Model save
Browse files- checkpoint-6330/config.json +39 -0
- checkpoint-6330/merges.txt +0 -0
- checkpoint-6330/optimizer.pt +3 -0
- checkpoint-6330/pytorch_model.bin +3 -0
- checkpoint-6330/rng_state.pth +3 -0
- checkpoint-6330/scaler.pt +3 -0
- checkpoint-6330/scheduler.pt +3 -0
- checkpoint-6330/special_tokens_map.json +1 -0
- checkpoint-6330/tokenizer.json +0 -0
- checkpoint-6330/tokenizer_config.json +1 -0
- checkpoint-6330/trainer_state.json +496 -0
- checkpoint-6330/training_args.bin +3 -0
- checkpoint-6330/vocab.json +0 -0
- pytorch_model.bin +1 -1
checkpoint-6330/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "cardiffnlp/twitter-roberta-base-2021-124m",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "LABEL_0",
|
| 16 |
+
"1": "LABEL_1",
|
| 17 |
+
"2": "LABEL_2"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"LABEL_0": 0,
|
| 23 |
+
"LABEL_1": 1,
|
| 24 |
+
"LABEL_2": 2
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_eps": 1e-05,
|
| 27 |
+
"max_position_embeddings": 514,
|
| 28 |
+
"model_type": "roberta",
|
| 29 |
+
"num_attention_heads": 12,
|
| 30 |
+
"num_hidden_layers": 12,
|
| 31 |
+
"pad_token_id": 1,
|
| 32 |
+
"position_embedding_type": "absolute",
|
| 33 |
+
"problem_type": "multi_label_classification",
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.17.0",
|
| 36 |
+
"type_vocab_size": 1,
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50265
|
| 39 |
+
}
|
checkpoint-6330/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-6330/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3a7437a40297797d76be970cda296f9e9de7a8a30fa9389e371eb8562f5f42f
|
| 3 |
+
size 997299037
|
checkpoint-6330/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db2a2541c80c8862d343b43e5a977acae2a331760df57a128a0a52ba846cab4e
|
| 3 |
+
size 498678125
|
checkpoint-6330/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:390cd45c4ee11734d1ab7d101342d7dae79fa27ff4441e5cf3e091eb490a9676
|
| 3 |
+
size 14503
|
checkpoint-6330/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72d438701c261247f06c00fce8d97d1e4e3627fb6f516cc51625dbd3758e8fca
|
| 3 |
+
size 559
|
checkpoint-6330/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bde601a56216968ec29e9ff347df864fea5a48cad34029eb336dcdefac69973f
|
| 3 |
+
size 623
|
checkpoint-6330/special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
checkpoint-6330/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-6330/tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "cardiffnlp/twitter-roberta-base-2021-124m", "normalization": true, "tokenizer_class": "RobertaTokenizer"}
|
checkpoint-6330/trainer_state.json
ADDED
|
@@ -0,0 +1,496 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7930196752075032,
|
| 3 |
+
"best_model_checkpoint": "outputs/time_lm_nli/checkpoint-4009",
|
| 4 |
+
"epoch": 30.0,
|
| 5 |
+
"global_step": 6330,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"learning_rate": 9.666666666666666e-07,
|
| 13 |
+
"loss": 0.5392,
|
| 14 |
+
"step": 211
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.7,
|
| 19 |
+
"eval_f1": 0.6998718119161117,
|
| 20 |
+
"eval_loss": 0.4048246741294861,
|
| 21 |
+
"eval_runtime": 5.0256,
|
| 22 |
+
"eval_samples_per_second": 596.939,
|
| 23 |
+
"eval_steps_per_second": 74.617,
|
| 24 |
+
"step": 211
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"learning_rate": 9.333333333333333e-07,
|
| 29 |
+
"loss": 0.3725,
|
| 30 |
+
"step": 422
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.0,
|
| 34 |
+
"eval_accuracy": 0.759,
|
| 35 |
+
"eval_f1": 0.7583549419422403,
|
| 36 |
+
"eval_loss": 0.3489450216293335,
|
| 37 |
+
"eval_runtime": 5.103,
|
| 38 |
+
"eval_samples_per_second": 587.885,
|
| 39 |
+
"eval_steps_per_second": 73.486,
|
| 40 |
+
"step": 422
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 3.0,
|
| 44 |
+
"learning_rate": 9e-07,
|
| 45 |
+
"loss": 0.3158,
|
| 46 |
+
"step": 633
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 3.0,
|
| 50 |
+
"eval_accuracy": 0.7613333333333333,
|
| 51 |
+
"eval_f1": 0.7569694772671423,
|
| 52 |
+
"eval_loss": 0.3286795914173126,
|
| 53 |
+
"eval_runtime": 5.4646,
|
| 54 |
+
"eval_samples_per_second": 548.991,
|
| 55 |
+
"eval_steps_per_second": 68.624,
|
| 56 |
+
"step": 633
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.0,
|
| 60 |
+
"learning_rate": 8.666666666666667e-07,
|
| 61 |
+
"loss": 0.289,
|
| 62 |
+
"step": 844
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.0,
|
| 66 |
+
"eval_accuracy": 0.769,
|
| 67 |
+
"eval_f1": 0.7684440341259363,
|
| 68 |
+
"eval_loss": 0.33065709471702576,
|
| 69 |
+
"eval_runtime": 5.2159,
|
| 70 |
+
"eval_samples_per_second": 575.162,
|
| 71 |
+
"eval_steps_per_second": 71.895,
|
| 72 |
+
"step": 844
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 5.0,
|
| 76 |
+
"learning_rate": 8.333333333333333e-07,
|
| 77 |
+
"loss": 0.2716,
|
| 78 |
+
"step": 1055
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 5.0,
|
| 82 |
+
"eval_accuracy": 0.7766666666666666,
|
| 83 |
+
"eval_f1": 0.775028474008066,
|
| 84 |
+
"eval_loss": 0.3240624666213989,
|
| 85 |
+
"eval_runtime": 5.2721,
|
| 86 |
+
"eval_samples_per_second": 569.029,
|
| 87 |
+
"eval_steps_per_second": 71.129,
|
| 88 |
+
"step": 1055
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 6.0,
|
| 92 |
+
"learning_rate": 8e-07,
|
| 93 |
+
"loss": 0.2575,
|
| 94 |
+
"step": 1266
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 6.0,
|
| 98 |
+
"eval_accuracy": 0.7786666666666666,
|
| 99 |
+
"eval_f1": 0.7782108653517272,
|
| 100 |
+
"eval_loss": 0.32720017433166504,
|
| 101 |
+
"eval_runtime": 5.4144,
|
| 102 |
+
"eval_samples_per_second": 554.075,
|
| 103 |
+
"eval_steps_per_second": 69.259,
|
| 104 |
+
"step": 1266
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 7.0,
|
| 108 |
+
"learning_rate": 7.666666666666667e-07,
|
| 109 |
+
"loss": 0.2441,
|
| 110 |
+
"step": 1477
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 7.0,
|
| 114 |
+
"eval_accuracy": 0.7783333333333333,
|
| 115 |
+
"eval_f1": 0.7775937336504917,
|
| 116 |
+
"eval_loss": 0.3257558345794678,
|
| 117 |
+
"eval_runtime": 5.0695,
|
| 118 |
+
"eval_samples_per_second": 591.777,
|
| 119 |
+
"eval_steps_per_second": 73.972,
|
| 120 |
+
"step": 1477
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 8.0,
|
| 124 |
+
"learning_rate": 7.333333333333332e-07,
|
| 125 |
+
"loss": 0.2363,
|
| 126 |
+
"step": 1688
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 8.0,
|
| 130 |
+
"eval_accuracy": 0.7776666666666666,
|
| 131 |
+
"eval_f1": 0.777267505288088,
|
| 132 |
+
"eval_loss": 0.331592321395874,
|
| 133 |
+
"eval_runtime": 5.1518,
|
| 134 |
+
"eval_samples_per_second": 582.323,
|
| 135 |
+
"eval_steps_per_second": 72.79,
|
| 136 |
+
"step": 1688
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 9.0,
|
| 140 |
+
"learning_rate": 7e-07,
|
| 141 |
+
"loss": 0.2262,
|
| 142 |
+
"step": 1899
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 9.0,
|
| 146 |
+
"eval_accuracy": 0.7843333333333333,
|
| 147 |
+
"eval_f1": 0.7814767734353214,
|
| 148 |
+
"eval_loss": 0.3149881064891815,
|
| 149 |
+
"eval_runtime": 5.1238,
|
| 150 |
+
"eval_samples_per_second": 585.508,
|
| 151 |
+
"eval_steps_per_second": 73.188,
|
| 152 |
+
"step": 1899
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 10.0,
|
| 156 |
+
"learning_rate": 6.666666666666666e-07,
|
| 157 |
+
"loss": 0.2191,
|
| 158 |
+
"step": 2110
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 10.0,
|
| 162 |
+
"eval_accuracy": 0.7813333333333333,
|
| 163 |
+
"eval_f1": 0.7801938582947333,
|
| 164 |
+
"eval_loss": 0.32408154010772705,
|
| 165 |
+
"eval_runtime": 5.366,
|
| 166 |
+
"eval_samples_per_second": 559.08,
|
| 167 |
+
"eval_steps_per_second": 69.885,
|
| 168 |
+
"step": 2110
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 11.0,
|
| 172 |
+
"learning_rate": 6.333333333333332e-07,
|
| 173 |
+
"loss": 0.2112,
|
| 174 |
+
"step": 2321
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 11.0,
|
| 178 |
+
"eval_accuracy": 0.7866666666666666,
|
| 179 |
+
"eval_f1": 0.785979422813256,
|
| 180 |
+
"eval_loss": 0.3275919258594513,
|
| 181 |
+
"eval_runtime": 5.1309,
|
| 182 |
+
"eval_samples_per_second": 584.694,
|
| 183 |
+
"eval_steps_per_second": 73.087,
|
| 184 |
+
"step": 2321
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 12.0,
|
| 188 |
+
"learning_rate": 6e-07,
|
| 189 |
+
"loss": 0.2047,
|
| 190 |
+
"step": 2532
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 12.0,
|
| 194 |
+
"eval_accuracy": 0.7896666666666666,
|
| 195 |
+
"eval_f1": 0.7886408467585846,
|
| 196 |
+
"eval_loss": 0.32662513852119446,
|
| 197 |
+
"eval_runtime": 5.3907,
|
| 198 |
+
"eval_samples_per_second": 556.515,
|
| 199 |
+
"eval_steps_per_second": 69.564,
|
| 200 |
+
"step": 2532
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 13.0,
|
| 204 |
+
"learning_rate": 5.666666666666666e-07,
|
| 205 |
+
"loss": 0.1973,
|
| 206 |
+
"step": 2743
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 13.0,
|
| 210 |
+
"eval_accuracy": 0.7893333333333333,
|
| 211 |
+
"eval_f1": 0.7883928571428571,
|
| 212 |
+
"eval_loss": 0.3298616409301758,
|
| 213 |
+
"eval_runtime": 5.1275,
|
| 214 |
+
"eval_samples_per_second": 585.084,
|
| 215 |
+
"eval_steps_per_second": 73.135,
|
| 216 |
+
"step": 2743
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 14.0,
|
| 220 |
+
"learning_rate": 5.333333333333333e-07,
|
| 221 |
+
"loss": 0.1897,
|
| 222 |
+
"step": 2954
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 14.0,
|
| 226 |
+
"eval_accuracy": 0.792,
|
| 227 |
+
"eval_f1": 0.790682602817108,
|
| 228 |
+
"eval_loss": 0.3300517499446869,
|
| 229 |
+
"eval_runtime": 5.2516,
|
| 230 |
+
"eval_samples_per_second": 571.251,
|
| 231 |
+
"eval_steps_per_second": 71.406,
|
| 232 |
+
"step": 2954
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 15.0,
|
| 236 |
+
"learning_rate": 5e-07,
|
| 237 |
+
"loss": 0.1862,
|
| 238 |
+
"step": 3165
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 15.0,
|
| 242 |
+
"eval_accuracy": 0.794,
|
| 243 |
+
"eval_f1": 0.7925361349683366,
|
| 244 |
+
"eval_loss": 0.3283214867115021,
|
| 245 |
+
"eval_runtime": 5.2002,
|
| 246 |
+
"eval_samples_per_second": 576.904,
|
| 247 |
+
"eval_steps_per_second": 72.113,
|
| 248 |
+
"step": 3165
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 16.0,
|
| 252 |
+
"learning_rate": 4.6666666666666666e-07,
|
| 253 |
+
"loss": 0.1802,
|
| 254 |
+
"step": 3376
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 16.0,
|
| 258 |
+
"eval_accuracy": 0.7906666666666666,
|
| 259 |
+
"eval_f1": 0.7902606112099692,
|
| 260 |
+
"eval_loss": 0.34650853276252747,
|
| 261 |
+
"eval_runtime": 5.3305,
|
| 262 |
+
"eval_samples_per_second": 562.794,
|
| 263 |
+
"eval_steps_per_second": 70.349,
|
| 264 |
+
"step": 3376
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 17.0,
|
| 268 |
+
"learning_rate": 4.3333333333333335e-07,
|
| 269 |
+
"loss": 0.1764,
|
| 270 |
+
"step": 3587
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 17.0,
|
| 274 |
+
"eval_accuracy": 0.7936666666666666,
|
| 275 |
+
"eval_f1": 0.7922121284784747,
|
| 276 |
+
"eval_loss": 0.33925381302833557,
|
| 277 |
+
"eval_runtime": 5.0983,
|
| 278 |
+
"eval_samples_per_second": 588.426,
|
| 279 |
+
"eval_steps_per_second": 73.553,
|
| 280 |
+
"step": 3587
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 18.0,
|
| 284 |
+
"learning_rate": 4e-07,
|
| 285 |
+
"loss": 0.1693,
|
| 286 |
+
"step": 3798
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 18.0,
|
| 290 |
+
"eval_accuracy": 0.7903333333333333,
|
| 291 |
+
"eval_f1": 0.7893497135234246,
|
| 292 |
+
"eval_loss": 0.34940385818481445,
|
| 293 |
+
"eval_runtime": 5.4092,
|
| 294 |
+
"eval_samples_per_second": 554.614,
|
| 295 |
+
"eval_steps_per_second": 69.327,
|
| 296 |
+
"step": 3798
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 19.0,
|
| 300 |
+
"learning_rate": 3.666666666666666e-07,
|
| 301 |
+
"loss": 0.1666,
|
| 302 |
+
"step": 4009
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 19.0,
|
| 306 |
+
"eval_accuracy": 0.7943333333333333,
|
| 307 |
+
"eval_f1": 0.7930196752075032,
|
| 308 |
+
"eval_loss": 0.3486180901527405,
|
| 309 |
+
"eval_runtime": 5.052,
|
| 310 |
+
"eval_samples_per_second": 593.829,
|
| 311 |
+
"eval_steps_per_second": 74.229,
|
| 312 |
+
"step": 4009
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 20.0,
|
| 316 |
+
"learning_rate": 3.333333333333333e-07,
|
| 317 |
+
"loss": 0.1631,
|
| 318 |
+
"step": 4220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 20.0,
|
| 322 |
+
"eval_accuracy": 0.7926666666666666,
|
| 323 |
+
"eval_f1": 0.7917035036676259,
|
| 324 |
+
"eval_loss": 0.3516102433204651,
|
| 325 |
+
"eval_runtime": 5.3133,
|
| 326 |
+
"eval_samples_per_second": 564.624,
|
| 327 |
+
"eval_steps_per_second": 70.578,
|
| 328 |
+
"step": 4220
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 21.0,
|
| 332 |
+
"learning_rate": 3e-07,
|
| 333 |
+
"loss": 0.1609,
|
| 334 |
+
"step": 4431
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 21.0,
|
| 338 |
+
"eval_accuracy": 0.7906666666666666,
|
| 339 |
+
"eval_f1": 0.7892955896569633,
|
| 340 |
+
"eval_loss": 0.3536934554576874,
|
| 341 |
+
"eval_runtime": 5.1456,
|
| 342 |
+
"eval_samples_per_second": 583.024,
|
| 343 |
+
"eval_steps_per_second": 72.878,
|
| 344 |
+
"step": 4431
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 22.0,
|
| 348 |
+
"learning_rate": 2.6666666666666667e-07,
|
| 349 |
+
"loss": 0.1581,
|
| 350 |
+
"step": 4642
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 22.0,
|
| 354 |
+
"eval_accuracy": 0.7913333333333333,
|
| 355 |
+
"eval_f1": 0.7901843830147219,
|
| 356 |
+
"eval_loss": 0.3585768938064575,
|
| 357 |
+
"eval_runtime": 5.0974,
|
| 358 |
+
"eval_samples_per_second": 588.53,
|
| 359 |
+
"eval_steps_per_second": 73.566,
|
| 360 |
+
"step": 4642
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 23.0,
|
| 364 |
+
"learning_rate": 2.3333333333333333e-07,
|
| 365 |
+
"loss": 0.1548,
|
| 366 |
+
"step": 4853
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 23.0,
|
| 370 |
+
"eval_accuracy": 0.789,
|
| 371 |
+
"eval_f1": 0.7883905412466281,
|
| 372 |
+
"eval_loss": 0.3698215186595917,
|
| 373 |
+
"eval_runtime": 5.1375,
|
| 374 |
+
"eval_samples_per_second": 583.94,
|
| 375 |
+
"eval_steps_per_second": 72.993,
|
| 376 |
+
"step": 4853
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 24.0,
|
| 380 |
+
"learning_rate": 2e-07,
|
| 381 |
+
"loss": 0.1535,
|
| 382 |
+
"step": 5064
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 24.0,
|
| 386 |
+
"eval_accuracy": 0.7893333333333333,
|
| 387 |
+
"eval_f1": 0.7880437917624159,
|
| 388 |
+
"eval_loss": 0.36223018169403076,
|
| 389 |
+
"eval_runtime": 5.0965,
|
| 390 |
+
"eval_samples_per_second": 588.636,
|
| 391 |
+
"eval_steps_per_second": 73.579,
|
| 392 |
+
"step": 5064
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 25.0,
|
| 396 |
+
"learning_rate": 1.6666666666666665e-07,
|
| 397 |
+
"loss": 0.1522,
|
| 398 |
+
"step": 5275
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 25.0,
|
| 402 |
+
"eval_accuracy": 0.7923333333333333,
|
| 403 |
+
"eval_f1": 0.7909159993560795,
|
| 404 |
+
"eval_loss": 0.3625110387802124,
|
| 405 |
+
"eval_runtime": 5.3082,
|
| 406 |
+
"eval_samples_per_second": 565.161,
|
| 407 |
+
"eval_steps_per_second": 70.645,
|
| 408 |
+
"step": 5275
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 26.0,
|
| 412 |
+
"learning_rate": 1.3333333333333334e-07,
|
| 413 |
+
"loss": 0.15,
|
| 414 |
+
"step": 5486
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 26.0,
|
| 418 |
+
"eval_accuracy": 0.7913333333333333,
|
| 419 |
+
"eval_f1": 0.7898741258741259,
|
| 420 |
+
"eval_loss": 0.3632138669490814,
|
| 421 |
+
"eval_runtime": 5.0849,
|
| 422 |
+
"eval_samples_per_second": 589.979,
|
| 423 |
+
"eval_steps_per_second": 73.747,
|
| 424 |
+
"step": 5486
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 27.0,
|
| 428 |
+
"learning_rate": 1e-07,
|
| 429 |
+
"loss": 0.1479,
|
| 430 |
+
"step": 5697
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 27.0,
|
| 434 |
+
"eval_accuracy": 0.792,
|
| 435 |
+
"eval_f1": 0.7908753742347737,
|
| 436 |
+
"eval_loss": 0.36770883202552795,
|
| 437 |
+
"eval_runtime": 5.1403,
|
| 438 |
+
"eval_samples_per_second": 583.629,
|
| 439 |
+
"eval_steps_per_second": 72.954,
|
| 440 |
+
"step": 5697
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 28.0,
|
| 444 |
+
"learning_rate": 6.666666666666667e-08,
|
| 445 |
+
"loss": 0.1441,
|
| 446 |
+
"step": 5908
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 28.0,
|
| 450 |
+
"eval_accuracy": 0.792,
|
| 451 |
+
"eval_f1": 0.7909361904196064,
|
| 452 |
+
"eval_loss": 0.37145498394966125,
|
| 453 |
+
"eval_runtime": 5.1508,
|
| 454 |
+
"eval_samples_per_second": 582.434,
|
| 455 |
+
"eval_steps_per_second": 72.804,
|
| 456 |
+
"step": 5908
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 29.0,
|
| 460 |
+
"learning_rate": 3.3333333333333334e-08,
|
| 461 |
+
"loss": 0.145,
|
| 462 |
+
"step": 6119
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 29.0,
|
| 466 |
+
"eval_accuracy": 0.792,
|
| 467 |
+
"eval_f1": 0.7906376559648808,
|
| 468 |
+
"eval_loss": 0.36812248826026917,
|
| 469 |
+
"eval_runtime": 5.1947,
|
| 470 |
+
"eval_samples_per_second": 577.512,
|
| 471 |
+
"eval_steps_per_second": 72.189,
|
| 472 |
+
"step": 6119
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 30.0,
|
| 476 |
+
"learning_rate": 0.0,
|
| 477 |
+
"loss": 0.1432,
|
| 478 |
+
"step": 6330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 30.0,
|
| 482 |
+
"eval_accuracy": 0.7913333333333333,
|
| 483 |
+
"eval_f1": 0.7899207605271177,
|
| 484 |
+
"eval_loss": 0.3683205842971802,
|
| 485 |
+
"eval_runtime": 5.2918,
|
| 486 |
+
"eval_samples_per_second": 566.919,
|
| 487 |
+
"eval_steps_per_second": 70.865,
|
| 488 |
+
"step": 6330
|
| 489 |
+
}
|
| 490 |
+
],
|
| 491 |
+
"max_steps": 6330,
|
| 492 |
+
"num_train_epochs": 30,
|
| 493 |
+
"total_flos": 4.300749969732518e+16,
|
| 494 |
+
"trial_name": null,
|
| 495 |
+
"trial_params": null
|
| 496 |
+
}
|
checkpoint-6330/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3966be765a13463da707bf5cd58cd4c0452776ca8eaf9c649e2dbde2a9daa7b1
|
| 3 |
+
size 3119
|
checkpoint-6330/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 498678125
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11ea0be995a1d96adbe0fcdf66ace0ea5cc280c8c4100f27184e3de232f18763
|
| 3 |
size 498678125
|