Training in progress, step 10500, checkpoint
Browse files- checkpoint-10500/config.json +186 -0
- checkpoint-10500/generation_config.json +7 -0
- checkpoint-10500/model.safetensors +3 -0
- checkpoint-10500/optimizer.pt +3 -0
- checkpoint-10500/rng_state.pth +3 -0
- checkpoint-10500/scheduler.pt +3 -0
- checkpoint-10500/trainer_state.json +453 -0
- checkpoint-10500/training_args.bin +3 -0
checkpoint-10500/config.json
ADDED
|
@@ -0,0 +1,186 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "NourFakih/Vit-GPT2-COCO2017Flickr-80k-08",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"VisionEncoderDecoderModel"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 50256,
|
| 7 |
+
"decoder": {
|
| 8 |
+
"_name_or_path": "",
|
| 9 |
+
"activation_function": "gelu_new",
|
| 10 |
+
"add_cross_attention": true,
|
| 11 |
+
"architectures": [
|
| 12 |
+
"GPT2LMHeadModel"
|
| 13 |
+
],
|
| 14 |
+
"attn_pdrop": 0.1,
|
| 15 |
+
"bad_words_ids": null,
|
| 16 |
+
"begin_suppress_tokens": null,
|
| 17 |
+
"bos_token_id": 50256,
|
| 18 |
+
"chunk_size_feed_forward": 0,
|
| 19 |
+
"cross_attention_hidden_size": null,
|
| 20 |
+
"decoder_start_token_id": 50256,
|
| 21 |
+
"diversity_penalty": 0.0,
|
| 22 |
+
"do_sample": false,
|
| 23 |
+
"early_stopping": false,
|
| 24 |
+
"embd_pdrop": 0.1,
|
| 25 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 26 |
+
"eos_token_id": 50256,
|
| 27 |
+
"exponential_decay_length_penalty": null,
|
| 28 |
+
"finetuning_task": null,
|
| 29 |
+
"forced_bos_token_id": null,
|
| 30 |
+
"forced_eos_token_id": null,
|
| 31 |
+
"id2label": {
|
| 32 |
+
"0": "LABEL_0",
|
| 33 |
+
"1": "LABEL_1"
|
| 34 |
+
},
|
| 35 |
+
"initializer_range": 0.02,
|
| 36 |
+
"is_decoder": true,
|
| 37 |
+
"is_encoder_decoder": false,
|
| 38 |
+
"label2id": {
|
| 39 |
+
"LABEL_0": 0,
|
| 40 |
+
"LABEL_1": 1
|
| 41 |
+
},
|
| 42 |
+
"layer_norm_epsilon": 1e-05,
|
| 43 |
+
"length_penalty": 1.0,
|
| 44 |
+
"max_length": 20,
|
| 45 |
+
"min_length": 0,
|
| 46 |
+
"model_type": "gpt2",
|
| 47 |
+
"n_ctx": 1024,
|
| 48 |
+
"n_embd": 768,
|
| 49 |
+
"n_head": 12,
|
| 50 |
+
"n_inner": null,
|
| 51 |
+
"n_layer": 12,
|
| 52 |
+
"n_positions": 1024,
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_beam_groups": 1,
|
| 55 |
+
"num_beams": 1,
|
| 56 |
+
"num_return_sequences": 1,
|
| 57 |
+
"output_attentions": false,
|
| 58 |
+
"output_hidden_states": false,
|
| 59 |
+
"output_scores": false,
|
| 60 |
+
"pad_token_id": 50256,
|
| 61 |
+
"prefix": null,
|
| 62 |
+
"problem_type": null,
|
| 63 |
+
"pruned_heads": {},
|
| 64 |
+
"remove_invalid_values": false,
|
| 65 |
+
"reorder_and_upcast_attn": false,
|
| 66 |
+
"repetition_penalty": 1.0,
|
| 67 |
+
"resid_pdrop": 0.1,
|
| 68 |
+
"return_dict": true,
|
| 69 |
+
"return_dict_in_generate": false,
|
| 70 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 71 |
+
"scale_attn_weights": true,
|
| 72 |
+
"sep_token_id": null,
|
| 73 |
+
"summary_activation": null,
|
| 74 |
+
"summary_first_dropout": 0.1,
|
| 75 |
+
"summary_proj_to_labels": true,
|
| 76 |
+
"summary_type": "cls_index",
|
| 77 |
+
"summary_use_proj": true,
|
| 78 |
+
"suppress_tokens": null,
|
| 79 |
+
"task_specific_params": {
|
| 80 |
+
"text-generation": {
|
| 81 |
+
"do_sample": true,
|
| 82 |
+
"max_length": 50
|
| 83 |
+
}
|
| 84 |
+
},
|
| 85 |
+
"temperature": 1.0,
|
| 86 |
+
"tf_legacy_loss": false,
|
| 87 |
+
"tie_encoder_decoder": false,
|
| 88 |
+
"tie_word_embeddings": true,
|
| 89 |
+
"tokenizer_class": null,
|
| 90 |
+
"top_k": 50,
|
| 91 |
+
"top_p": 1.0,
|
| 92 |
+
"torch_dtype": null,
|
| 93 |
+
"torchscript": false,
|
| 94 |
+
"typical_p": 1.0,
|
| 95 |
+
"use_bfloat16": false,
|
| 96 |
+
"use_cache": true,
|
| 97 |
+
"vocab_size": 50257
|
| 98 |
+
},
|
| 99 |
+
"decoder_start_token_id": 50256,
|
| 100 |
+
"encoder": {
|
| 101 |
+
"_name_or_path": "",
|
| 102 |
+
"add_cross_attention": false,
|
| 103 |
+
"architectures": [
|
| 104 |
+
"ViTModel"
|
| 105 |
+
],
|
| 106 |
+
"attention_probs_dropout_prob": 0.0,
|
| 107 |
+
"bad_words_ids": null,
|
| 108 |
+
"begin_suppress_tokens": null,
|
| 109 |
+
"bos_token_id": null,
|
| 110 |
+
"chunk_size_feed_forward": 0,
|
| 111 |
+
"cross_attention_hidden_size": null,
|
| 112 |
+
"decoder_start_token_id": null,
|
| 113 |
+
"diversity_penalty": 0.0,
|
| 114 |
+
"do_sample": false,
|
| 115 |
+
"early_stopping": false,
|
| 116 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 117 |
+
"encoder_stride": 16,
|
| 118 |
+
"eos_token_id": null,
|
| 119 |
+
"exponential_decay_length_penalty": null,
|
| 120 |
+
"finetuning_task": null,
|
| 121 |
+
"forced_bos_token_id": null,
|
| 122 |
+
"forced_eos_token_id": null,
|
| 123 |
+
"hidden_act": "gelu",
|
| 124 |
+
"hidden_dropout_prob": 0.0,
|
| 125 |
+
"hidden_size": 768,
|
| 126 |
+
"id2label": {
|
| 127 |
+
"0": "LABEL_0",
|
| 128 |
+
"1": "LABEL_1"
|
| 129 |
+
},
|
| 130 |
+
"image_size": 224,
|
| 131 |
+
"initializer_range": 0.02,
|
| 132 |
+
"intermediate_size": 3072,
|
| 133 |
+
"is_decoder": false,
|
| 134 |
+
"is_encoder_decoder": false,
|
| 135 |
+
"label2id": {
|
| 136 |
+
"LABEL_0": 0,
|
| 137 |
+
"LABEL_1": 1
|
| 138 |
+
},
|
| 139 |
+
"layer_norm_eps": 1e-12,
|
| 140 |
+
"length_penalty": 1.0,
|
| 141 |
+
"max_length": 20,
|
| 142 |
+
"min_length": 0,
|
| 143 |
+
"model_type": "vit",
|
| 144 |
+
"no_repeat_ngram_size": 0,
|
| 145 |
+
"num_attention_heads": 12,
|
| 146 |
+
"num_beam_groups": 1,
|
| 147 |
+
"num_beams": 1,
|
| 148 |
+
"num_channels": 3,
|
| 149 |
+
"num_hidden_layers": 12,
|
| 150 |
+
"num_return_sequences": 1,
|
| 151 |
+
"output_attentions": false,
|
| 152 |
+
"output_hidden_states": false,
|
| 153 |
+
"output_scores": false,
|
| 154 |
+
"pad_token_id": null,
|
| 155 |
+
"patch_size": 16,
|
| 156 |
+
"prefix": null,
|
| 157 |
+
"problem_type": null,
|
| 158 |
+
"pruned_heads": {},
|
| 159 |
+
"qkv_bias": true,
|
| 160 |
+
"remove_invalid_values": false,
|
| 161 |
+
"repetition_penalty": 1.0,
|
| 162 |
+
"return_dict": true,
|
| 163 |
+
"return_dict_in_generate": false,
|
| 164 |
+
"sep_token_id": null,
|
| 165 |
+
"suppress_tokens": null,
|
| 166 |
+
"task_specific_params": null,
|
| 167 |
+
"temperature": 1.0,
|
| 168 |
+
"tf_legacy_loss": false,
|
| 169 |
+
"tie_encoder_decoder": false,
|
| 170 |
+
"tie_word_embeddings": true,
|
| 171 |
+
"tokenizer_class": null,
|
| 172 |
+
"top_k": 50,
|
| 173 |
+
"top_p": 1.0,
|
| 174 |
+
"torch_dtype": null,
|
| 175 |
+
"torchscript": false,
|
| 176 |
+
"typical_p": 1.0,
|
| 177 |
+
"use_bfloat16": false
|
| 178 |
+
},
|
| 179 |
+
"eos_token_id": 50256,
|
| 180 |
+
"is_encoder_decoder": true,
|
| 181 |
+
"model_type": "vision-encoder-decoder",
|
| 182 |
+
"pad_token_id": 50256,
|
| 183 |
+
"tie_word_embeddings": false,
|
| 184 |
+
"torch_dtype": "float32",
|
| 185 |
+
"transformers_version": "4.41.2"
|
| 186 |
+
}
|
checkpoint-10500/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 50256,
|
| 3 |
+
"decoder_start_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"pad_token_id": 50256,
|
| 6 |
+
"transformers_version": "4.41.2"
|
| 7 |
+
}
|
checkpoint-10500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:355849ec0fdb4e53c42229aec358838b577e0c4f9d566aab93c3ddda1e473d3c
|
| 3 |
+
size 956835520
|
checkpoint-10500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3637533a0bdedefc9780ad15a0f98c1719d83cb1b197b6c642634907feb1ec4f
|
| 3 |
+
size 1909212608
|
checkpoint-10500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e25871ea3b0e5d524f42d13d21f0b6002a360057f09287da710ad306602629a
|
| 3 |
+
size 14244
|
checkpoint-10500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fbc14a7494fb7821b8b3fd27673a6e3c9ca568b195b34d91ef27fa2c66cac362
|
| 3 |
+
size 1064
|
checkpoint-10500/trainer_state.json
ADDED
|
@@ -0,0 +1,453 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.4623475670814514,
|
| 3 |
+
"best_model_checkpoint": "./Vit-GPT2-COCO2017Flickr-80k-08/checkpoint-3500",
|
| 4 |
+
"epoch": 2.1,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 10500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.1,
|
| 13 |
+
"grad_norm": 0.9981909990310669,
|
| 14 |
+
"learning_rate": 4.8333333333333334e-05,
|
| 15 |
+
"loss": 0.3691,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1,
|
| 20 |
+
"eval_gen_len": 11.77575,
|
| 21 |
+
"eval_loss": 0.4729623794555664,
|
| 22 |
+
"eval_rouge1": 39.8086,
|
| 23 |
+
"eval_rouge2": 14.7674,
|
| 24 |
+
"eval_rougeL": 36.1546,
|
| 25 |
+
"eval_rougeLsum": 36.1739,
|
| 26 |
+
"eval_runtime": 459.5392,
|
| 27 |
+
"eval_samples_per_second": 8.704,
|
| 28 |
+
"eval_steps_per_second": 2.176,
|
| 29 |
+
"step": 500
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.2,
|
| 33 |
+
"grad_norm": 0.8220647573471069,
|
| 34 |
+
"learning_rate": 4.666666666666667e-05,
|
| 35 |
+
"loss": 0.3706,
|
| 36 |
+
"step": 1000
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.2,
|
| 40 |
+
"eval_gen_len": 11.59775,
|
| 41 |
+
"eval_loss": 0.47387805581092834,
|
| 42 |
+
"eval_rouge1": 39.8972,
|
| 43 |
+
"eval_rouge2": 14.9064,
|
| 44 |
+
"eval_rougeL": 36.1193,
|
| 45 |
+
"eval_rougeLsum": 36.138,
|
| 46 |
+
"eval_runtime": 446.0956,
|
| 47 |
+
"eval_samples_per_second": 8.967,
|
| 48 |
+
"eval_steps_per_second": 2.242,
|
| 49 |
+
"step": 1000
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.3,
|
| 53 |
+
"grad_norm": 1.052058219909668,
|
| 54 |
+
"learning_rate": 4.5e-05,
|
| 55 |
+
"loss": 0.3709,
|
| 56 |
+
"step": 1500
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.3,
|
| 60 |
+
"eval_gen_len": 11.71025,
|
| 61 |
+
"eval_loss": 0.47592678666114807,
|
| 62 |
+
"eval_rouge1": 39.9874,
|
| 63 |
+
"eval_rouge2": 14.8528,
|
| 64 |
+
"eval_rougeL": 36.3155,
|
| 65 |
+
"eval_rougeLsum": 36.3317,
|
| 66 |
+
"eval_runtime": 466.5502,
|
| 67 |
+
"eval_samples_per_second": 8.574,
|
| 68 |
+
"eval_steps_per_second": 2.143,
|
| 69 |
+
"step": 1500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.4,
|
| 73 |
+
"grad_norm": 0.8642559051513672,
|
| 74 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 75 |
+
"loss": 0.3721,
|
| 76 |
+
"step": 2000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.4,
|
| 80 |
+
"eval_gen_len": 12.175,
|
| 81 |
+
"eval_loss": 0.4677760601043701,
|
| 82 |
+
"eval_rouge1": 39.7192,
|
| 83 |
+
"eval_rouge2": 14.5844,
|
| 84 |
+
"eval_rougeL": 35.8447,
|
| 85 |
+
"eval_rougeLsum": 35.8728,
|
| 86 |
+
"eval_runtime": 455.6895,
|
| 87 |
+
"eval_samples_per_second": 8.778,
|
| 88 |
+
"eval_steps_per_second": 2.194,
|
| 89 |
+
"step": 2000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.5,
|
| 93 |
+
"grad_norm": 0.8769400715827942,
|
| 94 |
+
"learning_rate": 4.166666666666667e-05,
|
| 95 |
+
"loss": 0.3655,
|
| 96 |
+
"step": 2500
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.5,
|
| 100 |
+
"eval_gen_len": 11.90025,
|
| 101 |
+
"eval_loss": 0.4683643877506256,
|
| 102 |
+
"eval_rouge1": 40.3132,
|
| 103 |
+
"eval_rouge2": 15.1157,
|
| 104 |
+
"eval_rougeL": 36.5749,
|
| 105 |
+
"eval_rougeLsum": 36.5823,
|
| 106 |
+
"eval_runtime": 449.7304,
|
| 107 |
+
"eval_samples_per_second": 8.894,
|
| 108 |
+
"eval_steps_per_second": 2.224,
|
| 109 |
+
"step": 2500
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.6,
|
| 113 |
+
"grad_norm": 0.8613843321800232,
|
| 114 |
+
"learning_rate": 4e-05,
|
| 115 |
+
"loss": 0.3623,
|
| 116 |
+
"step": 3000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.6,
|
| 120 |
+
"eval_gen_len": 12.025,
|
| 121 |
+
"eval_loss": 0.4671708345413208,
|
| 122 |
+
"eval_rouge1": 40.1643,
|
| 123 |
+
"eval_rouge2": 14.978,
|
| 124 |
+
"eval_rougeL": 36.3002,
|
| 125 |
+
"eval_rougeLsum": 36.3232,
|
| 126 |
+
"eval_runtime": 451.1814,
|
| 127 |
+
"eval_samples_per_second": 8.866,
|
| 128 |
+
"eval_steps_per_second": 2.216,
|
| 129 |
+
"step": 3000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.7,
|
| 133 |
+
"grad_norm": 0.8106393814086914,
|
| 134 |
+
"learning_rate": 3.8333333333333334e-05,
|
| 135 |
+
"loss": 0.3676,
|
| 136 |
+
"step": 3500
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.7,
|
| 140 |
+
"eval_gen_len": 11.815,
|
| 141 |
+
"eval_loss": 0.4623475670814514,
|
| 142 |
+
"eval_rouge1": 40.5036,
|
| 143 |
+
"eval_rouge2": 15.3751,
|
| 144 |
+
"eval_rougeL": 36.8369,
|
| 145 |
+
"eval_rougeLsum": 36.867,
|
| 146 |
+
"eval_runtime": 458.4461,
|
| 147 |
+
"eval_samples_per_second": 8.725,
|
| 148 |
+
"eval_steps_per_second": 2.181,
|
| 149 |
+
"step": 3500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.8,
|
| 153 |
+
"grad_norm": 0.914828360080719,
|
| 154 |
+
"learning_rate": 3.6666666666666666e-05,
|
| 155 |
+
"loss": 0.3613,
|
| 156 |
+
"step": 4000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.8,
|
| 160 |
+
"eval_gen_len": 12.054,
|
| 161 |
+
"eval_loss": 0.46470996737480164,
|
| 162 |
+
"eval_rouge1": 40.4078,
|
| 163 |
+
"eval_rouge2": 15.3105,
|
| 164 |
+
"eval_rougeL": 36.65,
|
| 165 |
+
"eval_rougeLsum": 36.6732,
|
| 166 |
+
"eval_runtime": 457.1563,
|
| 167 |
+
"eval_samples_per_second": 8.75,
|
| 168 |
+
"eval_steps_per_second": 2.187,
|
| 169 |
+
"step": 4000
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.9,
|
| 173 |
+
"grad_norm": 0.8004090189933777,
|
| 174 |
+
"learning_rate": 3.5e-05,
|
| 175 |
+
"loss": 0.3539,
|
| 176 |
+
"step": 4500
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.9,
|
| 180 |
+
"eval_gen_len": 11.904,
|
| 181 |
+
"eval_loss": 0.46335914731025696,
|
| 182 |
+
"eval_rouge1": 40.3794,
|
| 183 |
+
"eval_rouge2": 15.233,
|
| 184 |
+
"eval_rougeL": 36.7155,
|
| 185 |
+
"eval_rougeLsum": 36.7435,
|
| 186 |
+
"eval_runtime": 445.5568,
|
| 187 |
+
"eval_samples_per_second": 8.978,
|
| 188 |
+
"eval_steps_per_second": 2.244,
|
| 189 |
+
"step": 4500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.0,
|
| 193 |
+
"grad_norm": 0.876920223236084,
|
| 194 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 195 |
+
"loss": 0.3481,
|
| 196 |
+
"step": 5000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.0,
|
| 200 |
+
"eval_gen_len": 11.738,
|
| 201 |
+
"eval_loss": 0.46441808342933655,
|
| 202 |
+
"eval_rouge1": 40.037,
|
| 203 |
+
"eval_rouge2": 14.8477,
|
| 204 |
+
"eval_rougeL": 36.3648,
|
| 205 |
+
"eval_rougeLsum": 36.3903,
|
| 206 |
+
"eval_runtime": 442.7978,
|
| 207 |
+
"eval_samples_per_second": 9.033,
|
| 208 |
+
"eval_steps_per_second": 2.258,
|
| 209 |
+
"step": 5000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.1,
|
| 213 |
+
"grad_norm": 0.9966852068901062,
|
| 214 |
+
"learning_rate": 3.1666666666666666e-05,
|
| 215 |
+
"loss": 0.2889,
|
| 216 |
+
"step": 5500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.1,
|
| 220 |
+
"eval_gen_len": 11.55,
|
| 221 |
+
"eval_loss": 0.4897365868091583,
|
| 222 |
+
"eval_rouge1": 40.1394,
|
| 223 |
+
"eval_rouge2": 14.7595,
|
| 224 |
+
"eval_rougeL": 36.4428,
|
| 225 |
+
"eval_rougeLsum": 36.4696,
|
| 226 |
+
"eval_runtime": 431.6652,
|
| 227 |
+
"eval_samples_per_second": 9.266,
|
| 228 |
+
"eval_steps_per_second": 2.317,
|
| 229 |
+
"step": 5500
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.2,
|
| 233 |
+
"grad_norm": 0.857021152973175,
|
| 234 |
+
"learning_rate": 3e-05,
|
| 235 |
+
"loss": 0.2908,
|
| 236 |
+
"step": 6000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.2,
|
| 240 |
+
"eval_gen_len": 11.98225,
|
| 241 |
+
"eval_loss": 0.48649004101753235,
|
| 242 |
+
"eval_rouge1": 40.0479,
|
| 243 |
+
"eval_rouge2": 14.8181,
|
| 244 |
+
"eval_rougeL": 36.316,
|
| 245 |
+
"eval_rougeLsum": 36.3519,
|
| 246 |
+
"eval_runtime": 438.3532,
|
| 247 |
+
"eval_samples_per_second": 9.125,
|
| 248 |
+
"eval_steps_per_second": 2.281,
|
| 249 |
+
"step": 6000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.3,
|
| 253 |
+
"grad_norm": 0.8857397437095642,
|
| 254 |
+
"learning_rate": 2.8333333333333335e-05,
|
| 255 |
+
"loss": 0.2882,
|
| 256 |
+
"step": 6500
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.3,
|
| 260 |
+
"eval_gen_len": 11.7945,
|
| 261 |
+
"eval_loss": 0.48633432388305664,
|
| 262 |
+
"eval_rouge1": 40.5912,
|
| 263 |
+
"eval_rouge2": 15.3128,
|
| 264 |
+
"eval_rougeL": 36.7638,
|
| 265 |
+
"eval_rougeLsum": 36.7755,
|
| 266 |
+
"eval_runtime": 432.2098,
|
| 267 |
+
"eval_samples_per_second": 9.255,
|
| 268 |
+
"eval_steps_per_second": 2.314,
|
| 269 |
+
"step": 6500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.4,
|
| 273 |
+
"grad_norm": 0.792189359664917,
|
| 274 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 275 |
+
"loss": 0.2901,
|
| 276 |
+
"step": 7000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.4,
|
| 280 |
+
"eval_gen_len": 11.87,
|
| 281 |
+
"eval_loss": 0.48679661750793457,
|
| 282 |
+
"eval_rouge1": 40.3138,
|
| 283 |
+
"eval_rouge2": 14.9695,
|
| 284 |
+
"eval_rougeL": 36.5032,
|
| 285 |
+
"eval_rougeLsum": 36.5211,
|
| 286 |
+
"eval_runtime": 436.9846,
|
| 287 |
+
"eval_samples_per_second": 9.154,
|
| 288 |
+
"eval_steps_per_second": 2.288,
|
| 289 |
+
"step": 7000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.5,
|
| 293 |
+
"grad_norm": 0.8871281147003174,
|
| 294 |
+
"learning_rate": 2.5e-05,
|
| 295 |
+
"loss": 0.2857,
|
| 296 |
+
"step": 7500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.5,
|
| 300 |
+
"eval_gen_len": 11.776,
|
| 301 |
+
"eval_loss": 0.4834408462047577,
|
| 302 |
+
"eval_rouge1": 40.2242,
|
| 303 |
+
"eval_rouge2": 14.9881,
|
| 304 |
+
"eval_rougeL": 36.5381,
|
| 305 |
+
"eval_rougeLsum": 36.5607,
|
| 306 |
+
"eval_runtime": 452.1322,
|
| 307 |
+
"eval_samples_per_second": 8.847,
|
| 308 |
+
"eval_steps_per_second": 2.212,
|
| 309 |
+
"step": 7500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.6,
|
| 313 |
+
"grad_norm": 1.0286399126052856,
|
| 314 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 315 |
+
"loss": 0.279,
|
| 316 |
+
"step": 8000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.6,
|
| 320 |
+
"eval_gen_len": 12.01325,
|
| 321 |
+
"eval_loss": 0.4999020993709564,
|
| 322 |
+
"eval_rouge1": 40.2751,
|
| 323 |
+
"eval_rouge2": 15.0173,
|
| 324 |
+
"eval_rougeL": 36.4172,
|
| 325 |
+
"eval_rougeLsum": 36.4257,
|
| 326 |
+
"eval_runtime": 435.9247,
|
| 327 |
+
"eval_samples_per_second": 9.176,
|
| 328 |
+
"eval_steps_per_second": 2.294,
|
| 329 |
+
"step": 8000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.7,
|
| 333 |
+
"grad_norm": 0.9107884168624878,
|
| 334 |
+
"learning_rate": 2.1666666666666667e-05,
|
| 335 |
+
"loss": 0.281,
|
| 336 |
+
"step": 8500
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.7,
|
| 340 |
+
"eval_gen_len": 11.7685,
|
| 341 |
+
"eval_loss": 0.49508431553840637,
|
| 342 |
+
"eval_rouge1": 40.1172,
|
| 343 |
+
"eval_rouge2": 14.8119,
|
| 344 |
+
"eval_rougeL": 36.2966,
|
| 345 |
+
"eval_rougeLsum": 36.296,
|
| 346 |
+
"eval_runtime": 425.7116,
|
| 347 |
+
"eval_samples_per_second": 9.396,
|
| 348 |
+
"eval_steps_per_second": 2.349,
|
| 349 |
+
"step": 8500
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.8,
|
| 353 |
+
"grad_norm": 0.76063472032547,
|
| 354 |
+
"learning_rate": 2e-05,
|
| 355 |
+
"loss": 0.2831,
|
| 356 |
+
"step": 9000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.8,
|
| 360 |
+
"eval_gen_len": 12.22925,
|
| 361 |
+
"eval_loss": 0.49789097905158997,
|
| 362 |
+
"eval_rouge1": 39.9913,
|
| 363 |
+
"eval_rouge2": 14.7427,
|
| 364 |
+
"eval_rougeL": 36.1539,
|
| 365 |
+
"eval_rougeLsum": 36.1517,
|
| 366 |
+
"eval_runtime": 449.7047,
|
| 367 |
+
"eval_samples_per_second": 8.895,
|
| 368 |
+
"eval_steps_per_second": 2.224,
|
| 369 |
+
"step": 9000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.9,
|
| 373 |
+
"grad_norm": 0.9408590197563171,
|
| 374 |
+
"learning_rate": 1.8333333333333333e-05,
|
| 375 |
+
"loss": 0.2799,
|
| 376 |
+
"step": 9500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.9,
|
| 380 |
+
"eval_gen_len": 11.87175,
|
| 381 |
+
"eval_loss": 0.49114319682121277,
|
| 382 |
+
"eval_rouge1": 40.5123,
|
| 383 |
+
"eval_rouge2": 15.09,
|
| 384 |
+
"eval_rougeL": 36.7528,
|
| 385 |
+
"eval_rougeLsum": 36.7622,
|
| 386 |
+
"eval_runtime": 440.8811,
|
| 387 |
+
"eval_samples_per_second": 9.073,
|
| 388 |
+
"eval_steps_per_second": 2.268,
|
| 389 |
+
"step": 9500
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 2.0,
|
| 393 |
+
"grad_norm": 0.9572837948799133,
|
| 394 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 395 |
+
"loss": 0.2778,
|
| 396 |
+
"step": 10000
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 2.0,
|
| 400 |
+
"eval_gen_len": 12.02625,
|
| 401 |
+
"eval_loss": 0.4928734600543976,
|
| 402 |
+
"eval_rouge1": 40.5005,
|
| 403 |
+
"eval_rouge2": 15.1027,
|
| 404 |
+
"eval_rougeL": 36.6202,
|
| 405 |
+
"eval_rougeLsum": 36.6327,
|
| 406 |
+
"eval_runtime": 443.0336,
|
| 407 |
+
"eval_samples_per_second": 9.029,
|
| 408 |
+
"eval_steps_per_second": 2.257,
|
| 409 |
+
"step": 10000
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.1,
|
| 413 |
+
"grad_norm": 0.9376727938652039,
|
| 414 |
+
"learning_rate": 1.5e-05,
|
| 415 |
+
"loss": 0.2318,
|
| 416 |
+
"step": 10500
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.1,
|
| 420 |
+
"eval_gen_len": 12.133,
|
| 421 |
+
"eval_loss": 0.5237044095993042,
|
| 422 |
+
"eval_rouge1": 40.1565,
|
| 423 |
+
"eval_rouge2": 14.8022,
|
| 424 |
+
"eval_rougeL": 36.1946,
|
| 425 |
+
"eval_rougeLsum": 36.2074,
|
| 426 |
+
"eval_runtime": 434.3272,
|
| 427 |
+
"eval_samples_per_second": 9.21,
|
| 428 |
+
"eval_steps_per_second": 2.302,
|
| 429 |
+
"step": 10500
|
| 430 |
+
}
|
| 431 |
+
],
|
| 432 |
+
"logging_steps": 500,
|
| 433 |
+
"max_steps": 15000,
|
| 434 |
+
"num_input_tokens_seen": 0,
|
| 435 |
+
"num_train_epochs": 3,
|
| 436 |
+
"save_steps": 500,
|
| 437 |
+
"stateful_callbacks": {
|
| 438 |
+
"TrainerControl": {
|
| 439 |
+
"args": {
|
| 440 |
+
"should_epoch_stop": false,
|
| 441 |
+
"should_evaluate": false,
|
| 442 |
+
"should_log": false,
|
| 443 |
+
"should_save": true,
|
| 444 |
+
"should_training_stop": false
|
| 445 |
+
},
|
| 446 |
+
"attributes": {}
|
| 447 |
+
}
|
| 448 |
+
},
|
| 449 |
+
"total_flos": 3.0317933708181504e+19,
|
| 450 |
+
"train_batch_size": 4,
|
| 451 |
+
"trial_name": null,
|
| 452 |
+
"trial_params": null
|
| 453 |
+
}
|
checkpoint-10500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:141af1f39fdd49061532c4290e738a24fce49a19ce9bcc0917258330b2947b48
|
| 3 |
+
size 5304
|