Upload folder using huggingface_hub
Browse files- config.json +75 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +379 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/bart-large",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"BartForSequenceClassification"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.1,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.1,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 1024,
|
| 15 |
+
"decoder_attention_heads": 16,
|
| 16 |
+
"decoder_ffn_dim": 4096,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 12,
|
| 19 |
+
"decoder_start_token_id": 2,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"early_stopping": true,
|
| 22 |
+
"encoder_attention_heads": 16,
|
| 23 |
+
"encoder_ffn_dim": 4096,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 12,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"forced_bos_token_id": 0,
|
| 28 |
+
"forced_eos_token_id": 2,
|
| 29 |
+
"gradient_checkpointing": false,
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "LABEL_0",
|
| 32 |
+
"1": "LABEL_1",
|
| 33 |
+
"2": "LABEL_2"
|
| 34 |
+
},
|
| 35 |
+
"init_std": 0.02,
|
| 36 |
+
"is_encoder_decoder": true,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"LABEL_0": 0,
|
| 39 |
+
"LABEL_1": 1,
|
| 40 |
+
"LABEL_2": 2
|
| 41 |
+
},
|
| 42 |
+
"max_position_embeddings": 1024,
|
| 43 |
+
"model_type": "bart",
|
| 44 |
+
"no_repeat_ngram_size": 3,
|
| 45 |
+
"normalize_before": false,
|
| 46 |
+
"num_beams": 4,
|
| 47 |
+
"num_hidden_layers": 12,
|
| 48 |
+
"pad_token_id": 1,
|
| 49 |
+
"problem_type": "single_label_classification",
|
| 50 |
+
"scale_embedding": false,
|
| 51 |
+
"task_specific_params": {
|
| 52 |
+
"summarization": {
|
| 53 |
+
"length_penalty": 1.0,
|
| 54 |
+
"max_length": 128,
|
| 55 |
+
"min_length": 12,
|
| 56 |
+
"num_beams": 4
|
| 57 |
+
},
|
| 58 |
+
"summarization_cnn": {
|
| 59 |
+
"length_penalty": 2.0,
|
| 60 |
+
"max_length": 142,
|
| 61 |
+
"min_length": 56,
|
| 62 |
+
"num_beams": 4
|
| 63 |
+
},
|
| 64 |
+
"summarization_xsum": {
|
| 65 |
+
"length_penalty": 1.0,
|
| 66 |
+
"max_length": 62,
|
| 67 |
+
"min_length": 11,
|
| 68 |
+
"num_beams": 6
|
| 69 |
+
}
|
| 70 |
+
},
|
| 71 |
+
"torch_dtype": "float32",
|
| 72 |
+
"transformers_version": "4.38.2",
|
| 73 |
+
"use_cache": true,
|
| 74 |
+
"vocab_size": 50265
|
| 75 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:843cb11d766af36ac71491251c6a59e1c18acf437ae2a81f66e4f4c75fe0c1fd
|
| 3 |
+
size 1629436964
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c37b72249ab670a79f95e7a8a28b4295bc0d2474b70ef75088b7f94377a21cd
|
| 3 |
+
size 3259184731
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c615480f9132ca44d1a64f61d0ad33b4cfee708b0079b7d90597306c265b6e39
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20f8ea15f450d448adf5f088f5e69b322ba185360623de1fad0e8c5fa0932135
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,379 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 8.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 4232,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.19,
|
| 13 |
+
"grad_norm": 6.645576477050781,
|
| 14 |
+
"learning_rate": 1.9810964083175805e-05,
|
| 15 |
+
"loss": 0.5588,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.38,
|
| 20 |
+
"grad_norm": 4.662398815155029,
|
| 21 |
+
"learning_rate": 1.962192816635161e-05,
|
| 22 |
+
"loss": 0.3737,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.57,
|
| 27 |
+
"grad_norm": 5.282985687255859,
|
| 28 |
+
"learning_rate": 1.9432892249527412e-05,
|
| 29 |
+
"loss": 0.2863,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.76,
|
| 34 |
+
"grad_norm": 1.5854848623275757,
|
| 35 |
+
"learning_rate": 1.9243856332703215e-05,
|
| 36 |
+
"loss": 0.323,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.95,
|
| 41 |
+
"grad_norm": 19.09914779663086,
|
| 42 |
+
"learning_rate": 1.905482041587902e-05,
|
| 43 |
+
"loss": 0.2956,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.0,
|
| 48 |
+
"eval_loss": 0.20477035641670227,
|
| 49 |
+
"eval_runtime": 4.245,
|
| 50 |
+
"eval_samples_per_second": 91.638,
|
| 51 |
+
"eval_steps_per_second": 6.596,
|
| 52 |
+
"step": 529
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.13,
|
| 56 |
+
"grad_norm": 26.59105682373047,
|
| 57 |
+
"learning_rate": 1.8865784499054822e-05,
|
| 58 |
+
"loss": 0.2269,
|
| 59 |
+
"step": 600
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.32,
|
| 63 |
+
"grad_norm": 9.394390106201172,
|
| 64 |
+
"learning_rate": 1.8676748582230626e-05,
|
| 65 |
+
"loss": 0.2393,
|
| 66 |
+
"step": 700
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.51,
|
| 70 |
+
"grad_norm": 13.779593467712402,
|
| 71 |
+
"learning_rate": 1.848771266540643e-05,
|
| 72 |
+
"loss": 0.2135,
|
| 73 |
+
"step": 800
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 1.7,
|
| 77 |
+
"grad_norm": 0.6053704619407654,
|
| 78 |
+
"learning_rate": 1.8298676748582232e-05,
|
| 79 |
+
"loss": 0.2241,
|
| 80 |
+
"step": 900
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.89,
|
| 84 |
+
"grad_norm": 16.190296173095703,
|
| 85 |
+
"learning_rate": 1.8109640831758036e-05,
|
| 86 |
+
"loss": 0.2355,
|
| 87 |
+
"step": 1000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 2.0,
|
| 91 |
+
"eval_loss": 0.21921110153198242,
|
| 92 |
+
"eval_runtime": 4.2197,
|
| 93 |
+
"eval_samples_per_second": 92.187,
|
| 94 |
+
"eval_steps_per_second": 6.636,
|
| 95 |
+
"step": 1058
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 2.08,
|
| 99 |
+
"grad_norm": 0.10688259452581406,
|
| 100 |
+
"learning_rate": 1.792060491493384e-05,
|
| 101 |
+
"loss": 0.1909,
|
| 102 |
+
"step": 1100
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 2.27,
|
| 106 |
+
"grad_norm": 29.609710693359375,
|
| 107 |
+
"learning_rate": 1.7731568998109643e-05,
|
| 108 |
+
"loss": 0.1637,
|
| 109 |
+
"step": 1200
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 2.46,
|
| 113 |
+
"grad_norm": 0.16163112223148346,
|
| 114 |
+
"learning_rate": 1.7542533081285446e-05,
|
| 115 |
+
"loss": 0.1828,
|
| 116 |
+
"step": 1300
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.65,
|
| 120 |
+
"grad_norm": 2.127821207046509,
|
| 121 |
+
"learning_rate": 1.735349716446125e-05,
|
| 122 |
+
"loss": 0.1827,
|
| 123 |
+
"step": 1400
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.84,
|
| 127 |
+
"grad_norm": 0.030160142108798027,
|
| 128 |
+
"learning_rate": 1.7164461247637053e-05,
|
| 129 |
+
"loss": 0.1528,
|
| 130 |
+
"step": 1500
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 3.0,
|
| 134 |
+
"eval_loss": 0.2590792179107666,
|
| 135 |
+
"eval_runtime": 4.2371,
|
| 136 |
+
"eval_samples_per_second": 91.808,
|
| 137 |
+
"eval_steps_per_second": 6.608,
|
| 138 |
+
"step": 1587
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 3.02,
|
| 142 |
+
"grad_norm": 0.0637928918004036,
|
| 143 |
+
"learning_rate": 1.6975425330812856e-05,
|
| 144 |
+
"loss": 0.1574,
|
| 145 |
+
"step": 1600
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 3.21,
|
| 149 |
+
"grad_norm": 0.01419603731483221,
|
| 150 |
+
"learning_rate": 1.678638941398866e-05,
|
| 151 |
+
"loss": 0.0918,
|
| 152 |
+
"step": 1700
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.4,
|
| 156 |
+
"grad_norm": 9.31396770477295,
|
| 157 |
+
"learning_rate": 1.6597353497164463e-05,
|
| 158 |
+
"loss": 0.1175,
|
| 159 |
+
"step": 1800
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.59,
|
| 163 |
+
"grad_norm": 0.023506687954068184,
|
| 164 |
+
"learning_rate": 1.6408317580340267e-05,
|
| 165 |
+
"loss": 0.1094,
|
| 166 |
+
"step": 1900
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 3.78,
|
| 170 |
+
"grad_norm": 13.4344482421875,
|
| 171 |
+
"learning_rate": 1.621928166351607e-05,
|
| 172 |
+
"loss": 0.1103,
|
| 173 |
+
"step": 2000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 3.97,
|
| 177 |
+
"grad_norm": 30.01926040649414,
|
| 178 |
+
"learning_rate": 1.6030245746691873e-05,
|
| 179 |
+
"loss": 0.1398,
|
| 180 |
+
"step": 2100
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 4.0,
|
| 184 |
+
"eval_loss": 0.33959057927131653,
|
| 185 |
+
"eval_runtime": 4.2467,
|
| 186 |
+
"eval_samples_per_second": 91.601,
|
| 187 |
+
"eval_steps_per_second": 6.593,
|
| 188 |
+
"step": 2116
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 4.16,
|
| 192 |
+
"grad_norm": 0.12888406217098236,
|
| 193 |
+
"learning_rate": 1.5841209829867677e-05,
|
| 194 |
+
"loss": 0.0536,
|
| 195 |
+
"step": 2200
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 4.35,
|
| 199 |
+
"grad_norm": 0.06800971180200577,
|
| 200 |
+
"learning_rate": 1.565217391304348e-05,
|
| 201 |
+
"loss": 0.1039,
|
| 202 |
+
"step": 2300
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 4.54,
|
| 206 |
+
"grad_norm": 2.495684862136841,
|
| 207 |
+
"learning_rate": 1.5463137996219284e-05,
|
| 208 |
+
"loss": 0.0886,
|
| 209 |
+
"step": 2400
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 4.73,
|
| 213 |
+
"grad_norm": 3.7909159660339355,
|
| 214 |
+
"learning_rate": 1.5274102079395087e-05,
|
| 215 |
+
"loss": 0.0766,
|
| 216 |
+
"step": 2500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 4.91,
|
| 220 |
+
"grad_norm": 0.025901077315211296,
|
| 221 |
+
"learning_rate": 1.5085066162570889e-05,
|
| 222 |
+
"loss": 0.0916,
|
| 223 |
+
"step": 2600
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 5.0,
|
| 227 |
+
"eval_loss": 0.3040069341659546,
|
| 228 |
+
"eval_runtime": 4.2484,
|
| 229 |
+
"eval_samples_per_second": 91.564,
|
| 230 |
+
"eval_steps_per_second": 6.591,
|
| 231 |
+
"step": 2645
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 5.1,
|
| 235 |
+
"grad_norm": 0.011547481641173363,
|
| 236 |
+
"learning_rate": 1.4896030245746694e-05,
|
| 237 |
+
"loss": 0.0644,
|
| 238 |
+
"step": 2700
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 5.29,
|
| 242 |
+
"grad_norm": 0.026049258187413216,
|
| 243 |
+
"learning_rate": 1.4706994328922497e-05,
|
| 244 |
+
"loss": 0.0542,
|
| 245 |
+
"step": 2800
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 5.48,
|
| 249 |
+
"grad_norm": 0.35288381576538086,
|
| 250 |
+
"learning_rate": 1.45179584120983e-05,
|
| 251 |
+
"loss": 0.0512,
|
| 252 |
+
"step": 2900
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 5.67,
|
| 256 |
+
"grad_norm": 0.023430563509464264,
|
| 257 |
+
"learning_rate": 1.4328922495274103e-05,
|
| 258 |
+
"loss": 0.0491,
|
| 259 |
+
"step": 3000
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 5.86,
|
| 263 |
+
"grad_norm": 0.0032355256844311953,
|
| 264 |
+
"learning_rate": 1.4139886578449906e-05,
|
| 265 |
+
"loss": 0.0326,
|
| 266 |
+
"step": 3100
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 6.0,
|
| 270 |
+
"eval_loss": 0.3605019450187683,
|
| 271 |
+
"eval_runtime": 4.2462,
|
| 272 |
+
"eval_samples_per_second": 91.611,
|
| 273 |
+
"eval_steps_per_second": 6.594,
|
| 274 |
+
"step": 3174
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 6.05,
|
| 278 |
+
"grad_norm": 0.1259104311466217,
|
| 279 |
+
"learning_rate": 1.395085066162571e-05,
|
| 280 |
+
"loss": 0.0665,
|
| 281 |
+
"step": 3200
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 6.24,
|
| 285 |
+
"grad_norm": 0.08823427557945251,
|
| 286 |
+
"learning_rate": 1.3761814744801514e-05,
|
| 287 |
+
"loss": 0.0252,
|
| 288 |
+
"step": 3300
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 6.43,
|
| 292 |
+
"grad_norm": 101.22339630126953,
|
| 293 |
+
"learning_rate": 1.3572778827977318e-05,
|
| 294 |
+
"loss": 0.0416,
|
| 295 |
+
"step": 3400
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 6.62,
|
| 299 |
+
"grad_norm": 0.033835213631391525,
|
| 300 |
+
"learning_rate": 1.338374291115312e-05,
|
| 301 |
+
"loss": 0.0465,
|
| 302 |
+
"step": 3500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 6.81,
|
| 306 |
+
"grad_norm": 0.15451325476169586,
|
| 307 |
+
"learning_rate": 1.3194706994328923e-05,
|
| 308 |
+
"loss": 0.0358,
|
| 309 |
+
"step": 3600
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 6.99,
|
| 313 |
+
"grad_norm": 0.0031314522493630648,
|
| 314 |
+
"learning_rate": 1.3005671077504726e-05,
|
| 315 |
+
"loss": 0.0344,
|
| 316 |
+
"step": 3700
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 7.0,
|
| 320 |
+
"eval_loss": 0.41286924481391907,
|
| 321 |
+
"eval_runtime": 4.2519,
|
| 322 |
+
"eval_samples_per_second": 91.488,
|
| 323 |
+
"eval_steps_per_second": 6.585,
|
| 324 |
+
"step": 3703
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.18,
|
| 328 |
+
"grad_norm": 0.0014451502356678247,
|
| 329 |
+
"learning_rate": 1.281663516068053e-05,
|
| 330 |
+
"loss": 0.0148,
|
| 331 |
+
"step": 3800
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 7.37,
|
| 335 |
+
"grad_norm": 17.679460525512695,
|
| 336 |
+
"learning_rate": 1.2627599243856335e-05,
|
| 337 |
+
"loss": 0.0309,
|
| 338 |
+
"step": 3900
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 7.56,
|
| 342 |
+
"grad_norm": 0.03577155992388725,
|
| 343 |
+
"learning_rate": 1.2438563327032138e-05,
|
| 344 |
+
"loss": 0.0235,
|
| 345 |
+
"step": 4000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 7.75,
|
| 349 |
+
"grad_norm": 28.639484405517578,
|
| 350 |
+
"learning_rate": 1.224952741020794e-05,
|
| 351 |
+
"loss": 0.0296,
|
| 352 |
+
"step": 4100
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 7.94,
|
| 356 |
+
"grad_norm": 0.00975144561380148,
|
| 357 |
+
"learning_rate": 1.2060491493383744e-05,
|
| 358 |
+
"loss": 0.0218,
|
| 359 |
+
"step": 4200
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 8.0,
|
| 363 |
+
"eval_loss": 0.3556581735610962,
|
| 364 |
+
"eval_runtime": 4.245,
|
| 365 |
+
"eval_samples_per_second": 91.637,
|
| 366 |
+
"eval_steps_per_second": 6.596,
|
| 367 |
+
"step": 4232
|
| 368 |
+
}
|
| 369 |
+
],
|
| 370 |
+
"logging_steps": 100,
|
| 371 |
+
"max_steps": 10580,
|
| 372 |
+
"num_input_tokens_seen": 0,
|
| 373 |
+
"num_train_epochs": 20,
|
| 374 |
+
"save_steps": 500,
|
| 375 |
+
"total_flos": 4.321523491876685e+16,
|
| 376 |
+
"train_batch_size": 14,
|
| 377 |
+
"trial_name": null,
|
| 378 |
+
"trial_params": null
|
| 379 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e38d84d4a8a34ed1c3d4c1693843cfd19f859389604ec942e9d423aad70c82fc
|
| 3 |
+
size 4856
|