Training in progress, step 800, checkpoint
Browse files- checkpoint-800/config.json +39 -0
- checkpoint-800/merges.txt +0 -0
- checkpoint-800/optimizer.pt +3 -0
- checkpoint-800/pytorch_model.bin +3 -0
- checkpoint-800/rng_state.pth +3 -0
- checkpoint-800/scheduler.pt +3 -0
- checkpoint-800/special_tokens_map.json +15 -0
- checkpoint-800/tokenizer.json +0 -0
- checkpoint-800/tokenizer_config.json +57 -0
- checkpoint-800/trainer_state.json +859 -0
- checkpoint-800/training_args.bin +3 -0
- checkpoint-800/vocab.json +0 -0
checkpoint-800/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSentimentClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"finetuning_task": "text-classification",
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "0",
|
| 16 |
+
"1": "1",
|
| 17 |
+
"2": "2"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"0": 0,
|
| 23 |
+
"1": 1,
|
| 24 |
+
"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": "single_label_classification",
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.34.1",
|
| 36 |
+
"type_vocab_size": 1,
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50265
|
| 39 |
+
}
|
checkpoint-800/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-800/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b22cb3b590b4ee8524bf73bf908b348f2fc0c1b2ed544e74b8e765f611796c2
|
| 3 |
+
size 997351674
|
checkpoint-800/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ef559f3b2efd8823d0403db00470ce59158e221cd8be4b27bb151a5ca641f3e
|
| 3 |
+
size 498661166
|
checkpoint-800/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcee8a43ba19ce4d86c8ed1d2e2208c9e20a0e6abd7f97a31e6d5f50d0ddd890
|
| 3 |
+
size 14244
|
checkpoint-800/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78fecf021b73a0623f67cbd5f2b63f4d15eff4224badb9750241f41631d8bca2
|
| 3 |
+
size 1064
|
checkpoint-800/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
checkpoint-800/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-800/tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
checkpoint-800/trainer_state.json
ADDED
|
@@ -0,0 +1,859 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.4078254326561326,
|
| 5 |
+
"eval_steps": 20,
|
| 6 |
+
"global_step": 800,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"learning_rate": 5e-07,
|
| 14 |
+
"loss": 1.1046,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.06,
|
| 19 |
+
"learning_rate": 1e-06,
|
| 20 |
+
"loss": 1.0664,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.06,
|
| 25 |
+
"eval_accuracy": 0.44479243019924036,
|
| 26 |
+
"eval_loss": 1.065091609954834,
|
| 27 |
+
"eval_runtime": 50.348,
|
| 28 |
+
"eval_samples_per_second": 596.131,
|
| 29 |
+
"eval_steps_per_second": 1.172,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.09,
|
| 34 |
+
"learning_rate": 1.5e-06,
|
| 35 |
+
"loss": 1.0672,
|
| 36 |
+
"step": 30
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.12,
|
| 40 |
+
"learning_rate": 2e-06,
|
| 41 |
+
"loss": 1.0423,
|
| 42 |
+
"step": 40
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.12,
|
| 46 |
+
"eval_accuracy": 0.5033650962883988,
|
| 47 |
+
"eval_loss": 1.0188277959823608,
|
| 48 |
+
"eval_runtime": 49.614,
|
| 49 |
+
"eval_samples_per_second": 604.95,
|
| 50 |
+
"eval_steps_per_second": 1.189,
|
| 51 |
+
"step": 40
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.15,
|
| 55 |
+
"learning_rate": 2.5e-06,
|
| 56 |
+
"loss": 1.027,
|
| 57 |
+
"step": 50
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.18,
|
| 61 |
+
"learning_rate": 3e-06,
|
| 62 |
+
"loss": 1.0137,
|
| 63 |
+
"step": 60
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.18,
|
| 67 |
+
"eval_accuracy": 0.5279203038581995,
|
| 68 |
+
"eval_loss": 0.9871189594268799,
|
| 69 |
+
"eval_runtime": 49.5201,
|
| 70 |
+
"eval_samples_per_second": 606.098,
|
| 71 |
+
"eval_steps_per_second": 1.191,
|
| 72 |
+
"step": 60
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.21,
|
| 76 |
+
"learning_rate": 3.5e-06,
|
| 77 |
+
"loss": 1.0005,
|
| 78 |
+
"step": 70
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.24,
|
| 82 |
+
"learning_rate": 4e-06,
|
| 83 |
+
"loss": 1.0027,
|
| 84 |
+
"step": 80
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.24,
|
| 88 |
+
"eval_accuracy": 0.5308189511561271,
|
| 89 |
+
"eval_loss": 0.9888613224029541,
|
| 90 |
+
"eval_runtime": 49.4469,
|
| 91 |
+
"eval_samples_per_second": 606.994,
|
| 92 |
+
"eval_steps_per_second": 1.193,
|
| 93 |
+
"step": 80
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.27,
|
| 97 |
+
"learning_rate": 4.5e-06,
|
| 98 |
+
"loss": 0.9937,
|
| 99 |
+
"step": 90
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.3,
|
| 103 |
+
"learning_rate": 5e-06,
|
| 104 |
+
"loss": 0.9914,
|
| 105 |
+
"step": 100
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.3,
|
| 109 |
+
"eval_accuracy": 0.5307856333710935,
|
| 110 |
+
"eval_loss": 0.9762536883354187,
|
| 111 |
+
"eval_runtime": 49.4804,
|
| 112 |
+
"eval_samples_per_second": 606.583,
|
| 113 |
+
"eval_steps_per_second": 1.192,
|
| 114 |
+
"step": 100
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.33,
|
| 118 |
+
"learning_rate": 5.5e-06,
|
| 119 |
+
"loss": 0.9884,
|
| 120 |
+
"step": 110
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.36,
|
| 124 |
+
"learning_rate": 6e-06,
|
| 125 |
+
"loss": 0.9826,
|
| 126 |
+
"step": 120
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.36,
|
| 130 |
+
"eval_accuracy": 0.5387819017791697,
|
| 131 |
+
"eval_loss": 0.9713281989097595,
|
| 132 |
+
"eval_runtime": 49.4983,
|
| 133 |
+
"eval_samples_per_second": 606.364,
|
| 134 |
+
"eval_steps_per_second": 1.192,
|
| 135 |
+
"step": 120
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.39,
|
| 139 |
+
"learning_rate": 6.5e-06,
|
| 140 |
+
"loss": 0.9882,
|
| 141 |
+
"step": 130
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.42,
|
| 145 |
+
"learning_rate": 7e-06,
|
| 146 |
+
"loss": 0.9788,
|
| 147 |
+
"step": 140
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.42,
|
| 151 |
+
"eval_accuracy": 0.5312520823615646,
|
| 152 |
+
"eval_loss": 0.9766249656677246,
|
| 153 |
+
"eval_runtime": 49.5213,
|
| 154 |
+
"eval_samples_per_second": 606.083,
|
| 155 |
+
"eval_steps_per_second": 1.191,
|
| 156 |
+
"step": 140
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.45,
|
| 160 |
+
"learning_rate": 7.5e-06,
|
| 161 |
+
"loss": 0.9854,
|
| 162 |
+
"step": 150
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.48,
|
| 166 |
+
"learning_rate": 8e-06,
|
| 167 |
+
"loss": 0.984,
|
| 168 |
+
"step": 160
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.48,
|
| 172 |
+
"eval_accuracy": 0.5398147531152129,
|
| 173 |
+
"eval_loss": 0.9589501619338989,
|
| 174 |
+
"eval_runtime": 49.4977,
|
| 175 |
+
"eval_samples_per_second": 606.372,
|
| 176 |
+
"eval_steps_per_second": 1.192,
|
| 177 |
+
"step": 160
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.51,
|
| 181 |
+
"learning_rate": 8.500000000000002e-06,
|
| 182 |
+
"loss": 0.9795,
|
| 183 |
+
"step": 170
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.54,
|
| 187 |
+
"learning_rate": 9e-06,
|
| 188 |
+
"loss": 0.9694,
|
| 189 |
+
"step": 180
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.54,
|
| 193 |
+
"eval_accuracy": 0.5423469047777704,
|
| 194 |
+
"eval_loss": 0.953514814376831,
|
| 195 |
+
"eval_runtime": 49.4511,
|
| 196 |
+
"eval_samples_per_second": 606.943,
|
| 197 |
+
"eval_steps_per_second": 1.193,
|
| 198 |
+
"step": 180
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.57,
|
| 202 |
+
"learning_rate": 9.5e-06,
|
| 203 |
+
"loss": 0.9757,
|
| 204 |
+
"step": 190
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.6,
|
| 208 |
+
"learning_rate": 1e-05,
|
| 209 |
+
"loss": 0.9676,
|
| 210 |
+
"step": 200
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.6,
|
| 214 |
+
"eval_accuracy": 0.567201972412874,
|
| 215 |
+
"eval_loss": 0.9273685812950134,
|
| 216 |
+
"eval_runtime": 49.4122,
|
| 217 |
+
"eval_samples_per_second": 607.421,
|
| 218 |
+
"eval_steps_per_second": 1.194,
|
| 219 |
+
"step": 200
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.63,
|
| 223 |
+
"learning_rate": 1.0500000000000001e-05,
|
| 224 |
+
"loss": 0.9708,
|
| 225 |
+
"step": 210
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.66,
|
| 229 |
+
"learning_rate": 1.1e-05,
|
| 230 |
+
"loss": 0.9753,
|
| 231 |
+
"step": 220
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.66,
|
| 235 |
+
"eval_accuracy": 0.573598987139335,
|
| 236 |
+
"eval_loss": 0.912590503692627,
|
| 237 |
+
"eval_runtime": 49.2827,
|
| 238 |
+
"eval_samples_per_second": 609.017,
|
| 239 |
+
"eval_steps_per_second": 1.197,
|
| 240 |
+
"step": 220
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.69,
|
| 244 |
+
"learning_rate": 1.15e-05,
|
| 245 |
+
"loss": 0.9586,
|
| 246 |
+
"step": 230
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.72,
|
| 250 |
+
"learning_rate": 1.2e-05,
|
| 251 |
+
"loss": 0.9557,
|
| 252 |
+
"step": 240
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.72,
|
| 256 |
+
"eval_accuracy": 0.5759645498767242,
|
| 257 |
+
"eval_loss": 0.9052607417106628,
|
| 258 |
+
"eval_runtime": 49.4457,
|
| 259 |
+
"eval_samples_per_second": 607.01,
|
| 260 |
+
"eval_steps_per_second": 1.193,
|
| 261 |
+
"step": 240
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.75,
|
| 265 |
+
"learning_rate": 1.25e-05,
|
| 266 |
+
"loss": 0.9518,
|
| 267 |
+
"step": 250
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.78,
|
| 271 |
+
"learning_rate": 1.3e-05,
|
| 272 |
+
"loss": 0.9508,
|
| 273 |
+
"step": 260
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.78,
|
| 277 |
+
"eval_accuracy": 0.5766975411474645,
|
| 278 |
+
"eval_loss": 0.9178985953330994,
|
| 279 |
+
"eval_runtime": 49.3132,
|
| 280 |
+
"eval_samples_per_second": 608.641,
|
| 281 |
+
"eval_steps_per_second": 1.196,
|
| 282 |
+
"step": 260
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.81,
|
| 286 |
+
"learning_rate": 1.35e-05,
|
| 287 |
+
"loss": 0.9405,
|
| 288 |
+
"step": 270
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.84,
|
| 292 |
+
"learning_rate": 1.4e-05,
|
| 293 |
+
"loss": 0.9355,
|
| 294 |
+
"step": 280
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.84,
|
| 298 |
+
"eval_accuracy": 0.58915839275005,
|
| 299 |
+
"eval_loss": 0.8937407732009888,
|
| 300 |
+
"eval_runtime": 49.4342,
|
| 301 |
+
"eval_samples_per_second": 607.15,
|
| 302 |
+
"eval_steps_per_second": 1.194,
|
| 303 |
+
"step": 280
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.87,
|
| 307 |
+
"learning_rate": 1.4500000000000002e-05,
|
| 308 |
+
"loss": 0.9235,
|
| 309 |
+
"step": 290
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.9,
|
| 313 |
+
"learning_rate": 1.5e-05,
|
| 314 |
+
"loss": 0.9,
|
| 315 |
+
"step": 300
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.9,
|
| 319 |
+
"eval_accuracy": 0.613013926834144,
|
| 320 |
+
"eval_loss": 0.8468813300132751,
|
| 321 |
+
"eval_runtime": 49.5046,
|
| 322 |
+
"eval_samples_per_second": 606.287,
|
| 323 |
+
"eval_steps_per_second": 1.192,
|
| 324 |
+
"step": 300
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.93,
|
| 328 |
+
"learning_rate": 1.55e-05,
|
| 329 |
+
"loss": 0.8857,
|
| 330 |
+
"step": 310
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.96,
|
| 334 |
+
"learning_rate": 1.6e-05,
|
| 335 |
+
"loss": 0.993,
|
| 336 |
+
"step": 320
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.96,
|
| 340 |
+
"eval_accuracy": 0.6046511627906976,
|
| 341 |
+
"eval_loss": 0.8615403771400452,
|
| 342 |
+
"eval_runtime": 49.5041,
|
| 343 |
+
"eval_samples_per_second": 606.294,
|
| 344 |
+
"eval_steps_per_second": 1.192,
|
| 345 |
+
"step": 320
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.99,
|
| 349 |
+
"learning_rate": 1.65e-05,
|
| 350 |
+
"loss": 0.8418,
|
| 351 |
+
"step": 330
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.02,
|
| 355 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 356 |
+
"loss": 0.8527,
|
| 357 |
+
"step": 340
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.02,
|
| 361 |
+
"eval_accuracy": 0.6439328313453722,
|
| 362 |
+
"eval_loss": 0.7896137237548828,
|
| 363 |
+
"eval_runtime": 49.4448,
|
| 364 |
+
"eval_samples_per_second": 607.02,
|
| 365 |
+
"eval_steps_per_second": 1.193,
|
| 366 |
+
"step": 340
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.05,
|
| 370 |
+
"learning_rate": 1.7500000000000002e-05,
|
| 371 |
+
"loss": 0.8982,
|
| 372 |
+
"step": 350
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.08,
|
| 376 |
+
"learning_rate": 1.8e-05,
|
| 377 |
+
"loss": 0.966,
|
| 378 |
+
"step": 360
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.08,
|
| 382 |
+
"eval_accuracy": 0.5315852602119011,
|
| 383 |
+
"eval_loss": 1.0123510360717773,
|
| 384 |
+
"eval_runtime": 49.4838,
|
| 385 |
+
"eval_samples_per_second": 606.542,
|
| 386 |
+
"eval_steps_per_second": 1.192,
|
| 387 |
+
"step": 360
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.11,
|
| 391 |
+
"learning_rate": 1.85e-05,
|
| 392 |
+
"loss": 0.9413,
|
| 393 |
+
"step": 370
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.14,
|
| 397 |
+
"learning_rate": 1.9e-05,
|
| 398 |
+
"loss": 0.8441,
|
| 399 |
+
"step": 380
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.14,
|
| 403 |
+
"eval_accuracy": 0.6488638635303525,
|
| 404 |
+
"eval_loss": 0.791083574295044,
|
| 405 |
+
"eval_runtime": 49.4701,
|
| 406 |
+
"eval_samples_per_second": 606.71,
|
| 407 |
+
"eval_steps_per_second": 1.193,
|
| 408 |
+
"step": 380
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.17,
|
| 412 |
+
"learning_rate": 1.95e-05,
|
| 413 |
+
"loss": 0.8223,
|
| 414 |
+
"step": 390
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.2,
|
| 418 |
+
"learning_rate": 2e-05,
|
| 419 |
+
"loss": 0.8226,
|
| 420 |
+
"step": 400
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.2,
|
| 424 |
+
"eval_accuracy": 0.6699873392416872,
|
| 425 |
+
"eval_loss": 0.7472424507141113,
|
| 426 |
+
"eval_runtime": 49.4938,
|
| 427 |
+
"eval_samples_per_second": 606.419,
|
| 428 |
+
"eval_steps_per_second": 1.192,
|
| 429 |
+
"step": 400
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.23,
|
| 433 |
+
"learning_rate": 2.05e-05,
|
| 434 |
+
"loss": 0.7924,
|
| 435 |
+
"step": 410
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.26,
|
| 439 |
+
"learning_rate": 2.1000000000000002e-05,
|
| 440 |
+
"loss": 0.7948,
|
| 441 |
+
"step": 420
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.26,
|
| 445 |
+
"eval_accuracy": 0.6580595721996402,
|
| 446 |
+
"eval_loss": 0.7663838863372803,
|
| 447 |
+
"eval_runtime": 49.5064,
|
| 448 |
+
"eval_samples_per_second": 606.265,
|
| 449 |
+
"eval_steps_per_second": 1.192,
|
| 450 |
+
"step": 420
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.29,
|
| 454 |
+
"learning_rate": 2.1499999999999997e-05,
|
| 455 |
+
"loss": 0.776,
|
| 456 |
+
"step": 430
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.32,
|
| 460 |
+
"learning_rate": 2.2e-05,
|
| 461 |
+
"loss": 0.7428,
|
| 462 |
+
"step": 440
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.32,
|
| 466 |
+
"eval_accuracy": 0.6991737189311654,
|
| 467 |
+
"eval_loss": 0.6993714570999146,
|
| 468 |
+
"eval_runtime": 49.4888,
|
| 469 |
+
"eval_samples_per_second": 606.481,
|
| 470 |
+
"eval_steps_per_second": 1.192,
|
| 471 |
+
"step": 440
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.35,
|
| 475 |
+
"learning_rate": 2.2499999999999998e-05,
|
| 476 |
+
"loss": 0.7512,
|
| 477 |
+
"step": 450
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.38,
|
| 481 |
+
"learning_rate": 2.3e-05,
|
| 482 |
+
"loss": 0.7109,
|
| 483 |
+
"step": 460
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.38,
|
| 487 |
+
"eval_accuracy": 0.7283600986206437,
|
| 488 |
+
"eval_loss": 0.6510820984840393,
|
| 489 |
+
"eval_runtime": 49.5999,
|
| 490 |
+
"eval_samples_per_second": 605.122,
|
| 491 |
+
"eval_steps_per_second": 1.19,
|
| 492 |
+
"step": 460
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.41,
|
| 496 |
+
"learning_rate": 2.3500000000000002e-05,
|
| 497 |
+
"loss": 0.701,
|
| 498 |
+
"step": 470
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.44,
|
| 502 |
+
"learning_rate": 2.4e-05,
|
| 503 |
+
"loss": 0.6882,
|
| 504 |
+
"step": 480
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.44,
|
| 508 |
+
"eval_accuracy": 0.7576797494502565,
|
| 509 |
+
"eval_loss": 0.5987845063209534,
|
| 510 |
+
"eval_runtime": 49.5123,
|
| 511 |
+
"eval_samples_per_second": 606.192,
|
| 512 |
+
"eval_steps_per_second": 1.192,
|
| 513 |
+
"step": 480
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.47,
|
| 517 |
+
"learning_rate": 2.4500000000000003e-05,
|
| 518 |
+
"loss": 0.651,
|
| 519 |
+
"step": 490
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.5,
|
| 523 |
+
"learning_rate": 2.5e-05,
|
| 524 |
+
"loss": 0.7296,
|
| 525 |
+
"step": 500
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.5,
|
| 529 |
+
"eval_accuracy": 0.7564136736189778,
|
| 530 |
+
"eval_loss": 0.5992804765701294,
|
| 531 |
+
"eval_runtime": 49.5641,
|
| 532 |
+
"eval_samples_per_second": 605.56,
|
| 533 |
+
"eval_steps_per_second": 1.19,
|
| 534 |
+
"step": 500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.53,
|
| 538 |
+
"learning_rate": 2.55e-05,
|
| 539 |
+
"loss": 0.5943,
|
| 540 |
+
"step": 510
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.57,
|
| 544 |
+
"learning_rate": 2.6e-05,
|
| 545 |
+
"loss": 0.5677,
|
| 546 |
+
"step": 520
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.57,
|
| 550 |
+
"eval_accuracy": 0.8125874591857133,
|
| 551 |
+
"eval_loss": 0.5067983865737915,
|
| 552 |
+
"eval_runtime": 49.3712,
|
| 553 |
+
"eval_samples_per_second": 607.925,
|
| 554 |
+
"eval_steps_per_second": 1.195,
|
| 555 |
+
"step": 520
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.6,
|
| 559 |
+
"learning_rate": 2.65e-05,
|
| 560 |
+
"loss": 0.5818,
|
| 561 |
+
"step": 530
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.63,
|
| 565 |
+
"learning_rate": 2.7e-05,
|
| 566 |
+
"loss": 0.5096,
|
| 567 |
+
"step": 540
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.63,
|
| 571 |
+
"eval_accuracy": 0.8520023988805224,
|
| 572 |
+
"eval_loss": 0.42726200819015503,
|
| 573 |
+
"eval_runtime": 49.3448,
|
| 574 |
+
"eval_samples_per_second": 608.251,
|
| 575 |
+
"eval_steps_per_second": 1.196,
|
| 576 |
+
"step": 540
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.66,
|
| 580 |
+
"learning_rate": 2.75e-05,
|
| 581 |
+
"loss": 0.462,
|
| 582 |
+
"step": 550
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.69,
|
| 586 |
+
"learning_rate": 2.8e-05,
|
| 587 |
+
"loss": 0.4452,
|
| 588 |
+
"step": 560
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 1.69,
|
| 592 |
+
"eval_accuracy": 0.8721929766109149,
|
| 593 |
+
"eval_loss": 0.37960025668144226,
|
| 594 |
+
"eval_runtime": 49.2893,
|
| 595 |
+
"eval_samples_per_second": 608.936,
|
| 596 |
+
"eval_steps_per_second": 1.197,
|
| 597 |
+
"step": 560
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.72,
|
| 601 |
+
"learning_rate": 2.85e-05,
|
| 602 |
+
"loss": 0.4267,
|
| 603 |
+
"step": 570
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.75,
|
| 607 |
+
"learning_rate": 2.9000000000000004e-05,
|
| 608 |
+
"loss": 0.3836,
|
| 609 |
+
"step": 580
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.75,
|
| 613 |
+
"eval_accuracy": 0.8756580262544146,
|
| 614 |
+
"eval_loss": 0.3854842483997345,
|
| 615 |
+
"eval_runtime": 49.5207,
|
| 616 |
+
"eval_samples_per_second": 606.09,
|
| 617 |
+
"eval_steps_per_second": 1.191,
|
| 618 |
+
"step": 580
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.78,
|
| 622 |
+
"learning_rate": 2.95e-05,
|
| 623 |
+
"loss": 0.3828,
|
| 624 |
+
"step": 590
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 1.81,
|
| 628 |
+
"learning_rate": 3e-05,
|
| 629 |
+
"loss": 0.3783,
|
| 630 |
+
"step": 600
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 1.81,
|
| 634 |
+
"eval_accuracy": 0.8893849536882789,
|
| 635 |
+
"eval_loss": 0.35855188965797424,
|
| 636 |
+
"eval_runtime": 49.3852,
|
| 637 |
+
"eval_samples_per_second": 607.753,
|
| 638 |
+
"eval_steps_per_second": 1.195,
|
| 639 |
+
"step": 600
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.84,
|
| 643 |
+
"learning_rate": 3.05e-05,
|
| 644 |
+
"loss": 0.3466,
|
| 645 |
+
"step": 610
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 1.87,
|
| 649 |
+
"learning_rate": 3.1e-05,
|
| 650 |
+
"loss": 0.3496,
|
| 651 |
+
"step": 620
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 1.87,
|
| 655 |
+
"eval_accuracy": 0.8971813153861531,
|
| 656 |
+
"eval_loss": 0.321043998003006,
|
| 657 |
+
"eval_runtime": 49.4982,
|
| 658 |
+
"eval_samples_per_second": 606.366,
|
| 659 |
+
"eval_steps_per_second": 1.192,
|
| 660 |
+
"step": 620
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.9,
|
| 664 |
+
"learning_rate": 3.15e-05,
|
| 665 |
+
"loss": 0.3421,
|
| 666 |
+
"step": 630
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 1.93,
|
| 670 |
+
"learning_rate": 3.2e-05,
|
| 671 |
+
"loss": 0.3585,
|
| 672 |
+
"step": 640
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 1.93,
|
| 676 |
+
"eval_accuracy": 0.9035450123275804,
|
| 677 |
+
"eval_loss": 0.3006099760532379,
|
| 678 |
+
"eval_runtime": 49.5179,
|
| 679 |
+
"eval_samples_per_second": 606.124,
|
| 680 |
+
"eval_steps_per_second": 1.191,
|
| 681 |
+
"step": 640
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.96,
|
| 685 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 686 |
+
"loss": 0.3442,
|
| 687 |
+
"step": 650
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 1.99,
|
| 691 |
+
"learning_rate": 3.3e-05,
|
| 692 |
+
"loss": 0.345,
|
| 693 |
+
"step": 660
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 1.99,
|
| 697 |
+
"eval_accuracy": 0.9014126740854268,
|
| 698 |
+
"eval_loss": 0.30540063977241516,
|
| 699 |
+
"eval_runtime": 49.5044,
|
| 700 |
+
"eval_samples_per_second": 606.289,
|
| 701 |
+
"eval_steps_per_second": 1.192,
|
| 702 |
+
"step": 660
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 2.02,
|
| 706 |
+
"learning_rate": 3.35e-05,
|
| 707 |
+
"loss": 0.3246,
|
| 708 |
+
"step": 670
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 2.05,
|
| 712 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 713 |
+
"loss": 0.3327,
|
| 714 |
+
"step": 680
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 2.05,
|
| 718 |
+
"eval_accuracy": 0.8912507496501633,
|
| 719 |
+
"eval_loss": 0.3174073100090027,
|
| 720 |
+
"eval_runtime": 49.4656,
|
| 721 |
+
"eval_samples_per_second": 606.765,
|
| 722 |
+
"eval_steps_per_second": 1.193,
|
| 723 |
+
"step": 680
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 2.08,
|
| 727 |
+
"learning_rate": 3.4500000000000005e-05,
|
| 728 |
+
"loss": 0.3172,
|
| 729 |
+
"step": 690
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 2.11,
|
| 733 |
+
"learning_rate": 3.5000000000000004e-05,
|
| 734 |
+
"loss": 0.2962,
|
| 735 |
+
"step": 700
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 2.11,
|
| 739 |
+
"eval_accuracy": 0.9122076364363297,
|
| 740 |
+
"eval_loss": 0.2769884169101715,
|
| 741 |
+
"eval_runtime": 49.5225,
|
| 742 |
+
"eval_samples_per_second": 606.068,
|
| 743 |
+
"eval_steps_per_second": 1.191,
|
| 744 |
+
"step": 700
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 2.14,
|
| 748 |
+
"learning_rate": 3.5499999999999996e-05,
|
| 749 |
+
"loss": 0.287,
|
| 750 |
+
"step": 710
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 2.17,
|
| 754 |
+
"learning_rate": 3.6e-05,
|
| 755 |
+
"loss": 0.3032,
|
| 756 |
+
"step": 720
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 2.17,
|
| 760 |
+
"eval_accuracy": 0.9062437529153062,
|
| 761 |
+
"eval_loss": 0.2979203760623932,
|
| 762 |
+
"eval_runtime": 49.2758,
|
| 763 |
+
"eval_samples_per_second": 609.102,
|
| 764 |
+
"eval_steps_per_second": 1.197,
|
| 765 |
+
"step": 720
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 2.2,
|
| 769 |
+
"learning_rate": 3.65e-05,
|
| 770 |
+
"loss": 0.3017,
|
| 771 |
+
"step": 730
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 2.23,
|
| 775 |
+
"learning_rate": 3.7e-05,
|
| 776 |
+
"loss": 0.27,
|
| 777 |
+
"step": 740
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 2.23,
|
| 781 |
+
"eval_accuracy": 0.8997801026187779,
|
| 782 |
+
"eval_loss": 0.29734131693840027,
|
| 783 |
+
"eval_runtime": 49.4882,
|
| 784 |
+
"eval_samples_per_second": 606.488,
|
| 785 |
+
"eval_steps_per_second": 1.192,
|
| 786 |
+
"step": 740
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 2.26,
|
| 790 |
+
"learning_rate": 3.75e-05,
|
| 791 |
+
"loss": 0.3042,
|
| 792 |
+
"step": 750
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 2.29,
|
| 796 |
+
"learning_rate": 3.8e-05,
|
| 797 |
+
"loss": 0.2912,
|
| 798 |
+
"step": 760
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 2.29,
|
| 802 |
+
"eval_accuracy": 0.9221696541613914,
|
| 803 |
+
"eval_loss": 0.24671417474746704,
|
| 804 |
+
"eval_runtime": 49.5036,
|
| 805 |
+
"eval_samples_per_second": 606.299,
|
| 806 |
+
"eval_steps_per_second": 1.192,
|
| 807 |
+
"step": 760
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 2.32,
|
| 811 |
+
"learning_rate": 3.85e-05,
|
| 812 |
+
"loss": 0.2609,
|
| 813 |
+
"step": 770
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 2.35,
|
| 817 |
+
"learning_rate": 3.9e-05,
|
| 818 |
+
"loss": 0.2412,
|
| 819 |
+
"step": 780
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 2.35,
|
| 823 |
+
"eval_accuracy": 0.9113080562404211,
|
| 824 |
+
"eval_loss": 0.2760636806488037,
|
| 825 |
+
"eval_runtime": 49.4644,
|
| 826 |
+
"eval_samples_per_second": 606.78,
|
| 827 |
+
"eval_steps_per_second": 1.193,
|
| 828 |
+
"step": 780
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 2.38,
|
| 832 |
+
"learning_rate": 3.95e-05,
|
| 833 |
+
"loss": 0.2755,
|
| 834 |
+
"step": 790
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 2.41,
|
| 838 |
+
"learning_rate": 4e-05,
|
| 839 |
+
"loss": 0.2746,
|
| 840 |
+
"step": 800
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 2.41,
|
| 844 |
+
"eval_accuracy": 0.9260011994402612,
|
| 845 |
+
"eval_loss": 0.24102580547332764,
|
| 846 |
+
"eval_runtime": 49.464,
|
| 847 |
+
"eval_samples_per_second": 606.785,
|
| 848 |
+
"eval_steps_per_second": 1.193,
|
| 849 |
+
"step": 800
|
| 850 |
+
}
|
| 851 |
+
],
|
| 852 |
+
"logging_steps": 10,
|
| 853 |
+
"max_steps": 996,
|
| 854 |
+
"num_train_epochs": 3,
|
| 855 |
+
"save_steps": 100,
|
| 856 |
+
"total_flos": 1.077670425216942e+17,
|
| 857 |
+
"trial_name": null,
|
| 858 |
+
"trial_params": null
|
| 859 |
+
}
|
checkpoint-800/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f1be80ebe52f6e43af0b8aa087e72fad77310d5998b6e0b8f66a6a1d53be7b7
|
| 3 |
+
size 4536
|
checkpoint-800/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|