Training in progress, step 700, checkpoint
Browse files- checkpoint-700/config.json +35 -0
- checkpoint-700/model.safetensors +3 -0
- checkpoint-700/optimizer.pt +3 -0
- checkpoint-700/rng_state.pth +3 -0
- checkpoint-700/scheduler.pt +3 -0
- checkpoint-700/special_tokens_map.json +9 -0
- checkpoint-700/tokenizer.json +0 -0
- checkpoint-700/tokenizer_config.json +59 -0
- checkpoint-700/trainer_state.json +502 -0
- checkpoint-700/training_args.bin +3 -0
- checkpoint-700/vocab.txt +0 -0
checkpoint-700/config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "klue/roberta-large",
|
| 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": 1024,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "LABEL_0"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 4096,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"LABEL_0": 0
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-05,
|
| 23 |
+
"max_position_embeddings": 514,
|
| 24 |
+
"model_type": "roberta",
|
| 25 |
+
"num_attention_heads": 16,
|
| 26 |
+
"num_hidden_layers": 24,
|
| 27 |
+
"pad_token_id": 2,
|
| 28 |
+
"position_embedding_type": "absolute",
|
| 29 |
+
"tokenizer_class": "BertTokenizer",
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.35.0",
|
| 32 |
+
"type_vocab_size": 1,
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 32000
|
| 35 |
+
}
|
checkpoint-700/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44defb1dd9a2004e5bda7cbb5b8f9a1a6b73624fe9d38a9eb3c547c249e5cc40
|
| 3 |
+
size 1346677820
|
checkpoint-700/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a564a2e6d4a9ec53cf62f3e8a189458ba061a084f5f272af9be312aef23a3065
|
| 3 |
+
size 2693490618
|
checkpoint-700/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:222cc8d310dd2293b8b7a64a3612a777bd31352402909af04e13181981e4b9bd
|
| 3 |
+
size 14308
|
checkpoint-700/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a690ddf619e2bedc0f644439875bb3745f4010acfa6aab3153f7f6936fb55ec5
|
| 3 |
+
size 1064
|
checkpoint-700/special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": "[UNK]"
|
| 9 |
+
}
|
checkpoint-700/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-700/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[CLS]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[PAD]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_basic_tokenize": true,
|
| 48 |
+
"do_lower_case": false,
|
| 49 |
+
"eos_token": "[SEP]",
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"never_split": null,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"strip_accents": null,
|
| 56 |
+
"tokenize_chinese_chars": true,
|
| 57 |
+
"tokenizer_class": "BertTokenizer",
|
| 58 |
+
"unk_token": "[UNK]"
|
| 59 |
+
}
|
checkpoint-700/trainer_state.json
ADDED
|
@@ -0,0 +1,502 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.8800880088008801,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 700,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 8.996486892091073e-06,
|
| 14 |
+
"loss": 0.6543,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.03,
|
| 19 |
+
"learning_rate": 8.985953053665263e-06,
|
| 20 |
+
"loss": 0.469,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.04,
|
| 25 |
+
"learning_rate": 8.968414932060827e-06,
|
| 26 |
+
"loss": 0.2958,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.05,
|
| 31 |
+
"learning_rate": 8.94389991097275e-06,
|
| 32 |
+
"loss": 0.2424,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.06,
|
| 37 |
+
"learning_rate": 8.912446267696357e-06,
|
| 38 |
+
"loss": 0.2481,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.08,
|
| 43 |
+
"learning_rate": 8.874103113361848e-06,
|
| 44 |
+
"loss": 0.251,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.09,
|
| 49 |
+
"learning_rate": 8.828930316253112e-06,
|
| 50 |
+
"loss": 0.1803,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1,
|
| 55 |
+
"learning_rate": 8.7769984083305e-06,
|
| 56 |
+
"loss": 0.2148,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.11,
|
| 61 |
+
"learning_rate": 8.718388475103545e-06,
|
| 62 |
+
"loss": 0.1926,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.13,
|
| 67 |
+
"learning_rate": 8.653192029025561e-06,
|
| 68 |
+
"loss": 0.2202,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.13,
|
| 73 |
+
"eval_accuracy": 0.0,
|
| 74 |
+
"eval_loss": 0.07498380541801453,
|
| 75 |
+
"eval_runtime": 28.9719,
|
| 76 |
+
"eval_samples_per_second": 97.612,
|
| 77 |
+
"eval_steps_per_second": 24.403,
|
| 78 |
+
"step": 100
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.14,
|
| 82 |
+
"learning_rate": 8.581510866607817e-06,
|
| 83 |
+
"loss": 0.1805,
|
| 84 |
+
"step": 110
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.15,
|
| 88 |
+
"learning_rate": 8.503456909476364e-06,
|
| 89 |
+
"loss": 0.2322,
|
| 90 |
+
"step": 120
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.16,
|
| 94 |
+
"learning_rate": 8.419152029619696e-06,
|
| 95 |
+
"loss": 0.1636,
|
| 96 |
+
"step": 130
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.18,
|
| 100 |
+
"learning_rate": 8.32872785910012e-06,
|
| 101 |
+
"loss": 0.1689,
|
| 102 |
+
"step": 140
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.19,
|
| 106 |
+
"learning_rate": 8.232325584525908e-06,
|
| 107 |
+
"loss": 0.1738,
|
| 108 |
+
"step": 150
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.2,
|
| 112 |
+
"learning_rate": 8.130095726605169e-06,
|
| 113 |
+
"loss": 0.1509,
|
| 114 |
+
"step": 160
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.21,
|
| 118 |
+
"learning_rate": 8.022197905125629e-06,
|
| 119 |
+
"loss": 0.1821,
|
| 120 |
+
"step": 170
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.23,
|
| 124 |
+
"learning_rate": 7.90880058972729e-06,
|
| 125 |
+
"loss": 0.1435,
|
| 126 |
+
"step": 180
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.24,
|
| 130 |
+
"learning_rate": 7.790080836857073e-06,
|
| 131 |
+
"loss": 0.1621,
|
| 132 |
+
"step": 190
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.25,
|
| 136 |
+
"learning_rate": 7.666224013316203e-06,
|
| 137 |
+
"loss": 0.1527,
|
| 138 |
+
"step": 200
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.25,
|
| 142 |
+
"eval_accuracy": 0.0,
|
| 143 |
+
"eval_loss": 0.03772040829062462,
|
| 144 |
+
"eval_runtime": 29.7593,
|
| 145 |
+
"eval_samples_per_second": 95.029,
|
| 146 |
+
"eval_steps_per_second": 23.757,
|
| 147 |
+
"step": 200
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.26,
|
| 151 |
+
"learning_rate": 7.537423506831948e-06,
|
| 152 |
+
"loss": 0.1684,
|
| 153 |
+
"step": 210
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.28,
|
| 157 |
+
"learning_rate": 7.403880424105644e-06,
|
| 158 |
+
"loss": 0.2118,
|
| 159 |
+
"step": 220
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.29,
|
| 163 |
+
"learning_rate": 7.2658032768084485e-06,
|
| 164 |
+
"loss": 0.1381,
|
| 165 |
+
"step": 230
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.3,
|
| 169 |
+
"learning_rate": 7.123407656015124e-06,
|
| 170 |
+
"loss": 0.1364,
|
| 171 |
+
"step": 240
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.31,
|
| 175 |
+
"learning_rate": 6.976915895584163e-06,
|
| 176 |
+
"loss": 0.1147,
|
| 177 |
+
"step": 250
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.33,
|
| 181 |
+
"learning_rate": 6.826556725009857e-06,
|
| 182 |
+
"loss": 0.1129,
|
| 183 |
+
"step": 260
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.34,
|
| 187 |
+
"learning_rate": 6.672564912288353e-06,
|
| 188 |
+
"loss": 0.1357,
|
| 189 |
+
"step": 270
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.35,
|
| 193 |
+
"learning_rate": 6.515180897355285e-06,
|
| 194 |
+
"loss": 0.1285,
|
| 195 |
+
"step": 280
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.36,
|
| 199 |
+
"learning_rate": 6.354650416667365e-06,
|
| 200 |
+
"loss": 0.1013,
|
| 201 |
+
"step": 290
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.38,
|
| 205 |
+
"learning_rate": 6.191224119514071e-06,
|
| 206 |
+
"loss": 0.1483,
|
| 207 |
+
"step": 300
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.38,
|
| 211 |
+
"eval_accuracy": 0.0,
|
| 212 |
+
"eval_loss": 0.07286300510168076,
|
| 213 |
+
"eval_runtime": 29.1592,
|
| 214 |
+
"eval_samples_per_second": 96.985,
|
| 215 |
+
"eval_steps_per_second": 24.246,
|
| 216 |
+
"step": 300
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.39,
|
| 220 |
+
"learning_rate": 6.0251571766585436e-06,
|
| 221 |
+
"loss": 0.1199,
|
| 222 |
+
"step": 310
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.4,
|
| 226 |
+
"learning_rate": 5.856708881918714e-06,
|
| 227 |
+
"loss": 0.1211,
|
| 228 |
+
"step": 320
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.41,
|
| 232 |
+
"learning_rate": 5.6861422473108045e-06,
|
| 233 |
+
"loss": 0.1637,
|
| 234 |
+
"step": 330
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.43,
|
| 238 |
+
"learning_rate": 5.513723592387277e-06,
|
| 239 |
+
"loss": 0.1656,
|
| 240 |
+
"step": 340
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.44,
|
| 244 |
+
"learning_rate": 5.339722128410471e-06,
|
| 245 |
+
"loss": 0.1099,
|
| 246 |
+
"step": 350
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.45,
|
| 250 |
+
"learning_rate": 5.164409538011166e-06,
|
| 251 |
+
"loss": 0.1771,
|
| 252 |
+
"step": 360
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.47,
|
| 256 |
+
"learning_rate": 4.988059550988415e-06,
|
| 257 |
+
"loss": 0.1509,
|
| 258 |
+
"step": 370
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.48,
|
| 262 |
+
"learning_rate": 4.810947516912951e-06,
|
| 263 |
+
"loss": 0.1177,
|
| 264 |
+
"step": 380
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.49,
|
| 268 |
+
"learning_rate": 4.633349975201519e-06,
|
| 269 |
+
"loss": 0.1135,
|
| 270 |
+
"step": 390
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.5,
|
| 274 |
+
"learning_rate": 4.455544223333405e-06,
|
| 275 |
+
"loss": 0.1896,
|
| 276 |
+
"step": 400
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.5,
|
| 280 |
+
"eval_accuracy": 0.0,
|
| 281 |
+
"eval_loss": 0.14649830758571625,
|
| 282 |
+
"eval_runtime": 29.7909,
|
| 283 |
+
"eval_samples_per_second": 94.928,
|
| 284 |
+
"eval_steps_per_second": 23.732,
|
| 285 |
+
"step": 400
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.52,
|
| 289 |
+
"learning_rate": 4.277807883883337e-06,
|
| 290 |
+
"loss": 0.1044,
|
| 291 |
+
"step": 410
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.53,
|
| 295 |
+
"learning_rate": 4.100418471046794e-06,
|
| 296 |
+
"loss": 0.1084,
|
| 297 |
+
"step": 420
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.54,
|
| 301 |
+
"learning_rate": 3.9236529573345295e-06,
|
| 302 |
+
"loss": 0.0895,
|
| 303 |
+
"step": 430
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.55,
|
| 307 |
+
"learning_rate": 3.7477873411128757e-06,
|
| 308 |
+
"loss": 0.0877,
|
| 309 |
+
"step": 440
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.57,
|
| 313 |
+
"learning_rate": 3.573096215665058e-06,
|
| 314 |
+
"loss": 0.1421,
|
| 315 |
+
"step": 450
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.58,
|
| 319 |
+
"learning_rate": 3.399852340446378e-06,
|
| 320 |
+
"loss": 0.1461,
|
| 321 |
+
"step": 460
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.59,
|
| 325 |
+
"learning_rate": 3.2283262152027056e-06,
|
| 326 |
+
"loss": 0.1126,
|
| 327 |
+
"step": 470
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.6,
|
| 331 |
+
"learning_rate": 3.0587856576172314e-06,
|
| 332 |
+
"loss": 0.0901,
|
| 333 |
+
"step": 480
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.62,
|
| 337 |
+
"learning_rate": 2.89149538514495e-06,
|
| 338 |
+
"loss": 0.1441,
|
| 339 |
+
"step": 490
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.63,
|
| 343 |
+
"learning_rate": 2.726716601687775e-06,
|
| 344 |
+
"loss": 0.1341,
|
| 345 |
+
"step": 500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.63,
|
| 349 |
+
"eval_accuracy": 0.0,
|
| 350 |
+
"eval_loss": 0.07294097542762756,
|
| 351 |
+
"eval_runtime": 29.0559,
|
| 352 |
+
"eval_samples_per_second": 97.33,
|
| 353 |
+
"eval_steps_per_second": 24.332,
|
| 354 |
+
"step": 500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.64,
|
| 358 |
+
"learning_rate": 2.5647065897556595e-06,
|
| 359 |
+
"loss": 0.0889,
|
| 360 |
+
"step": 510
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.65,
|
| 364 |
+
"learning_rate": 2.405718308750485e-06,
|
| 365 |
+
"loss": 0.0849,
|
| 366 |
+
"step": 520
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.67,
|
| 370 |
+
"learning_rate": 2.250000000000001e-06,
|
| 371 |
+
"loss": 0.1501,
|
| 372 |
+
"step": 530
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 0.68,
|
| 376 |
+
"learning_rate": 2.097794799158444e-06,
|
| 377 |
+
"loss": 0.0813,
|
| 378 |
+
"step": 540
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.69,
|
| 382 |
+
"learning_rate": 1.9493403565790804e-06,
|
| 383 |
+
"loss": 0.0866,
|
| 384 |
+
"step": 550
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.7,
|
| 388 |
+
"learning_rate": 1.8048684662514e-06,
|
| 389 |
+
"loss": 0.1651,
|
| 390 |
+
"step": 560
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.72,
|
| 394 |
+
"learning_rate": 1.6646047038823006e-06,
|
| 395 |
+
"loss": 0.1361,
|
| 396 |
+
"step": 570
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.73,
|
| 400 |
+
"learning_rate": 1.5287680746864134e-06,
|
| 401 |
+
"loss": 0.1593,
|
| 402 |
+
"step": 580
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.74,
|
| 406 |
+
"learning_rate": 1.3975706714354478e-06,
|
| 407 |
+
"loss": 0.0883,
|
| 408 |
+
"step": 590
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.75,
|
| 412 |
+
"learning_rate": 1.2712173433005088e-06,
|
| 413 |
+
"loss": 0.0876,
|
| 414 |
+
"step": 600
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.75,
|
| 418 |
+
"eval_accuracy": 0.0,
|
| 419 |
+
"eval_loss": 0.035098280757665634,
|
| 420 |
+
"eval_runtime": 29.6788,
|
| 421 |
+
"eval_samples_per_second": 95.287,
|
| 422 |
+
"eval_steps_per_second": 23.822,
|
| 423 |
+
"step": 600
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.77,
|
| 427 |
+
"learning_rate": 1.1499053760044425e-06,
|
| 428 |
+
"loss": 0.1194,
|
| 429 |
+
"step": 610
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.78,
|
| 433 |
+
"learning_rate": 1.0338241837835812e-06,
|
| 434 |
+
"loss": 0.1013,
|
| 435 |
+
"step": 620
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.79,
|
| 439 |
+
"learning_rate": 9.231550136399099e-07,
|
| 440 |
+
"loss": 0.1059,
|
| 441 |
+
"step": 630
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.8,
|
| 445 |
+
"learning_rate": 8.180706623453892e-07,
|
| 446 |
+
"loss": 0.1042,
|
| 447 |
+
"step": 640
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.82,
|
| 451 |
+
"learning_rate": 7.187352066403012e-07,
|
| 452 |
+
"loss": 0.1477,
|
| 453 |
+
"step": 650
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.83,
|
| 457 |
+
"learning_rate": 6.253037470469e-07,
|
| 458 |
+
"loss": 0.1009,
|
| 459 |
+
"step": 660
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.84,
|
| 463 |
+
"learning_rate": 5.379221656983615e-07,
|
| 464 |
+
"loss": 0.0672,
|
| 465 |
+
"step": 670
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.85,
|
| 469 |
+
"learning_rate": 4.567268985611408e-07,
|
| 470 |
+
"loss": 0.0963,
|
| 471 |
+
"step": 680
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.87,
|
| 475 |
+
"learning_rate": 3.8184472240641696e-07,
|
| 476 |
+
"loss": 0.0679,
|
| 477 |
+
"step": 690
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.88,
|
| 481 |
+
"learning_rate": 3.133925568632049e-07,
|
| 482 |
+
"loss": 0.1345,
|
| 483 |
+
"step": 700
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.88,
|
| 487 |
+
"eval_accuracy": 0.0,
|
| 488 |
+
"eval_loss": 0.06039029359817505,
|
| 489 |
+
"eval_runtime": 29.1232,
|
| 490 |
+
"eval_samples_per_second": 97.105,
|
| 491 |
+
"eval_steps_per_second": 24.276,
|
| 492 |
+
"step": 700
|
| 493 |
+
}
|
| 494 |
+
],
|
| 495 |
+
"logging_steps": 10,
|
| 496 |
+
"max_steps": 795,
|
| 497 |
+
"num_train_epochs": 1,
|
| 498 |
+
"save_steps": 100,
|
| 499 |
+
"total_flos": 0.0,
|
| 500 |
+
"trial_name": null,
|
| 501 |
+
"trial_params": null
|
| 502 |
+
}
|
checkpoint-700/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97515eaa596c1259df8da372577f8444c126856d2334b3f90d539244c52eb51c
|
| 3 |
+
size 4664
|
checkpoint-700/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|