Spaces:
Build error
Build error
add pattern generator
Browse files- pattern_generator/config.json +172 -0
- pattern_generator/merges.txt +0 -0
- pattern_generator/optimizer.pt +3 -0
- pattern_generator/pytorch_model.bin +3 -0
- pattern_generator/rng_state.pth +3 -0
- pattern_generator/scaler.pt +3 -0
- pattern_generator/scheduler.pt +3 -0
- pattern_generator/special_tokens_map.json +1 -0
- pattern_generator/tokenizer_config.json +1 -0
- pattern_generator/trainer_state.json +1416 -0
- pattern_generator/training_args.bin +3 -0
- pattern_generator/vocab.json +0 -0
pattern_generator/config.json
ADDED
|
@@ -0,0 +1,172 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./models/codebert2codebert_all_ckpt10/checkpoint-3250",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"EncoderDecoderModel"
|
| 5 |
+
],
|
| 6 |
+
"decoder": {
|
| 7 |
+
"_name_or_path": "microsoft/codebert-base",
|
| 8 |
+
"add_cross_attention": true,
|
| 9 |
+
"architectures": [
|
| 10 |
+
"RobertaModel"
|
| 11 |
+
],
|
| 12 |
+
"attention_probs_dropout_prob": 0.1,
|
| 13 |
+
"bad_words_ids": 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 |
+
"hidden_act": "gelu",
|
| 29 |
+
"hidden_dropout_prob": 0.1,
|
| 30 |
+
"hidden_size": 768,
|
| 31 |
+
"id2label": {
|
| 32 |
+
"0": "LABEL_0",
|
| 33 |
+
"1": "LABEL_1"
|
| 34 |
+
},
|
| 35 |
+
"initializer_range": 0.02,
|
| 36 |
+
"intermediate_size": 3072,
|
| 37 |
+
"is_decoder": true,
|
| 38 |
+
"is_encoder_decoder": false,
|
| 39 |
+
"label2id": {
|
| 40 |
+
"LABEL_0": 0,
|
| 41 |
+
"LABEL_1": 1
|
| 42 |
+
},
|
| 43 |
+
"layer_norm_eps": 1e-05,
|
| 44 |
+
"length_penalty": 1.0,
|
| 45 |
+
"max_length": 20,
|
| 46 |
+
"max_position_embeddings": 514,
|
| 47 |
+
"min_length": 0,
|
| 48 |
+
"model_type": "roberta",
|
| 49 |
+
"no_repeat_ngram_size": 0,
|
| 50 |
+
"num_attention_heads": 12,
|
| 51 |
+
"num_beam_groups": 1,
|
| 52 |
+
"num_beams": 1,
|
| 53 |
+
"num_hidden_layers": 12,
|
| 54 |
+
"num_return_sequences": 1,
|
| 55 |
+
"output_attentions": false,
|
| 56 |
+
"output_hidden_states": false,
|
| 57 |
+
"output_past": true,
|
| 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 |
+
"task_specific_params": null,
|
| 70 |
+
"temperature": 1.0,
|
| 71 |
+
"tie_encoder_decoder": false,
|
| 72 |
+
"tie_word_embeddings": true,
|
| 73 |
+
"tokenizer_class": null,
|
| 74 |
+
"top_k": 50,
|
| 75 |
+
"top_p": 1.0,
|
| 76 |
+
"torch_dtype": null,
|
| 77 |
+
"torchscript": false,
|
| 78 |
+
"transformers_version": "4.18.0",
|
| 79 |
+
"type_vocab_size": 1,
|
| 80 |
+
"typical_p": 1.0,
|
| 81 |
+
"use_bfloat16": false,
|
| 82 |
+
"use_cache": true,
|
| 83 |
+
"vocab_size": 50265
|
| 84 |
+
},
|
| 85 |
+
"decoder_start_token_id": 0,
|
| 86 |
+
"encoder": {
|
| 87 |
+
"_name_or_path": "microsoft/codebert-base",
|
| 88 |
+
"add_cross_attention": false,
|
| 89 |
+
"architectures": [
|
| 90 |
+
"RobertaModel"
|
| 91 |
+
],
|
| 92 |
+
"attention_probs_dropout_prob": 0.1,
|
| 93 |
+
"bad_words_ids": null,
|
| 94 |
+
"bos_token_id": 0,
|
| 95 |
+
"chunk_size_feed_forward": 0,
|
| 96 |
+
"classifier_dropout": null,
|
| 97 |
+
"cross_attention_hidden_size": null,
|
| 98 |
+
"decoder_start_token_id": null,
|
| 99 |
+
"diversity_penalty": 0.0,
|
| 100 |
+
"do_sample": false,
|
| 101 |
+
"early_stopping": false,
|
| 102 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 103 |
+
"eos_token_id": 2,
|
| 104 |
+
"exponential_decay_length_penalty": null,
|
| 105 |
+
"finetuning_task": null,
|
| 106 |
+
"forced_bos_token_id": null,
|
| 107 |
+
"forced_eos_token_id": null,
|
| 108 |
+
"hidden_act": "gelu",
|
| 109 |
+
"hidden_dropout_prob": 0.1,
|
| 110 |
+
"hidden_size": 768,
|
| 111 |
+
"id2label": {
|
| 112 |
+
"0": "LABEL_0",
|
| 113 |
+
"1": "LABEL_1"
|
| 114 |
+
},
|
| 115 |
+
"initializer_range": 0.02,
|
| 116 |
+
"intermediate_size": 3072,
|
| 117 |
+
"is_decoder": false,
|
| 118 |
+
"is_encoder_decoder": false,
|
| 119 |
+
"label2id": {
|
| 120 |
+
"LABEL_0": 0,
|
| 121 |
+
"LABEL_1": 1
|
| 122 |
+
},
|
| 123 |
+
"layer_norm_eps": 1e-05,
|
| 124 |
+
"length_penalty": 1.0,
|
| 125 |
+
"max_length": 20,
|
| 126 |
+
"max_position_embeddings": 514,
|
| 127 |
+
"min_length": 0,
|
| 128 |
+
"model_type": "roberta",
|
| 129 |
+
"no_repeat_ngram_size": 0,
|
| 130 |
+
"num_attention_heads": 12,
|
| 131 |
+
"num_beam_groups": 1,
|
| 132 |
+
"num_beams": 1,
|
| 133 |
+
"num_hidden_layers": 12,
|
| 134 |
+
"num_return_sequences": 1,
|
| 135 |
+
"output_attentions": false,
|
| 136 |
+
"output_hidden_states": false,
|
| 137 |
+
"output_past": true,
|
| 138 |
+
"output_scores": false,
|
| 139 |
+
"pad_token_id": 1,
|
| 140 |
+
"position_embedding_type": "absolute",
|
| 141 |
+
"prefix": null,
|
| 142 |
+
"problem_type": null,
|
| 143 |
+
"pruned_heads": {},
|
| 144 |
+
"remove_invalid_values": false,
|
| 145 |
+
"repetition_penalty": 1.0,
|
| 146 |
+
"return_dict": true,
|
| 147 |
+
"return_dict_in_generate": false,
|
| 148 |
+
"sep_token_id": null,
|
| 149 |
+
"task_specific_params": null,
|
| 150 |
+
"temperature": 1.0,
|
| 151 |
+
"tie_encoder_decoder": false,
|
| 152 |
+
"tie_word_embeddings": true,
|
| 153 |
+
"tokenizer_class": null,
|
| 154 |
+
"top_k": 50,
|
| 155 |
+
"top_p": 1.0,
|
| 156 |
+
"torch_dtype": null,
|
| 157 |
+
"torchscript": false,
|
| 158 |
+
"transformers_version": "4.18.0",
|
| 159 |
+
"type_vocab_size": 1,
|
| 160 |
+
"typical_p": 1.0,
|
| 161 |
+
"use_bfloat16": false,
|
| 162 |
+
"use_cache": true,
|
| 163 |
+
"vocab_size": 50265
|
| 164 |
+
},
|
| 165 |
+
"is_encoder_decoder": true,
|
| 166 |
+
"max_length": 150,
|
| 167 |
+
"model_type": "encoder-decoder",
|
| 168 |
+
"pad_token_id": 1,
|
| 169 |
+
"torch_dtype": "float32",
|
| 170 |
+
"transformers_version": null,
|
| 171 |
+
"vocab_size": 50265
|
| 172 |
+
}
|
pattern_generator/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pattern_generator/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e06ec22ab1be4d9ba139e2e4eb57eff7b6ab893fd1273d554387262aea5288d6
|
| 3 |
+
size 2217280621
|
pattern_generator/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37dcc9a1a8f175402c0c525c592876982b0696963c1677d53de24aaa157ccbda
|
| 3 |
+
size 1111040466
|
pattern_generator/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cca4c9efb31720c9ae67647b30a990797581fb8a67079ef164590700f0821b6a
|
| 3 |
+
size 14657
|
pattern_generator/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0915acefc2cec9aab4ff91745afaa2910b16ae18f4576f1e7666d97c1702edd
|
| 3 |
+
size 559
|
pattern_generator/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e332a820e74b70711b39b9471328059b04d39c19ecd2110bbb2e9f83301324a9
|
| 3 |
+
size 623
|
pattern_generator/special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}
|
pattern_generator/tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"errors": "replace", "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 512, "special_tokens_map_file": "/root/.cache/huggingface/transformers/4da22fec5578ecec5fbe32b80d5a43c6fb66b0f6ad5e359979463f0722ac3b5f.0dc5b1041f62041ebbd23b1297f2f573769d5c97d8b7c28180ec86b8f6185aa8", "name_or_path": "./models/codebert2codebert_all_ckpt10/checkpoint-3250", "tokenizer_class": "RobertaTokenizer"}
|
pattern_generator/trainer_state.json
ADDED
|
@@ -0,0 +1,1416 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 99.9976976208749,
|
| 5 |
+
"global_step": 32500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"learning_rate": 1.6250000000000002e-05,
|
| 13 |
+
"loss": 1.0806,
|
| 14 |
+
"step": 325
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_loss": 0.7577828168869019,
|
| 19 |
+
"eval_runtime": 1.6267,
|
| 20 |
+
"eval_samples_per_second": 307.365,
|
| 21 |
+
"eval_steps_per_second": 38.728,
|
| 22 |
+
"step": 325
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 2.0,
|
| 26 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 27 |
+
"loss": 0.8255,
|
| 28 |
+
"step": 650
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"eval_loss": 0.556172788143158,
|
| 33 |
+
"eval_runtime": 1.6277,
|
| 34 |
+
"eval_samples_per_second": 307.186,
|
| 35 |
+
"eval_steps_per_second": 38.705,
|
| 36 |
+
"step": 650
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 3.0,
|
| 40 |
+
"learning_rate": 4.875e-05,
|
| 41 |
+
"loss": 0.6001,
|
| 42 |
+
"step": 975
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.0,
|
| 46 |
+
"eval_loss": 0.421012818813324,
|
| 47 |
+
"eval_runtime": 1.6279,
|
| 48 |
+
"eval_samples_per_second": 307.149,
|
| 49 |
+
"eval_steps_per_second": 38.701,
|
| 50 |
+
"step": 975
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.0,
|
| 54 |
+
"learning_rate": 4.9523809523809525e-05,
|
| 55 |
+
"loss": 0.4523,
|
| 56 |
+
"step": 1300
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.0,
|
| 60 |
+
"eval_loss": 0.3349049389362335,
|
| 61 |
+
"eval_runtime": 1.6071,
|
| 62 |
+
"eval_samples_per_second": 311.117,
|
| 63 |
+
"eval_steps_per_second": 39.201,
|
| 64 |
+
"step": 1300
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 5.0,
|
| 68 |
+
"learning_rate": 4.900793650793651e-05,
|
| 69 |
+
"loss": 0.3601,
|
| 70 |
+
"step": 1625
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 5.0,
|
| 74 |
+
"eval_loss": 0.29192015528678894,
|
| 75 |
+
"eval_runtime": 1.6111,
|
| 76 |
+
"eval_samples_per_second": 310.348,
|
| 77 |
+
"eval_steps_per_second": 39.104,
|
| 78 |
+
"step": 1625
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 6.0,
|
| 82 |
+
"learning_rate": 4.84920634920635e-05,
|
| 83 |
+
"loss": 0.3035,
|
| 84 |
+
"step": 1950
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 6.0,
|
| 88 |
+
"eval_loss": 0.25816571712493896,
|
| 89 |
+
"eval_runtime": 1.6209,
|
| 90 |
+
"eval_samples_per_second": 308.476,
|
| 91 |
+
"eval_steps_per_second": 38.868,
|
| 92 |
+
"step": 1950
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 7.0,
|
| 96 |
+
"learning_rate": 4.797619047619048e-05,
|
| 97 |
+
"loss": 0.2648,
|
| 98 |
+
"step": 2275
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 7.0,
|
| 102 |
+
"eval_loss": 0.239731565117836,
|
| 103 |
+
"eval_runtime": 1.6133,
|
| 104 |
+
"eval_samples_per_second": 309.927,
|
| 105 |
+
"eval_steps_per_second": 39.051,
|
| 106 |
+
"step": 2275
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 8.0,
|
| 110 |
+
"learning_rate": 4.746031746031746e-05,
|
| 111 |
+
"loss": 0.2367,
|
| 112 |
+
"step": 2600
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 8.0,
|
| 116 |
+
"eval_loss": 0.22367145121097565,
|
| 117 |
+
"eval_runtime": 1.6208,
|
| 118 |
+
"eval_samples_per_second": 308.483,
|
| 119 |
+
"eval_steps_per_second": 38.869,
|
| 120 |
+
"step": 2600
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 9.0,
|
| 124 |
+
"learning_rate": 4.6944444444444446e-05,
|
| 125 |
+
"loss": 0.216,
|
| 126 |
+
"step": 2925
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 9.0,
|
| 130 |
+
"eval_loss": 0.21722149848937988,
|
| 131 |
+
"eval_runtime": 1.6243,
|
| 132 |
+
"eval_samples_per_second": 307.822,
|
| 133 |
+
"eval_steps_per_second": 38.786,
|
| 134 |
+
"step": 2925
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 10.0,
|
| 138 |
+
"learning_rate": 4.642857142857143e-05,
|
| 139 |
+
"loss": 0.199,
|
| 140 |
+
"step": 3250
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 10.0,
|
| 144 |
+
"eval_loss": 0.21139533817768097,
|
| 145 |
+
"eval_runtime": 1.624,
|
| 146 |
+
"eval_samples_per_second": 307.888,
|
| 147 |
+
"eval_steps_per_second": 38.794,
|
| 148 |
+
"step": 3250
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 11.0,
|
| 152 |
+
"learning_rate": 4.591269841269841e-05,
|
| 153 |
+
"loss": 0.1856,
|
| 154 |
+
"step": 3575
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 11.0,
|
| 158 |
+
"eval_loss": 0.21221421658992767,
|
| 159 |
+
"eval_runtime": 1.6173,
|
| 160 |
+
"eval_samples_per_second": 309.16,
|
| 161 |
+
"eval_steps_per_second": 38.954,
|
| 162 |
+
"step": 3575
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 12.0,
|
| 166 |
+
"learning_rate": 4.5396825396825395e-05,
|
| 167 |
+
"loss": 0.1751,
|
| 168 |
+
"step": 3900
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 12.0,
|
| 172 |
+
"eval_loss": 0.20572426915168762,
|
| 173 |
+
"eval_runtime": 1.6208,
|
| 174 |
+
"eval_samples_per_second": 308.486,
|
| 175 |
+
"eval_steps_per_second": 38.869,
|
| 176 |
+
"step": 3900
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 13.0,
|
| 180 |
+
"learning_rate": 4.4880952380952385e-05,
|
| 181 |
+
"loss": 0.1667,
|
| 182 |
+
"step": 4225
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 13.0,
|
| 186 |
+
"eval_loss": 0.20298737287521362,
|
| 187 |
+
"eval_runtime": 1.6143,
|
| 188 |
+
"eval_samples_per_second": 309.733,
|
| 189 |
+
"eval_steps_per_second": 39.026,
|
| 190 |
+
"step": 4225
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 14.0,
|
| 194 |
+
"learning_rate": 4.436507936507937e-05,
|
| 195 |
+
"loss": 0.1592,
|
| 196 |
+
"step": 4550
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 14.0,
|
| 200 |
+
"eval_loss": 0.20216256380081177,
|
| 201 |
+
"eval_runtime": 1.6176,
|
| 202 |
+
"eval_samples_per_second": 309.097,
|
| 203 |
+
"eval_steps_per_second": 38.946,
|
| 204 |
+
"step": 4550
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 15.0,
|
| 208 |
+
"learning_rate": 4.384920634920635e-05,
|
| 209 |
+
"loss": 0.1528,
|
| 210 |
+
"step": 4875
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 15.0,
|
| 214 |
+
"eval_loss": 0.19866463541984558,
|
| 215 |
+
"eval_runtime": 1.5537,
|
| 216 |
+
"eval_samples_per_second": 321.813,
|
| 217 |
+
"eval_steps_per_second": 40.548,
|
| 218 |
+
"step": 4875
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 16.0,
|
| 222 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 223 |
+
"loss": 0.1475,
|
| 224 |
+
"step": 5200
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 16.0,
|
| 228 |
+
"eval_loss": 0.194817915558815,
|
| 229 |
+
"eval_runtime": 1.6315,
|
| 230 |
+
"eval_samples_per_second": 306.466,
|
| 231 |
+
"eval_steps_per_second": 38.615,
|
| 232 |
+
"step": 5200
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 17.0,
|
| 236 |
+
"learning_rate": 4.282063492063492e-05,
|
| 237 |
+
"loss": 0.1435,
|
| 238 |
+
"step": 5525
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 17.0,
|
| 242 |
+
"eval_loss": 0.20059792697429657,
|
| 243 |
+
"eval_runtime": 1.6283,
|
| 244 |
+
"eval_samples_per_second": 307.061,
|
| 245 |
+
"eval_steps_per_second": 38.69,
|
| 246 |
+
"step": 5525
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 18.0,
|
| 250 |
+
"learning_rate": 4.230476190476191e-05,
|
| 251 |
+
"loss": 0.1394,
|
| 252 |
+
"step": 5850
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 18.0,
|
| 256 |
+
"eval_loss": 0.19283074140548706,
|
| 257 |
+
"eval_runtime": 1.6289,
|
| 258 |
+
"eval_samples_per_second": 306.96,
|
| 259 |
+
"eval_steps_per_second": 38.677,
|
| 260 |
+
"step": 5850
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 19.0,
|
| 264 |
+
"learning_rate": 4.178888888888889e-05,
|
| 265 |
+
"loss": 0.1353,
|
| 266 |
+
"step": 6175
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 19.0,
|
| 270 |
+
"eval_loss": 0.19786441326141357,
|
| 271 |
+
"eval_runtime": 1.6304,
|
| 272 |
+
"eval_samples_per_second": 306.678,
|
| 273 |
+
"eval_steps_per_second": 38.641,
|
| 274 |
+
"step": 6175
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 20.0,
|
| 278 |
+
"learning_rate": 4.1273015873015876e-05,
|
| 279 |
+
"loss": 0.132,
|
| 280 |
+
"step": 6500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 20.0,
|
| 284 |
+
"eval_loss": 0.1935906708240509,
|
| 285 |
+
"eval_runtime": 1.6121,
|
| 286 |
+
"eval_samples_per_second": 310.148,
|
| 287 |
+
"eval_steps_per_second": 39.079,
|
| 288 |
+
"step": 6500
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 21.0,
|
| 292 |
+
"learning_rate": 4.075714285714286e-05,
|
| 293 |
+
"loss": 0.1286,
|
| 294 |
+
"step": 6825
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 21.0,
|
| 298 |
+
"eval_loss": 0.19877703487873077,
|
| 299 |
+
"eval_runtime": 1.616,
|
| 300 |
+
"eval_samples_per_second": 309.413,
|
| 301 |
+
"eval_steps_per_second": 38.986,
|
| 302 |
+
"step": 6825
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 22.0,
|
| 306 |
+
"learning_rate": 4.024126984126984e-05,
|
| 307 |
+
"loss": 0.126,
|
| 308 |
+
"step": 7150
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 22.0,
|
| 312 |
+
"eval_loss": 0.19710922241210938,
|
| 313 |
+
"eval_runtime": 1.6082,
|
| 314 |
+
"eval_samples_per_second": 310.904,
|
| 315 |
+
"eval_steps_per_second": 39.174,
|
| 316 |
+
"step": 7150
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 23.0,
|
| 320 |
+
"learning_rate": 3.9725396825396825e-05,
|
| 321 |
+
"loss": 0.1235,
|
| 322 |
+
"step": 7475
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 23.0,
|
| 326 |
+
"eval_loss": 0.19361434876918793,
|
| 327 |
+
"eval_runtime": 1.6189,
|
| 328 |
+
"eval_samples_per_second": 308.861,
|
| 329 |
+
"eval_steps_per_second": 38.916,
|
| 330 |
+
"step": 7475
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 24.0,
|
| 334 |
+
"learning_rate": 3.921111111111112e-05,
|
| 335 |
+
"loss": 0.1222,
|
| 336 |
+
"step": 7800
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 24.0,
|
| 340 |
+
"eval_loss": 0.19744054973125458,
|
| 341 |
+
"eval_runtime": 1.6204,
|
| 342 |
+
"eval_samples_per_second": 308.557,
|
| 343 |
+
"eval_steps_per_second": 38.878,
|
| 344 |
+
"step": 7800
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 25.0,
|
| 348 |
+
"learning_rate": 3.869523809523809e-05,
|
| 349 |
+
"loss": 0.1197,
|
| 350 |
+
"step": 8125
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 25.0,
|
| 354 |
+
"eval_loss": 0.1937996745109558,
|
| 355 |
+
"eval_runtime": 1.6179,
|
| 356 |
+
"eval_samples_per_second": 309.05,
|
| 357 |
+
"eval_steps_per_second": 38.94,
|
| 358 |
+
"step": 8125
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 26.0,
|
| 362 |
+
"learning_rate": 3.817936507936508e-05,
|
| 363 |
+
"loss": 0.1178,
|
| 364 |
+
"step": 8450
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 26.0,
|
| 368 |
+
"eval_loss": 0.195204496383667,
|
| 369 |
+
"eval_runtime": 1.6285,
|
| 370 |
+
"eval_samples_per_second": 307.033,
|
| 371 |
+
"eval_steps_per_second": 38.686,
|
| 372 |
+
"step": 8450
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 27.0,
|
| 376 |
+
"learning_rate": 3.7663492063492066e-05,
|
| 377 |
+
"loss": 0.1158,
|
| 378 |
+
"step": 8775
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 27.0,
|
| 382 |
+
"eval_loss": 0.1947883665561676,
|
| 383 |
+
"eval_runtime": 1.631,
|
| 384 |
+
"eval_samples_per_second": 306.561,
|
| 385 |
+
"eval_steps_per_second": 38.627,
|
| 386 |
+
"step": 8775
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 28.0,
|
| 390 |
+
"learning_rate": 3.714761904761905e-05,
|
| 391 |
+
"loss": 0.1146,
|
| 392 |
+
"step": 9100
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 28.0,
|
| 396 |
+
"eval_loss": 0.19417957961559296,
|
| 397 |
+
"eval_runtime": 1.6321,
|
| 398 |
+
"eval_samples_per_second": 306.362,
|
| 399 |
+
"eval_steps_per_second": 38.602,
|
| 400 |
+
"step": 9100
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 29.0,
|
| 404 |
+
"learning_rate": 3.663174603174603e-05,
|
| 405 |
+
"loss": 0.1126,
|
| 406 |
+
"step": 9425
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 29.0,
|
| 410 |
+
"eval_loss": 0.19478720426559448,
|
| 411 |
+
"eval_runtime": 1.6326,
|
| 412 |
+
"eval_samples_per_second": 306.262,
|
| 413 |
+
"eval_steps_per_second": 38.589,
|
| 414 |
+
"step": 9425
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 30.0,
|
| 418 |
+
"learning_rate": 3.611587301587302e-05,
|
| 419 |
+
"loss": 0.1113,
|
| 420 |
+
"step": 9750
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 30.0,
|
| 424 |
+
"eval_loss": 0.1987549215555191,
|
| 425 |
+
"eval_runtime": 1.6326,
|
| 426 |
+
"eval_samples_per_second": 306.255,
|
| 427 |
+
"eval_steps_per_second": 38.588,
|
| 428 |
+
"step": 9750
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 31.0,
|
| 432 |
+
"learning_rate": 3.56e-05,
|
| 433 |
+
"loss": 0.1103,
|
| 434 |
+
"step": 10075
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 31.0,
|
| 438 |
+
"eval_loss": 0.19776514172554016,
|
| 439 |
+
"eval_runtime": 1.6335,
|
| 440 |
+
"eval_samples_per_second": 306.099,
|
| 441 |
+
"eval_steps_per_second": 38.568,
|
| 442 |
+
"step": 10075
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 32.0,
|
| 446 |
+
"learning_rate": 3.508412698412699e-05,
|
| 447 |
+
"loss": 0.1091,
|
| 448 |
+
"step": 10400
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 32.0,
|
| 452 |
+
"eval_loss": 0.19811394810676575,
|
| 453 |
+
"eval_runtime": 1.6237,
|
| 454 |
+
"eval_samples_per_second": 307.933,
|
| 455 |
+
"eval_steps_per_second": 38.8,
|
| 456 |
+
"step": 10400
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 33.0,
|
| 460 |
+
"learning_rate": 3.456825396825397e-05,
|
| 461 |
+
"loss": 0.108,
|
| 462 |
+
"step": 10725
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 33.0,
|
| 466 |
+
"eval_loss": 0.1984662413597107,
|
| 467 |
+
"eval_runtime": 1.6185,
|
| 468 |
+
"eval_samples_per_second": 308.924,
|
| 469 |
+
"eval_steps_per_second": 38.924,
|
| 470 |
+
"step": 10725
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 34.0,
|
| 474 |
+
"learning_rate": 3.4052380952380954e-05,
|
| 475 |
+
"loss": 0.1071,
|
| 476 |
+
"step": 11050
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 34.0,
|
| 480 |
+
"eval_loss": 0.19538824260234833,
|
| 481 |
+
"eval_runtime": 1.6308,
|
| 482 |
+
"eval_samples_per_second": 306.593,
|
| 483 |
+
"eval_steps_per_second": 38.631,
|
| 484 |
+
"step": 11050
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 35.0,
|
| 488 |
+
"learning_rate": 3.353650793650794e-05,
|
| 489 |
+
"loss": 0.1058,
|
| 490 |
+
"step": 11375
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 35.0,
|
| 494 |
+
"eval_loss": 0.19716860353946686,
|
| 495 |
+
"eval_runtime": 1.6308,
|
| 496 |
+
"eval_samples_per_second": 306.593,
|
| 497 |
+
"eval_steps_per_second": 38.631,
|
| 498 |
+
"step": 11375
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 36.0,
|
| 502 |
+
"learning_rate": 3.3020634920634926e-05,
|
| 503 |
+
"loss": 0.1046,
|
| 504 |
+
"step": 11700
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 36.0,
|
| 508 |
+
"eval_loss": 0.19588053226470947,
|
| 509 |
+
"eval_runtime": 1.6331,
|
| 510 |
+
"eval_samples_per_second": 306.174,
|
| 511 |
+
"eval_steps_per_second": 38.578,
|
| 512 |
+
"step": 11700
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 37.0,
|
| 516 |
+
"learning_rate": 3.25047619047619e-05,
|
| 517 |
+
"loss": 0.1039,
|
| 518 |
+
"step": 12025
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 37.0,
|
| 522 |
+
"eval_loss": 0.19945307075977325,
|
| 523 |
+
"eval_runtime": 1.6342,
|
| 524 |
+
"eval_samples_per_second": 305.961,
|
| 525 |
+
"eval_steps_per_second": 38.551,
|
| 526 |
+
"step": 12025
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 38.0,
|
| 530 |
+
"learning_rate": 3.198888888888889e-05,
|
| 531 |
+
"loss": 0.1033,
|
| 532 |
+
"step": 12350
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 38.0,
|
| 536 |
+
"eval_loss": 0.19728580117225647,
|
| 537 |
+
"eval_runtime": 1.6182,
|
| 538 |
+
"eval_samples_per_second": 308.98,
|
| 539 |
+
"eval_steps_per_second": 38.931,
|
| 540 |
+
"step": 12350
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 39.0,
|
| 544 |
+
"learning_rate": 3.1473015873015875e-05,
|
| 545 |
+
"loss": 0.1021,
|
| 546 |
+
"step": 12675
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 39.0,
|
| 550 |
+
"eval_loss": 0.19883698225021362,
|
| 551 |
+
"eval_runtime": 1.6098,
|
| 552 |
+
"eval_samples_per_second": 310.588,
|
| 553 |
+
"eval_steps_per_second": 39.134,
|
| 554 |
+
"step": 12675
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 40.0,
|
| 558 |
+
"learning_rate": 3.095714285714286e-05,
|
| 559 |
+
"loss": 0.1014,
|
| 560 |
+
"step": 13000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 40.0,
|
| 564 |
+
"eval_loss": 0.19719742238521576,
|
| 565 |
+
"eval_runtime": 1.6198,
|
| 566 |
+
"eval_samples_per_second": 308.678,
|
| 567 |
+
"eval_steps_per_second": 38.893,
|
| 568 |
+
"step": 13000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 41.0,
|
| 572 |
+
"learning_rate": 3.044126984126984e-05,
|
| 573 |
+
"loss": 0.101,
|
| 574 |
+
"step": 13325
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 41.0,
|
| 578 |
+
"eval_loss": 0.1962202489376068,
|
| 579 |
+
"eval_runtime": 1.6168,
|
| 580 |
+
"eval_samples_per_second": 309.257,
|
| 581 |
+
"eval_steps_per_second": 38.966,
|
| 582 |
+
"step": 13325
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 42.0,
|
| 586 |
+
"learning_rate": 2.9925396825396828e-05,
|
| 587 |
+
"loss": 0.1001,
|
| 588 |
+
"step": 13650
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 42.0,
|
| 592 |
+
"eval_loss": 0.19871322810649872,
|
| 593 |
+
"eval_runtime": 1.6213,
|
| 594 |
+
"eval_samples_per_second": 308.398,
|
| 595 |
+
"eval_steps_per_second": 38.858,
|
| 596 |
+
"step": 13650
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 43.0,
|
| 600 |
+
"learning_rate": 2.9409523809523807e-05,
|
| 601 |
+
"loss": 0.0993,
|
| 602 |
+
"step": 13975
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 43.0,
|
| 606 |
+
"eval_loss": 0.20118726789951324,
|
| 607 |
+
"eval_runtime": 1.6162,
|
| 608 |
+
"eval_samples_per_second": 309.364,
|
| 609 |
+
"eval_steps_per_second": 38.98,
|
| 610 |
+
"step": 13975
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 44.0,
|
| 614 |
+
"learning_rate": 2.8893650793650794e-05,
|
| 615 |
+
"loss": 0.0989,
|
| 616 |
+
"step": 14300
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 44.0,
|
| 620 |
+
"eval_loss": 0.20416098833084106,
|
| 621 |
+
"eval_runtime": 1.615,
|
| 622 |
+
"eval_samples_per_second": 309.592,
|
| 623 |
+
"eval_steps_per_second": 39.009,
|
| 624 |
+
"step": 14300
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 45.0,
|
| 628 |
+
"learning_rate": 2.837777777777778e-05,
|
| 629 |
+
"loss": 0.0981,
|
| 630 |
+
"step": 14625
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 45.0,
|
| 634 |
+
"eval_loss": 0.20017844438552856,
|
| 635 |
+
"eval_runtime": 1.6211,
|
| 636 |
+
"eval_samples_per_second": 308.434,
|
| 637 |
+
"eval_steps_per_second": 38.863,
|
| 638 |
+
"step": 14625
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 46.0,
|
| 642 |
+
"learning_rate": 2.786190476190476e-05,
|
| 643 |
+
"loss": 0.0977,
|
| 644 |
+
"step": 14950
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 46.0,
|
| 648 |
+
"eval_loss": 0.1984575241804123,
|
| 649 |
+
"eval_runtime": 1.6178,
|
| 650 |
+
"eval_samples_per_second": 309.053,
|
| 651 |
+
"eval_steps_per_second": 38.941,
|
| 652 |
+
"step": 14950
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 47.0,
|
| 656 |
+
"learning_rate": 2.7346031746031746e-05,
|
| 657 |
+
"loss": 0.0972,
|
| 658 |
+
"step": 15275
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 47.0,
|
| 662 |
+
"eval_loss": 0.1984962373971939,
|
| 663 |
+
"eval_runtime": 1.6179,
|
| 664 |
+
"eval_samples_per_second": 309.052,
|
| 665 |
+
"eval_steps_per_second": 38.941,
|
| 666 |
+
"step": 15275
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 48.0,
|
| 670 |
+
"learning_rate": 2.6830158730158732e-05,
|
| 671 |
+
"loss": 0.0967,
|
| 672 |
+
"step": 15600
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 48.0,
|
| 676 |
+
"eval_loss": 0.20049268007278442,
|
| 677 |
+
"eval_runtime": 1.6168,
|
| 678 |
+
"eval_samples_per_second": 309.261,
|
| 679 |
+
"eval_steps_per_second": 38.967,
|
| 680 |
+
"step": 15600
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 49.0,
|
| 684 |
+
"learning_rate": 2.6315873015873017e-05,
|
| 685 |
+
"loss": 0.0961,
|
| 686 |
+
"step": 15925
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 49.0,
|
| 690 |
+
"eval_loss": 0.20437875390052795,
|
| 691 |
+
"eval_runtime": 1.6219,
|
| 692 |
+
"eval_samples_per_second": 308.282,
|
| 693 |
+
"eval_steps_per_second": 38.843,
|
| 694 |
+
"step": 15925
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 50.0,
|
| 698 |
+
"learning_rate": 2.58e-05,
|
| 699 |
+
"loss": 0.0954,
|
| 700 |
+
"step": 16250
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 50.0,
|
| 704 |
+
"eval_loss": 0.20537793636322021,
|
| 705 |
+
"eval_runtime": 1.615,
|
| 706 |
+
"eval_samples_per_second": 309.596,
|
| 707 |
+
"eval_steps_per_second": 39.009,
|
| 708 |
+
"step": 16250
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 51.0,
|
| 712 |
+
"learning_rate": 2.5284126984126987e-05,
|
| 713 |
+
"loss": 0.095,
|
| 714 |
+
"step": 16575
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 51.0,
|
| 718 |
+
"eval_loss": 0.20233562588691711,
|
| 719 |
+
"eval_runtime": 1.6189,
|
| 720 |
+
"eval_samples_per_second": 308.861,
|
| 721 |
+
"eval_steps_per_second": 38.916,
|
| 722 |
+
"step": 16575
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 52.0,
|
| 726 |
+
"learning_rate": 2.476825396825397e-05,
|
| 727 |
+
"loss": 0.0946,
|
| 728 |
+
"step": 16900
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 52.0,
|
| 732 |
+
"eval_loss": 0.2065245360136032,
|
| 733 |
+
"eval_runtime": 1.6223,
|
| 734 |
+
"eval_samples_per_second": 308.199,
|
| 735 |
+
"eval_steps_per_second": 38.833,
|
| 736 |
+
"step": 16900
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 53.0,
|
| 740 |
+
"learning_rate": 2.4253968253968255e-05,
|
| 741 |
+
"loss": 0.0943,
|
| 742 |
+
"step": 17225
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 53.0,
|
| 746 |
+
"eval_loss": 0.2037389576435089,
|
| 747 |
+
"eval_runtime": 1.6223,
|
| 748 |
+
"eval_samples_per_second": 308.208,
|
| 749 |
+
"eval_steps_per_second": 38.834,
|
| 750 |
+
"step": 17225
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 54.0,
|
| 754 |
+
"learning_rate": 2.373809523809524e-05,
|
| 755 |
+
"loss": 0.0938,
|
| 756 |
+
"step": 17550
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 54.0,
|
| 760 |
+
"eval_loss": 0.20668557286262512,
|
| 761 |
+
"eval_runtime": 1.6254,
|
| 762 |
+
"eval_samples_per_second": 307.609,
|
| 763 |
+
"eval_steps_per_second": 38.759,
|
| 764 |
+
"step": 17550
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 55.0,
|
| 768 |
+
"learning_rate": 2.3222222222222224e-05,
|
| 769 |
+
"loss": 0.0935,
|
| 770 |
+
"step": 17875
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 55.0,
|
| 774 |
+
"eval_loss": 0.2060803920030594,
|
| 775 |
+
"eval_runtime": 1.6215,
|
| 776 |
+
"eval_samples_per_second": 308.359,
|
| 777 |
+
"eval_steps_per_second": 38.853,
|
| 778 |
+
"step": 17875
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 56.0,
|
| 782 |
+
"learning_rate": 2.2706349206349207e-05,
|
| 783 |
+
"loss": 0.0932,
|
| 784 |
+
"step": 18200
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 56.0,
|
| 788 |
+
"eval_loss": 0.20473302900791168,
|
| 789 |
+
"eval_runtime": 1.6144,
|
| 790 |
+
"eval_samples_per_second": 309.707,
|
| 791 |
+
"eval_steps_per_second": 39.023,
|
| 792 |
+
"step": 18200
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 57.0,
|
| 796 |
+
"learning_rate": 2.2192063492063492e-05,
|
| 797 |
+
"loss": 0.093,
|
| 798 |
+
"step": 18525
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 57.0,
|
| 802 |
+
"eval_loss": 0.2071973830461502,
|
| 803 |
+
"eval_runtime": 1.657,
|
| 804 |
+
"eval_samples_per_second": 301.749,
|
| 805 |
+
"eval_steps_per_second": 38.02,
|
| 806 |
+
"step": 18525
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 58.0,
|
| 810 |
+
"learning_rate": 2.1676190476190478e-05,
|
| 811 |
+
"loss": 0.0923,
|
| 812 |
+
"step": 18850
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 58.0,
|
| 816 |
+
"eval_loss": 0.20672236382961273,
|
| 817 |
+
"eval_runtime": 1.619,
|
| 818 |
+
"eval_samples_per_second": 308.841,
|
| 819 |
+
"eval_steps_per_second": 38.914,
|
| 820 |
+
"step": 18850
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 59.0,
|
| 824 |
+
"learning_rate": 2.116031746031746e-05,
|
| 825 |
+
"loss": 0.092,
|
| 826 |
+
"step": 19175
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 59.0,
|
| 830 |
+
"eval_loss": 0.20423702895641327,
|
| 831 |
+
"eval_runtime": 1.6318,
|
| 832 |
+
"eval_samples_per_second": 306.408,
|
| 833 |
+
"eval_steps_per_second": 38.607,
|
| 834 |
+
"step": 19175
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 60.0,
|
| 838 |
+
"learning_rate": 2.0644444444444447e-05,
|
| 839 |
+
"loss": 0.0916,
|
| 840 |
+
"step": 19500
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 60.0,
|
| 844 |
+
"eval_loss": 0.20601221919059753,
|
| 845 |
+
"eval_runtime": 1.6198,
|
| 846 |
+
"eval_samples_per_second": 308.675,
|
| 847 |
+
"eval_steps_per_second": 38.893,
|
| 848 |
+
"step": 19500
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 61.0,
|
| 852 |
+
"learning_rate": 2.012857142857143e-05,
|
| 853 |
+
"loss": 0.0913,
|
| 854 |
+
"step": 19825
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 61.0,
|
| 858 |
+
"eval_loss": 0.20910584926605225,
|
| 859 |
+
"eval_runtime": 1.6185,
|
| 860 |
+
"eval_samples_per_second": 308.926,
|
| 861 |
+
"eval_steps_per_second": 38.925,
|
| 862 |
+
"step": 19825
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 62.0,
|
| 866 |
+
"learning_rate": 1.9612698412698413e-05,
|
| 867 |
+
"loss": 0.091,
|
| 868 |
+
"step": 20150
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 62.0,
|
| 872 |
+
"eval_loss": 0.20686961710453033,
|
| 873 |
+
"eval_runtime": 1.6312,
|
| 874 |
+
"eval_samples_per_second": 306.52,
|
| 875 |
+
"eval_steps_per_second": 38.621,
|
| 876 |
+
"step": 20150
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 63.0,
|
| 880 |
+
"learning_rate": 1.90968253968254e-05,
|
| 881 |
+
"loss": 0.0907,
|
| 882 |
+
"step": 20475
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 63.0,
|
| 886 |
+
"eval_loss": 0.20606577396392822,
|
| 887 |
+
"eval_runtime": 1.6309,
|
| 888 |
+
"eval_samples_per_second": 306.575,
|
| 889 |
+
"eval_steps_per_second": 38.628,
|
| 890 |
+
"step": 20475
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 64.0,
|
| 894 |
+
"learning_rate": 1.8580952380952383e-05,
|
| 895 |
+
"loss": 0.0905,
|
| 896 |
+
"step": 20800
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 64.0,
|
| 900 |
+
"eval_loss": 0.20628054440021515,
|
| 901 |
+
"eval_runtime": 1.6321,
|
| 902 |
+
"eval_samples_per_second": 306.359,
|
| 903 |
+
"eval_steps_per_second": 38.601,
|
| 904 |
+
"step": 20800
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 65.0,
|
| 908 |
+
"learning_rate": 1.8065079365079366e-05,
|
| 909 |
+
"loss": 0.09,
|
| 910 |
+
"step": 21125
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 65.0,
|
| 914 |
+
"eval_loss": 0.2085714489221573,
|
| 915 |
+
"eval_runtime": 1.615,
|
| 916 |
+
"eval_samples_per_second": 309.598,
|
| 917 |
+
"eval_steps_per_second": 39.009,
|
| 918 |
+
"step": 21125
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 66.0,
|
| 922 |
+
"learning_rate": 1.7549206349206352e-05,
|
| 923 |
+
"loss": 0.0899,
|
| 924 |
+
"step": 21450
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 66.0,
|
| 928 |
+
"eval_loss": 0.20817407965660095,
|
| 929 |
+
"eval_runtime": 1.6322,
|
| 930 |
+
"eval_samples_per_second": 306.34,
|
| 931 |
+
"eval_steps_per_second": 38.599,
|
| 932 |
+
"step": 21450
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 67.0,
|
| 936 |
+
"learning_rate": 1.7033333333333335e-05,
|
| 937 |
+
"loss": 0.0897,
|
| 938 |
+
"step": 21775
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 67.0,
|
| 942 |
+
"eval_loss": 0.20880760252475739,
|
| 943 |
+
"eval_runtime": 1.6231,
|
| 944 |
+
"eval_samples_per_second": 308.059,
|
| 945 |
+
"eval_steps_per_second": 38.815,
|
| 946 |
+
"step": 21775
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 68.0,
|
| 950 |
+
"learning_rate": 1.6517460317460318e-05,
|
| 951 |
+
"loss": 0.0892,
|
| 952 |
+
"step": 22100
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 68.0,
|
| 956 |
+
"eval_loss": 0.20673272013664246,
|
| 957 |
+
"eval_runtime": 1.6194,
|
| 958 |
+
"eval_samples_per_second": 308.75,
|
| 959 |
+
"eval_steps_per_second": 38.902,
|
| 960 |
+
"step": 22100
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 69.0,
|
| 964 |
+
"learning_rate": 1.6001587301587305e-05,
|
| 965 |
+
"loss": 0.0891,
|
| 966 |
+
"step": 22425
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 69.0,
|
| 970 |
+
"eval_loss": 0.20683825016021729,
|
| 971 |
+
"eval_runtime": 1.5781,
|
| 972 |
+
"eval_samples_per_second": 316.838,
|
| 973 |
+
"eval_steps_per_second": 39.922,
|
| 974 |
+
"step": 22425
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 70.0,
|
| 978 |
+
"learning_rate": 1.5485714285714287e-05,
|
| 979 |
+
"loss": 0.0888,
|
| 980 |
+
"step": 22750
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 70.0,
|
| 984 |
+
"eval_loss": 0.20834441483020782,
|
| 985 |
+
"eval_runtime": 1.6043,
|
| 986 |
+
"eval_samples_per_second": 311.654,
|
| 987 |
+
"eval_steps_per_second": 39.268,
|
| 988 |
+
"step": 22750
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 71.0,
|
| 992 |
+
"learning_rate": 1.496984126984127e-05,
|
| 993 |
+
"loss": 0.0886,
|
| 994 |
+
"step": 23075
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 71.0,
|
| 998 |
+
"eval_loss": 0.20795977115631104,
|
| 999 |
+
"eval_runtime": 1.5947,
|
| 1000 |
+
"eval_samples_per_second": 313.545,
|
| 1001 |
+
"eval_steps_per_second": 39.507,
|
| 1002 |
+
"step": 23075
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 72.0,
|
| 1006 |
+
"learning_rate": 1.4453968253968255e-05,
|
| 1007 |
+
"loss": 0.0884,
|
| 1008 |
+
"step": 23400
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 72.0,
|
| 1012 |
+
"eval_loss": 0.20644958317279816,
|
| 1013 |
+
"eval_runtime": 1.6293,
|
| 1014 |
+
"eval_samples_per_second": 306.871,
|
| 1015 |
+
"eval_steps_per_second": 38.666,
|
| 1016 |
+
"step": 23400
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 73.0,
|
| 1020 |
+
"learning_rate": 1.3938095238095238e-05,
|
| 1021 |
+
"loss": 0.0881,
|
| 1022 |
+
"step": 23725
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 73.0,
|
| 1026 |
+
"eval_loss": 0.20805425941944122,
|
| 1027 |
+
"eval_runtime": 1.6284,
|
| 1028 |
+
"eval_samples_per_second": 307.046,
|
| 1029 |
+
"eval_steps_per_second": 38.688,
|
| 1030 |
+
"step": 23725
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 74.0,
|
| 1034 |
+
"learning_rate": 1.3422222222222223e-05,
|
| 1035 |
+
"loss": 0.0878,
|
| 1036 |
+
"step": 24050
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 74.0,
|
| 1040 |
+
"eval_loss": 0.20709100365638733,
|
| 1041 |
+
"eval_runtime": 1.6294,
|
| 1042 |
+
"eval_samples_per_second": 306.866,
|
| 1043 |
+
"eval_steps_per_second": 38.665,
|
| 1044 |
+
"step": 24050
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 75.0,
|
| 1048 |
+
"learning_rate": 1.2906349206349208e-05,
|
| 1049 |
+
"loss": 0.0875,
|
| 1050 |
+
"step": 24375
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 75.0,
|
| 1054 |
+
"eval_loss": 0.2094418704509735,
|
| 1055 |
+
"eval_runtime": 1.6183,
|
| 1056 |
+
"eval_samples_per_second": 308.957,
|
| 1057 |
+
"eval_steps_per_second": 38.929,
|
| 1058 |
+
"step": 24375
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 76.0,
|
| 1062 |
+
"learning_rate": 1.239047619047619e-05,
|
| 1063 |
+
"loss": 0.0875,
|
| 1064 |
+
"step": 24700
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 76.0,
|
| 1068 |
+
"eval_loss": 0.2107103168964386,
|
| 1069 |
+
"eval_runtime": 1.628,
|
| 1070 |
+
"eval_samples_per_second": 307.132,
|
| 1071 |
+
"eval_steps_per_second": 38.699,
|
| 1072 |
+
"step": 24700
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 77.0,
|
| 1076 |
+
"learning_rate": 1.1874603174603175e-05,
|
| 1077 |
+
"loss": 0.0871,
|
| 1078 |
+
"step": 25025
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 77.0,
|
| 1082 |
+
"eval_loss": 0.21094562113285065,
|
| 1083 |
+
"eval_runtime": 1.6329,
|
| 1084 |
+
"eval_samples_per_second": 306.207,
|
| 1085 |
+
"eval_steps_per_second": 38.582,
|
| 1086 |
+
"step": 25025
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 78.0,
|
| 1090 |
+
"learning_rate": 1.1358730158730158e-05,
|
| 1091 |
+
"loss": 0.087,
|
| 1092 |
+
"step": 25350
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 78.0,
|
| 1096 |
+
"eval_loss": 0.21239960193634033,
|
| 1097 |
+
"eval_runtime": 1.6224,
|
| 1098 |
+
"eval_samples_per_second": 308.182,
|
| 1099 |
+
"eval_steps_per_second": 38.831,
|
| 1100 |
+
"step": 25350
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 79.0,
|
| 1104 |
+
"learning_rate": 1.0842857142857143e-05,
|
| 1105 |
+
"loss": 0.0868,
|
| 1106 |
+
"step": 25675
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 79.0,
|
| 1110 |
+
"eval_loss": 0.21309518814086914,
|
| 1111 |
+
"eval_runtime": 1.6334,
|
| 1112 |
+
"eval_samples_per_second": 306.113,
|
| 1113 |
+
"eval_steps_per_second": 38.57,
|
| 1114 |
+
"step": 25675
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 80.0,
|
| 1118 |
+
"learning_rate": 1.0326984126984128e-05,
|
| 1119 |
+
"loss": 0.0867,
|
| 1120 |
+
"step": 26000
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 80.0,
|
| 1124 |
+
"eval_loss": 0.21296508610248566,
|
| 1125 |
+
"eval_runtime": 1.6313,
|
| 1126 |
+
"eval_samples_per_second": 306.503,
|
| 1127 |
+
"eval_steps_per_second": 38.619,
|
| 1128 |
+
"step": 26000
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 81.0,
|
| 1132 |
+
"learning_rate": 9.81111111111111e-06,
|
| 1133 |
+
"loss": 0.0864,
|
| 1134 |
+
"step": 26325
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 81.0,
|
| 1138 |
+
"eval_loss": 0.2111913114786148,
|
| 1139 |
+
"eval_runtime": 1.63,
|
| 1140 |
+
"eval_samples_per_second": 306.746,
|
| 1141 |
+
"eval_steps_per_second": 38.65,
|
| 1142 |
+
"step": 26325
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 82.0,
|
| 1146 |
+
"learning_rate": 9.295238095238095e-06,
|
| 1147 |
+
"loss": 0.0863,
|
| 1148 |
+
"step": 26650
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 82.0,
|
| 1152 |
+
"eval_loss": 0.21297475695610046,
|
| 1153 |
+
"eval_runtime": 1.6157,
|
| 1154 |
+
"eval_samples_per_second": 309.46,
|
| 1155 |
+
"eval_steps_per_second": 38.992,
|
| 1156 |
+
"step": 26650
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 83.0,
|
| 1160 |
+
"learning_rate": 8.780952380952382e-06,
|
| 1161 |
+
"loss": 0.086,
|
| 1162 |
+
"step": 26975
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 83.0,
|
| 1166 |
+
"eval_loss": 0.21185711026191711,
|
| 1167 |
+
"eval_runtime": 1.6153,
|
| 1168 |
+
"eval_samples_per_second": 309.538,
|
| 1169 |
+
"eval_steps_per_second": 39.002,
|
| 1170 |
+
"step": 26975
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 84.0,
|
| 1174 |
+
"learning_rate": 8.265079365079366e-06,
|
| 1175 |
+
"loss": 0.0858,
|
| 1176 |
+
"step": 27300
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 84.0,
|
| 1180 |
+
"eval_loss": 0.2126666158437729,
|
| 1181 |
+
"eval_runtime": 1.6047,
|
| 1182 |
+
"eval_samples_per_second": 311.576,
|
| 1183 |
+
"eval_steps_per_second": 39.259,
|
| 1184 |
+
"step": 27300
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 85.0,
|
| 1188 |
+
"learning_rate": 7.74920634920635e-06,
|
| 1189 |
+
"loss": 0.0856,
|
| 1190 |
+
"step": 27625
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 85.0,
|
| 1194 |
+
"eval_loss": 0.21050776541233063,
|
| 1195 |
+
"eval_runtime": 1.6118,
|
| 1196 |
+
"eval_samples_per_second": 310.205,
|
| 1197 |
+
"eval_steps_per_second": 39.086,
|
| 1198 |
+
"step": 27625
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 86.0,
|
| 1202 |
+
"learning_rate": 7.233333333333333e-06,
|
| 1203 |
+
"loss": 0.0854,
|
| 1204 |
+
"step": 27950
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 86.0,
|
| 1208 |
+
"eval_loss": 0.21171194314956665,
|
| 1209 |
+
"eval_runtime": 1.6187,
|
| 1210 |
+
"eval_samples_per_second": 308.884,
|
| 1211 |
+
"eval_steps_per_second": 38.919,
|
| 1212 |
+
"step": 27950
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 87.0,
|
| 1216 |
+
"learning_rate": 6.717460317460318e-06,
|
| 1217 |
+
"loss": 0.0853,
|
| 1218 |
+
"step": 28275
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 87.0,
|
| 1222 |
+
"eval_loss": 0.21184836328029633,
|
| 1223 |
+
"eval_runtime": 1.6069,
|
| 1224 |
+
"eval_samples_per_second": 311.153,
|
| 1225 |
+
"eval_steps_per_second": 39.205,
|
| 1226 |
+
"step": 28275
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 88.0,
|
| 1230 |
+
"learning_rate": 6.201587301587302e-06,
|
| 1231 |
+
"loss": 0.085,
|
| 1232 |
+
"step": 28600
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 88.0,
|
| 1236 |
+
"eval_loss": 0.21248288452625275,
|
| 1237 |
+
"eval_runtime": 1.6139,
|
| 1238 |
+
"eval_samples_per_second": 309.805,
|
| 1239 |
+
"eval_steps_per_second": 39.035,
|
| 1240 |
+
"step": 28600
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 89.0,
|
| 1244 |
+
"learning_rate": 5.685714285714286e-06,
|
| 1245 |
+
"loss": 0.0848,
|
| 1246 |
+
"step": 28925
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 89.0,
|
| 1250 |
+
"eval_loss": 0.21106228232383728,
|
| 1251 |
+
"eval_runtime": 1.631,
|
| 1252 |
+
"eval_samples_per_second": 306.568,
|
| 1253 |
+
"eval_steps_per_second": 38.628,
|
| 1254 |
+
"step": 28925
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 90.0,
|
| 1258 |
+
"learning_rate": 5.16984126984127e-06,
|
| 1259 |
+
"loss": 0.0847,
|
| 1260 |
+
"step": 29250
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 90.0,
|
| 1264 |
+
"eval_loss": 0.21153707802295685,
|
| 1265 |
+
"eval_runtime": 1.6322,
|
| 1266 |
+
"eval_samples_per_second": 306.329,
|
| 1267 |
+
"eval_steps_per_second": 38.598,
|
| 1268 |
+
"step": 29250
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 91.0,
|
| 1272 |
+
"learning_rate": 4.655555555555556e-06,
|
| 1273 |
+
"loss": 0.0845,
|
| 1274 |
+
"step": 29575
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 91.0,
|
| 1278 |
+
"eval_loss": 0.2115468680858612,
|
| 1279 |
+
"eval_runtime": 1.6278,
|
| 1280 |
+
"eval_samples_per_second": 307.165,
|
| 1281 |
+
"eval_steps_per_second": 38.703,
|
| 1282 |
+
"step": 29575
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 92.0,
|
| 1286 |
+
"learning_rate": 4.13968253968254e-06,
|
| 1287 |
+
"loss": 0.0844,
|
| 1288 |
+
"step": 29900
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 92.0,
|
| 1292 |
+
"eval_loss": 0.21205155551433563,
|
| 1293 |
+
"eval_runtime": 1.6299,
|
| 1294 |
+
"eval_samples_per_second": 306.762,
|
| 1295 |
+
"eval_steps_per_second": 38.652,
|
| 1296 |
+
"step": 29900
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 93.0,
|
| 1300 |
+
"learning_rate": 3.6238095238095236e-06,
|
| 1301 |
+
"loss": 0.0842,
|
| 1302 |
+
"step": 30225
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 93.0,
|
| 1306 |
+
"eval_loss": 0.21224457025527954,
|
| 1307 |
+
"eval_runtime": 1.6302,
|
| 1308 |
+
"eval_samples_per_second": 306.709,
|
| 1309 |
+
"eval_steps_per_second": 38.645,
|
| 1310 |
+
"step": 30225
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 94.0,
|
| 1314 |
+
"learning_rate": 3.107936507936508e-06,
|
| 1315 |
+
"loss": 0.0839,
|
| 1316 |
+
"step": 30550
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 94.0,
|
| 1320 |
+
"eval_loss": 0.21223796904087067,
|
| 1321 |
+
"eval_runtime": 1.6205,
|
| 1322 |
+
"eval_samples_per_second": 308.552,
|
| 1323 |
+
"eval_steps_per_second": 38.878,
|
| 1324 |
+
"step": 30550
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 95.0,
|
| 1328 |
+
"learning_rate": 2.592063492063492e-06,
|
| 1329 |
+
"loss": 0.0839,
|
| 1330 |
+
"step": 30875
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 95.0,
|
| 1334 |
+
"eval_loss": 0.2121766060590744,
|
| 1335 |
+
"eval_runtime": 1.626,
|
| 1336 |
+
"eval_samples_per_second": 307.496,
|
| 1337 |
+
"eval_steps_per_second": 38.745,
|
| 1338 |
+
"step": 30875
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 96.0,
|
| 1342 |
+
"learning_rate": 2.0761904761904764e-06,
|
| 1343 |
+
"loss": 0.0836,
|
| 1344 |
+
"step": 31200
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 96.0,
|
| 1348 |
+
"eval_loss": 0.21236176788806915,
|
| 1349 |
+
"eval_runtime": 1.6277,
|
| 1350 |
+
"eval_samples_per_second": 307.178,
|
| 1351 |
+
"eval_steps_per_second": 38.704,
|
| 1352 |
+
"step": 31200
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 97.0,
|
| 1356 |
+
"learning_rate": 1.561904761904762e-06,
|
| 1357 |
+
"loss": 0.0836,
|
| 1358 |
+
"step": 31525
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 97.0,
|
| 1362 |
+
"eval_loss": 0.21288882195949554,
|
| 1363 |
+
"eval_runtime": 1.6293,
|
| 1364 |
+
"eval_samples_per_second": 306.882,
|
| 1365 |
+
"eval_steps_per_second": 38.667,
|
| 1366 |
+
"step": 31525
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 98.0,
|
| 1370 |
+
"learning_rate": 1.046031746031746e-06,
|
| 1371 |
+
"loss": 0.0834,
|
| 1372 |
+
"step": 31850
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 98.0,
|
| 1376 |
+
"eval_loss": 0.21266008913516998,
|
| 1377 |
+
"eval_runtime": 1.6301,
|
| 1378 |
+
"eval_samples_per_second": 306.725,
|
| 1379 |
+
"eval_steps_per_second": 38.647,
|
| 1380 |
+
"step": 31850
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 99.0,
|
| 1384 |
+
"learning_rate": 5.301587301587302e-07,
|
| 1385 |
+
"loss": 0.0833,
|
| 1386 |
+
"step": 32175
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 99.0,
|
| 1390 |
+
"eval_loss": 0.2126527726650238,
|
| 1391 |
+
"eval_runtime": 1.6305,
|
| 1392 |
+
"eval_samples_per_second": 306.648,
|
| 1393 |
+
"eval_steps_per_second": 38.638,
|
| 1394 |
+
"step": 32175
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 100.0,
|
| 1398 |
+
"learning_rate": 1.4285714285714288e-08,
|
| 1399 |
+
"loss": 0.0831,
|
| 1400 |
+
"step": 32500
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 100.0,
|
| 1404 |
+
"eval_loss": 0.21250146627426147,
|
| 1405 |
+
"eval_runtime": 1.6061,
|
| 1406 |
+
"eval_samples_per_second": 311.323,
|
| 1407 |
+
"eval_steps_per_second": 39.227,
|
| 1408 |
+
"step": 32500
|
| 1409 |
+
}
|
| 1410 |
+
],
|
| 1411 |
+
"max_steps": 32500,
|
| 1412 |
+
"num_train_epochs": 100,
|
| 1413 |
+
"total_flos": 3.044459658533238e+17,
|
| 1414 |
+
"trial_name": null,
|
| 1415 |
+
"trial_params": null
|
| 1416 |
+
}
|
pattern_generator/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f6e909803e233d3dbb73e34058a5cab80b5f7283540c7514fac596bafa43df7
|
| 3 |
+
size 3183
|
pattern_generator/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|