Training in progress, step 15000, checkpoint
Browse files- checkpoint-15000/config.json +186 -0
- checkpoint-15000/generation_config.json +7 -0
- checkpoint-15000/model.safetensors +3 -0
- checkpoint-15000/optimizer.pt +3 -0
- checkpoint-15000/rng_state.pth +3 -0
- checkpoint-15000/scheduler.pt +3 -0
- checkpoint-15000/trainer_state.json +633 -0
- checkpoint-15000/training_args.bin +3 -0
checkpoint-15000/config.json
ADDED
|
@@ -0,0 +1,186 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "NourFakih/Vit-GPT2-COCO2017Flickr-85k-11",
|
| 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-15000/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-15000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7627d90d6a5efa7031bc4aab9d96084fddb30087a935fa0f6e2ea52637e21169
|
| 3 |
+
size 956835520
|
checkpoint-15000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce2b1f2a722383ec920b83444ce8bd60b5ad67ed462925419c3e3cbf736d596d
|
| 3 |
+
size 1909212608
|
checkpoint-15000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cca53a473deb41d39165ee21109663d87707cf6442bf015b8c86f0064ef665d9
|
| 3 |
+
size 14244
|
checkpoint-15000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a945cd1933910dcf46938a69d9bf1cc2194a1010df5e597070b7b60a897baa70
|
| 3 |
+
size 1064
|
checkpoint-15000/trainer_state.json
ADDED
|
@@ -0,0 +1,633 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.4608415365219116,
|
| 3 |
+
"best_model_checkpoint": "./Vit-GPT2-COCO2017Flickr-85k-11/checkpoint-4500",
|
| 4 |
+
"epoch": 2.799477465708687,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 15000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.09330969487729775,
|
| 13 |
+
"grad_norm": 1.14389169216156,
|
| 14 |
+
"learning_rate": 4.8444693293517484e-05,
|
| 15 |
+
"loss": 0.378,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.09330969487729775,
|
| 20 |
+
"eval_gen_len": 11.7725,
|
| 21 |
+
"eval_loss": 0.469292551279068,
|
| 22 |
+
"eval_rouge1": 40.2274,
|
| 23 |
+
"eval_rouge2": 15.0119,
|
| 24 |
+
"eval_rougeL": 36.4563,
|
| 25 |
+
"eval_rougeLsum": 36.4656,
|
| 26 |
+
"eval_runtime": 450.3853,
|
| 27 |
+
"eval_samples_per_second": 8.881,
|
| 28 |
+
"eval_steps_per_second": 2.22,
|
| 29 |
+
"step": 500
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.1866193897545955,
|
| 33 |
+
"grad_norm": 0.8436835408210754,
|
| 34 |
+
"learning_rate": 4.6889386587034965e-05,
|
| 35 |
+
"loss": 0.3748,
|
| 36 |
+
"step": 1000
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.1866193897545955,
|
| 40 |
+
"eval_gen_len": 12.16675,
|
| 41 |
+
"eval_loss": 0.46400758624076843,
|
| 42 |
+
"eval_rouge1": 40.199,
|
| 43 |
+
"eval_rouge2": 15.321,
|
| 44 |
+
"eval_rougeL": 36.4279,
|
| 45 |
+
"eval_rougeLsum": 36.4457,
|
| 46 |
+
"eval_runtime": 431.1423,
|
| 47 |
+
"eval_samples_per_second": 9.278,
|
| 48 |
+
"eval_steps_per_second": 2.319,
|
| 49 |
+
"step": 1000
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.27992908463189325,
|
| 53 |
+
"grad_norm": 0.8730084896087646,
|
| 54 |
+
"learning_rate": 4.5334079880552446e-05,
|
| 55 |
+
"loss": 0.374,
|
| 56 |
+
"step": 1500
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.27992908463189325,
|
| 60 |
+
"eval_gen_len": 11.8,
|
| 61 |
+
"eval_loss": 0.4668748080730438,
|
| 62 |
+
"eval_rouge1": 39.9523,
|
| 63 |
+
"eval_rouge2": 15.0587,
|
| 64 |
+
"eval_rougeL": 36.3639,
|
| 65 |
+
"eval_rougeLsum": 36.375,
|
| 66 |
+
"eval_runtime": 424.8986,
|
| 67 |
+
"eval_samples_per_second": 9.414,
|
| 68 |
+
"eval_steps_per_second": 2.354,
|
| 69 |
+
"step": 1500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.373238779509191,
|
| 73 |
+
"grad_norm": 0.8020262718200684,
|
| 74 |
+
"learning_rate": 4.3778773174069934e-05,
|
| 75 |
+
"loss": 0.3721,
|
| 76 |
+
"step": 2000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.373238779509191,
|
| 80 |
+
"eval_gen_len": 11.2095,
|
| 81 |
+
"eval_loss": 0.46446970105171204,
|
| 82 |
+
"eval_rouge1": 40.3597,
|
| 83 |
+
"eval_rouge2": 15.2173,
|
| 84 |
+
"eval_rougeL": 36.6938,
|
| 85 |
+
"eval_rougeLsum": 36.705,
|
| 86 |
+
"eval_runtime": 410.7504,
|
| 87 |
+
"eval_samples_per_second": 9.738,
|
| 88 |
+
"eval_steps_per_second": 2.435,
|
| 89 |
+
"step": 2000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.4665484743864888,
|
| 93 |
+
"grad_norm": 0.8208432793617249,
|
| 94 |
+
"learning_rate": 4.222346646758741e-05,
|
| 95 |
+
"loss": 0.3673,
|
| 96 |
+
"step": 2500
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.4665484743864888,
|
| 100 |
+
"eval_gen_len": 11.93425,
|
| 101 |
+
"eval_loss": 0.4631750285625458,
|
| 102 |
+
"eval_rouge1": 40.3875,
|
| 103 |
+
"eval_rouge2": 15.2532,
|
| 104 |
+
"eval_rougeL": 36.5923,
|
| 105 |
+
"eval_rougeLsum": 36.6182,
|
| 106 |
+
"eval_runtime": 441.242,
|
| 107 |
+
"eval_samples_per_second": 9.065,
|
| 108 |
+
"eval_steps_per_second": 2.266,
|
| 109 |
+
"step": 2500
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.5598581692637865,
|
| 113 |
+
"grad_norm": 0.807547926902771,
|
| 114 |
+
"learning_rate": 4.066815976110489e-05,
|
| 115 |
+
"loss": 0.365,
|
| 116 |
+
"step": 3000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.5598581692637865,
|
| 120 |
+
"eval_gen_len": 12.26475,
|
| 121 |
+
"eval_loss": 0.4623391330242157,
|
| 122 |
+
"eval_rouge1": 39.9395,
|
| 123 |
+
"eval_rouge2": 15.0315,
|
| 124 |
+
"eval_rougeL": 36.1682,
|
| 125 |
+
"eval_rougeLsum": 36.1781,
|
| 126 |
+
"eval_runtime": 440.5083,
|
| 127 |
+
"eval_samples_per_second": 9.08,
|
| 128 |
+
"eval_steps_per_second": 2.27,
|
| 129 |
+
"step": 3000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.6531678641410843,
|
| 133 |
+
"grad_norm": 0.6434993147850037,
|
| 134 |
+
"learning_rate": 3.911285305462237e-05,
|
| 135 |
+
"loss": 0.3652,
|
| 136 |
+
"step": 3500
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.6531678641410843,
|
| 140 |
+
"eval_gen_len": 11.8965,
|
| 141 |
+
"eval_loss": 0.4611285328865051,
|
| 142 |
+
"eval_rouge1": 39.8792,
|
| 143 |
+
"eval_rouge2": 14.9961,
|
| 144 |
+
"eval_rougeL": 36.2488,
|
| 145 |
+
"eval_rougeLsum": 36.2734,
|
| 146 |
+
"eval_runtime": 429.9024,
|
| 147 |
+
"eval_samples_per_second": 9.304,
|
| 148 |
+
"eval_steps_per_second": 2.326,
|
| 149 |
+
"step": 3500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.746477559018382,
|
| 153 |
+
"grad_norm": 0.8740318417549133,
|
| 154 |
+
"learning_rate": 3.755754634813985e-05,
|
| 155 |
+
"loss": 0.3601,
|
| 156 |
+
"step": 4000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.746477559018382,
|
| 160 |
+
"eval_gen_len": 12.0545,
|
| 161 |
+
"eval_loss": 0.4625248610973358,
|
| 162 |
+
"eval_rouge1": 40.57,
|
| 163 |
+
"eval_rouge2": 15.2972,
|
| 164 |
+
"eval_rougeL": 36.8012,
|
| 165 |
+
"eval_rougeLsum": 36.8227,
|
| 166 |
+
"eval_runtime": 431.0422,
|
| 167 |
+
"eval_samples_per_second": 9.28,
|
| 168 |
+
"eval_steps_per_second": 2.32,
|
| 169 |
+
"step": 4000
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.8397872538956798,
|
| 173 |
+
"grad_norm": 0.7394187450408936,
|
| 174 |
+
"learning_rate": 3.600223964165734e-05,
|
| 175 |
+
"loss": 0.3574,
|
| 176 |
+
"step": 4500
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.8397872538956798,
|
| 180 |
+
"eval_gen_len": 11.72875,
|
| 181 |
+
"eval_loss": 0.4608415365219116,
|
| 182 |
+
"eval_rouge1": 40.3276,
|
| 183 |
+
"eval_rouge2": 15.1742,
|
| 184 |
+
"eval_rougeL": 36.7679,
|
| 185 |
+
"eval_rougeLsum": 36.7575,
|
| 186 |
+
"eval_runtime": 467.6774,
|
| 187 |
+
"eval_samples_per_second": 8.553,
|
| 188 |
+
"eval_steps_per_second": 2.138,
|
| 189 |
+
"step": 4500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.9330969487729776,
|
| 193 |
+
"grad_norm": 0.841187059879303,
|
| 194 |
+
"learning_rate": 3.444693293517482e-05,
|
| 195 |
+
"loss": 0.351,
|
| 196 |
+
"step": 5000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.9330969487729776,
|
| 200 |
+
"eval_gen_len": 11.76625,
|
| 201 |
+
"eval_loss": 0.4650140404701233,
|
| 202 |
+
"eval_rouge1": 40.7345,
|
| 203 |
+
"eval_rouge2": 15.5295,
|
| 204 |
+
"eval_rougeL": 37.0769,
|
| 205 |
+
"eval_rougeLsum": 37.0911,
|
| 206 |
+
"eval_runtime": 475.4278,
|
| 207 |
+
"eval_samples_per_second": 8.413,
|
| 208 |
+
"eval_steps_per_second": 2.103,
|
| 209 |
+
"step": 5000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.0264066436502752,
|
| 213 |
+
"grad_norm": 0.8910800814628601,
|
| 214 |
+
"learning_rate": 3.28916262286923e-05,
|
| 215 |
+
"loss": 0.3322,
|
| 216 |
+
"step": 5500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.0264066436502752,
|
| 220 |
+
"eval_gen_len": 12.06,
|
| 221 |
+
"eval_loss": 0.48306143283843994,
|
| 222 |
+
"eval_rouge1": 40.5582,
|
| 223 |
+
"eval_rouge2": 15.2954,
|
| 224 |
+
"eval_rougeL": 36.6682,
|
| 225 |
+
"eval_rougeLsum": 36.6694,
|
| 226 |
+
"eval_runtime": 444.1346,
|
| 227 |
+
"eval_samples_per_second": 9.006,
|
| 228 |
+
"eval_steps_per_second": 2.252,
|
| 229 |
+
"step": 5500
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.119716338527573,
|
| 233 |
+
"grad_norm": 0.9060000777244568,
|
| 234 |
+
"learning_rate": 3.1336319522209783e-05,
|
| 235 |
+
"loss": 0.2914,
|
| 236 |
+
"step": 6000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.119716338527573,
|
| 240 |
+
"eval_gen_len": 11.8405,
|
| 241 |
+
"eval_loss": 0.4901696741580963,
|
| 242 |
+
"eval_rouge1": 40.054,
|
| 243 |
+
"eval_rouge2": 15.019,
|
| 244 |
+
"eval_rougeL": 36.5476,
|
| 245 |
+
"eval_rougeLsum": 36.556,
|
| 246 |
+
"eval_runtime": 432.4768,
|
| 247 |
+
"eval_samples_per_second": 9.249,
|
| 248 |
+
"eval_steps_per_second": 2.312,
|
| 249 |
+
"step": 6000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.2130260334048708,
|
| 253 |
+
"grad_norm": 0.9239944219589233,
|
| 254 |
+
"learning_rate": 2.978101281572726e-05,
|
| 255 |
+
"loss": 0.2945,
|
| 256 |
+
"step": 6500
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.2130260334048708,
|
| 260 |
+
"eval_gen_len": 11.84225,
|
| 261 |
+
"eval_loss": 0.48632147908210754,
|
| 262 |
+
"eval_rouge1": 40.3126,
|
| 263 |
+
"eval_rouge2": 15.3154,
|
| 264 |
+
"eval_rougeL": 36.61,
|
| 265 |
+
"eval_rougeLsum": 36.6146,
|
| 266 |
+
"eval_runtime": 433.2065,
|
| 267 |
+
"eval_samples_per_second": 9.233,
|
| 268 |
+
"eval_steps_per_second": 2.308,
|
| 269 |
+
"step": 6500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.3063357282821686,
|
| 273 |
+
"grad_norm": 0.9310933351516724,
|
| 274 |
+
"learning_rate": 2.8225706109244742e-05,
|
| 275 |
+
"loss": 0.2845,
|
| 276 |
+
"step": 7000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.3063357282821686,
|
| 280 |
+
"eval_gen_len": 12.0445,
|
| 281 |
+
"eval_loss": 0.48827481269836426,
|
| 282 |
+
"eval_rouge1": 40.228,
|
| 283 |
+
"eval_rouge2": 15.0904,
|
| 284 |
+
"eval_rougeL": 36.3179,
|
| 285 |
+
"eval_rougeLsum": 36.3086,
|
| 286 |
+
"eval_runtime": 445.7913,
|
| 287 |
+
"eval_samples_per_second": 8.973,
|
| 288 |
+
"eval_steps_per_second": 2.243,
|
| 289 |
+
"step": 7000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.3996454231594662,
|
| 293 |
+
"grad_norm": 0.8383007645606995,
|
| 294 |
+
"learning_rate": 2.6670399402762224e-05,
|
| 295 |
+
"loss": 0.2879,
|
| 296 |
+
"step": 7500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.3996454231594662,
|
| 300 |
+
"eval_gen_len": 11.93575,
|
| 301 |
+
"eval_loss": 0.4833485782146454,
|
| 302 |
+
"eval_rouge1": 40.6501,
|
| 303 |
+
"eval_rouge2": 15.5682,
|
| 304 |
+
"eval_rougeL": 36.8945,
|
| 305 |
+
"eval_rougeLsum": 36.8823,
|
| 306 |
+
"eval_runtime": 438.3851,
|
| 307 |
+
"eval_samples_per_second": 9.124,
|
| 308 |
+
"eval_steps_per_second": 2.281,
|
| 309 |
+
"step": 7500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.492955118036764,
|
| 313 |
+
"grad_norm": 0.8517706990242004,
|
| 314 |
+
"learning_rate": 2.5115092696279708e-05,
|
| 315 |
+
"loss": 0.2859,
|
| 316 |
+
"step": 8000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.492955118036764,
|
| 320 |
+
"eval_gen_len": 12.17425,
|
| 321 |
+
"eval_loss": 0.4833007752895355,
|
| 322 |
+
"eval_rouge1": 40.3187,
|
| 323 |
+
"eval_rouge2": 15.0418,
|
| 324 |
+
"eval_rougeL": 36.3561,
|
| 325 |
+
"eval_rougeLsum": 36.3582,
|
| 326 |
+
"eval_runtime": 441.1227,
|
| 327 |
+
"eval_samples_per_second": 9.068,
|
| 328 |
+
"eval_steps_per_second": 2.267,
|
| 329 |
+
"step": 8000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.5862648129140617,
|
| 333 |
+
"grad_norm": 0.951680064201355,
|
| 334 |
+
"learning_rate": 2.355978598979719e-05,
|
| 335 |
+
"loss": 0.2844,
|
| 336 |
+
"step": 8500
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.5862648129140617,
|
| 340 |
+
"eval_gen_len": 12.17025,
|
| 341 |
+
"eval_loss": 0.48842066526412964,
|
| 342 |
+
"eval_rouge1": 40.2896,
|
| 343 |
+
"eval_rouge2": 15.1032,
|
| 344 |
+
"eval_rougeL": 36.4039,
|
| 345 |
+
"eval_rougeLsum": 36.3862,
|
| 346 |
+
"eval_runtime": 458.4907,
|
| 347 |
+
"eval_samples_per_second": 8.724,
|
| 348 |
+
"eval_steps_per_second": 2.181,
|
| 349 |
+
"step": 8500
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.6795745077913595,
|
| 353 |
+
"grad_norm": 0.6958986520767212,
|
| 354 |
+
"learning_rate": 2.200447928331467e-05,
|
| 355 |
+
"loss": 0.2838,
|
| 356 |
+
"step": 9000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.6795745077913595,
|
| 360 |
+
"eval_gen_len": 11.95875,
|
| 361 |
+
"eval_loss": 0.49017783999443054,
|
| 362 |
+
"eval_rouge1": 40.3419,
|
| 363 |
+
"eval_rouge2": 15.1863,
|
| 364 |
+
"eval_rougeL": 36.4631,
|
| 365 |
+
"eval_rougeLsum": 36.4728,
|
| 366 |
+
"eval_runtime": 462.8508,
|
| 367 |
+
"eval_samples_per_second": 8.642,
|
| 368 |
+
"eval_steps_per_second": 2.161,
|
| 369 |
+
"step": 9000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.7728842026686573,
|
| 373 |
+
"grad_norm": 0.876482367515564,
|
| 374 |
+
"learning_rate": 2.0449172576832152e-05,
|
| 375 |
+
"loss": 0.2789,
|
| 376 |
+
"step": 9500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.7728842026686573,
|
| 380 |
+
"eval_gen_len": 12.05675,
|
| 381 |
+
"eval_loss": 0.48646843433380127,
|
| 382 |
+
"eval_rouge1": 40.6284,
|
| 383 |
+
"eval_rouge2": 15.3404,
|
| 384 |
+
"eval_rougeL": 36.7035,
|
| 385 |
+
"eval_rougeLsum": 36.6876,
|
| 386 |
+
"eval_runtime": 447.3126,
|
| 387 |
+
"eval_samples_per_second": 8.942,
|
| 388 |
+
"eval_steps_per_second": 2.236,
|
| 389 |
+
"step": 9500
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.8661938975459549,
|
| 393 |
+
"grad_norm": 0.8670400381088257,
|
| 394 |
+
"learning_rate": 1.8893865870349633e-05,
|
| 395 |
+
"loss": 0.2758,
|
| 396 |
+
"step": 10000
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.8661938975459549,
|
| 400 |
+
"eval_gen_len": 11.823,
|
| 401 |
+
"eval_loss": 0.49086475372314453,
|
| 402 |
+
"eval_rouge1": 40.1138,
|
| 403 |
+
"eval_rouge2": 14.9247,
|
| 404 |
+
"eval_rougeL": 36.4884,
|
| 405 |
+
"eval_rougeLsum": 36.4836,
|
| 406 |
+
"eval_runtime": 445.2778,
|
| 407 |
+
"eval_samples_per_second": 8.983,
|
| 408 |
+
"eval_steps_per_second": 2.246,
|
| 409 |
+
"step": 10000
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.959503592423253,
|
| 413 |
+
"grad_norm": 0.92488694190979,
|
| 414 |
+
"learning_rate": 1.7338559163867114e-05,
|
| 415 |
+
"loss": 0.2741,
|
| 416 |
+
"step": 10500
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.959503592423253,
|
| 420 |
+
"eval_gen_len": 11.95375,
|
| 421 |
+
"eval_loss": 0.4892323315143585,
|
| 422 |
+
"eval_rouge1": 40.3204,
|
| 423 |
+
"eval_rouge2": 14.9594,
|
| 424 |
+
"eval_rougeL": 36.539,
|
| 425 |
+
"eval_rougeLsum": 36.5311,
|
| 426 |
+
"eval_runtime": 454.063,
|
| 427 |
+
"eval_samples_per_second": 8.809,
|
| 428 |
+
"eval_steps_per_second": 2.202,
|
| 429 |
+
"step": 10500
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.052906596995428,
|
| 433 |
+
"grad_norm": 0.8728746771812439,
|
| 434 |
+
"learning_rate": 1.57832524573846e-05,
|
| 435 |
+
"loss": 0.253,
|
| 436 |
+
"step": 11000
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 2.052906596995428,
|
| 440 |
+
"eval_gen_len": 11.97125,
|
| 441 |
+
"eval_loss": 0.5200562477111816,
|
| 442 |
+
"eval_rouge1": 40.0224,
|
| 443 |
+
"eval_rouge2": 14.9662,
|
| 444 |
+
"eval_rougeL": 36.3433,
|
| 445 |
+
"eval_rougeLsum": 36.3705,
|
| 446 |
+
"eval_runtime": 455.8555,
|
| 447 |
+
"eval_samples_per_second": 8.775,
|
| 448 |
+
"eval_steps_per_second": 2.194,
|
| 449 |
+
"step": 11000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 2.1462162918727254,
|
| 453 |
+
"grad_norm": 0.900993287563324,
|
| 454 |
+
"learning_rate": 1.4227945750902078e-05,
|
| 455 |
+
"loss": 0.2261,
|
| 456 |
+
"step": 11500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 2.1462162918727254,
|
| 460 |
+
"eval_gen_len": 11.89175,
|
| 461 |
+
"eval_loss": 0.5247754454612732,
|
| 462 |
+
"eval_rouge1": 39.698,
|
| 463 |
+
"eval_rouge2": 14.3092,
|
| 464 |
+
"eval_rougeL": 35.9144,
|
| 465 |
+
"eval_rougeLsum": 35.9107,
|
| 466 |
+
"eval_runtime": 441.6478,
|
| 467 |
+
"eval_samples_per_second": 9.057,
|
| 468 |
+
"eval_steps_per_second": 2.264,
|
| 469 |
+
"step": 11500
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 2.2395259867500235,
|
| 473 |
+
"grad_norm": 0.9417188763618469,
|
| 474 |
+
"learning_rate": 1.267263904441956e-05,
|
| 475 |
+
"loss": 0.2245,
|
| 476 |
+
"step": 12000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.2395259867500235,
|
| 480 |
+
"eval_gen_len": 12.02525,
|
| 481 |
+
"eval_loss": 0.5204368233680725,
|
| 482 |
+
"eval_rouge1": 40.136,
|
| 483 |
+
"eval_rouge2": 14.8487,
|
| 484 |
+
"eval_rougeL": 36.4154,
|
| 485 |
+
"eval_rougeLsum": 36.3989,
|
| 486 |
+
"eval_runtime": 444.7649,
|
| 487 |
+
"eval_samples_per_second": 8.994,
|
| 488 |
+
"eval_steps_per_second": 2.248,
|
| 489 |
+
"step": 12000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.332835681627321,
|
| 493 |
+
"grad_norm": 0.8910666704177856,
|
| 494 |
+
"learning_rate": 1.1117332337937042e-05,
|
| 495 |
+
"loss": 0.2293,
|
| 496 |
+
"step": 12500
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 2.332835681627321,
|
| 500 |
+
"eval_gen_len": 11.86225,
|
| 501 |
+
"eval_loss": 0.526066243648529,
|
| 502 |
+
"eval_rouge1": 39.9269,
|
| 503 |
+
"eval_rouge2": 14.6665,
|
| 504 |
+
"eval_rougeL": 36.2594,
|
| 505 |
+
"eval_rougeLsum": 36.2517,
|
| 506 |
+
"eval_runtime": 441.3755,
|
| 507 |
+
"eval_samples_per_second": 9.063,
|
| 508 |
+
"eval_steps_per_second": 2.266,
|
| 509 |
+
"step": 12500
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 2.4261453765046186,
|
| 513 |
+
"grad_norm": 1.0765278339385986,
|
| 514 |
+
"learning_rate": 9.562025631454523e-06,
|
| 515 |
+
"loss": 0.2255,
|
| 516 |
+
"step": 13000
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 2.4261453765046186,
|
| 520 |
+
"eval_gen_len": 11.9165,
|
| 521 |
+
"eval_loss": 0.5216917991638184,
|
| 522 |
+
"eval_rouge1": 40.1403,
|
| 523 |
+
"eval_rouge2": 14.7327,
|
| 524 |
+
"eval_rougeL": 36.4161,
|
| 525 |
+
"eval_rougeLsum": 36.4139,
|
| 526 |
+
"eval_runtime": 438.6494,
|
| 527 |
+
"eval_samples_per_second": 9.119,
|
| 528 |
+
"eval_steps_per_second": 2.28,
|
| 529 |
+
"step": 13000
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.5194550713819166,
|
| 533 |
+
"grad_norm": 0.8093633651733398,
|
| 534 |
+
"learning_rate": 8.006718924972005e-06,
|
| 535 |
+
"loss": 0.228,
|
| 536 |
+
"step": 13500
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.5194550713819166,
|
| 540 |
+
"eval_gen_len": 11.94775,
|
| 541 |
+
"eval_loss": 0.5267027020454407,
|
| 542 |
+
"eval_rouge1": 39.7979,
|
| 543 |
+
"eval_rouge2": 14.4362,
|
| 544 |
+
"eval_rougeL": 36.0457,
|
| 545 |
+
"eval_rougeLsum": 36.0611,
|
| 546 |
+
"eval_runtime": 453.3166,
|
| 547 |
+
"eval_samples_per_second": 8.824,
|
| 548 |
+
"eval_steps_per_second": 2.206,
|
| 549 |
+
"step": 13500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.612764766259214,
|
| 553 |
+
"grad_norm": 1.1676660776138306,
|
| 554 |
+
"learning_rate": 6.451412218489486e-06,
|
| 555 |
+
"loss": 0.2233,
|
| 556 |
+
"step": 14000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 2.612764766259214,
|
| 560 |
+
"eval_gen_len": 12.0495,
|
| 561 |
+
"eval_loss": 0.5299362540245056,
|
| 562 |
+
"eval_rouge1": 39.8343,
|
| 563 |
+
"eval_rouge2": 14.4579,
|
| 564 |
+
"eval_rougeL": 36.0728,
|
| 565 |
+
"eval_rougeLsum": 36.0824,
|
| 566 |
+
"eval_runtime": 435.3299,
|
| 567 |
+
"eval_samples_per_second": 9.188,
|
| 568 |
+
"eval_steps_per_second": 2.297,
|
| 569 |
+
"step": 14000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.7061677708313896,
|
| 573 |
+
"grad_norm": 1.0289031267166138,
|
| 574 |
+
"learning_rate": 4.896105512006968e-06,
|
| 575 |
+
"loss": 0.2239,
|
| 576 |
+
"step": 14500
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.7061677708313896,
|
| 580 |
+
"eval_gen_len": 12.13075,
|
| 581 |
+
"eval_loss": 0.527421236038208,
|
| 582 |
+
"eval_rouge1": 39.9561,
|
| 583 |
+
"eval_rouge2": 14.5286,
|
| 584 |
+
"eval_rougeL": 36.1101,
|
| 585 |
+
"eval_rougeLsum": 36.1017,
|
| 586 |
+
"eval_runtime": 477.477,
|
| 587 |
+
"eval_samples_per_second": 8.377,
|
| 588 |
+
"eval_steps_per_second": 2.094,
|
| 589 |
+
"step": 14500
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 2.799477465708687,
|
| 593 |
+
"grad_norm": 0.9075950384140015,
|
| 594 |
+
"learning_rate": 3.34079880552445e-06,
|
| 595 |
+
"loss": 0.2254,
|
| 596 |
+
"step": 15000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 2.799477465708687,
|
| 600 |
+
"eval_gen_len": 12.0845,
|
| 601 |
+
"eval_loss": 0.5292052030563354,
|
| 602 |
+
"eval_rouge1": 39.9252,
|
| 603 |
+
"eval_rouge2": 14.5215,
|
| 604 |
+
"eval_rougeL": 36.1396,
|
| 605 |
+
"eval_rougeLsum": 36.1203,
|
| 606 |
+
"eval_runtime": 442.8833,
|
| 607 |
+
"eval_samples_per_second": 9.032,
|
| 608 |
+
"eval_steps_per_second": 2.258,
|
| 609 |
+
"step": 15000
|
| 610 |
+
}
|
| 611 |
+
],
|
| 612 |
+
"logging_steps": 500,
|
| 613 |
+
"max_steps": 16074,
|
| 614 |
+
"num_input_tokens_seen": 0,
|
| 615 |
+
"num_train_epochs": 3,
|
| 616 |
+
"save_steps": 500,
|
| 617 |
+
"stateful_callbacks": {
|
| 618 |
+
"TrainerControl": {
|
| 619 |
+
"args": {
|
| 620 |
+
"should_epoch_stop": false,
|
| 621 |
+
"should_evaluate": false,
|
| 622 |
+
"should_log": false,
|
| 623 |
+
"should_save": true,
|
| 624 |
+
"should_training_stop": false
|
| 625 |
+
},
|
| 626 |
+
"attributes": {}
|
| 627 |
+
}
|
| 628 |
+
},
|
| 629 |
+
"total_flos": 4.331061201326624e+19,
|
| 630 |
+
"train_batch_size": 4,
|
| 631 |
+
"trial_name": null,
|
| 632 |
+
"trial_params": null
|
| 633 |
+
}
|
checkpoint-15000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1807c3e93ef9af426942bcfd1f83debe8738c01fb3cf84f5470c70bdb8900eb
|
| 3 |
+
size 5304
|