Upload 6 files
Browse files- config.json +173 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- trainer_state.json +321 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,173 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"VisionEncoderDecoderModel"
|
| 4 |
+
],
|
| 5 |
+
"decoder": {
|
| 6 |
+
"_name_or_path": "klue/roberta-base",
|
| 7 |
+
"add_cross_attention": true,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"RobertaForMaskedLM"
|
| 10 |
+
],
|
| 11 |
+
"attention_probs_dropout_prob": 0.1,
|
| 12 |
+
"bad_words_ids": null,
|
| 13 |
+
"begin_suppress_tokens": null,
|
| 14 |
+
"bos_token_id": 0,
|
| 15 |
+
"chunk_size_feed_forward": 0,
|
| 16 |
+
"classifier_dropout": null,
|
| 17 |
+
"cross_attention_hidden_size": null,
|
| 18 |
+
"decoder_start_token_id": null,
|
| 19 |
+
"diversity_penalty": 0.0,
|
| 20 |
+
"do_sample": false,
|
| 21 |
+
"early_stopping": false,
|
| 22 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 23 |
+
"eos_token_id": 2,
|
| 24 |
+
"exponential_decay_length_penalty": null,
|
| 25 |
+
"finetuning_task": null,
|
| 26 |
+
"forced_bos_token_id": null,
|
| 27 |
+
"forced_eos_token_id": null,
|
| 28 |
+
"gradient_checkpointing": false,
|
| 29 |
+
"hidden_act": "gelu",
|
| 30 |
+
"hidden_dropout_prob": 0.1,
|
| 31 |
+
"hidden_size": 768,
|
| 32 |
+
"id2label": {
|
| 33 |
+
"0": "LABEL_0",
|
| 34 |
+
"1": "LABEL_1"
|
| 35 |
+
},
|
| 36 |
+
"initializer_range": 0.02,
|
| 37 |
+
"intermediate_size": 3072,
|
| 38 |
+
"is_decoder": true,
|
| 39 |
+
"is_encoder_decoder": false,
|
| 40 |
+
"label2id": {
|
| 41 |
+
"LABEL_0": 0,
|
| 42 |
+
"LABEL_1": 1
|
| 43 |
+
},
|
| 44 |
+
"layer_norm_eps": 1e-05,
|
| 45 |
+
"length_penalty": 1.0,
|
| 46 |
+
"max_length": 20,
|
| 47 |
+
"max_position_embeddings": 514,
|
| 48 |
+
"min_length": 0,
|
| 49 |
+
"model_type": "roberta",
|
| 50 |
+
"no_repeat_ngram_size": 0,
|
| 51 |
+
"num_attention_heads": 12,
|
| 52 |
+
"num_beam_groups": 1,
|
| 53 |
+
"num_beams": 1,
|
| 54 |
+
"num_hidden_layers": 12,
|
| 55 |
+
"num_return_sequences": 1,
|
| 56 |
+
"output_attentions": false,
|
| 57 |
+
"output_hidden_states": false,
|
| 58 |
+
"output_scores": false,
|
| 59 |
+
"pad_token_id": 1,
|
| 60 |
+
"position_embedding_type": "absolute",
|
| 61 |
+
"prefix": null,
|
| 62 |
+
"problem_type": null,
|
| 63 |
+
"pruned_heads": {},
|
| 64 |
+
"remove_invalid_values": false,
|
| 65 |
+
"repetition_penalty": 1.0,
|
| 66 |
+
"return_dict": true,
|
| 67 |
+
"return_dict_in_generate": false,
|
| 68 |
+
"sep_token_id": null,
|
| 69 |
+
"suppress_tokens": null,
|
| 70 |
+
"task_specific_params": null,
|
| 71 |
+
"temperature": 1.0,
|
| 72 |
+
"tf_legacy_loss": false,
|
| 73 |
+
"tie_encoder_decoder": false,
|
| 74 |
+
"tie_word_embeddings": true,
|
| 75 |
+
"tokenizer_class": "BertTokenizer",
|
| 76 |
+
"top_k": 50,
|
| 77 |
+
"top_p": 1.0,
|
| 78 |
+
"torch_dtype": null,
|
| 79 |
+
"torchscript": false,
|
| 80 |
+
"type_vocab_size": 1,
|
| 81 |
+
"typical_p": 1.0,
|
| 82 |
+
"use_bfloat16": false,
|
| 83 |
+
"use_cache": true,
|
| 84 |
+
"vocab_size": 32000
|
| 85 |
+
},
|
| 86 |
+
"decoder_start_token_id": 0,
|
| 87 |
+
"encoder": {
|
| 88 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
| 89 |
+
"add_cross_attention": false,
|
| 90 |
+
"architectures": [
|
| 91 |
+
"ViTModel"
|
| 92 |
+
],
|
| 93 |
+
"attention_probs_dropout_prob": 0.0,
|
| 94 |
+
"bad_words_ids": null,
|
| 95 |
+
"begin_suppress_tokens": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"early_stopping": false,
|
| 103 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 104 |
+
"encoder_stride": 16,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "gelu",
|
| 111 |
+
"hidden_dropout_prob": 0.0,
|
| 112 |
+
"hidden_size": 768,
|
| 113 |
+
"id2label": {
|
| 114 |
+
"0": "LABEL_0",
|
| 115 |
+
"1": "LABEL_1"
|
| 116 |
+
},
|
| 117 |
+
"image_size": 224,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-12,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "vit",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 16,
|
| 143 |
+
"prefix": null,
|
| 144 |
+
"problem_type": null,
|
| 145 |
+
"pruned_heads": {},
|
| 146 |
+
"qkv_bias": true,
|
| 147 |
+
"remove_invalid_values": false,
|
| 148 |
+
"repetition_penalty": 1.0,
|
| 149 |
+
"return_dict": true,
|
| 150 |
+
"return_dict_in_generate": false,
|
| 151 |
+
"sep_token_id": null,
|
| 152 |
+
"suppress_tokens": null,
|
| 153 |
+
"task_specific_params": null,
|
| 154 |
+
"temperature": 1.0,
|
| 155 |
+
"tf_legacy_loss": false,
|
| 156 |
+
"tie_encoder_decoder": false,
|
| 157 |
+
"tie_word_embeddings": true,
|
| 158 |
+
"tokenizer_class": null,
|
| 159 |
+
"top_k": 50,
|
| 160 |
+
"top_p": 1.0,
|
| 161 |
+
"torch_dtype": null,
|
| 162 |
+
"torchscript": false,
|
| 163 |
+
"typical_p": 1.0,
|
| 164 |
+
"use_bfloat16": false
|
| 165 |
+
},
|
| 166 |
+
"eos_token_id": 2,
|
| 167 |
+
"is_encoder_decoder": true,
|
| 168 |
+
"model_type": "vision-encoder-decoder",
|
| 169 |
+
"pad_token_id": 2,
|
| 170 |
+
"tie_word_embeddings": false,
|
| 171 |
+
"torch_dtype": "float32",
|
| 172 |
+
"transformers_version": "4.43.3"
|
| 173 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 0,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"pad_token_id": 1,
|
| 5 |
+
"transformers_version": "4.43.3"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:286b0f04d00d206225bc71b352f2fc1ee9bcfe04d6e73cec11cafc461173bf8c
|
| 3 |
+
size 901697272
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTFeatureExtractor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"resample": 2,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 224,
|
| 20 |
+
"width": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,321 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3077,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.032499187520311994,
|
| 13 |
+
"grad_norm": 0.38231489062309265,
|
| 14 |
+
"learning_rate": 4.8375040623984405e-05,
|
| 15 |
+
"loss": 0.1722,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06499837504062399,
|
| 20 |
+
"grad_norm": 0.29991772770881653,
|
| 21 |
+
"learning_rate": 4.67500812479688e-05,
|
| 22 |
+
"loss": 0.1983,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.09749756256093597,
|
| 27 |
+
"grad_norm": 0.3033580780029297,
|
| 28 |
+
"learning_rate": 4.51251218719532e-05,
|
| 29 |
+
"loss": 0.2034,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.12999675008124797,
|
| 34 |
+
"grad_norm": 0.31061500310897827,
|
| 35 |
+
"learning_rate": 4.3500162495937604e-05,
|
| 36 |
+
"loss": 0.2022,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.16249593760155995,
|
| 41 |
+
"grad_norm": 0.27624836564064026,
|
| 42 |
+
"learning_rate": 4.1875203119922e-05,
|
| 43 |
+
"loss": 0.1975,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.16249593760155995,
|
| 48 |
+
"eval_gen_len": 19.964290067032298,
|
| 49 |
+
"eval_loss": 0.18788783252239227,
|
| 50 |
+
"eval_rouge1": 0.0068,
|
| 51 |
+
"eval_rouge2": 0.0,
|
| 52 |
+
"eval_rougeL": 0.0068,
|
| 53 |
+
"eval_rougeLsum": 0.0068,
|
| 54 |
+
"eval_runtime": 2174.226,
|
| 55 |
+
"eval_samples_per_second": 11.321,
|
| 56 |
+
"eval_steps_per_second": 0.354,
|
| 57 |
+
"step": 500
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.19499512512187195,
|
| 61 |
+
"grad_norm": 0.2493065893650055,
|
| 62 |
+
"learning_rate": 4.02502437439064e-05,
|
| 63 |
+
"loss": 0.1943,
|
| 64 |
+
"step": 600
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.22749431264218395,
|
| 68 |
+
"grad_norm": 0.2768040597438812,
|
| 69 |
+
"learning_rate": 3.8625284367890804e-05,
|
| 70 |
+
"loss": 0.1919,
|
| 71 |
+
"step": 700
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.25999350016249595,
|
| 75 |
+
"grad_norm": 0.2641097605228424,
|
| 76 |
+
"learning_rate": 3.7000324991875206e-05,
|
| 77 |
+
"loss": 0.1883,
|
| 78 |
+
"step": 800
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.29249268768280795,
|
| 82 |
+
"grad_norm": 0.266985148191452,
|
| 83 |
+
"learning_rate": 3.537536561585961e-05,
|
| 84 |
+
"loss": 0.1866,
|
| 85 |
+
"step": 900
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.3249918752031199,
|
| 89 |
+
"grad_norm": 0.2505531311035156,
|
| 90 |
+
"learning_rate": 3.3750406239844004e-05,
|
| 91 |
+
"loss": 0.186,
|
| 92 |
+
"step": 1000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.3249918752031199,
|
| 96 |
+
"eval_gen_len": 19.9981718464351,
|
| 97 |
+
"eval_loss": 0.1798761785030365,
|
| 98 |
+
"eval_rouge1": 0.0108,
|
| 99 |
+
"eval_rouge2": 0.0041,
|
| 100 |
+
"eval_rougeL": 0.0108,
|
| 101 |
+
"eval_rougeLsum": 0.0108,
|
| 102 |
+
"eval_runtime": 2176.3057,
|
| 103 |
+
"eval_samples_per_second": 11.31,
|
| 104 |
+
"eval_steps_per_second": 0.354,
|
| 105 |
+
"step": 1000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.3574910627234319,
|
| 109 |
+
"grad_norm": 0.2498556226491928,
|
| 110 |
+
"learning_rate": 3.2125446863828406e-05,
|
| 111 |
+
"loss": 0.1839,
|
| 112 |
+
"step": 1100
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.3899902502437439,
|
| 116 |
+
"grad_norm": 0.2563565969467163,
|
| 117 |
+
"learning_rate": 3.0500487487812808e-05,
|
| 118 |
+
"loss": 0.1835,
|
| 119 |
+
"step": 1200
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.4224894377640559,
|
| 123 |
+
"grad_norm": 0.25993165373802185,
|
| 124 |
+
"learning_rate": 2.8875528111797207e-05,
|
| 125 |
+
"loss": 0.1837,
|
| 126 |
+
"step": 1300
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.4549886252843679,
|
| 130 |
+
"grad_norm": 0.2639683485031128,
|
| 131 |
+
"learning_rate": 2.7250568735781606e-05,
|
| 132 |
+
"loss": 0.1814,
|
| 133 |
+
"step": 1400
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.4874878128046799,
|
| 137 |
+
"grad_norm": 0.25668901205062866,
|
| 138 |
+
"learning_rate": 2.5625609359766008e-05,
|
| 139 |
+
"loss": 0.1762,
|
| 140 |
+
"step": 1500
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.4874878128046799,
|
| 144 |
+
"eval_gen_len": 19.983384115376804,
|
| 145 |
+
"eval_loss": 0.17473776638507843,
|
| 146 |
+
"eval_rouge1": 0.1836,
|
| 147 |
+
"eval_rouge2": 0.0,
|
| 148 |
+
"eval_rougeL": 0.1828,
|
| 149 |
+
"eval_rougeLsum": 0.1851,
|
| 150 |
+
"eval_runtime": 2167.8807,
|
| 151 |
+
"eval_samples_per_second": 11.354,
|
| 152 |
+
"eval_steps_per_second": 0.355,
|
| 153 |
+
"step": 1500
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.5199870003249919,
|
| 157 |
+
"grad_norm": 0.2645615041255951,
|
| 158 |
+
"learning_rate": 2.4000649983750407e-05,
|
| 159 |
+
"loss": 0.1794,
|
| 160 |
+
"step": 1600
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.5524861878453039,
|
| 164 |
+
"grad_norm": 0.24295924603939056,
|
| 165 |
+
"learning_rate": 2.237569060773481e-05,
|
| 166 |
+
"loss": 0.1769,
|
| 167 |
+
"step": 1700
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.5849853753656159,
|
| 171 |
+
"grad_norm": 0.25981849431991577,
|
| 172 |
+
"learning_rate": 2.0750731231719208e-05,
|
| 173 |
+
"loss": 0.1785,
|
| 174 |
+
"step": 1800
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.6174845628859279,
|
| 178 |
+
"grad_norm": 0.24553097784519196,
|
| 179 |
+
"learning_rate": 1.912577185570361e-05,
|
| 180 |
+
"loss": 0.173,
|
| 181 |
+
"step": 1900
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.6499837504062398,
|
| 185 |
+
"grad_norm": 0.24243266880512238,
|
| 186 |
+
"learning_rate": 1.750081247968801e-05,
|
| 187 |
+
"loss": 0.1764,
|
| 188 |
+
"step": 2000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.6499837504062398,
|
| 192 |
+
"eval_gen_len": 19.99471866747918,
|
| 193 |
+
"eval_loss": 0.17154192924499512,
|
| 194 |
+
"eval_rouge1": 0.1151,
|
| 195 |
+
"eval_rouge2": 0.0,
|
| 196 |
+
"eval_rougeL": 0.1151,
|
| 197 |
+
"eval_rougeLsum": 0.1165,
|
| 198 |
+
"eval_runtime": 2157.4938,
|
| 199 |
+
"eval_samples_per_second": 11.409,
|
| 200 |
+
"eval_steps_per_second": 0.357,
|
| 201 |
+
"step": 2000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.6824829379265518,
|
| 205 |
+
"grad_norm": 0.26906952261924744,
|
| 206 |
+
"learning_rate": 1.5875853103672408e-05,
|
| 207 |
+
"loss": 0.1789,
|
| 208 |
+
"step": 2100
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.7149821254468638,
|
| 212 |
+
"grad_norm": 0.2654452919960022,
|
| 213 |
+
"learning_rate": 1.4250893727656808e-05,
|
| 214 |
+
"loss": 0.1727,
|
| 215 |
+
"step": 2200
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.7474813129671758,
|
| 219 |
+
"grad_norm": 0.24443137645721436,
|
| 220 |
+
"learning_rate": 1.2625934351641208e-05,
|
| 221 |
+
"loss": 0.1767,
|
| 222 |
+
"step": 2300
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.7799805004874878,
|
| 226 |
+
"grad_norm": 0.24741144478321075,
|
| 227 |
+
"learning_rate": 1.1000974975625609e-05,
|
| 228 |
+
"loss": 0.1745,
|
| 229 |
+
"step": 2400
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.8124796880077998,
|
| 233 |
+
"grad_norm": 0.2507327198982239,
|
| 234 |
+
"learning_rate": 9.376015599610011e-06,
|
| 235 |
+
"loss": 0.1756,
|
| 236 |
+
"step": 2500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.8124796880077998,
|
| 240 |
+
"eval_gen_len": 19.99869997968718,
|
| 241 |
+
"eval_loss": 0.1691381335258484,
|
| 242 |
+
"eval_rouge1": 0.0027,
|
| 243 |
+
"eval_rouge2": 0.0,
|
| 244 |
+
"eval_rougeL": 0.0027,
|
| 245 |
+
"eval_rougeLsum": 0.0027,
|
| 246 |
+
"eval_runtime": 2163.6252,
|
| 247 |
+
"eval_samples_per_second": 11.377,
|
| 248 |
+
"eval_steps_per_second": 0.356,
|
| 249 |
+
"step": 2500
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.8449788755281118,
|
| 253 |
+
"grad_norm": 0.23773913085460663,
|
| 254 |
+
"learning_rate": 7.75105622359441e-06,
|
| 255 |
+
"loss": 0.1733,
|
| 256 |
+
"step": 2600
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.8774780630484238,
|
| 260 |
+
"grad_norm": 0.24695108830928802,
|
| 261 |
+
"learning_rate": 6.1260968475788104e-06,
|
| 262 |
+
"loss": 0.1744,
|
| 263 |
+
"step": 2700
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.9099772505687358,
|
| 267 |
+
"grad_norm": 0.23871463537216187,
|
| 268 |
+
"learning_rate": 4.501137471563211e-06,
|
| 269 |
+
"loss": 0.1741,
|
| 270 |
+
"step": 2800
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.9424764380890478,
|
| 274 |
+
"grad_norm": 0.24402374029159546,
|
| 275 |
+
"learning_rate": 2.8761780955476114e-06,
|
| 276 |
+
"loss": 0.1703,
|
| 277 |
+
"step": 2900
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.9749756256093598,
|
| 281 |
+
"grad_norm": 0.24215468764305115,
|
| 282 |
+
"learning_rate": 1.2512187195320117e-06,
|
| 283 |
+
"loss": 0.1724,
|
| 284 |
+
"step": 3000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.9749756256093598,
|
| 288 |
+
"eval_gen_len": 19.99163111923624,
|
| 289 |
+
"eval_loss": 0.1676524430513382,
|
| 290 |
+
"eval_rouge1": 0.0257,
|
| 291 |
+
"eval_rouge2": 0.0,
|
| 292 |
+
"eval_rougeL": 0.0244,
|
| 293 |
+
"eval_rougeLsum": 0.0257,
|
| 294 |
+
"eval_runtime": 2148.352,
|
| 295 |
+
"eval_samples_per_second": 11.458,
|
| 296 |
+
"eval_steps_per_second": 0.358,
|
| 297 |
+
"step": 3000
|
| 298 |
+
}
|
| 299 |
+
],
|
| 300 |
+
"logging_steps": 100,
|
| 301 |
+
"max_steps": 3077,
|
| 302 |
+
"num_input_tokens_seen": 0,
|
| 303 |
+
"num_train_epochs": 1,
|
| 304 |
+
"save_steps": 500,
|
| 305 |
+
"stateful_callbacks": {
|
| 306 |
+
"TrainerControl": {
|
| 307 |
+
"args": {
|
| 308 |
+
"should_epoch_stop": false,
|
| 309 |
+
"should_evaluate": false,
|
| 310 |
+
"should_log": false,
|
| 311 |
+
"should_save": true,
|
| 312 |
+
"should_training_stop": true
|
| 313 |
+
},
|
| 314 |
+
"attributes": {}
|
| 315 |
+
}
|
| 316 |
+
},
|
| 317 |
+
"total_flos": 1.7819450187495506e+19,
|
| 318 |
+
"train_batch_size": 32,
|
| 319 |
+
"trial_name": null,
|
| 320 |
+
"trial_params": null
|
| 321 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:194ce32cec5fe69bed212938bb3ed6d454d649295f789cd68caef98b2b3225af
|
| 3 |
+
size 5304
|