Commit
•
e398b96
1
Parent(s):
7785526
Training in progress, step 290, checkpoint
Browse files
last-checkpoint/config.json
ADDED
|
@@ -0,0 +1,167 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "clip_roberta",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"VisionTextDualEncoderModel"
|
| 5 |
+
],
|
| 6 |
+
"device": "auto",
|
| 7 |
+
"logit_scale_init_value": 2.6592,
|
| 8 |
+
"model_type": "vision-text-dual-encoder",
|
| 9 |
+
"projection_dim": 512,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "allenai/biomed_roberta_base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": null,
|
| 14 |
+
"attention_probs_dropout_prob": 0.1,
|
| 15 |
+
"bad_words_ids": null,
|
| 16 |
+
"begin_suppress_tokens": null,
|
| 17 |
+
"bos_token_id": 0,
|
| 18 |
+
"chunk_size_feed_forward": 0,
|
| 19 |
+
"classifier_dropout": null,
|
| 20 |
+
"cross_attention_hidden_size": null,
|
| 21 |
+
"decoder_start_token_id": null,
|
| 22 |
+
"diversity_penalty": 0.0,
|
| 23 |
+
"do_sample": false,
|
| 24 |
+
"early_stopping": false,
|
| 25 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"exponential_decay_length_penalty": null,
|
| 28 |
+
"finetuning_task": null,
|
| 29 |
+
"forced_bos_token_id": null,
|
| 30 |
+
"forced_eos_token_id": null,
|
| 31 |
+
"hidden_act": "gelu",
|
| 32 |
+
"hidden_dropout_prob": 0.1,
|
| 33 |
+
"hidden_size": 768,
|
| 34 |
+
"id2label": {
|
| 35 |
+
"0": "LABEL_0",
|
| 36 |
+
"1": "LABEL_1"
|
| 37 |
+
},
|
| 38 |
+
"initializer_range": 0.02,
|
| 39 |
+
"intermediate_size": 3072,
|
| 40 |
+
"is_decoder": false,
|
| 41 |
+
"is_encoder_decoder": false,
|
| 42 |
+
"label2id": {
|
| 43 |
+
"LABEL_0": 0,
|
| 44 |
+
"LABEL_1": 1
|
| 45 |
+
},
|
| 46 |
+
"layer_norm_eps": 1e-05,
|
| 47 |
+
"length_penalty": 1.0,
|
| 48 |
+
"max_length": 20,
|
| 49 |
+
"max_position_embeddings": 514,
|
| 50 |
+
"min_length": 0,
|
| 51 |
+
"model_type": "roberta",
|
| 52 |
+
"no_repeat_ngram_size": 0,
|
| 53 |
+
"num_attention_heads": 12,
|
| 54 |
+
"num_beam_groups": 1,
|
| 55 |
+
"num_beams": 1,
|
| 56 |
+
"num_hidden_layers": 12,
|
| 57 |
+
"num_return_sequences": 1,
|
| 58 |
+
"output_attentions": false,
|
| 59 |
+
"output_hidden_states": false,
|
| 60 |
+
"output_scores": false,
|
| 61 |
+
"pad_token_id": 1,
|
| 62 |
+
"position_embedding_type": "absolute",
|
| 63 |
+
"prefix": null,
|
| 64 |
+
"problem_type": null,
|
| 65 |
+
"pruned_heads": {},
|
| 66 |
+
"remove_invalid_values": false,
|
| 67 |
+
"repetition_penalty": 1.0,
|
| 68 |
+
"return_dict": true,
|
| 69 |
+
"return_dict_in_generate": false,
|
| 70 |
+
"sep_token_id": null,
|
| 71 |
+
"suppress_tokens": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"type_vocab_size": 1,
|
| 83 |
+
"typical_p": 1.0,
|
| 84 |
+
"use_bfloat16": false,
|
| 85 |
+
"use_cache": true,
|
| 86 |
+
"vocab_size": 50265
|
| 87 |
+
},
|
| 88 |
+
"torch_dtype": "float32",
|
| 89 |
+
"transformers_version": "4.41.2",
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "openai/clip-vit-large-patch14-336",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"begin_suppress_tokens": null,
|
| 97 |
+
"bos_token_id": null,
|
| 98 |
+
"chunk_size_feed_forward": 0,
|
| 99 |
+
"cross_attention_hidden_size": null,
|
| 100 |
+
"decoder_start_token_id": null,
|
| 101 |
+
"diversity_penalty": 0.0,
|
| 102 |
+
"do_sample": false,
|
| 103 |
+
"dropout": 0.0,
|
| 104 |
+
"early_stopping": false,
|
| 105 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 106 |
+
"eos_token_id": null,
|
| 107 |
+
"exponential_decay_length_penalty": null,
|
| 108 |
+
"finetuning_task": null,
|
| 109 |
+
"forced_bos_token_id": null,
|
| 110 |
+
"forced_eos_token_id": null,
|
| 111 |
+
"hidden_act": "quick_gelu",
|
| 112 |
+
"hidden_size": 1024,
|
| 113 |
+
"id2label": {
|
| 114 |
+
"0": "LABEL_0",
|
| 115 |
+
"1": "LABEL_1"
|
| 116 |
+
},
|
| 117 |
+
"image_size": 336,
|
| 118 |
+
"initializer_factor": 1.0,
|
| 119 |
+
"initializer_range": 0.02,
|
| 120 |
+
"intermediate_size": 4096,
|
| 121 |
+
"is_decoder": false,
|
| 122 |
+
"is_encoder_decoder": false,
|
| 123 |
+
"label2id": {
|
| 124 |
+
"LABEL_0": 0,
|
| 125 |
+
"LABEL_1": 1
|
| 126 |
+
},
|
| 127 |
+
"layer_norm_eps": 1e-05,
|
| 128 |
+
"length_penalty": 1.0,
|
| 129 |
+
"max_length": 20,
|
| 130 |
+
"min_length": 0,
|
| 131 |
+
"model_type": "clip_vision_model",
|
| 132 |
+
"no_repeat_ngram_size": 0,
|
| 133 |
+
"num_attention_heads": 16,
|
| 134 |
+
"num_beam_groups": 1,
|
| 135 |
+
"num_beams": 1,
|
| 136 |
+
"num_channels": 3,
|
| 137 |
+
"num_hidden_layers": 24,
|
| 138 |
+
"num_return_sequences": 1,
|
| 139 |
+
"output_attentions": false,
|
| 140 |
+
"output_hidden_states": false,
|
| 141 |
+
"output_scores": false,
|
| 142 |
+
"pad_token_id": null,
|
| 143 |
+
"patch_size": 14,
|
| 144 |
+
"prefix": null,
|
| 145 |
+
"problem_type": null,
|
| 146 |
+
"projection_dim": 768,
|
| 147 |
+
"pruned_heads": {},
|
| 148 |
+
"remove_invalid_values": false,
|
| 149 |
+
"repetition_penalty": 1.0,
|
| 150 |
+
"return_dict": true,
|
| 151 |
+
"return_dict_in_generate": false,
|
| 152 |
+
"sep_token_id": null,
|
| 153 |
+
"suppress_tokens": null,
|
| 154 |
+
"task_specific_params": null,
|
| 155 |
+
"temperature": 1.0,
|
| 156 |
+
"tf_legacy_loss": false,
|
| 157 |
+
"tie_encoder_decoder": false,
|
| 158 |
+
"tie_word_embeddings": true,
|
| 159 |
+
"tokenizer_class": null,
|
| 160 |
+
"top_k": 50,
|
| 161 |
+
"top_p": 1.0,
|
| 162 |
+
"torch_dtype": null,
|
| 163 |
+
"torchscript": false,
|
| 164 |
+
"typical_p": 1.0,
|
| 165 |
+
"use_bfloat16": false
|
| 166 |
+
}
|
| 167 |
+
}
|
last-checkpoint/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75ba32a6a980d07cca836962a5fdd17f6b6926777b18d34c5af86618a9be1738
|
| 3 |
+
size 1716360444
|
last-checkpoint/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95f4b568a69abb8f6c5da393b3f78e170d1894ce16ad50e775e979dce8c4e4fa
|
| 3 |
+
size 3433062021
|
last-checkpoint/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e02233346cbcb946b752897f87023e9d403d991c1b309b3efa1ba885df37f89
|
| 3 |
+
size 14244
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86350fdae01589a1549fc93951b29457c1b24a63cda252c3ce14d2834db690d3
|
| 3 |
+
size 1064
|
last-checkpoint/trainer_state.json
ADDED
|
@@ -0,0 +1,252 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.03546532958297664,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 290,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0012229423994129876,
|
| 13 |
+
"grad_norm": 8.550562858581543,
|
| 14 |
+
"learning_rate": 4.9999998154440774e-05,
|
| 15 |
+
"loss": 1.4167,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.002445884798825975,
|
| 20 |
+
"grad_norm": 0.5481640100479126,
|
| 21 |
+
"learning_rate": 4.999998338996858e-05,
|
| 22 |
+
"loss": 1.3926,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.003668827198238963,
|
| 27 |
+
"grad_norm": 0.5930708050727844,
|
| 28 |
+
"learning_rate": 4.99999538610329e-05,
|
| 29 |
+
"loss": 1.3889,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.00489176959765195,
|
| 34 |
+
"grad_norm": 1.3264710903167725,
|
| 35 |
+
"learning_rate": 4.9999909567651185e-05,
|
| 36 |
+
"loss": 1.3986,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0061147119970649385,
|
| 41 |
+
"grad_norm": 0.3282574415206909,
|
| 42 |
+
"learning_rate": 4.999985050984959e-05,
|
| 43 |
+
"loss": 1.3884,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.007337654396477926,
|
| 48 |
+
"grad_norm": 0.41542303562164307,
|
| 49 |
+
"learning_rate": 4.999977668766299e-05,
|
| 50 |
+
"loss": 1.3872,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.008560596795890914,
|
| 55 |
+
"grad_norm": 0.1591300368309021,
|
| 56 |
+
"learning_rate": 4.9999688101134984e-05,
|
| 57 |
+
"loss": 1.387,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0097835391953039,
|
| 62 |
+
"grad_norm": 0.16393418610095978,
|
| 63 |
+
"learning_rate": 4.9999584750317896e-05,
|
| 64 |
+
"loss": 1.3877,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.011006481594716889,
|
| 69 |
+
"grad_norm": 0.8973674774169922,
|
| 70 |
+
"learning_rate": 4.9999466635272754e-05,
|
| 71 |
+
"loss": 1.3909,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.012229423994129877,
|
| 76 |
+
"grad_norm": 0.08877847343683243,
|
| 77 |
+
"learning_rate": 4.9999333756069325e-05,
|
| 78 |
+
"loss": 1.3872,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.012229423994129877,
|
| 83 |
+
"eval_loss": 1.401173710823059,
|
| 84 |
+
"eval_runtime": 690.9581,
|
| 85 |
+
"eval_samples_per_second": 11.831,
|
| 86 |
+
"eval_steps_per_second": 2.958,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.013452366393542864,
|
| 91 |
+
"grad_norm": 0.23952262103557587,
|
| 92 |
+
"learning_rate": 4.9999186112786065e-05,
|
| 93 |
+
"loss": 1.387,
|
| 94 |
+
"step": 110
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.014675308792955852,
|
| 98 |
+
"grad_norm": 0.18997414410114288,
|
| 99 |
+
"learning_rate": 4.999902370551019e-05,
|
| 100 |
+
"loss": 1.3883,
|
| 101 |
+
"step": 120
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.01589825119236884,
|
| 105 |
+
"grad_norm": 0.18813131749629974,
|
| 106 |
+
"learning_rate": 4.999884653433761e-05,
|
| 107 |
+
"loss": 1.4139,
|
| 108 |
+
"step": 130
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.017121193591781828,
|
| 112 |
+
"grad_norm": 0.11846957355737686,
|
| 113 |
+
"learning_rate": 4.999865459937294e-05,
|
| 114 |
+
"loss": 1.3871,
|
| 115 |
+
"step": 140
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.018344135991194815,
|
| 119 |
+
"grad_norm": 0.1004200130701065,
|
| 120 |
+
"learning_rate": 4.999844790072956e-05,
|
| 121 |
+
"loss": 1.3877,
|
| 122 |
+
"step": 150
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.0195670783906078,
|
| 126 |
+
"grad_norm": 0.081375852227211,
|
| 127 |
+
"learning_rate": 4.9998226438529526e-05,
|
| 128 |
+
"loss": 1.3866,
|
| 129 |
+
"step": 160
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.02079002079002079,
|
| 133 |
+
"grad_norm": 0.07120374590158463,
|
| 134 |
+
"learning_rate": 4.999799021290363e-05,
|
| 135 |
+
"loss": 1.3869,
|
| 136 |
+
"step": 170
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.022012963189433778,
|
| 140 |
+
"grad_norm": 0.07981643080711365,
|
| 141 |
+
"learning_rate": 4.999773922399139e-05,
|
| 142 |
+
"loss": 1.3863,
|
| 143 |
+
"step": 180
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.023235905588846764,
|
| 147 |
+
"grad_norm": 0.25061705708503723,
|
| 148 |
+
"learning_rate": 4.9997473471941025e-05,
|
| 149 |
+
"loss": 1.3857,
|
| 150 |
+
"step": 190
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.024458847988259754,
|
| 154 |
+
"grad_norm": 0.15727828443050385,
|
| 155 |
+
"learning_rate": 4.9997192956909486e-05,
|
| 156 |
+
"loss": 1.3868,
|
| 157 |
+
"step": 200
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.024458847988259754,
|
| 161 |
+
"eval_loss": 1.386336326599121,
|
| 162 |
+
"eval_runtime": 688.7718,
|
| 163 |
+
"eval_samples_per_second": 11.869,
|
| 164 |
+
"eval_steps_per_second": 2.968,
|
| 165 |
+
"step": 200
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.02568179038767274,
|
| 169 |
+
"grad_norm": 0.1090032234787941,
|
| 170 |
+
"learning_rate": 4.999689767906244e-05,
|
| 171 |
+
"loss": 1.3862,
|
| 172 |
+
"step": 210
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.026904732787085727,
|
| 176 |
+
"grad_norm": 0.38592782616615295,
|
| 177 |
+
"learning_rate": 4.999658763857427e-05,
|
| 178 |
+
"loss": 1.3853,
|
| 179 |
+
"step": 220
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.028127675186498717,
|
| 183 |
+
"grad_norm": 0.21041220426559448,
|
| 184 |
+
"learning_rate": 4.999626283562808e-05,
|
| 185 |
+
"loss": 1.3875,
|
| 186 |
+
"step": 230
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.029350617585911704,
|
| 190 |
+
"grad_norm": 0.39740511775016785,
|
| 191 |
+
"learning_rate": 4.999592327041569e-05,
|
| 192 |
+
"loss": 1.3854,
|
| 193 |
+
"step": 240
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.03057355998532469,
|
| 197 |
+
"grad_norm": 1.6249710321426392,
|
| 198 |
+
"learning_rate": 4.999556894313765e-05,
|
| 199 |
+
"loss": 1.3831,
|
| 200 |
+
"step": 250
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.03179650238473768,
|
| 204 |
+
"grad_norm": 0.07549172639846802,
|
| 205 |
+
"learning_rate": 4.9995199854003204e-05,
|
| 206 |
+
"loss": 1.3915,
|
| 207 |
+
"step": 260
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.03301944478415067,
|
| 211 |
+
"grad_norm": 0.2217286378145218,
|
| 212 |
+
"learning_rate": 4.999481600323034e-05,
|
| 213 |
+
"loss": 1.3926,
|
| 214 |
+
"step": 270
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.034242387183563656,
|
| 218 |
+
"grad_norm": 0.3971492350101471,
|
| 219 |
+
"learning_rate": 4.999441739104575e-05,
|
| 220 |
+
"loss": 1.3869,
|
| 221 |
+
"step": 280
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.03546532958297664,
|
| 225 |
+
"grad_norm": 0.15463902056217194,
|
| 226 |
+
"learning_rate": 4.999400401768483e-05,
|
| 227 |
+
"loss": 1.3871,
|
| 228 |
+
"step": 290
|
| 229 |
+
}
|
| 230 |
+
],
|
| 231 |
+
"logging_steps": 10,
|
| 232 |
+
"max_steps": 40885,
|
| 233 |
+
"num_input_tokens_seen": 0,
|
| 234 |
+
"num_train_epochs": 5,
|
| 235 |
+
"save_steps": 10,
|
| 236 |
+
"stateful_callbacks": {
|
| 237 |
+
"TrainerControl": {
|
| 238 |
+
"args": {
|
| 239 |
+
"should_epoch_stop": false,
|
| 240 |
+
"should_evaluate": false,
|
| 241 |
+
"should_log": false,
|
| 242 |
+
"should_save": true,
|
| 243 |
+
"should_training_stop": false
|
| 244 |
+
},
|
| 245 |
+
"attributes": {}
|
| 246 |
+
}
|
| 247 |
+
},
|
| 248 |
+
"total_flos": 693961140940800.0,
|
| 249 |
+
"train_batch_size": 4,
|
| 250 |
+
"trial_name": null,
|
| 251 |
+
"trial_params": null
|
| 252 |
+
}
|
last-checkpoint/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e820e6e61d47352f62234a870d3aedd3ee854655d286bbbf399539e9f3f89f1
|
| 3 |
+
size 5112
|