Training in progress, epoch 1, checkpoint
Browse files
checkpoint-555/config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-t5/t5-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 4096,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 1024,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "relu",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "relu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": false,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "t5",
|
| 20 |
+
"n_positions": 512,
|
| 21 |
+
"num_decoder_layers": 24,
|
| 22 |
+
"num_heads": 16,
|
| 23 |
+
"num_layers": 24,
|
| 24 |
+
"output_past": true,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"relative_attention_max_distance": 128,
|
| 27 |
+
"relative_attention_num_buckets": 32,
|
| 28 |
+
"task_specific_params": {
|
| 29 |
+
"summarization": {
|
| 30 |
+
"early_stopping": true,
|
| 31 |
+
"length_penalty": 2.0,
|
| 32 |
+
"max_length": 200,
|
| 33 |
+
"min_length": 30,
|
| 34 |
+
"no_repeat_ngram_size": 3,
|
| 35 |
+
"num_beams": 4,
|
| 36 |
+
"prefix": "summarize: "
|
| 37 |
+
},
|
| 38 |
+
"translation_en_to_de": {
|
| 39 |
+
"early_stopping": true,
|
| 40 |
+
"max_length": 300,
|
| 41 |
+
"num_beams": 4,
|
| 42 |
+
"prefix": "translate English to German: "
|
| 43 |
+
},
|
| 44 |
+
"translation_en_to_fr": {
|
| 45 |
+
"early_stopping": true,
|
| 46 |
+
"max_length": 300,
|
| 47 |
+
"num_beams": 4,
|
| 48 |
+
"prefix": "translate English to French: "
|
| 49 |
+
},
|
| 50 |
+
"translation_en_to_ro": {
|
| 51 |
+
"early_stopping": true,
|
| 52 |
+
"max_length": 300,
|
| 53 |
+
"num_beams": 4,
|
| 54 |
+
"prefix": "translate English to Romanian: "
|
| 55 |
+
}
|
| 56 |
+
},
|
| 57 |
+
"torch_dtype": "float32",
|
| 58 |
+
"transformers_version": "4.47.0",
|
| 59 |
+
"use_cache": true,
|
| 60 |
+
"vocab_size": 32128
|
| 61 |
+
}
|
checkpoint-555/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:146d938bde9708f939eb267b0b66b81f71aaed6770b32836982cdc5810ce2cb2
|
| 3 |
+
size 2954947648
|
checkpoint-555/trainer_state.json
ADDED
|
@@ -0,0 +1,440 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 555,
|
| 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,
|
| 13 |
+
"eval_f1": 0.0,
|
| 14 |
+
"eval_loss": 0.5020396709442139,
|
| 15 |
+
"eval_precision": 0.0,
|
| 16 |
+
"eval_recall": 0.0,
|
| 17 |
+
"eval_runtime": 132.3528,
|
| 18 |
+
"eval_samples_per_second": 35.307,
|
| 19 |
+
"eval_steps_per_second": 4.42,
|
| 20 |
+
"step": 0
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.018026137899954935,
|
| 24 |
+
"grad_norm": 11.620719909667969,
|
| 25 |
+
"learning_rate": 4.9548736462093865e-05,
|
| 26 |
+
"loss": 0.2661,
|
| 27 |
+
"step": 10
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.03605227579990987,
|
| 31 |
+
"grad_norm": 1.2112946510314941,
|
| 32 |
+
"learning_rate": 4.909747292418773e-05,
|
| 33 |
+
"loss": 0.0513,
|
| 34 |
+
"step": 20
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.054078413699864804,
|
| 38 |
+
"grad_norm": 0.3561903238296509,
|
| 39 |
+
"learning_rate": 4.864620938628159e-05,
|
| 40 |
+
"loss": 0.0542,
|
| 41 |
+
"step": 30
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.07210455159981974,
|
| 45 |
+
"grad_norm": 15.130791664123535,
|
| 46 |
+
"learning_rate": 4.819494584837546e-05,
|
| 47 |
+
"loss": 0.1113,
|
| 48 |
+
"step": 40
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.09013068949977468,
|
| 52 |
+
"grad_norm": 10.50532054901123,
|
| 53 |
+
"learning_rate": 4.7743682310469314e-05,
|
| 54 |
+
"loss": 0.0417,
|
| 55 |
+
"step": 50
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.10815682739972961,
|
| 59 |
+
"grad_norm": 7.872809410095215,
|
| 60 |
+
"learning_rate": 4.7292418772563177e-05,
|
| 61 |
+
"loss": 0.0652,
|
| 62 |
+
"step": 60
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.12618296529968454,
|
| 66 |
+
"grad_norm": 0.3549640476703644,
|
| 67 |
+
"learning_rate": 4.684115523465704e-05,
|
| 68 |
+
"loss": 0.0476,
|
| 69 |
+
"step": 70
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.14420910319963948,
|
| 73 |
+
"grad_norm": 3.7721316814422607,
|
| 74 |
+
"learning_rate": 4.63898916967509e-05,
|
| 75 |
+
"loss": 0.0489,
|
| 76 |
+
"step": 80
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.16223524109959442,
|
| 80 |
+
"grad_norm": 1.7026127576828003,
|
| 81 |
+
"learning_rate": 4.5938628158844764e-05,
|
| 82 |
+
"loss": 0.0795,
|
| 83 |
+
"step": 90
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.18026137899954936,
|
| 87 |
+
"grad_norm": 0.6303790807723999,
|
| 88 |
+
"learning_rate": 4.548736462093863e-05,
|
| 89 |
+
"loss": 0.0187,
|
| 90 |
+
"step": 100
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.19828751689950427,
|
| 94 |
+
"grad_norm": 0.14402388036251068,
|
| 95 |
+
"learning_rate": 4.5036101083032495e-05,
|
| 96 |
+
"loss": 0.056,
|
| 97 |
+
"step": 110
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.21631365479945922,
|
| 101 |
+
"grad_norm": 0.2994736135005951,
|
| 102 |
+
"learning_rate": 4.458483754512636e-05,
|
| 103 |
+
"loss": 0.0697,
|
| 104 |
+
"step": 120
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.23433979269941416,
|
| 108 |
+
"grad_norm": 0.5501758456230164,
|
| 109 |
+
"learning_rate": 4.413357400722022e-05,
|
| 110 |
+
"loss": 0.0518,
|
| 111 |
+
"step": 130
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.25236593059936907,
|
| 115 |
+
"grad_norm": 6.304769992828369,
|
| 116 |
+
"learning_rate": 4.368231046931408e-05,
|
| 117 |
+
"loss": 0.0583,
|
| 118 |
+
"step": 140
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.270392068499324,
|
| 122 |
+
"grad_norm": 0.6018352508544922,
|
| 123 |
+
"learning_rate": 4.3231046931407945e-05,
|
| 124 |
+
"loss": 0.0455,
|
| 125 |
+
"step": 150
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.28841820639927895,
|
| 129 |
+
"grad_norm": 5.612204551696777,
|
| 130 |
+
"learning_rate": 4.277978339350181e-05,
|
| 131 |
+
"loss": 0.0415,
|
| 132 |
+
"step": 160
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.3064443442992339,
|
| 136 |
+
"grad_norm": 8.740653991699219,
|
| 137 |
+
"learning_rate": 4.232851985559567e-05,
|
| 138 |
+
"loss": 0.0435,
|
| 139 |
+
"step": 170
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 0.32447048219918884,
|
| 143 |
+
"grad_norm": 0.3686186373233795,
|
| 144 |
+
"learning_rate": 4.187725631768953e-05,
|
| 145 |
+
"loss": 0.0629,
|
| 146 |
+
"step": 180
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.3424966200991438,
|
| 150 |
+
"grad_norm": 0.5254208445549011,
|
| 151 |
+
"learning_rate": 4.1425992779783394e-05,
|
| 152 |
+
"loss": 0.0544,
|
| 153 |
+
"step": 190
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.3605227579990987,
|
| 157 |
+
"grad_norm": 6.638070583343506,
|
| 158 |
+
"learning_rate": 4.0974729241877256e-05,
|
| 159 |
+
"loss": 0.0833,
|
| 160 |
+
"step": 200
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.3785488958990536,
|
| 164 |
+
"grad_norm": 7.016050815582275,
|
| 165 |
+
"learning_rate": 4.052346570397112e-05,
|
| 166 |
+
"loss": 0.0641,
|
| 167 |
+
"step": 210
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.39657503379900855,
|
| 171 |
+
"grad_norm": 0.49279534816741943,
|
| 172 |
+
"learning_rate": 4.007220216606498e-05,
|
| 173 |
+
"loss": 0.031,
|
| 174 |
+
"step": 220
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.4146011716989635,
|
| 178 |
+
"grad_norm": 2.8472509384155273,
|
| 179 |
+
"learning_rate": 3.962093862815885e-05,
|
| 180 |
+
"loss": 0.081,
|
| 181 |
+
"step": 230
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.43262730959891843,
|
| 185 |
+
"grad_norm": 3.4148313999176025,
|
| 186 |
+
"learning_rate": 3.916967509025271e-05,
|
| 187 |
+
"loss": 0.0579,
|
| 188 |
+
"step": 240
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.45065344749887337,
|
| 192 |
+
"grad_norm": 0.18055088818073273,
|
| 193 |
+
"learning_rate": 3.8718411552346575e-05,
|
| 194 |
+
"loss": 0.0238,
|
| 195 |
+
"step": 250
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.4686795853988283,
|
| 199 |
+
"grad_norm": 0.2409915030002594,
|
| 200 |
+
"learning_rate": 3.826714801444044e-05,
|
| 201 |
+
"loss": 0.0179,
|
| 202 |
+
"step": 260
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.48670572329878325,
|
| 206 |
+
"grad_norm": 10.743939399719238,
|
| 207 |
+
"learning_rate": 3.78158844765343e-05,
|
| 208 |
+
"loss": 0.0578,
|
| 209 |
+
"step": 270
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.5047318611987381,
|
| 213 |
+
"grad_norm": 20.40981674194336,
|
| 214 |
+
"learning_rate": 3.7364620938628155e-05,
|
| 215 |
+
"loss": 0.0667,
|
| 216 |
+
"step": 280
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.5227579990986931,
|
| 220 |
+
"grad_norm": 0.8752731680870056,
|
| 221 |
+
"learning_rate": 3.6913357400722025e-05,
|
| 222 |
+
"loss": 0.0312,
|
| 223 |
+
"step": 290
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.540784136998648,
|
| 227 |
+
"grad_norm": 4.817637920379639,
|
| 228 |
+
"learning_rate": 3.646209386281589e-05,
|
| 229 |
+
"loss": 0.0517,
|
| 230 |
+
"step": 300
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.558810274898603,
|
| 234 |
+
"grad_norm": 6.971864700317383,
|
| 235 |
+
"learning_rate": 3.601083032490975e-05,
|
| 236 |
+
"loss": 0.0344,
|
| 237 |
+
"step": 310
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.5768364127985579,
|
| 241 |
+
"grad_norm": 0.742476224899292,
|
| 242 |
+
"learning_rate": 3.555956678700361e-05,
|
| 243 |
+
"loss": 0.0561,
|
| 244 |
+
"step": 320
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.5948625506985128,
|
| 248 |
+
"grad_norm": 0.7727406024932861,
|
| 249 |
+
"learning_rate": 3.5108303249097474e-05,
|
| 250 |
+
"loss": 0.0617,
|
| 251 |
+
"step": 330
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.6128886885984678,
|
| 255 |
+
"grad_norm": 0.6510533094406128,
|
| 256 |
+
"learning_rate": 3.4657039711191336e-05,
|
| 257 |
+
"loss": 0.0551,
|
| 258 |
+
"step": 340
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.6309148264984227,
|
| 262 |
+
"grad_norm": 4.241283893585205,
|
| 263 |
+
"learning_rate": 3.42057761732852e-05,
|
| 264 |
+
"loss": 0.026,
|
| 265 |
+
"step": 350
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.6489409643983777,
|
| 269 |
+
"grad_norm": 0.18860740959644318,
|
| 270 |
+
"learning_rate": 3.375451263537907e-05,
|
| 271 |
+
"loss": 0.0367,
|
| 272 |
+
"step": 360
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.6669671022983326,
|
| 276 |
+
"grad_norm": 0.13881151378154755,
|
| 277 |
+
"learning_rate": 3.330324909747293e-05,
|
| 278 |
+
"loss": 0.0434,
|
| 279 |
+
"step": 370
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.6849932401982876,
|
| 283 |
+
"grad_norm": 0.45671743154525757,
|
| 284 |
+
"learning_rate": 3.2851985559566786e-05,
|
| 285 |
+
"loss": 0.049,
|
| 286 |
+
"step": 380
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.7030193780982424,
|
| 290 |
+
"grad_norm": 0.5025729537010193,
|
| 291 |
+
"learning_rate": 3.240072202166065e-05,
|
| 292 |
+
"loss": 0.0266,
|
| 293 |
+
"step": 390
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.7210455159981974,
|
| 297 |
+
"grad_norm": 0.3955366611480713,
|
| 298 |
+
"learning_rate": 3.194945848375451e-05,
|
| 299 |
+
"loss": 0.0264,
|
| 300 |
+
"step": 400
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.7390716538981523,
|
| 304 |
+
"grad_norm": 11.814117431640625,
|
| 305 |
+
"learning_rate": 3.149819494584837e-05,
|
| 306 |
+
"loss": 0.0495,
|
| 307 |
+
"step": 410
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.7570977917981072,
|
| 311 |
+
"grad_norm": 10.024807929992676,
|
| 312 |
+
"learning_rate": 3.104693140794224e-05,
|
| 313 |
+
"loss": 0.0262,
|
| 314 |
+
"step": 420
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.7751239296980622,
|
| 318 |
+
"grad_norm": 0.23220416903495789,
|
| 319 |
+
"learning_rate": 3.0595667870036104e-05,
|
| 320 |
+
"loss": 0.0826,
|
| 321 |
+
"step": 430
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.7931500675980171,
|
| 325 |
+
"grad_norm": 1.059012532234192,
|
| 326 |
+
"learning_rate": 3.0144404332129967e-05,
|
| 327 |
+
"loss": 0.0323,
|
| 328 |
+
"step": 440
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.8111762054979721,
|
| 332 |
+
"grad_norm": 5.872659683227539,
|
| 333 |
+
"learning_rate": 2.969314079422383e-05,
|
| 334 |
+
"loss": 0.0616,
|
| 335 |
+
"step": 450
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.829202343397927,
|
| 339 |
+
"grad_norm": 0.3091956377029419,
|
| 340 |
+
"learning_rate": 2.924187725631769e-05,
|
| 341 |
+
"loss": 0.0439,
|
| 342 |
+
"step": 460
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.847228481297882,
|
| 346 |
+
"grad_norm": 0.7430059909820557,
|
| 347 |
+
"learning_rate": 2.879061371841155e-05,
|
| 348 |
+
"loss": 0.0758,
|
| 349 |
+
"step": 470
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.8652546191978369,
|
| 353 |
+
"grad_norm": 0.5902143120765686,
|
| 354 |
+
"learning_rate": 2.8339350180505413e-05,
|
| 355 |
+
"loss": 0.0448,
|
| 356 |
+
"step": 480
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.8832807570977917,
|
| 360 |
+
"grad_norm": 5.876249313354492,
|
| 361 |
+
"learning_rate": 2.7888086642599282e-05,
|
| 362 |
+
"loss": 0.0356,
|
| 363 |
+
"step": 490
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.9013068949977467,
|
| 367 |
+
"grad_norm": 3.5948667526245117,
|
| 368 |
+
"learning_rate": 2.7436823104693144e-05,
|
| 369 |
+
"loss": 0.053,
|
| 370 |
+
"step": 500
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.9193330328977016,
|
| 374 |
+
"grad_norm": 9.958101272583008,
|
| 375 |
+
"learning_rate": 2.6985559566787007e-05,
|
| 376 |
+
"loss": 0.0234,
|
| 377 |
+
"step": 510
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.9373591707976566,
|
| 381 |
+
"grad_norm": 0.7074028253555298,
|
| 382 |
+
"learning_rate": 2.6534296028880866e-05,
|
| 383 |
+
"loss": 0.052,
|
| 384 |
+
"step": 520
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.9553853086976115,
|
| 388 |
+
"grad_norm": 0.37822696566581726,
|
| 389 |
+
"learning_rate": 2.6083032490974728e-05,
|
| 390 |
+
"loss": 0.0517,
|
| 391 |
+
"step": 530
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.9734114465975665,
|
| 395 |
+
"grad_norm": 0.5355275869369507,
|
| 396 |
+
"learning_rate": 2.563176895306859e-05,
|
| 397 |
+
"loss": 0.0327,
|
| 398 |
+
"step": 540
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.9914375844975214,
|
| 402 |
+
"grad_norm": 0.4926086366176605,
|
| 403 |
+
"learning_rate": 2.518050541516246e-05,
|
| 404 |
+
"loss": 0.042,
|
| 405 |
+
"step": 550
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.0,
|
| 409 |
+
"eval_f1": 0.0,
|
| 410 |
+
"eval_loss": 0.04069153591990471,
|
| 411 |
+
"eval_precision": 0.0,
|
| 412 |
+
"eval_recall": 0.0,
|
| 413 |
+
"eval_runtime": 142.0447,
|
| 414 |
+
"eval_samples_per_second": 32.898,
|
| 415 |
+
"eval_steps_per_second": 4.118,
|
| 416 |
+
"step": 555
|
| 417 |
+
}
|
| 418 |
+
],
|
| 419 |
+
"logging_steps": 10,
|
| 420 |
+
"max_steps": 1108,
|
| 421 |
+
"num_input_tokens_seen": 0,
|
| 422 |
+
"num_train_epochs": 2,
|
| 423 |
+
"save_steps": 500,
|
| 424 |
+
"stateful_callbacks": {
|
| 425 |
+
"TrainerControl": {
|
| 426 |
+
"args": {
|
| 427 |
+
"should_epoch_stop": false,
|
| 428 |
+
"should_evaluate": false,
|
| 429 |
+
"should_log": false,
|
| 430 |
+
"should_save": true,
|
| 431 |
+
"should_training_stop": false
|
| 432 |
+
},
|
| 433 |
+
"attributes": {}
|
| 434 |
+
}
|
| 435 |
+
},
|
| 436 |
+
"total_flos": 3.84912704311296e+16,
|
| 437 |
+
"train_batch_size": 8,
|
| 438 |
+
"trial_name": null,
|
| 439 |
+
"trial_params": null
|
| 440 |
+
}
|
checkpoint-555/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97afd7a398103d448d50fc55ef878deb079a18d40d6865b60599e2b7a529812d
|
| 3 |
+
size 5432
|