Upload folder using huggingface_hub
Browse files- config.json +191 -0
- generation_config.json +10 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer_config.json +57 -0
- trainer_state.json +466 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,191 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "patrickvonplaten/longformer2roberta-cnn_dailymail-fp16",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"EncoderDecoderModel"
|
| 5 |
+
],
|
| 6 |
+
"decoder": {
|
| 7 |
+
"_name_or_path": "",
|
| 8 |
+
"add_cross_attention": true,
|
| 9 |
+
"architectures": [
|
| 10 |
+
"RobertaForMaskedLM"
|
| 11 |
+
],
|
| 12 |
+
"attention_probs_dropout_prob": 0.1,
|
| 13 |
+
"bad_words_ids": null,
|
| 14 |
+
"begin_suppress_tokens": null,
|
| 15 |
+
"bos_token_id": 0,
|
| 16 |
+
"chunk_size_feed_forward": 0,
|
| 17 |
+
"classifier_dropout": null,
|
| 18 |
+
"cross_attention_hidden_size": null,
|
| 19 |
+
"decoder_start_token_id": null,
|
| 20 |
+
"diversity_penalty": 0.0,
|
| 21 |
+
"do_sample": false,
|
| 22 |
+
"early_stopping": false,
|
| 23 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 24 |
+
"eos_token_id": 2,
|
| 25 |
+
"exponential_decay_length_penalty": null,
|
| 26 |
+
"finetuning_task": null,
|
| 27 |
+
"forced_bos_token_id": null,
|
| 28 |
+
"forced_eos_token_id": null,
|
| 29 |
+
"gradient_checkpointing": false,
|
| 30 |
+
"hidden_act": "gelu",
|
| 31 |
+
"hidden_dropout_prob": 0.1,
|
| 32 |
+
"hidden_size": 768,
|
| 33 |
+
"id2label": {
|
| 34 |
+
"0": "LABEL_0",
|
| 35 |
+
"1": "LABEL_1"
|
| 36 |
+
},
|
| 37 |
+
"initializer_range": 0.02,
|
| 38 |
+
"intermediate_size": 3072,
|
| 39 |
+
"is_decoder": true,
|
| 40 |
+
"is_encoder_decoder": false,
|
| 41 |
+
"label2id": {
|
| 42 |
+
"LABEL_0": 0,
|
| 43 |
+
"LABEL_1": 1
|
| 44 |
+
},
|
| 45 |
+
"layer_norm_eps": 1e-05,
|
| 46 |
+
"length_penalty": 1.0,
|
| 47 |
+
"max_length": 20,
|
| 48 |
+
"max_position_embeddings": 514,
|
| 49 |
+
"min_length": 0,
|
| 50 |
+
"model_type": "roberta",
|
| 51 |
+
"no_repeat_ngram_size": 0,
|
| 52 |
+
"num_attention_heads": 12,
|
| 53 |
+
"num_beam_groups": 1,
|
| 54 |
+
"num_beams": 1,
|
| 55 |
+
"num_hidden_layers": 12,
|
| 56 |
+
"num_return_sequences": 1,
|
| 57 |
+
"output_attentions": false,
|
| 58 |
+
"output_hidden_states": false,
|
| 59 |
+
"output_scores": false,
|
| 60 |
+
"pad_token_id": 1,
|
| 61 |
+
"position_embedding_type": "absolute",
|
| 62 |
+
"prefix": null,
|
| 63 |
+
"problem_type": null,
|
| 64 |
+
"pruned_heads": {},
|
| 65 |
+
"remove_invalid_values": false,
|
| 66 |
+
"repetition_penalty": 1.0,
|
| 67 |
+
"return_dict": false,
|
| 68 |
+
"return_dict_in_generate": false,
|
| 69 |
+
"sep_token_id": null,
|
| 70 |
+
"suppress_tokens": null,
|
| 71 |
+
"task_specific_params": null,
|
| 72 |
+
"temperature": 1.0,
|
| 73 |
+
"tf_legacy_loss": false,
|
| 74 |
+
"tie_encoder_decoder": false,
|
| 75 |
+
"tie_word_embeddings": true,
|
| 76 |
+
"tokenizer_class": null,
|
| 77 |
+
"top_k": 50,
|
| 78 |
+
"top_p": 1.0,
|
| 79 |
+
"torch_dtype": null,
|
| 80 |
+
"torchscript": false,
|
| 81 |
+
"type_vocab_size": 1,
|
| 82 |
+
"typical_p": 1.0,
|
| 83 |
+
"use_bfloat16": false,
|
| 84 |
+
"use_cache": true,
|
| 85 |
+
"vocab_size": 50265
|
| 86 |
+
},
|
| 87 |
+
"decoder_start_token_id": 0,
|
| 88 |
+
"encoder": {
|
| 89 |
+
"_name_or_path": "",
|
| 90 |
+
"add_cross_attention": false,
|
| 91 |
+
"architectures": null,
|
| 92 |
+
"attention_mode": "longformer",
|
| 93 |
+
"attention_probs_dropout_prob": 0.1,
|
| 94 |
+
"attention_window": [
|
| 95 |
+
512,
|
| 96 |
+
512,
|
| 97 |
+
512,
|
| 98 |
+
512,
|
| 99 |
+
512,
|
| 100 |
+
512,
|
| 101 |
+
512,
|
| 102 |
+
512,
|
| 103 |
+
512,
|
| 104 |
+
512,
|
| 105 |
+
512,
|
| 106 |
+
512
|
| 107 |
+
],
|
| 108 |
+
"bad_words_ids": null,
|
| 109 |
+
"begin_suppress_tokens": null,
|
| 110 |
+
"bos_token_id": 0,
|
| 111 |
+
"chunk_size_feed_forward": 0,
|
| 112 |
+
"cross_attention_hidden_size": null,
|
| 113 |
+
"decoder_start_token_id": null,
|
| 114 |
+
"diversity_penalty": 0.0,
|
| 115 |
+
"do_sample": false,
|
| 116 |
+
"early_stopping": false,
|
| 117 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 118 |
+
"eos_token_id": 2,
|
| 119 |
+
"exponential_decay_length_penalty": null,
|
| 120 |
+
"finetuning_task": null,
|
| 121 |
+
"forced_bos_token_id": null,
|
| 122 |
+
"forced_eos_token_id": null,
|
| 123 |
+
"gradient_checkpointing": false,
|
| 124 |
+
"hidden_act": "gelu",
|
| 125 |
+
"hidden_dropout_prob": 0.1,
|
| 126 |
+
"hidden_size": 768,
|
| 127 |
+
"id2label": {
|
| 128 |
+
"0": "LABEL_0",
|
| 129 |
+
"1": "LABEL_1"
|
| 130 |
+
},
|
| 131 |
+
"ignore_attention_mask": false,
|
| 132 |
+
"initializer_range": 0.02,
|
| 133 |
+
"intermediate_size": 3072,
|
| 134 |
+
"is_decoder": false,
|
| 135 |
+
"is_encoder_decoder": false,
|
| 136 |
+
"label2id": {
|
| 137 |
+
"LABEL_0": 0,
|
| 138 |
+
"LABEL_1": 1
|
| 139 |
+
},
|
| 140 |
+
"layer_norm_eps": 1e-05,
|
| 141 |
+
"length_penalty": 1.0,
|
| 142 |
+
"max_length": 20,
|
| 143 |
+
"max_position_embeddings": 4098,
|
| 144 |
+
"min_length": 0,
|
| 145 |
+
"model_type": "longformer",
|
| 146 |
+
"no_repeat_ngram_size": 0,
|
| 147 |
+
"num_attention_heads": 12,
|
| 148 |
+
"num_beam_groups": 1,
|
| 149 |
+
"num_beams": 1,
|
| 150 |
+
"num_hidden_layers": 12,
|
| 151 |
+
"num_return_sequences": 1,
|
| 152 |
+
"onnx_export": false,
|
| 153 |
+
"output_attentions": false,
|
| 154 |
+
"output_hidden_states": false,
|
| 155 |
+
"output_scores": false,
|
| 156 |
+
"pad_token_id": 1,
|
| 157 |
+
"prefix": null,
|
| 158 |
+
"problem_type": null,
|
| 159 |
+
"pruned_heads": {},
|
| 160 |
+
"remove_invalid_values": false,
|
| 161 |
+
"repetition_penalty": 1.0,
|
| 162 |
+
"return_dict": false,
|
| 163 |
+
"return_dict_in_generate": false,
|
| 164 |
+
"sep_token_id": 2,
|
| 165 |
+
"suppress_tokens": null,
|
| 166 |
+
"task_specific_params": null,
|
| 167 |
+
"temperature": 1.0,
|
| 168 |
+
"tf_legacy_loss": false,
|
| 169 |
+
"tie_encoder_decoder": false,
|
| 170 |
+
"tie_word_embeddings": true,
|
| 171 |
+
"tokenizer_class": null,
|
| 172 |
+
"top_k": 50,
|
| 173 |
+
"top_p": 1.0,
|
| 174 |
+
"torch_dtype": null,
|
| 175 |
+
"torchscript": false,
|
| 176 |
+
"type_vocab_size": 1,
|
| 177 |
+
"typical_p": 1.0,
|
| 178 |
+
"use_bfloat16": false,
|
| 179 |
+
"use_cache": true,
|
| 180 |
+
"vocab_size": 50265
|
| 181 |
+
},
|
| 182 |
+
"eos_token_id": 2,
|
| 183 |
+
"is_encoder_decoder": true,
|
| 184 |
+
"max_length": 142,
|
| 185 |
+
"min_length": 56,
|
| 186 |
+
"model_type": "encoder-decoder",
|
| 187 |
+
"no_repeat_ngram_size": 3,
|
| 188 |
+
"pad_token_id": 2,
|
| 189 |
+
"torch_dtype": "float32",
|
| 190 |
+
"transformers_version": "4.38.2"
|
| 191 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 0,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"max_length": 142,
|
| 6 |
+
"min_length": 56,
|
| 7 |
+
"no_repeat_ngram_size": 3,
|
| 8 |
+
"pad_token_id": 2,
|
| 9 |
+
"transformers_version": "4.38.2"
|
| 10 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55f7a8201aac477cf1c9127712a90a9edbd49a80f2f77e7dd86ee2146c78b8d7
|
| 3 |
+
size 1206970564
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6e0b8ea78bc36ca28b68a30c965b253af82617e7cab7cd7c1162dfd82231163
|
| 3 |
+
size 2239409895
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63fd23f79f918958cb0dbe93549eeabbe2af1235dd38bfa86dbdc7caf9ea1a20
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0eda73623e5c1792f1b626b67e9794340b053f30867c922ffc8a1c038552d5cf
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 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": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 4096,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "LongformerTokenizer",
|
| 55 |
+
"unk_token": "<unk>",
|
| 56 |
+
"use_fast": true
|
| 57 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,466 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 397,
|
| 6 |
+
"global_step": 9536,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.17,
|
| 13 |
+
"eval_gen_len": 83.5593,
|
| 14 |
+
"eval_loss": 1.6528608798980713,
|
| 15 |
+
"eval_rouge1": 50.4957,
|
| 16 |
+
"eval_rouge2": 32.5323,
|
| 17 |
+
"eval_rougeL": 40.7567,
|
| 18 |
+
"eval_rougeLsum": 40.5733,
|
| 19 |
+
"eval_runtime": 41.984,
|
| 20 |
+
"eval_samples_per_second": 1.405,
|
| 21 |
+
"eval_steps_per_second": 0.715,
|
| 22 |
+
"step": 397
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.21,
|
| 26 |
+
"grad_norm": 8.36017894744873,
|
| 27 |
+
"learning_rate": 1.9404362416107384e-05,
|
| 28 |
+
"loss": 2.7418,
|
| 29 |
+
"step": 500
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.33,
|
| 33 |
+
"eval_gen_len": 83.3729,
|
| 34 |
+
"eval_loss": 1.3848459720611572,
|
| 35 |
+
"eval_rouge1": 49.9993,
|
| 36 |
+
"eval_rouge2": 31.5422,
|
| 37 |
+
"eval_rougeL": 40.7043,
|
| 38 |
+
"eval_rougeLsum": 40.6632,
|
| 39 |
+
"eval_runtime": 41.848,
|
| 40 |
+
"eval_samples_per_second": 1.41,
|
| 41 |
+
"eval_steps_per_second": 0.717,
|
| 42 |
+
"step": 794
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.42,
|
| 46 |
+
"grad_norm": 10.013521194458008,
|
| 47 |
+
"learning_rate": 1.880512943432407e-05,
|
| 48 |
+
"loss": 1.6117,
|
| 49 |
+
"step": 1000
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.5,
|
| 53 |
+
"eval_gen_len": 84.8983,
|
| 54 |
+
"eval_loss": 1.3274192810058594,
|
| 55 |
+
"eval_rouge1": 50.0655,
|
| 56 |
+
"eval_rouge2": 31.4638,
|
| 57 |
+
"eval_rougeL": 40.2184,
|
| 58 |
+
"eval_rougeLsum": 39.9987,
|
| 59 |
+
"eval_runtime": 42.1731,
|
| 60 |
+
"eval_samples_per_second": 1.399,
|
| 61 |
+
"eval_steps_per_second": 0.711,
|
| 62 |
+
"step": 1191
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.63,
|
| 66 |
+
"grad_norm": 9.272841453552246,
|
| 67 |
+
"learning_rate": 1.820589645254075e-05,
|
| 68 |
+
"loss": 1.4861,
|
| 69 |
+
"step": 1500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.67,
|
| 73 |
+
"eval_gen_len": 87.1864,
|
| 74 |
+
"eval_loss": 1.3262691497802734,
|
| 75 |
+
"eval_rouge1": 51.2154,
|
| 76 |
+
"eval_rouge2": 33.6289,
|
| 77 |
+
"eval_rougeL": 41.9642,
|
| 78 |
+
"eval_rougeLsum": 41.7649,
|
| 79 |
+
"eval_runtime": 43.0575,
|
| 80 |
+
"eval_samples_per_second": 1.37,
|
| 81 |
+
"eval_steps_per_second": 0.697,
|
| 82 |
+
"step": 1588
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.83,
|
| 86 |
+
"eval_gen_len": 85.9661,
|
| 87 |
+
"eval_loss": 1.2881355285644531,
|
| 88 |
+
"eval_rouge1": 52.2072,
|
| 89 |
+
"eval_rouge2": 34.2681,
|
| 90 |
+
"eval_rougeL": 42.7582,
|
| 91 |
+
"eval_rougeLsum": 42.5683,
|
| 92 |
+
"eval_runtime": 42.4338,
|
| 93 |
+
"eval_samples_per_second": 1.39,
|
| 94 |
+
"eval_steps_per_second": 0.707,
|
| 95 |
+
"step": 1985
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.84,
|
| 99 |
+
"grad_norm": 10.048806190490723,
|
| 100 |
+
"learning_rate": 1.7609060402684567e-05,
|
| 101 |
+
"loss": 1.495,
|
| 102 |
+
"step": 2000
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.0,
|
| 106 |
+
"eval_gen_len": 80.1864,
|
| 107 |
+
"eval_loss": 1.2640005350112915,
|
| 108 |
+
"eval_rouge1": 52.1344,
|
| 109 |
+
"eval_rouge2": 34.3518,
|
| 110 |
+
"eval_rougeL": 42.9145,
|
| 111 |
+
"eval_rougeLsum": 42.7837,
|
| 112 |
+
"eval_runtime": 40.643,
|
| 113 |
+
"eval_samples_per_second": 1.452,
|
| 114 |
+
"eval_steps_per_second": 0.738,
|
| 115 |
+
"step": 2382
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.05,
|
| 119 |
+
"grad_norm": 9.145220756530762,
|
| 120 |
+
"learning_rate": 1.7009827420901247e-05,
|
| 121 |
+
"loss": 1.4292,
|
| 122 |
+
"step": 2500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.17,
|
| 126 |
+
"eval_gen_len": 83.5593,
|
| 127 |
+
"eval_loss": 1.2814366817474365,
|
| 128 |
+
"eval_rouge1": 51.9388,
|
| 129 |
+
"eval_rouge2": 33.6073,
|
| 130 |
+
"eval_rougeL": 41.9771,
|
| 131 |
+
"eval_rougeLsum": 41.8638,
|
| 132 |
+
"eval_runtime": 41.9785,
|
| 133 |
+
"eval_samples_per_second": 1.405,
|
| 134 |
+
"eval_steps_per_second": 0.715,
|
| 135 |
+
"step": 2779
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.26,
|
| 139 |
+
"grad_norm": 9.626166343688965,
|
| 140 |
+
"learning_rate": 1.641059443911793e-05,
|
| 141 |
+
"loss": 1.2572,
|
| 142 |
+
"step": 3000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.33,
|
| 146 |
+
"eval_gen_len": 81.7458,
|
| 147 |
+
"eval_loss": 1.3041572570800781,
|
| 148 |
+
"eval_rouge1": 52.685,
|
| 149 |
+
"eval_rouge2": 34.8664,
|
| 150 |
+
"eval_rougeL": 43.247,
|
| 151 |
+
"eval_rougeLsum": 43.2174,
|
| 152 |
+
"eval_runtime": 40.4041,
|
| 153 |
+
"eval_samples_per_second": 1.46,
|
| 154 |
+
"eval_steps_per_second": 0.742,
|
| 155 |
+
"step": 3176
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.47,
|
| 159 |
+
"grad_norm": 8.85732364654541,
|
| 160 |
+
"learning_rate": 1.5811361457334612e-05,
|
| 161 |
+
"loss": 1.2858,
|
| 162 |
+
"step": 3500
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.5,
|
| 166 |
+
"eval_gen_len": 83.4915,
|
| 167 |
+
"eval_loss": 1.250982403755188,
|
| 168 |
+
"eval_rouge1": 53.1395,
|
| 169 |
+
"eval_rouge2": 35.0366,
|
| 170 |
+
"eval_rougeL": 44.0336,
|
| 171 |
+
"eval_rougeLsum": 43.8277,
|
| 172 |
+
"eval_runtime": 41.066,
|
| 173 |
+
"eval_samples_per_second": 1.437,
|
| 174 |
+
"eval_steps_per_second": 0.731,
|
| 175 |
+
"step": 3573
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.67,
|
| 179 |
+
"eval_gen_len": 85.7797,
|
| 180 |
+
"eval_loss": 1.2450958490371704,
|
| 181 |
+
"eval_rouge1": 53.2435,
|
| 182 |
+
"eval_rouge2": 34.0265,
|
| 183 |
+
"eval_rougeL": 43.1606,
|
| 184 |
+
"eval_rougeLsum": 42.9125,
|
| 185 |
+
"eval_runtime": 42.4863,
|
| 186 |
+
"eval_samples_per_second": 1.389,
|
| 187 |
+
"eval_steps_per_second": 0.706,
|
| 188 |
+
"step": 3970
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.68,
|
| 192 |
+
"grad_norm": 9.060718536376953,
|
| 193 |
+
"learning_rate": 1.5212128475551296e-05,
|
| 194 |
+
"loss": 1.2632,
|
| 195 |
+
"step": 4000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.83,
|
| 199 |
+
"eval_gen_len": 84.0678,
|
| 200 |
+
"eval_loss": 1.2505569458007812,
|
| 201 |
+
"eval_rouge1": 52.9033,
|
| 202 |
+
"eval_rouge2": 34.6637,
|
| 203 |
+
"eval_rougeL": 43.0146,
|
| 204 |
+
"eval_rougeLsum": 42.8985,
|
| 205 |
+
"eval_runtime": 42.1089,
|
| 206 |
+
"eval_samples_per_second": 1.401,
|
| 207 |
+
"eval_steps_per_second": 0.712,
|
| 208 |
+
"step": 4367
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.89,
|
| 212 |
+
"grad_norm": 7.555502414703369,
|
| 213 |
+
"learning_rate": 1.4612895493767978e-05,
|
| 214 |
+
"loss": 1.2367,
|
| 215 |
+
"step": 4500
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 2.0,
|
| 219 |
+
"eval_gen_len": 82.322,
|
| 220 |
+
"eval_loss": 1.2485252618789673,
|
| 221 |
+
"eval_rouge1": 50.1387,
|
| 222 |
+
"eval_rouge2": 31.1201,
|
| 223 |
+
"eval_rougeL": 40.0786,
|
| 224 |
+
"eval_rougeLsum": 40.1657,
|
| 225 |
+
"eval_runtime": 41.189,
|
| 226 |
+
"eval_samples_per_second": 1.432,
|
| 227 |
+
"eval_steps_per_second": 0.728,
|
| 228 |
+
"step": 4764
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 2.1,
|
| 232 |
+
"grad_norm": 7.1890788078308105,
|
| 233 |
+
"learning_rate": 1.401366251198466e-05,
|
| 234 |
+
"loss": 1.1512,
|
| 235 |
+
"step": 5000
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 2.16,
|
| 239 |
+
"eval_gen_len": 82.9322,
|
| 240 |
+
"eval_loss": 1.261144757270813,
|
| 241 |
+
"eval_rouge1": 52.7072,
|
| 242 |
+
"eval_rouge2": 34.6442,
|
| 243 |
+
"eval_rougeL": 43.2377,
|
| 244 |
+
"eval_rougeLsum": 43.1384,
|
| 245 |
+
"eval_runtime": 41.2591,
|
| 246 |
+
"eval_samples_per_second": 1.43,
|
| 247 |
+
"eval_steps_per_second": 0.727,
|
| 248 |
+
"step": 5161
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.31,
|
| 252 |
+
"grad_norm": 7.86561918258667,
|
| 253 |
+
"learning_rate": 1.341562799616491e-05,
|
| 254 |
+
"loss": 1.0728,
|
| 255 |
+
"step": 5500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.33,
|
| 259 |
+
"eval_gen_len": 86.4237,
|
| 260 |
+
"eval_loss": 1.2699768543243408,
|
| 261 |
+
"eval_rouge1": 52.3383,
|
| 262 |
+
"eval_rouge2": 34.7756,
|
| 263 |
+
"eval_rougeL": 42.9406,
|
| 264 |
+
"eval_rougeLsum": 42.7658,
|
| 265 |
+
"eval_runtime": 42.4715,
|
| 266 |
+
"eval_samples_per_second": 1.389,
|
| 267 |
+
"eval_steps_per_second": 0.706,
|
| 268 |
+
"step": 5558
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 2.5,
|
| 272 |
+
"eval_gen_len": 84.3051,
|
| 273 |
+
"eval_loss": 1.2631828784942627,
|
| 274 |
+
"eval_rouge1": 52.8233,
|
| 275 |
+
"eval_rouge2": 35.1768,
|
| 276 |
+
"eval_rougeL": 43.8642,
|
| 277 |
+
"eval_rougeLsum": 43.7259,
|
| 278 |
+
"eval_runtime": 41.727,
|
| 279 |
+
"eval_samples_per_second": 1.414,
|
| 280 |
+
"eval_steps_per_second": 0.719,
|
| 281 |
+
"step": 5955
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.52,
|
| 285 |
+
"grad_norm": 7.868692398071289,
|
| 286 |
+
"learning_rate": 1.2816395014381592e-05,
|
| 287 |
+
"loss": 1.0826,
|
| 288 |
+
"step": 6000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.66,
|
| 292 |
+
"eval_gen_len": 82.8644,
|
| 293 |
+
"eval_loss": 1.2638760805130005,
|
| 294 |
+
"eval_rouge1": 53.9367,
|
| 295 |
+
"eval_rouge2": 36.2676,
|
| 296 |
+
"eval_rougeL": 44.9414,
|
| 297 |
+
"eval_rougeLsum": 44.7603,
|
| 298 |
+
"eval_runtime": 42.7574,
|
| 299 |
+
"eval_samples_per_second": 1.38,
|
| 300 |
+
"eval_steps_per_second": 0.702,
|
| 301 |
+
"step": 6352
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 2.73,
|
| 305 |
+
"grad_norm": 7.449892997741699,
|
| 306 |
+
"learning_rate": 1.2217162032598275e-05,
|
| 307 |
+
"loss": 1.0921,
|
| 308 |
+
"step": 6500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.83,
|
| 312 |
+
"eval_gen_len": 82.4237,
|
| 313 |
+
"eval_loss": 1.2491506338119507,
|
| 314 |
+
"eval_rouge1": 52.8146,
|
| 315 |
+
"eval_rouge2": 34.6392,
|
| 316 |
+
"eval_rougeL": 43.5323,
|
| 317 |
+
"eval_rougeLsum": 43.4647,
|
| 318 |
+
"eval_runtime": 42.5398,
|
| 319 |
+
"eval_samples_per_second": 1.387,
|
| 320 |
+
"eval_steps_per_second": 0.705,
|
| 321 |
+
"step": 6749
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.94,
|
| 325 |
+
"grad_norm": 7.139917850494385,
|
| 326 |
+
"learning_rate": 1.1617929050814957e-05,
|
| 327 |
+
"loss": 1.1129,
|
| 328 |
+
"step": 7000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 3.0,
|
| 332 |
+
"eval_gen_len": 83.1356,
|
| 333 |
+
"eval_loss": 1.2625495195388794,
|
| 334 |
+
"eval_rouge1": 53.6493,
|
| 335 |
+
"eval_rouge2": 35.0396,
|
| 336 |
+
"eval_rougeL": 43.501,
|
| 337 |
+
"eval_rougeLsum": 43.4039,
|
| 338 |
+
"eval_runtime": 43.1051,
|
| 339 |
+
"eval_samples_per_second": 1.369,
|
| 340 |
+
"eval_steps_per_second": 0.696,
|
| 341 |
+
"step": 7146
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 3.15,
|
| 345 |
+
"grad_norm": 5.8409600257873535,
|
| 346 |
+
"learning_rate": 1.1018696069031641e-05,
|
| 347 |
+
"loss": 0.9783,
|
| 348 |
+
"step": 7500
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 3.16,
|
| 352 |
+
"eval_gen_len": 84.7797,
|
| 353 |
+
"eval_loss": 1.293487787246704,
|
| 354 |
+
"eval_rouge1": 53.245,
|
| 355 |
+
"eval_rouge2": 35.655,
|
| 356 |
+
"eval_rougeL": 44.4306,
|
| 357 |
+
"eval_rougeLsum": 44.482,
|
| 358 |
+
"eval_runtime": 41.7791,
|
| 359 |
+
"eval_samples_per_second": 1.412,
|
| 360 |
+
"eval_steps_per_second": 0.718,
|
| 361 |
+
"step": 7543
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 3.33,
|
| 365 |
+
"eval_gen_len": 84.1186,
|
| 366 |
+
"eval_loss": 1.266953706741333,
|
| 367 |
+
"eval_rouge1": 52.146,
|
| 368 |
+
"eval_rouge2": 33.0632,
|
| 369 |
+
"eval_rougeL": 41.4382,
|
| 370 |
+
"eval_rougeLsum": 41.5159,
|
| 371 |
+
"eval_runtime": 41.1238,
|
| 372 |
+
"eval_samples_per_second": 1.435,
|
| 373 |
+
"eval_steps_per_second": 0.73,
|
| 374 |
+
"step": 7940
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 3.36,
|
| 378 |
+
"grad_norm": 8.737879753112793,
|
| 379 |
+
"learning_rate": 1.0419463087248323e-05,
|
| 380 |
+
"loss": 0.9771,
|
| 381 |
+
"step": 8000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 3.5,
|
| 385 |
+
"eval_gen_len": 82.8475,
|
| 386 |
+
"eval_loss": 1.275550127029419,
|
| 387 |
+
"eval_rouge1": 51.7108,
|
| 388 |
+
"eval_rouge2": 33.5352,
|
| 389 |
+
"eval_rougeL": 42.4153,
|
| 390 |
+
"eval_rougeLsum": 42.4572,
|
| 391 |
+
"eval_runtime": 41.088,
|
| 392 |
+
"eval_samples_per_second": 1.436,
|
| 393 |
+
"eval_steps_per_second": 0.73,
|
| 394 |
+
"step": 8337
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 3.57,
|
| 398 |
+
"grad_norm": 8.45171070098877,
|
| 399 |
+
"learning_rate": 9.820230105465006e-06,
|
| 400 |
+
"loss": 0.9841,
|
| 401 |
+
"step": 8500
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 3.66,
|
| 405 |
+
"eval_gen_len": 84.322,
|
| 406 |
+
"eval_loss": 1.260237455368042,
|
| 407 |
+
"eval_rouge1": 53.2394,
|
| 408 |
+
"eval_rouge2": 34.9695,
|
| 409 |
+
"eval_rougeL": 43.2182,
|
| 410 |
+
"eval_rougeLsum": 43.1333,
|
| 411 |
+
"eval_runtime": 41.5567,
|
| 412 |
+
"eval_samples_per_second": 1.42,
|
| 413 |
+
"eval_steps_per_second": 0.722,
|
| 414 |
+
"step": 8734
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 3.78,
|
| 418 |
+
"grad_norm": 47.454078674316406,
|
| 419 |
+
"learning_rate": 9.220997123681688e-06,
|
| 420 |
+
"loss": 0.9643,
|
| 421 |
+
"step": 9000
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 3.83,
|
| 425 |
+
"eval_gen_len": 81.4915,
|
| 426 |
+
"eval_loss": 1.27409827709198,
|
| 427 |
+
"eval_rouge1": 53.5588,
|
| 428 |
+
"eval_rouge2": 36.0425,
|
| 429 |
+
"eval_rougeL": 44.2044,
|
| 430 |
+
"eval_rougeLsum": 44.2287,
|
| 431 |
+
"eval_runtime": 40.5566,
|
| 432 |
+
"eval_samples_per_second": 1.455,
|
| 433 |
+
"eval_steps_per_second": 0.74,
|
| 434 |
+
"step": 9131
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 3.98,
|
| 438 |
+
"grad_norm": 7.34140157699585,
|
| 439 |
+
"learning_rate": 8.62176414189837e-06,
|
| 440 |
+
"loss": 0.9439,
|
| 441 |
+
"step": 9500
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 4.0,
|
| 445 |
+
"eval_gen_len": 86.1864,
|
| 446 |
+
"eval_loss": 1.2641756534576416,
|
| 447 |
+
"eval_rouge1": 53.7305,
|
| 448 |
+
"eval_rouge2": 35.3844,
|
| 449 |
+
"eval_rougeL": 43.8211,
|
| 450 |
+
"eval_rougeLsum": 43.7597,
|
| 451 |
+
"eval_runtime": 42.1877,
|
| 452 |
+
"eval_samples_per_second": 1.399,
|
| 453 |
+
"eval_steps_per_second": 0.711,
|
| 454 |
+
"step": 9528
|
| 455 |
+
}
|
| 456 |
+
],
|
| 457 |
+
"logging_steps": 500,
|
| 458 |
+
"max_steps": 16688,
|
| 459 |
+
"num_input_tokens_seen": 0,
|
| 460 |
+
"num_train_epochs": 7,
|
| 461 |
+
"save_steps": 1192,
|
| 462 |
+
"total_flos": 2.071244574793728e+17,
|
| 463 |
+
"train_batch_size": 2,
|
| 464 |
+
"trial_name": null,
|
| 465 |
+
"trial_params": null
|
| 466 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db073b7f8991a4ca5cb2d52b57ccec8017ce67c286d4cb0797f4071623be282d
|
| 3 |
+
size 4984
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|