 9e-06,
|
| 71 |
+
"loss": 150.1405,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.11060723371308484,
|
| 76 |
+
"grad_norm": 716.1102905273438,
|
| 77 |
+
"learning_rate": 1e-05,
|
| 78 |
+
"loss": 54.1946,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.12166795708439332,
|
| 83 |
+
"grad_norm": 1669.779052734375,
|
| 84 |
+
"learning_rate": 9.88888888888889e-06,
|
| 85 |
+
"loss": 119.7225,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1327286804557018,
|
| 90 |
+
"grad_norm": 1085.806884765625,
|
| 91 |
+
"learning_rate": 9.777777777777779e-06,
|
| 92 |
+
"loss": 104.1395,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.14378940382701028,
|
| 97 |
+
"grad_norm": 317.991943359375,
|
| 98 |
+
"learning_rate": 9.666666666666667e-06,
|
| 99 |
+
"loss": 167.9486,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.15485012719831878,
|
| 104 |
+
"grad_norm": 225.4032745361328,
|
| 105 |
+
"learning_rate": 9.555555555555556e-06,
|
| 106 |
+
"loss": 65.5434,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.16591085056962726,
|
| 111 |
+
"grad_norm": 443.49407958984375,
|
| 112 |
+
"learning_rate": 9.444444444444445e-06,
|
| 113 |
+
"loss": 68.5829,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.17697157394093574,
|
| 118 |
+
"grad_norm": 492.5722961425781,
|
| 119 |
+
"learning_rate": 9.333333333333334e-06,
|
| 120 |
+
"loss": 97.6923,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.18803229731224422,
|
| 125 |
+
"grad_norm": 1269.8448486328125,
|
| 126 |
+
"learning_rate": 9.222222222222224e-06,
|
| 127 |
+
"loss": 95.6809,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.1990930206835527,
|
| 132 |
+
"grad_norm": 271.0899963378906,
|
| 133 |
+
"learning_rate": 9.111111111111112e-06,
|
| 134 |
+
"loss": 68.7351,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.21015374405486117,
|
| 139 |
+
"grad_norm": 300.30364990234375,
|
| 140 |
+
"learning_rate": 9e-06,
|
| 141 |
+
"loss": 113.9254,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.22121446742616968,
|
| 146 |
+
"grad_norm": 2832.990234375,
|
| 147 |
+
"learning_rate": 8.888888888888888e-06,
|
| 148 |
+
"loss": 176.4239,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.23227519079747816,
|
| 153 |
+
"grad_norm": 1707.886962890625,
|
| 154 |
+
"learning_rate": 8.777777777777778e-06,
|
| 155 |
+
"loss": 121.4123,
|
| 156 |
+
"step": 2100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.24333591416878664,
|
| 160 |
+
"grad_norm": 432.3907470703125,
|
| 161 |
+
"learning_rate": 8.666666666666668e-06,
|
| 162 |
+
"loss": 90.216,
|
| 163 |
+
"step": 2200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.2543966375400951,
|
| 167 |
+
"grad_norm": 759.7860717773438,
|
| 168 |
+
"learning_rate": 8.555555555555556e-06,
|
| 169 |
+
"loss": 80.3294,
|
| 170 |
+
"step": 2300
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.2654573609114036,
|
| 174 |
+
"grad_norm": 1113.482666015625,
|
| 175 |
+
"learning_rate": 8.444444444444446e-06,
|
| 176 |
+
"loss": 100.8702,
|
| 177 |
+
"step": 2400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.2765180842827121,
|
| 181 |
+
"grad_norm": 242.53280639648438,
|
| 182 |
+
"learning_rate": 8.333333333333334e-06,
|
| 183 |
+
"loss": 200.5789,
|
| 184 |
+
"step": 2500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.28757880765402055,
|
| 188 |
+
"grad_norm": 14315.33203125,
|
| 189 |
+
"learning_rate": 8.222222222222222e-06,
|
| 190 |
+
"loss": 131.5917,
|
| 191 |
+
"step": 2600
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.29863953102532903,
|
| 195 |
+
"grad_norm": 1412.022705078125,
|
| 196 |
+
"learning_rate": 8.111111111111112e-06,
|
| 197 |
+
"loss": 114.6078,
|
| 198 |
+
"step": 2700
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.30970025439663756,
|
| 202 |
+
"grad_norm": 481.417724609375,
|
| 203 |
+
"learning_rate": 8.000000000000001e-06,
|
| 204 |
+
"loss": 85.9446,
|
| 205 |
+
"step": 2800
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.32076097776794604,
|
| 209 |
+
"grad_norm": 1741.899169921875,
|
| 210 |
+
"learning_rate": 7.88888888888889e-06,
|
| 211 |
+
"loss": 76.5052,
|
| 212 |
+
"step": 2900
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.3318217011392545,
|
| 216 |
+
"grad_norm": 2144.94189453125,
|
| 217 |
+
"learning_rate": 7.77777777777778e-06,
|
| 218 |
+
"loss": 84.6808,
|
| 219 |
+
"step": 3000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.342882424510563,
|
| 223 |
+
"grad_norm": 641.1427001953125,
|
| 224 |
+
"learning_rate": 7.666666666666667e-06,
|
| 225 |
+
"loss": 85.521,
|
| 226 |
+
"step": 3100
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.3539431478818715,
|
| 230 |
+
"grad_norm": 305.78216552734375,
|
| 231 |
+
"learning_rate": 7.555555555555556e-06,
|
| 232 |
+
"loss": 64.7245,
|
| 233 |
+
"step": 3200
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.36500387125317996,
|
| 237 |
+
"grad_norm": 591.6135864257812,
|
| 238 |
+
"learning_rate": 7.444444444444445e-06,
|
| 239 |
+
"loss": 77.5208,
|
| 240 |
+
"step": 3300
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.37606459462448844,
|
| 244 |
+
"grad_norm": 391.4192810058594,
|
| 245 |
+
"learning_rate": 7.333333333333333e-06,
|
| 246 |
+
"loss": 62.7838,
|
| 247 |
+
"step": 3400
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.3871253179957969,
|
| 251 |
+
"grad_norm": 534.8387451171875,
|
| 252 |
+
"learning_rate": 7.222222222222223e-06,
|
| 253 |
+
"loss": 75.2527,
|
| 254 |
+
"step": 3500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.3981860413671054,
|
| 258 |
+
"grad_norm": 202.5685577392578,
|
| 259 |
+
"learning_rate": 7.111111111111112e-06,
|
| 260 |
+
"loss": 89.4137,
|
| 261 |
+
"step": 3600
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.40924676473841387,
|
| 265 |
+
"grad_norm": 714.9501953125,
|
| 266 |
+
"learning_rate": 7e-06,
|
| 267 |
+
"loss": 71.5902,
|
| 268 |
+
"step": 3700
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.42030748810972235,
|
| 272 |
+
"grad_norm": 127.53585052490234,
|
| 273 |
+
"learning_rate": 6.88888888888889e-06,
|
| 274 |
+
"loss": 121.4861,
|
| 275 |
+
"step": 3800
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.4313682114810309,
|
| 279 |
+
"grad_norm": 195.28065490722656,
|
| 280 |
+
"learning_rate": 6.777777777777779e-06,
|
| 281 |
+
"loss": 103.2692,
|
| 282 |
+
"step": 3900
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.44242893485233936,
|
| 286 |
+
"grad_norm": 452.83935546875,
|
| 287 |
+
"learning_rate": 6.666666666666667e-06,
|
| 288 |
+
"loss": 173.6033,
|
| 289 |
+
"step": 4000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.45348965822364784,
|
| 293 |
+
"grad_norm": 2889.515869140625,
|
| 294 |
+
"learning_rate": 6.555555555555556e-06,
|
| 295 |
+
"loss": 52.3384,
|
| 296 |
+
"step": 4100
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.4645503815949563,
|
| 300 |
+
"grad_norm": 3502.135986328125,
|
| 301 |
+
"learning_rate": 6.444444444444445e-06,
|
| 302 |
+
"loss": 89.3744,
|
| 303 |
+
"step": 4200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.4756111049662648,
|
| 307 |
+
"grad_norm": 224.1280517578125,
|
| 308 |
+
"learning_rate": 6.333333333333333e-06,
|
| 309 |
+
"loss": 84.7305,
|
| 310 |
+
"step": 4300
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.4866718283375733,
|
| 314 |
+
"grad_norm": 78.53791046142578,
|
| 315 |
+
"learning_rate": 6.222222222222223e-06,
|
| 316 |
+
"loss": 115.2134,
|
| 317 |
+
"step": 4400
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.49773255170888175,
|
| 321 |
+
"grad_norm": 146.20570373535156,
|
| 322 |
+
"learning_rate": 6.111111111111112e-06,
|
| 323 |
+
"loss": 84.5645,
|
| 324 |
+
"step": 4500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.5087932750801902,
|
| 328 |
+
"grad_norm": 535.9326171875,
|
| 329 |
+
"learning_rate": 6e-06,
|
| 330 |
+
"loss": 95.7671,
|
| 331 |
+
"step": 4600
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5198539984514987,
|
| 335 |
+
"grad_norm": 356.42462158203125,
|
| 336 |
+
"learning_rate": 5.88888888888889e-06,
|
| 337 |
+
"loss": 78.2208,
|
| 338 |
+
"step": 4700
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.5309147218228072,
|
| 342 |
+
"grad_norm": 744.9382934570312,
|
| 343 |
+
"learning_rate": 5.777777777777778e-06,
|
| 344 |
+
"loss": 67.7703,
|
| 345 |
+
"step": 4800
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.5419754451941157,
|
| 349 |
+
"grad_norm": 585.5819091796875,
|
| 350 |
+
"learning_rate": 5.666666666666667e-06,
|
| 351 |
+
"loss": 115.4916,
|
| 352 |
+
"step": 4900
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.5530361685654241,
|
| 356 |
+
"grad_norm": 955.3712768554688,
|
| 357 |
+
"learning_rate": 5.555555555555557e-06,
|
| 358 |
+
"loss": 46.3012,
|
| 359 |
+
"step": 5000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.5640968919367326,
|
| 363 |
+
"grad_norm": 675.9095458984375,
|
| 364 |
+
"learning_rate": 5.444444444444445e-06,
|
| 365 |
+
"loss": 191.4264,
|
| 366 |
+
"step": 5100
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.5751576153080411,
|
| 370 |
+
"grad_norm": 525.0625,
|
| 371 |
+
"learning_rate": 5.333333333333334e-06,
|
| 372 |
+
"loss": 73.2462,
|
| 373 |
+
"step": 5200
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.5862183386793496,
|
| 377 |
+
"grad_norm": 649.7520141601562,
|
| 378 |
+
"learning_rate": 5.2222222222222226e-06,
|
| 379 |
+
"loss": 57.1971,
|
| 380 |
+
"step": 5300
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.5972790620506581,
|
| 384 |
+
"grad_norm": 167.98040771484375,
|
| 385 |
+
"learning_rate": 5.1111111111111115e-06,
|
| 386 |
+
"loss": 128.9888,
|
| 387 |
+
"step": 5400
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.6083397854219667,
|
| 391 |
+
"grad_norm": 450.4929504394531,
|
| 392 |
+
"learning_rate": 5e-06,
|
| 393 |
+
"loss": 97.4584,
|
| 394 |
+
"step": 5500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.6194005087932751,
|
| 398 |
+
"grad_norm": 994.5988159179688,
|
| 399 |
+
"learning_rate": 4.888888888888889e-06,
|
| 400 |
+
"loss": 148.1406,
|
| 401 |
+
"step": 5600
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.6304612321645836,
|
| 405 |
+
"grad_norm": 977.2152099609375,
|
| 406 |
+
"learning_rate": 4.777777777777778e-06,
|
| 407 |
+
"loss": 59.5398,
|
| 408 |
+
"step": 5700
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.6415219555358921,
|
| 412 |
+
"grad_norm": 692.0723876953125,
|
| 413 |
+
"learning_rate": 4.666666666666667e-06,
|
| 414 |
+
"loss": 151.1167,
|
| 415 |
+
"step": 5800
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.6525826789072006,
|
| 419 |
+
"grad_norm": 906.3406982421875,
|
| 420 |
+
"learning_rate": 4.555555555555556e-06,
|
| 421 |
+
"loss": 80.2065,
|
| 422 |
+
"step": 5900
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.663643402278509,
|
| 426 |
+
"grad_norm": 654.7086181640625,
|
| 427 |
+
"learning_rate": 4.444444444444444e-06,
|
| 428 |
+
"loss": 125.2885,
|
| 429 |
+
"step": 6000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.6747041256498175,
|
| 433 |
+
"grad_norm": 470.31787109375,
|
| 434 |
+
"learning_rate": 4.333333333333334e-06,
|
| 435 |
+
"loss": 48.1181,
|
| 436 |
+
"step": 6100
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.685764849021126,
|
| 440 |
+
"grad_norm": 462.6188049316406,
|
| 441 |
+
"learning_rate": 4.222222222222223e-06,
|
| 442 |
+
"loss": 72.0648,
|
| 443 |
+
"step": 6200
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.6968255723924345,
|
| 447 |
+
"grad_norm": 669.2234497070312,
|
| 448 |
+
"learning_rate": 4.111111111111111e-06,
|
| 449 |
+
"loss": 92.0509,
|
| 450 |
+
"step": 6300
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.707886295763743,
|
| 454 |
+
"grad_norm": 428.6507263183594,
|
| 455 |
+
"learning_rate": 4.000000000000001e-06,
|
| 456 |
+
"loss": 64.739,
|
| 457 |
+
"step": 6400
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.7189470191350514,
|
| 461 |
+
"grad_norm": 893.17138671875,
|
| 462 |
+
"learning_rate": 3.88888888888889e-06,
|
| 463 |
+
"loss": 79.4529,
|
| 464 |
+
"step": 6500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.7300077425063599,
|
| 468 |
+
"grad_norm": 1005.3417358398438,
|
| 469 |
+
"learning_rate": 3.777777777777778e-06,
|
| 470 |
+
"loss": 45.9996,
|
| 471 |
+
"step": 6600
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.7410684658776684,
|
| 475 |
+
"grad_norm": 1213.5457763671875,
|
| 476 |
+
"learning_rate": 3.6666666666666666e-06,
|
| 477 |
+
"loss": 84.1884,
|
| 478 |
+
"step": 6700
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.7521291892489769,
|
| 482 |
+
"grad_norm": 706.6162109375,
|
| 483 |
+
"learning_rate": 3.555555555555556e-06,
|
| 484 |
+
"loss": 80.2486,
|
| 485 |
+
"step": 6800
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.7631899126202853,
|
| 489 |
+
"grad_norm": 311.6005859375,
|
| 490 |
+
"learning_rate": 3.444444444444445e-06,
|
| 491 |
+
"loss": 86.258,
|
| 492 |
+
"step": 6900
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.7742506359915938,
|
| 496 |
+
"grad_norm": 1002.1148071289062,
|
| 497 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 498 |
+
"loss": 48.6228,
|
| 499 |
+
"step": 7000
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.7853113593629023,
|
| 503 |
+
"grad_norm": 238.88232421875,
|
| 504 |
+
"learning_rate": 3.2222222222222227e-06,
|
| 505 |
+
"loss": 58.1885,
|
| 506 |
+
"step": 7100
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.7963720827342108,
|
| 510 |
+
"grad_norm": 332.437255859375,
|
| 511 |
+
"learning_rate": 3.1111111111111116e-06,
|
| 512 |
+
"loss": 53.2679,
|
| 513 |
+
"step": 7200
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.8074328061055193,
|
| 517 |
+
"grad_norm": 365.4303283691406,
|
| 518 |
+
"learning_rate": 3e-06,
|
| 519 |
+
"loss": 68.5481,
|
| 520 |
+
"step": 7300
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.8184935294768277,
|
| 524 |
+
"grad_norm": 2730.581787109375,
|
| 525 |
+
"learning_rate": 2.888888888888889e-06,
|
| 526 |
+
"loss": 87.514,
|
| 527 |
+
"step": 7400
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.8295542528481362,
|
| 531 |
+
"grad_norm": 276.9474792480469,
|
| 532 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 533 |
+
"loss": 50.4965,
|
| 534 |
+
"step": 7500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.8406149762194447,
|
| 538 |
+
"grad_norm": 2384.289306640625,
|
| 539 |
+
"learning_rate": 2.666666666666667e-06,
|
| 540 |
+
"loss": 93.6163,
|
| 541 |
+
"step": 7600
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.8516756995907533,
|
| 545 |
+
"grad_norm": 2390.2421875,
|
| 546 |
+
"learning_rate": 2.5555555555555557e-06,
|
| 547 |
+
"loss": 56.3228,
|
| 548 |
+
"step": 7700
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.8627364229620618,
|
| 552 |
+
"grad_norm": 818.0576782226562,
|
| 553 |
+
"learning_rate": 2.4444444444444447e-06,
|
| 554 |
+
"loss": 68.8869,
|
| 555 |
+
"step": 7800
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.8737971463333702,
|
| 559 |
+
"grad_norm": 792.1302490234375,
|
| 560 |
+
"learning_rate": 2.3333333333333336e-06,
|
| 561 |
+
"loss": 67.4239,
|
| 562 |
+
"step": 7900
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.8848578697046787,
|
| 566 |
+
"grad_norm": 995.8483276367188,
|
| 567 |
+
"learning_rate": 2.222222222222222e-06,
|
| 568 |
+
"loss": 63.2453,
|
| 569 |
+
"step": 8000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.8959185930759872,
|
| 573 |
+
"grad_norm": 788.3203125,
|
| 574 |
+
"learning_rate": 2.1111111111111114e-06,
|
| 575 |
+
"loss": 131.5255,
|
| 576 |
+
"step": 8100
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.9069793164472957,
|
| 580 |
+
"grad_norm": 708.2405395507812,
|
| 581 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 582 |
+
"loss": 57.5729,
|
| 583 |
+
"step": 8200
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.9180400398186042,
|
| 587 |
+
"grad_norm": 1030.069580078125,
|
| 588 |
+
"learning_rate": 1.888888888888889e-06,
|
| 589 |
+
"loss": 100.5658,
|
| 590 |
+
"step": 8300
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.9291007631899126,
|
| 594 |
+
"grad_norm": 927.4437866210938,
|
| 595 |
+
"learning_rate": 1.777777777777778e-06,
|
| 596 |
+
"loss": 73.2141,
|
| 597 |
+
"step": 8400
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.9401614865612211,
|
| 601 |
+
"grad_norm": 204.16241455078125,
|
| 602 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 603 |
+
"loss": 59.6098,
|
| 604 |
+
"step": 8500
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.9512222099325296,
|
| 608 |
+
"grad_norm": 242.94900512695312,
|
| 609 |
+
"learning_rate": 1.5555555555555558e-06,
|
| 610 |
+
"loss": 84.2695,
|
| 611 |
+
"step": 8600
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.9622829333038381,
|
| 615 |
+
"grad_norm": 318.7410888671875,
|
| 616 |
+
"learning_rate": 1.4444444444444445e-06,
|
| 617 |
+
"loss": 43.2253,
|
| 618 |
+
"step": 8700
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.9733436566751466,
|
| 622 |
+
"grad_norm": 791.7606811523438,
|
| 623 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 624 |
+
"loss": 138.4619,
|
| 625 |
+
"step": 8800
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.984404380046455,
|
| 629 |
+
"grad_norm": 389.98565673828125,
|
| 630 |
+
"learning_rate": 1.2222222222222223e-06,
|
| 631 |
+
"loss": 83.4004,
|
| 632 |
+
"step": 8900
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.9954651034177635,
|
| 636 |
+
"grad_norm": 158.41607666015625,
|
| 637 |
+
"learning_rate": 1.111111111111111e-06,
|
| 638 |
+
"loss": 84.5722,
|
| 639 |
+
"step": 9000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.0,
|
| 643 |
+
"eval_loss": 78.85076141357422,
|
| 644 |
+
"eval_runtime": 53.3119,
|
| 645 |
+
"eval_samples_per_second": 37.703,
|
| 646 |
+
"eval_steps_per_second": 18.851,
|
| 647 |
+
"step": 9041
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.006525826789072,
|
| 651 |
+
"grad_norm": 783.9674072265625,
|
| 652 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 653 |
+
"loss": 65.1962,
|
| 654 |
+
"step": 9100
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.0175865501603805,
|
| 658 |
+
"grad_norm": 1137.7186279296875,
|
| 659 |
+
"learning_rate": 8.88888888888889e-07,
|
| 660 |
+
"loss": 58.0089,
|
| 661 |
+
"step": 9200
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.028647273531689,
|
| 665 |
+
"grad_norm": 88.58700561523438,
|
| 666 |
+
"learning_rate": 7.777777777777779e-07,
|
| 667 |
+
"loss": 49.665,
|
| 668 |
+
"step": 9300
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.0397079969029974,
|
| 672 |
+
"grad_norm": 218.33413696289062,
|
| 673 |
+
"learning_rate": 6.666666666666667e-07,
|
| 674 |
+
"loss": 64.1321,
|
| 675 |
+
"step": 9400
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.050768720274306,
|
| 679 |
+
"grad_norm": 222.10977172851562,
|
| 680 |
+
"learning_rate": 5.555555555555555e-07,
|
| 681 |
+
"loss": 117.5688,
|
| 682 |
+
"step": 9500
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.0618294436456144,
|
| 686 |
+
"grad_norm": 1043.607177734375,
|
| 687 |
+
"learning_rate": 4.444444444444445e-07,
|
| 688 |
+
"loss": 72.3682,
|
| 689 |
+
"step": 9600
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.0728901670169229,
|
| 693 |
+
"grad_norm": 369.0968017578125,
|
| 694 |
+
"learning_rate": 3.3333333333333335e-07,
|
| 695 |
+
"loss": 128.3121,
|
| 696 |
+
"step": 9700
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.0839508903882313,
|
| 700 |
+
"grad_norm": 939.8422241210938,
|
| 701 |
+
"learning_rate": 2.2222222222222224e-07,
|
| 702 |
+
"loss": 112.3189,
|
| 703 |
+
"step": 9800
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.0950116137595398,
|
| 707 |
+
"grad_norm": 643.8301391601562,
|
| 708 |
+
"learning_rate": 1.1111111111111112e-07,
|
| 709 |
+
"loss": 55.195,
|
| 710 |
+
"step": 9900
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.1060723371308483,
|
| 714 |
+
"grad_norm": 335.5890808105469,
|
| 715 |
+
"learning_rate": 0.0,
|
| 716 |
+
"loss": 146.6059,
|
| 717 |
+
"step": 10000
|
| 718 |
+
}
|
| 719 |
+
],
|
| 720 |
+
"logging_steps": 100,
|
| 721 |
+
"max_steps": 10000,
|
| 722 |
+
"num_input_tokens_seen": 0,
|
| 723 |
+
"num_train_epochs": 2,
|
| 724 |
+
"save_steps": 5000,
|
| 725 |
+
"stateful_callbacks": {
|
| 726 |
+
"TrainerControl": {
|
| 727 |
+
"args": {
|
| 728 |
+
"should_epoch_stop": false,
|
| 729 |
+
"should_evaluate": false,
|
| 730 |
+
"should_log": false,
|
| 731 |
+
"should_save": true,
|
| 732 |
+
"should_training_stop": true
|
| 733 |
+
},
|
| 734 |
+
"attributes": {}
|
| 735 |
+
}
|
| 736 |
+
},
|
| 737 |
+
"total_flos": 0.0,
|
| 738 |
+
"train_batch_size": 2,
|
| 739 |
+
"trial_name": null,
|
| 740 |
+
"trial_params": null
|
| 741 |
+
}
|