root
commited on
Commit
·
ce3976c
1
Parent(s):
44f4756
model trained
Browse files- config.json +177 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +356 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,177 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"CLIPModel"
|
| 4 |
+
],
|
| 5 |
+
"initializer_factor": 1.0,
|
| 6 |
+
"logit_scale_init_value": 2.6592,
|
| 7 |
+
"model_type": "clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"text_config": {
|
| 10 |
+
"_name_or_path": "",
|
| 11 |
+
"add_cross_attention": false,
|
| 12 |
+
"architectures": null,
|
| 13 |
+
"attention_dropout": 0.0,
|
| 14 |
+
"bad_words_ids": null,
|
| 15 |
+
"bos_token_id": 0,
|
| 16 |
+
"chunk_size_feed_forward": 0,
|
| 17 |
+
"cross_attention_hidden_size": null,
|
| 18 |
+
"decoder_start_token_id": null,
|
| 19 |
+
"diversity_penalty": 0.0,
|
| 20 |
+
"do_sample": false,
|
| 21 |
+
"dropout": 0.0,
|
| 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 |
+
"hidden_act": "quick_gelu",
|
| 30 |
+
"hidden_size": 1,
|
| 31 |
+
"id2label": {
|
| 32 |
+
"0": "LABEL_0",
|
| 33 |
+
"1": "LABEL_1"
|
| 34 |
+
},
|
| 35 |
+
"initializer_factor": 1.0,
|
| 36 |
+
"initializer_range": 0.02,
|
| 37 |
+
"intermediate_size": 2048,
|
| 38 |
+
"is_decoder": false,
|
| 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": 0,
|
| 48 |
+
"min_length": 0,
|
| 49 |
+
"model_type": "clip_text_model",
|
| 50 |
+
"no_repeat_ngram_size": 0,
|
| 51 |
+
"num_attention_heads": 8,
|
| 52 |
+
"num_beam_groups": 1,
|
| 53 |
+
"num_beams": 1,
|
| 54 |
+
"num_hidden_layers": 0,
|
| 55 |
+
"num_return_sequences": 1,
|
| 56 |
+
"output_attentions": false,
|
| 57 |
+
"output_hidden_states": false,
|
| 58 |
+
"output_scores": false,
|
| 59 |
+
"pad_token_id": 1,
|
| 60 |
+
"patch_size": 1,
|
| 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 |
+
"task_specific_params": null,
|
| 70 |
+
"temperature": 1.0,
|
| 71 |
+
"tf_legacy_loss": false,
|
| 72 |
+
"tie_encoder_decoder": false,
|
| 73 |
+
"tie_word_embeddings": true,
|
| 74 |
+
"tokenizer_class": null,
|
| 75 |
+
"top_k": 50,
|
| 76 |
+
"top_p": 1.0,
|
| 77 |
+
"torch_dtype": null,
|
| 78 |
+
"torchscript": false,
|
| 79 |
+
"transformers_version": "4.21.1",
|
| 80 |
+
"typical_p": 1.0,
|
| 81 |
+
"use_bfloat16": false,
|
| 82 |
+
"vocab_size": 0
|
| 83 |
+
},
|
| 84 |
+
"text_config_dict": {
|
| 85 |
+
"hidden_size": 1,
|
| 86 |
+
"max_position_embeddings": 0,
|
| 87 |
+
"num_hidden_layers": 0,
|
| 88 |
+
"patch_size": 1,
|
| 89 |
+
"vocab_size": 0
|
| 90 |
+
},
|
| 91 |
+
"torch_dtype": "float32",
|
| 92 |
+
"transformers_version": null,
|
| 93 |
+
"vision_config": {
|
| 94 |
+
"_name_or_path": "",
|
| 95 |
+
"add_cross_attention": false,
|
| 96 |
+
"architectures": null,
|
| 97 |
+
"attention_dropout": 0.0,
|
| 98 |
+
"bad_words_ids": null,
|
| 99 |
+
"bos_token_id": null,
|
| 100 |
+
"chunk_size_feed_forward": 0,
|
| 101 |
+
"cross_attention_hidden_size": null,
|
| 102 |
+
"decoder_start_token_id": null,
|
| 103 |
+
"diversity_penalty": 0.0,
|
| 104 |
+
"do_sample": false,
|
| 105 |
+
"dropout": 0.0,
|
| 106 |
+
"early_stopping": false,
|
| 107 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 108 |
+
"eos_token_id": null,
|
| 109 |
+
"exponential_decay_length_penalty": null,
|
| 110 |
+
"finetuning_task": null,
|
| 111 |
+
"forced_bos_token_id": null,
|
| 112 |
+
"forced_eos_token_id": null,
|
| 113 |
+
"hidden_act": "quick_gelu",
|
| 114 |
+
"hidden_size": 1,
|
| 115 |
+
"id2label": {
|
| 116 |
+
"0": "LABEL_0",
|
| 117 |
+
"1": "LABEL_1"
|
| 118 |
+
},
|
| 119 |
+
"image_size": 224,
|
| 120 |
+
"initializer_factor": 1.0,
|
| 121 |
+
"initializer_range": 0.02,
|
| 122 |
+
"intermediate_size": 3072,
|
| 123 |
+
"is_decoder": false,
|
| 124 |
+
"is_encoder_decoder": false,
|
| 125 |
+
"label2id": {
|
| 126 |
+
"LABEL_0": 0,
|
| 127 |
+
"LABEL_1": 1
|
| 128 |
+
},
|
| 129 |
+
"layer_norm_eps": 1e-05,
|
| 130 |
+
"length_penalty": 1.0,
|
| 131 |
+
"max_length": 20,
|
| 132 |
+
"max_position_embeddings": 0,
|
| 133 |
+
"min_length": 0,
|
| 134 |
+
"model_type": "clip_vision_model",
|
| 135 |
+
"no_repeat_ngram_size": 0,
|
| 136 |
+
"num_attention_heads": 12,
|
| 137 |
+
"num_beam_groups": 1,
|
| 138 |
+
"num_beams": 1,
|
| 139 |
+
"num_channels": 3,
|
| 140 |
+
"num_hidden_layers": 0,
|
| 141 |
+
"num_return_sequences": 1,
|
| 142 |
+
"output_attentions": false,
|
| 143 |
+
"output_hidden_states": false,
|
| 144 |
+
"output_scores": false,
|
| 145 |
+
"pad_token_id": null,
|
| 146 |
+
"patch_size": 1,
|
| 147 |
+
"prefix": null,
|
| 148 |
+
"problem_type": null,
|
| 149 |
+
"pruned_heads": {},
|
| 150 |
+
"remove_invalid_values": false,
|
| 151 |
+
"repetition_penalty": 1.0,
|
| 152 |
+
"return_dict": true,
|
| 153 |
+
"return_dict_in_generate": false,
|
| 154 |
+
"sep_token_id": null,
|
| 155 |
+
"task_specific_params": null,
|
| 156 |
+
"temperature": 1.0,
|
| 157 |
+
"tf_legacy_loss": false,
|
| 158 |
+
"tie_encoder_decoder": false,
|
| 159 |
+
"tie_word_embeddings": true,
|
| 160 |
+
"tokenizer_class": null,
|
| 161 |
+
"top_k": 50,
|
| 162 |
+
"top_p": 1.0,
|
| 163 |
+
"torch_dtype": null,
|
| 164 |
+
"torchscript": false,
|
| 165 |
+
"transformers_version": "4.21.1",
|
| 166 |
+
"typical_p": 1.0,
|
| 167 |
+
"use_bfloat16": false,
|
| 168 |
+
"vocab_size": 0
|
| 169 |
+
},
|
| 170 |
+
"vision_config_dict": {
|
| 171 |
+
"hidden_size": 1,
|
| 172 |
+
"max_position_embeddings": 0,
|
| 173 |
+
"num_hidden_layers": 0,
|
| 174 |
+
"patch_size": 1,
|
| 175 |
+
"vocab_size": 0
|
| 176 |
+
}
|
| 177 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9419b0eb7839d5e42ca271954b41f67991b101009766c0844982d592f8182675
|
| 3 |
+
size 1575738181
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:472de990d8149c4c98f9c4d9fc04749f29d8f591735c97266ff7ccfb00af577d
|
| 3 |
+
size 787895775
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fedf0b601049d3e138f125d5ae7fc032c75040b14857ef8bae20f0d3d37de50
|
| 3 |
+
size 14503
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1183dc560918171dd71579eda592900e97fdd64a88c22c27997a4148326cda9f
|
| 3 |
+
size 623
|
trainer_state.json
ADDED
|
@@ -0,0 +1,356 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.319148936170213,
|
| 5 |
+
"global_step": 500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.11,
|
| 12 |
+
"learning_rate": 3e-06,
|
| 13 |
+
"loss": 3.4862,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.21,
|
| 18 |
+
"learning_rate": 6e-06,
|
| 19 |
+
"loss": 3.4466,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.32,
|
| 24 |
+
"learning_rate": 9e-06,
|
| 25 |
+
"loss": 3.3785,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.43,
|
| 30 |
+
"learning_rate": 1.2e-05,
|
| 31 |
+
"loss": 3.1635,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.53,
|
| 36 |
+
"learning_rate": 1.5e-05,
|
| 37 |
+
"loss": 2.7939,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.64,
|
| 42 |
+
"learning_rate": 1.8e-05,
|
| 43 |
+
"loss": 2.6209,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.74,
|
| 48 |
+
"learning_rate": 2.1e-05,
|
| 49 |
+
"loss": 2.546,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.85,
|
| 54 |
+
"learning_rate": 2.4e-05,
|
| 55 |
+
"loss": 2.4935,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.96,
|
| 60 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 61 |
+
"loss": 2.5316,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.06,
|
| 66 |
+
"learning_rate": 3e-05,
|
| 67 |
+
"loss": 2.2506,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.06,
|
| 72 |
+
"eval_loss": 2.3243110179901123,
|
| 73 |
+
"eval_runtime": 30.5113,
|
| 74 |
+
"eval_samples_per_second": 5.178,
|
| 75 |
+
"eval_steps_per_second": 0.164,
|
| 76 |
+
"step": 100
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 1.17,
|
| 80 |
+
"learning_rate": 2.9642857142857144e-05,
|
| 81 |
+
"loss": 2.4025,
|
| 82 |
+
"step": 110
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.28,
|
| 86 |
+
"learning_rate": 2.9285714285714284e-05,
|
| 87 |
+
"loss": 2.1887,
|
| 88 |
+
"step": 120
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.38,
|
| 92 |
+
"learning_rate": 2.892857142857143e-05,
|
| 93 |
+
"loss": 2.1512,
|
| 94 |
+
"step": 130
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.49,
|
| 98 |
+
"learning_rate": 2.857142857142857e-05,
|
| 99 |
+
"loss": 1.9806,
|
| 100 |
+
"step": 140
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.6,
|
| 104 |
+
"learning_rate": 2.8214285714285714e-05,
|
| 105 |
+
"loss": 1.9524,
|
| 106 |
+
"step": 150
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.7,
|
| 110 |
+
"learning_rate": 2.7857142857142858e-05,
|
| 111 |
+
"loss": 1.9475,
|
| 112 |
+
"step": 160
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.81,
|
| 116 |
+
"learning_rate": 2.75e-05,
|
| 117 |
+
"loss": 1.927,
|
| 118 |
+
"step": 170
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.91,
|
| 122 |
+
"learning_rate": 2.7142857142857144e-05,
|
| 123 |
+
"loss": 1.9126,
|
| 124 |
+
"step": 180
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 2.02,
|
| 128 |
+
"learning_rate": 2.6785714285714288e-05,
|
| 129 |
+
"loss": 1.8077,
|
| 130 |
+
"step": 190
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 2.13,
|
| 134 |
+
"learning_rate": 2.6428571428571428e-05,
|
| 135 |
+
"loss": 1.4381,
|
| 136 |
+
"step": 200
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 2.13,
|
| 140 |
+
"eval_loss": 1.754191279411316,
|
| 141 |
+
"eval_runtime": 31.7299,
|
| 142 |
+
"eval_samples_per_second": 4.98,
|
| 143 |
+
"eval_steps_per_second": 0.158,
|
| 144 |
+
"step": 200
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 2.23,
|
| 148 |
+
"learning_rate": 2.607142857142857e-05,
|
| 149 |
+
"loss": 1.5071,
|
| 150 |
+
"step": 210
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 2.34,
|
| 154 |
+
"learning_rate": 2.5714285714285714e-05,
|
| 155 |
+
"loss": 1.426,
|
| 156 |
+
"step": 220
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 2.45,
|
| 160 |
+
"learning_rate": 2.5357142857142858e-05,
|
| 161 |
+
"loss": 1.4455,
|
| 162 |
+
"step": 230
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.55,
|
| 166 |
+
"learning_rate": 2.5e-05,
|
| 167 |
+
"loss": 1.4927,
|
| 168 |
+
"step": 240
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.66,
|
| 172 |
+
"learning_rate": 2.464285714285714e-05,
|
| 173 |
+
"loss": 1.4041,
|
| 174 |
+
"step": 250
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.77,
|
| 178 |
+
"learning_rate": 2.4285714285714288e-05,
|
| 179 |
+
"loss": 1.4084,
|
| 180 |
+
"step": 260
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 2.87,
|
| 184 |
+
"learning_rate": 2.392857142857143e-05,
|
| 185 |
+
"loss": 1.414,
|
| 186 |
+
"step": 270
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.98,
|
| 190 |
+
"learning_rate": 2.357142857142857e-05,
|
| 191 |
+
"loss": 1.385,
|
| 192 |
+
"step": 280
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 3.09,
|
| 196 |
+
"learning_rate": 2.3214285714285715e-05,
|
| 197 |
+
"loss": 1.0958,
|
| 198 |
+
"step": 290
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 3.19,
|
| 202 |
+
"learning_rate": 2.2857142857142858e-05,
|
| 203 |
+
"loss": 1.0876,
|
| 204 |
+
"step": 300
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 3.19,
|
| 208 |
+
"eval_loss": 1.5441479682922363,
|
| 209 |
+
"eval_runtime": 42.3423,
|
| 210 |
+
"eval_samples_per_second": 3.731,
|
| 211 |
+
"eval_steps_per_second": 0.118,
|
| 212 |
+
"step": 300
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 3.3,
|
| 216 |
+
"learning_rate": 2.25e-05,
|
| 217 |
+
"loss": 1.0589,
|
| 218 |
+
"step": 310
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.4,
|
| 222 |
+
"learning_rate": 2.2142857142857145e-05,
|
| 223 |
+
"loss": 1.137,
|
| 224 |
+
"step": 320
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 3.51,
|
| 228 |
+
"learning_rate": 2.1785714285714285e-05,
|
| 229 |
+
"loss": 1.0838,
|
| 230 |
+
"step": 330
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 3.62,
|
| 234 |
+
"learning_rate": 2.1428571428571428e-05,
|
| 235 |
+
"loss": 1.1054,
|
| 236 |
+
"step": 340
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 3.72,
|
| 240 |
+
"learning_rate": 2.107142857142857e-05,
|
| 241 |
+
"loss": 1.0415,
|
| 242 |
+
"step": 350
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 3.83,
|
| 246 |
+
"learning_rate": 2.0714285714285715e-05,
|
| 247 |
+
"loss": 1.0444,
|
| 248 |
+
"step": 360
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 3.94,
|
| 252 |
+
"learning_rate": 2.0357142857142858e-05,
|
| 253 |
+
"loss": 0.9463,
|
| 254 |
+
"step": 370
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 4.04,
|
| 258 |
+
"learning_rate": 1.9999999999999998e-05,
|
| 259 |
+
"loss": 1.0593,
|
| 260 |
+
"step": 380
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 4.15,
|
| 264 |
+
"learning_rate": 1.9642857142857145e-05,
|
| 265 |
+
"loss": 0.8724,
|
| 266 |
+
"step": 390
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 4.26,
|
| 270 |
+
"learning_rate": 1.928571428571429e-05,
|
| 271 |
+
"loss": 0.8654,
|
| 272 |
+
"step": 400
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 4.26,
|
| 276 |
+
"eval_loss": 1.2680882215499878,
|
| 277 |
+
"eval_runtime": 30.013,
|
| 278 |
+
"eval_samples_per_second": 5.264,
|
| 279 |
+
"eval_steps_per_second": 0.167,
|
| 280 |
+
"step": 400
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 4.36,
|
| 284 |
+
"learning_rate": 1.892857142857143e-05,
|
| 285 |
+
"loss": 0.8456,
|
| 286 |
+
"step": 410
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 4.47,
|
| 290 |
+
"learning_rate": 1.8571428571428572e-05,
|
| 291 |
+
"loss": 0.8181,
|
| 292 |
+
"step": 420
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 4.57,
|
| 296 |
+
"learning_rate": 1.8214285714285712e-05,
|
| 297 |
+
"loss": 0.8859,
|
| 298 |
+
"step": 430
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 4.68,
|
| 302 |
+
"learning_rate": 1.785714285714286e-05,
|
| 303 |
+
"loss": 0.7514,
|
| 304 |
+
"step": 440
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 4.79,
|
| 308 |
+
"learning_rate": 1.7500000000000002e-05,
|
| 309 |
+
"loss": 0.8128,
|
| 310 |
+
"step": 450
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 4.89,
|
| 314 |
+
"learning_rate": 1.7142857142857142e-05,
|
| 315 |
+
"loss": 0.8051,
|
| 316 |
+
"step": 460
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 5.0,
|
| 320 |
+
"learning_rate": 1.6785714285714285e-05,
|
| 321 |
+
"loss": 0.7211,
|
| 322 |
+
"step": 470
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 5.11,
|
| 326 |
+
"learning_rate": 1.6428571428571432e-05,
|
| 327 |
+
"loss": 0.6213,
|
| 328 |
+
"step": 480
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 5.21,
|
| 332 |
+
"learning_rate": 1.6071428571428572e-05,
|
| 333 |
+
"loss": 0.6465,
|
| 334 |
+
"step": 490
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 5.32,
|
| 338 |
+
"learning_rate": 1.5714285714285715e-05,
|
| 339 |
+
"loss": 0.6749,
|
| 340 |
+
"step": 500
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 5.32,
|
| 344 |
+
"eval_loss": 1.1592129468917847,
|
| 345 |
+
"eval_runtime": 26.8811,
|
| 346 |
+
"eval_samples_per_second": 5.878,
|
| 347 |
+
"eval_steps_per_second": 0.186,
|
| 348 |
+
"step": 500
|
| 349 |
+
}
|
| 350 |
+
],
|
| 351 |
+
"max_steps": 940,
|
| 352 |
+
"num_train_epochs": 10,
|
| 353 |
+
"total_flos": 1325810169734400.0,
|
| 354 |
+
"trial_name": null,
|
| 355 |
+
"trial_params": null
|
| 356 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b898b254fd52b5f76b47c7563c394df3170917e3ca8dbd76b57a13829029972d
|
| 3 |
+
size 3247
|