Training in progress, step 1000, checkpoint
Browse files- checkpoint-1000/config.json +39 -0
- checkpoint-1000/merges.txt +0 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/pytorch_model.bin +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/special_tokens_map.json +51 -0
- checkpoint-1000/tokenizer.json +0 -0
- checkpoint-1000/tokenizer_config.json +57 -0
- checkpoint-1000/trainer_state.json +1269 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-1000/vocab.json +0 -0
checkpoint-1000/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "sheepy928/default",
|
| 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-1000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:552abcb3e123814686b6c004398104e605e802352e518ca4ee6a4c1b16d6242a
|
| 3 |
+
size 997351674
|
checkpoint-1000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b94337a27ae42eb457b034d86783a897de3f67a0ad0c0e0d3e54a565b167676e
|
| 3 |
+
size 498661166
|
checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a896a7951f3fee8df174a586461402f24fc4697e9dad3bcbf98dbb419f6ede5d
|
| 3 |
+
size 14244
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:246b5fc88eebb030322fae5f39eb576516f2c2a8a21a5037e285c349f58e19e4
|
| 3 |
+
size 1064
|
checkpoint-1000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-1000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/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-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,1269 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.319148936170213,
|
| 5 |
+
"eval_steps": 20,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"learning_rate": 0.0004995563442768412,
|
| 14 |
+
"loss": 1.3139,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.11,
|
| 19 |
+
"learning_rate": 0.0004986690328305235,
|
| 20 |
+
"loss": 1.2812,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.11,
|
| 25 |
+
"eval_accuracy": 0.7386666666666667,
|
| 26 |
+
"eval_combined_score": 0.6626504648943422,
|
| 27 |
+
"eval_f1": 0.6276400817995911,
|
| 28 |
+
"eval_loss": 0.8499402403831482,
|
| 29 |
+
"eval_precision": 0.5456284444444445,
|
| 30 |
+
"eval_recall": 0.7386666666666667,
|
| 31 |
+
"eval_runtime": 125.9807,
|
| 32 |
+
"eval_samples_per_second": 11.907,
|
| 33 |
+
"eval_steps_per_second": 0.373,
|
| 34 |
+
"step": 20
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.16,
|
| 38 |
+
"learning_rate": 0.0004977817213842058,
|
| 39 |
+
"loss": 0.832,
|
| 40 |
+
"step": 30
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.21,
|
| 44 |
+
"learning_rate": 0.0004968944099378882,
|
| 45 |
+
"loss": 0.8156,
|
| 46 |
+
"step": 40
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.21,
|
| 50 |
+
"eval_accuracy": 0.7386666666666667,
|
| 51 |
+
"eval_combined_score": 0.6626504648943422,
|
| 52 |
+
"eval_f1": 0.6276400817995911,
|
| 53 |
+
"eval_loss": 0.8848057985305786,
|
| 54 |
+
"eval_precision": 0.5456284444444445,
|
| 55 |
+
"eval_recall": 0.7386666666666667,
|
| 56 |
+
"eval_runtime": 46.3365,
|
| 57 |
+
"eval_samples_per_second": 32.372,
|
| 58 |
+
"eval_steps_per_second": 1.014,
|
| 59 |
+
"step": 40
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.27,
|
| 63 |
+
"learning_rate": 0.0004960070984915705,
|
| 64 |
+
"loss": 0.7475,
|
| 65 |
+
"step": 50
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.32,
|
| 69 |
+
"learning_rate": 0.0004951197870452529,
|
| 70 |
+
"loss": 0.7478,
|
| 71 |
+
"step": 60
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.32,
|
| 75 |
+
"eval_accuracy": 0.7386666666666667,
|
| 76 |
+
"eval_combined_score": 0.6626504648943422,
|
| 77 |
+
"eval_f1": 0.6276400817995911,
|
| 78 |
+
"eval_loss": 0.7691774964332581,
|
| 79 |
+
"eval_precision": 0.5456284444444445,
|
| 80 |
+
"eval_recall": 0.7386666666666667,
|
| 81 |
+
"eval_runtime": 6.0551,
|
| 82 |
+
"eval_samples_per_second": 247.726,
|
| 83 |
+
"eval_steps_per_second": 7.762,
|
| 84 |
+
"step": 60
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.37,
|
| 88 |
+
"learning_rate": 0.0004942324755989353,
|
| 89 |
+
"loss": 0.7663,
|
| 90 |
+
"step": 70
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.43,
|
| 94 |
+
"learning_rate": 0.0004933451641526176,
|
| 95 |
+
"loss": 0.6034,
|
| 96 |
+
"step": 80
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.43,
|
| 100 |
+
"eval_accuracy": 0.7386666666666667,
|
| 101 |
+
"eval_combined_score": 0.6626504648943422,
|
| 102 |
+
"eval_f1": 0.6276400817995911,
|
| 103 |
+
"eval_loss": 0.7553095817565918,
|
| 104 |
+
"eval_precision": 0.5456284444444445,
|
| 105 |
+
"eval_recall": 0.7386666666666667,
|
| 106 |
+
"eval_runtime": 6.025,
|
| 107 |
+
"eval_samples_per_second": 248.962,
|
| 108 |
+
"eval_steps_per_second": 7.801,
|
| 109 |
+
"step": 80
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.48,
|
| 113 |
+
"learning_rate": 0.0004924578527063,
|
| 114 |
+
"loss": 0.9511,
|
| 115 |
+
"step": 90
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.53,
|
| 119 |
+
"learning_rate": 0.0004915705412599822,
|
| 120 |
+
"loss": 0.7548,
|
| 121 |
+
"step": 100
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.53,
|
| 125 |
+
"eval_accuracy": 0.7386666666666667,
|
| 126 |
+
"eval_combined_score": 0.6626504648943422,
|
| 127 |
+
"eval_f1": 0.6276400817995911,
|
| 128 |
+
"eval_loss": 0.7768574357032776,
|
| 129 |
+
"eval_precision": 0.5456284444444445,
|
| 130 |
+
"eval_recall": 0.7386666666666667,
|
| 131 |
+
"eval_runtime": 5.9796,
|
| 132 |
+
"eval_samples_per_second": 250.851,
|
| 133 |
+
"eval_steps_per_second": 7.86,
|
| 134 |
+
"step": 100
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.59,
|
| 138 |
+
"learning_rate": 0.0004906832298136646,
|
| 139 |
+
"loss": 0.858,
|
| 140 |
+
"step": 110
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.64,
|
| 144 |
+
"learning_rate": 0.0004897959183673469,
|
| 145 |
+
"loss": 0.8452,
|
| 146 |
+
"step": 120
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.64,
|
| 150 |
+
"eval_accuracy": 0.7386666666666667,
|
| 151 |
+
"eval_combined_score": 0.6626504648943422,
|
| 152 |
+
"eval_f1": 0.6276400817995911,
|
| 153 |
+
"eval_loss": 0.745326817035675,
|
| 154 |
+
"eval_precision": 0.5456284444444445,
|
| 155 |
+
"eval_recall": 0.7386666666666667,
|
| 156 |
+
"eval_runtime": 6.1179,
|
| 157 |
+
"eval_samples_per_second": 245.183,
|
| 158 |
+
"eval_steps_per_second": 7.682,
|
| 159 |
+
"step": 120
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.69,
|
| 163 |
+
"learning_rate": 0.0004889086069210293,
|
| 164 |
+
"loss": 0.8152,
|
| 165 |
+
"step": 130
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.74,
|
| 169 |
+
"learning_rate": 0.00048802129547471164,
|
| 170 |
+
"loss": 0.8972,
|
| 171 |
+
"step": 140
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.74,
|
| 175 |
+
"eval_accuracy": 0.7386666666666667,
|
| 176 |
+
"eval_combined_score": 0.6626504648943422,
|
| 177 |
+
"eval_f1": 0.6276400817995911,
|
| 178 |
+
"eval_loss": 0.7610827088356018,
|
| 179 |
+
"eval_precision": 0.5456284444444445,
|
| 180 |
+
"eval_recall": 0.7386666666666667,
|
| 181 |
+
"eval_runtime": 6.0456,
|
| 182 |
+
"eval_samples_per_second": 248.113,
|
| 183 |
+
"eval_steps_per_second": 7.774,
|
| 184 |
+
"step": 140
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.8,
|
| 188 |
+
"learning_rate": 0.000487133984028394,
|
| 189 |
+
"loss": 0.7226,
|
| 190 |
+
"step": 150
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.85,
|
| 194 |
+
"learning_rate": 0.0004862466725820763,
|
| 195 |
+
"loss": 0.9377,
|
| 196 |
+
"step": 160
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.85,
|
| 200 |
+
"eval_accuracy": 0.7386666666666667,
|
| 201 |
+
"eval_combined_score": 0.6626504648943422,
|
| 202 |
+
"eval_f1": 0.6276400817995911,
|
| 203 |
+
"eval_loss": 0.7714303135871887,
|
| 204 |
+
"eval_precision": 0.5456284444444445,
|
| 205 |
+
"eval_recall": 0.7386666666666667,
|
| 206 |
+
"eval_runtime": 5.9995,
|
| 207 |
+
"eval_samples_per_second": 250.022,
|
| 208 |
+
"eval_steps_per_second": 7.834,
|
| 209 |
+
"step": 160
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.9,
|
| 213 |
+
"learning_rate": 0.0004853593611357587,
|
| 214 |
+
"loss": 0.594,
|
| 215 |
+
"step": 170
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.96,
|
| 219 |
+
"learning_rate": 0.00048447204968944104,
|
| 220 |
+
"loss": 1.0968,
|
| 221 |
+
"step": 180
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.96,
|
| 225 |
+
"eval_accuracy": 0.7386666666666667,
|
| 226 |
+
"eval_combined_score": 0.6626504648943422,
|
| 227 |
+
"eval_f1": 0.6276400817995911,
|
| 228 |
+
"eval_loss": 0.9954016804695129,
|
| 229 |
+
"eval_precision": 0.5456284444444445,
|
| 230 |
+
"eval_recall": 0.7386666666666667,
|
| 231 |
+
"eval_runtime": 5.9871,
|
| 232 |
+
"eval_samples_per_second": 250.537,
|
| 233 |
+
"eval_steps_per_second": 7.85,
|
| 234 |
+
"step": 180
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.01,
|
| 238 |
+
"learning_rate": 0.00048358473824312333,
|
| 239 |
+
"loss": 0.9644,
|
| 240 |
+
"step": 190
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.06,
|
| 244 |
+
"learning_rate": 0.00048269742679680566,
|
| 245 |
+
"loss": 0.7502,
|
| 246 |
+
"step": 200
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.06,
|
| 250 |
+
"eval_accuracy": 0.7386666666666667,
|
| 251 |
+
"eval_combined_score": 0.6626504648943422,
|
| 252 |
+
"eval_f1": 0.6276400817995911,
|
| 253 |
+
"eval_loss": 0.7544593214988708,
|
| 254 |
+
"eval_precision": 0.5456284444444445,
|
| 255 |
+
"eval_recall": 0.7386666666666667,
|
| 256 |
+
"eval_runtime": 6.0077,
|
| 257 |
+
"eval_samples_per_second": 249.679,
|
| 258 |
+
"eval_steps_per_second": 7.823,
|
| 259 |
+
"step": 200
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.12,
|
| 263 |
+
"learning_rate": 0.000481810115350488,
|
| 264 |
+
"loss": 0.7231,
|
| 265 |
+
"step": 210
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.17,
|
| 269 |
+
"learning_rate": 0.0004809228039041704,
|
| 270 |
+
"loss": 0.7902,
|
| 271 |
+
"step": 220
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.17,
|
| 275 |
+
"eval_accuracy": 0.7386666666666667,
|
| 276 |
+
"eval_combined_score": 0.6626504648943422,
|
| 277 |
+
"eval_f1": 0.6276400817995911,
|
| 278 |
+
"eval_loss": 0.7758567929267883,
|
| 279 |
+
"eval_precision": 0.5456284444444445,
|
| 280 |
+
"eval_recall": 0.7386666666666667,
|
| 281 |
+
"eval_runtime": 6.0531,
|
| 282 |
+
"eval_samples_per_second": 247.806,
|
| 283 |
+
"eval_steps_per_second": 7.765,
|
| 284 |
+
"step": 220
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.22,
|
| 288 |
+
"learning_rate": 0.00048003549245785273,
|
| 289 |
+
"loss": 0.7591,
|
| 290 |
+
"step": 230
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.28,
|
| 294 |
+
"learning_rate": 0.00047914818101153507,
|
| 295 |
+
"loss": 0.817,
|
| 296 |
+
"step": 240
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.28,
|
| 300 |
+
"eval_accuracy": 0.7386666666666667,
|
| 301 |
+
"eval_combined_score": 0.6626504648943422,
|
| 302 |
+
"eval_f1": 0.6276400817995911,
|
| 303 |
+
"eval_loss": 0.767899751663208,
|
| 304 |
+
"eval_precision": 0.5456284444444445,
|
| 305 |
+
"eval_recall": 0.7386666666666667,
|
| 306 |
+
"eval_runtime": 6.1711,
|
| 307 |
+
"eval_samples_per_second": 243.067,
|
| 308 |
+
"eval_steps_per_second": 7.616,
|
| 309 |
+
"step": 240
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.33,
|
| 313 |
+
"learning_rate": 0.0004782608695652174,
|
| 314 |
+
"loss": 0.6681,
|
| 315 |
+
"step": 250
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.38,
|
| 319 |
+
"learning_rate": 0.00047737355811889974,
|
| 320 |
+
"loss": 0.9199,
|
| 321 |
+
"step": 260
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.38,
|
| 325 |
+
"eval_accuracy": 0.7386666666666667,
|
| 326 |
+
"eval_combined_score": 0.6626504648943422,
|
| 327 |
+
"eval_f1": 0.6276400817995911,
|
| 328 |
+
"eval_loss": 0.7462519407272339,
|
| 329 |
+
"eval_precision": 0.5456284444444445,
|
| 330 |
+
"eval_recall": 0.7386666666666667,
|
| 331 |
+
"eval_runtime": 6.0331,
|
| 332 |
+
"eval_samples_per_second": 248.63,
|
| 333 |
+
"eval_steps_per_second": 7.79,
|
| 334 |
+
"step": 260
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.44,
|
| 338 |
+
"learning_rate": 0.00047648624667258213,
|
| 339 |
+
"loss": 0.7409,
|
| 340 |
+
"step": 270
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 1.49,
|
| 344 |
+
"learning_rate": 0.0004755989352262644,
|
| 345 |
+
"loss": 0.7246,
|
| 346 |
+
"step": 280
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.49,
|
| 350 |
+
"eval_accuracy": 0.7386666666666667,
|
| 351 |
+
"eval_combined_score": 0.6626504648943422,
|
| 352 |
+
"eval_f1": 0.6276400817995911,
|
| 353 |
+
"eval_loss": 0.7581822872161865,
|
| 354 |
+
"eval_precision": 0.5456284444444445,
|
| 355 |
+
"eval_recall": 0.7386666666666667,
|
| 356 |
+
"eval_runtime": 6.1558,
|
| 357 |
+
"eval_samples_per_second": 243.673,
|
| 358 |
+
"eval_steps_per_second": 7.635,
|
| 359 |
+
"step": 280
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.54,
|
| 363 |
+
"learning_rate": 0.00047471162377994675,
|
| 364 |
+
"loss": 0.6876,
|
| 365 |
+
"step": 290
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.6,
|
| 369 |
+
"learning_rate": 0.0004738243123336291,
|
| 370 |
+
"loss": 0.7508,
|
| 371 |
+
"step": 300
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1.6,
|
| 375 |
+
"eval_accuracy": 0.7386666666666667,
|
| 376 |
+
"eval_combined_score": 0.6626504648943422,
|
| 377 |
+
"eval_f1": 0.6276400817995911,
|
| 378 |
+
"eval_loss": 0.7464602589607239,
|
| 379 |
+
"eval_precision": 0.5456284444444445,
|
| 380 |
+
"eval_recall": 0.7386666666666667,
|
| 381 |
+
"eval_runtime": 6.1548,
|
| 382 |
+
"eval_samples_per_second": 243.711,
|
| 383 |
+
"eval_steps_per_second": 7.636,
|
| 384 |
+
"step": 300
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.65,
|
| 388 |
+
"learning_rate": 0.0004729370008873114,
|
| 389 |
+
"loss": 0.8539,
|
| 390 |
+
"step": 310
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.7,
|
| 394 |
+
"learning_rate": 0.0004720496894409938,
|
| 395 |
+
"loss": 0.7011,
|
| 396 |
+
"step": 320
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.7,
|
| 400 |
+
"eval_accuracy": 0.7386666666666667,
|
| 401 |
+
"eval_combined_score": 0.6626504648943422,
|
| 402 |
+
"eval_f1": 0.6276400817995911,
|
| 403 |
+
"eval_loss": 0.788334310054779,
|
| 404 |
+
"eval_precision": 0.5456284444444445,
|
| 405 |
+
"eval_recall": 0.7386666666666667,
|
| 406 |
+
"eval_runtime": 6.1655,
|
| 407 |
+
"eval_samples_per_second": 243.289,
|
| 408 |
+
"eval_steps_per_second": 7.623,
|
| 409 |
+
"step": 320
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.76,
|
| 413 |
+
"learning_rate": 0.00047116237799467615,
|
| 414 |
+
"loss": 0.9111,
|
| 415 |
+
"step": 330
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.81,
|
| 419 |
+
"learning_rate": 0.0004702750665483585,
|
| 420 |
+
"loss": 0.8442,
|
| 421 |
+
"step": 340
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 1.81,
|
| 425 |
+
"eval_accuracy": 0.7386666666666667,
|
| 426 |
+
"eval_combined_score": 0.6626504648943422,
|
| 427 |
+
"eval_f1": 0.6276400817995911,
|
| 428 |
+
"eval_loss": 0.7656621336936951,
|
| 429 |
+
"eval_precision": 0.5456284444444445,
|
| 430 |
+
"eval_recall": 0.7386666666666667,
|
| 431 |
+
"eval_runtime": 6.2177,
|
| 432 |
+
"eval_samples_per_second": 241.249,
|
| 433 |
+
"eval_steps_per_second": 7.559,
|
| 434 |
+
"step": 340
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.86,
|
| 438 |
+
"learning_rate": 0.00046938775510204083,
|
| 439 |
+
"loss": 0.7179,
|
| 440 |
+
"step": 350
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.91,
|
| 444 |
+
"learning_rate": 0.00046850044365572317,
|
| 445 |
+
"loss": 1.0021,
|
| 446 |
+
"step": 360
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.91,
|
| 450 |
+
"eval_accuracy": 0.7386666666666667,
|
| 451 |
+
"eval_combined_score": 0.6626504648943422,
|
| 452 |
+
"eval_f1": 0.6276400817995911,
|
| 453 |
+
"eval_loss": 0.7755117416381836,
|
| 454 |
+
"eval_precision": 0.5456284444444445,
|
| 455 |
+
"eval_recall": 0.7386666666666667,
|
| 456 |
+
"eval_runtime": 6.0871,
|
| 457 |
+
"eval_samples_per_second": 246.422,
|
| 458 |
+
"eval_steps_per_second": 7.721,
|
| 459 |
+
"step": 360
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.97,
|
| 463 |
+
"learning_rate": 0.0004676131322094055,
|
| 464 |
+
"loss": 0.8331,
|
| 465 |
+
"step": 370
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.02,
|
| 469 |
+
"learning_rate": 0.00046672582076308784,
|
| 470 |
+
"loss": 0.7982,
|
| 471 |
+
"step": 380
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.02,
|
| 475 |
+
"eval_accuracy": 0.7386666666666667,
|
| 476 |
+
"eval_combined_score": 0.6626504648943422,
|
| 477 |
+
"eval_f1": 0.6276400817995911,
|
| 478 |
+
"eval_loss": 0.8436231017112732,
|
| 479 |
+
"eval_precision": 0.5456284444444445,
|
| 480 |
+
"eval_recall": 0.7386666666666667,
|
| 481 |
+
"eval_runtime": 6.0719,
|
| 482 |
+
"eval_samples_per_second": 247.04,
|
| 483 |
+
"eval_steps_per_second": 7.741,
|
| 484 |
+
"step": 380
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 2.07,
|
| 488 |
+
"learning_rate": 0.0004658385093167702,
|
| 489 |
+
"loss": 0.8408,
|
| 490 |
+
"step": 390
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 2.13,
|
| 494 |
+
"learning_rate": 0.0004649511978704525,
|
| 495 |
+
"loss": 0.8299,
|
| 496 |
+
"step": 400
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 2.13,
|
| 500 |
+
"eval_accuracy": 0.7386666666666667,
|
| 501 |
+
"eval_combined_score": 0.6626504648943422,
|
| 502 |
+
"eval_f1": 0.6276400817995911,
|
| 503 |
+
"eval_loss": 0.7582988142967224,
|
| 504 |
+
"eval_precision": 0.5456284444444445,
|
| 505 |
+
"eval_recall": 0.7386666666666667,
|
| 506 |
+
"eval_runtime": 6.2274,
|
| 507 |
+
"eval_samples_per_second": 240.873,
|
| 508 |
+
"eval_steps_per_second": 7.547,
|
| 509 |
+
"step": 400
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 2.18,
|
| 513 |
+
"learning_rate": 0.0004640638864241349,
|
| 514 |
+
"loss": 0.7852,
|
| 515 |
+
"step": 410
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.23,
|
| 519 |
+
"learning_rate": 0.00046317657497781724,
|
| 520 |
+
"loss": 0.8789,
|
| 521 |
+
"step": 420
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.23,
|
| 525 |
+
"eval_accuracy": 0.7386666666666667,
|
| 526 |
+
"eval_combined_score": 0.6626504648943422,
|
| 527 |
+
"eval_f1": 0.6276400817995911,
|
| 528 |
+
"eval_loss": 0.7546933889389038,
|
| 529 |
+
"eval_precision": 0.5456284444444445,
|
| 530 |
+
"eval_recall": 0.7386666666666667,
|
| 531 |
+
"eval_runtime": 6.3059,
|
| 532 |
+
"eval_samples_per_second": 237.872,
|
| 533 |
+
"eval_steps_per_second": 7.453,
|
| 534 |
+
"step": 420
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.29,
|
| 538 |
+
"learning_rate": 0.0004622892635314996,
|
| 539 |
+
"loss": 0.6384,
|
| 540 |
+
"step": 430
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 2.34,
|
| 544 |
+
"learning_rate": 0.0004614019520851819,
|
| 545 |
+
"loss": 0.8853,
|
| 546 |
+
"step": 440
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 2.34,
|
| 550 |
+
"eval_accuracy": 0.7386666666666667,
|
| 551 |
+
"eval_combined_score": 0.6626504648943422,
|
| 552 |
+
"eval_f1": 0.6276400817995911,
|
| 553 |
+
"eval_loss": 0.7661357522010803,
|
| 554 |
+
"eval_precision": 0.5456284444444445,
|
| 555 |
+
"eval_recall": 0.7386666666666667,
|
| 556 |
+
"eval_runtime": 6.3477,
|
| 557 |
+
"eval_samples_per_second": 236.306,
|
| 558 |
+
"eval_steps_per_second": 7.404,
|
| 559 |
+
"step": 440
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 2.39,
|
| 563 |
+
"learning_rate": 0.0004605146406388642,
|
| 564 |
+
"loss": 0.7721,
|
| 565 |
+
"step": 450
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 2.45,
|
| 569 |
+
"learning_rate": 0.0004596273291925466,
|
| 570 |
+
"loss": 0.7522,
|
| 571 |
+
"step": 460
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.45,
|
| 575 |
+
"eval_accuracy": 0.7386666666666667,
|
| 576 |
+
"eval_combined_score": 0.6626504648943422,
|
| 577 |
+
"eval_f1": 0.6276400817995911,
|
| 578 |
+
"eval_loss": 0.7484121322631836,
|
| 579 |
+
"eval_precision": 0.5456284444444445,
|
| 580 |
+
"eval_recall": 0.7386666666666667,
|
| 581 |
+
"eval_runtime": 6.2677,
|
| 582 |
+
"eval_samples_per_second": 239.321,
|
| 583 |
+
"eval_steps_per_second": 7.499,
|
| 584 |
+
"step": 460
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.5,
|
| 588 |
+
"learning_rate": 0.0004587400177462289,
|
| 589 |
+
"loss": 0.8076,
|
| 590 |
+
"step": 470
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.55,
|
| 594 |
+
"learning_rate": 0.00045785270629991126,
|
| 595 |
+
"loss": 0.9035,
|
| 596 |
+
"step": 480
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 2.55,
|
| 600 |
+
"eval_accuracy": 0.7386666666666667,
|
| 601 |
+
"eval_combined_score": 0.6626504648943422,
|
| 602 |
+
"eval_f1": 0.6276400817995911,
|
| 603 |
+
"eval_loss": 0.7667799592018127,
|
| 604 |
+
"eval_precision": 0.5456284444444445,
|
| 605 |
+
"eval_recall": 0.7386666666666667,
|
| 606 |
+
"eval_runtime": 6.4501,
|
| 607 |
+
"eval_samples_per_second": 232.554,
|
| 608 |
+
"eval_steps_per_second": 7.287,
|
| 609 |
+
"step": 480
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 2.61,
|
| 613 |
+
"learning_rate": 0.0004569653948535936,
|
| 614 |
+
"loss": 0.7544,
|
| 615 |
+
"step": 490
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 2.66,
|
| 619 |
+
"learning_rate": 0.000456078083407276,
|
| 620 |
+
"loss": 0.8717,
|
| 621 |
+
"step": 500
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 2.66,
|
| 625 |
+
"eval_accuracy": 0.7386666666666667,
|
| 626 |
+
"eval_combined_score": 0.6626504648943422,
|
| 627 |
+
"eval_f1": 0.6276400817995911,
|
| 628 |
+
"eval_loss": 0.7541614770889282,
|
| 629 |
+
"eval_precision": 0.5456284444444445,
|
| 630 |
+
"eval_recall": 0.7386666666666667,
|
| 631 |
+
"eval_runtime": 6.4865,
|
| 632 |
+
"eval_samples_per_second": 231.251,
|
| 633 |
+
"eval_steps_per_second": 7.246,
|
| 634 |
+
"step": 500
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.71,
|
| 638 |
+
"learning_rate": 0.00045519077196095833,
|
| 639 |
+
"loss": 0.6823,
|
| 640 |
+
"step": 510
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.77,
|
| 644 |
+
"learning_rate": 0.00045430346051464067,
|
| 645 |
+
"loss": 0.8903,
|
| 646 |
+
"step": 520
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 2.77,
|
| 650 |
+
"eval_accuracy": 0.7386666666666667,
|
| 651 |
+
"eval_combined_score": 0.6626504648943422,
|
| 652 |
+
"eval_f1": 0.6276400817995911,
|
| 653 |
+
"eval_loss": 0.801760733127594,
|
| 654 |
+
"eval_precision": 0.5456284444444445,
|
| 655 |
+
"eval_recall": 0.7386666666666667,
|
| 656 |
+
"eval_runtime": 6.3567,
|
| 657 |
+
"eval_samples_per_second": 235.972,
|
| 658 |
+
"eval_steps_per_second": 7.394,
|
| 659 |
+
"step": 520
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 2.82,
|
| 663 |
+
"learning_rate": 0.000453416149068323,
|
| 664 |
+
"loss": 0.7565,
|
| 665 |
+
"step": 530
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 2.87,
|
| 669 |
+
"learning_rate": 0.0004525288376220053,
|
| 670 |
+
"loss": 0.7392,
|
| 671 |
+
"step": 540
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 2.87,
|
| 675 |
+
"eval_accuracy": 0.7386666666666667,
|
| 676 |
+
"eval_combined_score": 0.6626504648943422,
|
| 677 |
+
"eval_f1": 0.6276400817995911,
|
| 678 |
+
"eval_loss": 0.7826161980628967,
|
| 679 |
+
"eval_precision": 0.5456284444444445,
|
| 680 |
+
"eval_recall": 0.7386666666666667,
|
| 681 |
+
"eval_runtime": 6.5294,
|
| 682 |
+
"eval_samples_per_second": 229.731,
|
| 683 |
+
"eval_steps_per_second": 7.198,
|
| 684 |
+
"step": 540
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 2.93,
|
| 688 |
+
"learning_rate": 0.0004516415261756877,
|
| 689 |
+
"loss": 0.629,
|
| 690 |
+
"step": 550
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.98,
|
| 694 |
+
"learning_rate": 0.00045075421472937,
|
| 695 |
+
"loss": 0.8626,
|
| 696 |
+
"step": 560
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 2.98,
|
| 700 |
+
"eval_accuracy": 0.7386666666666667,
|
| 701 |
+
"eval_combined_score": 0.6626504648943422,
|
| 702 |
+
"eval_f1": 0.6276400817995911,
|
| 703 |
+
"eval_loss": 0.7489452958106995,
|
| 704 |
+
"eval_precision": 0.5456284444444445,
|
| 705 |
+
"eval_recall": 0.7386666666666667,
|
| 706 |
+
"eval_runtime": 6.3521,
|
| 707 |
+
"eval_samples_per_second": 236.143,
|
| 708 |
+
"eval_steps_per_second": 7.399,
|
| 709 |
+
"step": 560
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 3.03,
|
| 713 |
+
"learning_rate": 0.00044986690328305235,
|
| 714 |
+
"loss": 0.7379,
|
| 715 |
+
"step": 570
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 3.09,
|
| 719 |
+
"learning_rate": 0.0004489795918367347,
|
| 720 |
+
"loss": 0.6063,
|
| 721 |
+
"step": 580
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 3.09,
|
| 725 |
+
"eval_accuracy": 0.7386666666666667,
|
| 726 |
+
"eval_combined_score": 0.6626504648943422,
|
| 727 |
+
"eval_f1": 0.6276400817995911,
|
| 728 |
+
"eval_loss": 0.9793464541435242,
|
| 729 |
+
"eval_precision": 0.5456284444444445,
|
| 730 |
+
"eval_recall": 0.7386666666666667,
|
| 731 |
+
"eval_runtime": 6.3272,
|
| 732 |
+
"eval_samples_per_second": 237.071,
|
| 733 |
+
"eval_steps_per_second": 7.428,
|
| 734 |
+
"step": 580
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 3.14,
|
| 738 |
+
"learning_rate": 0.000448092280390417,
|
| 739 |
+
"loss": 0.9408,
|
| 740 |
+
"step": 590
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 3.19,
|
| 744 |
+
"learning_rate": 0.0004472049689440994,
|
| 745 |
+
"loss": 0.8703,
|
| 746 |
+
"step": 600
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 3.19,
|
| 750 |
+
"eval_accuracy": 0.7386666666666667,
|
| 751 |
+
"eval_combined_score": 0.6626504648943422,
|
| 752 |
+
"eval_f1": 0.6276400817995911,
|
| 753 |
+
"eval_loss": 0.7475989460945129,
|
| 754 |
+
"eval_precision": 0.5456284444444445,
|
| 755 |
+
"eval_recall": 0.7386666666666667,
|
| 756 |
+
"eval_runtime": 6.3253,
|
| 757 |
+
"eval_samples_per_second": 237.143,
|
| 758 |
+
"eval_steps_per_second": 7.43,
|
| 759 |
+
"step": 600
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 3.24,
|
| 763 |
+
"learning_rate": 0.00044631765749778175,
|
| 764 |
+
"loss": 0.8594,
|
| 765 |
+
"step": 610
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 3.3,
|
| 769 |
+
"learning_rate": 0.0004454303460514641,
|
| 770 |
+
"loss": 0.797,
|
| 771 |
+
"step": 620
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 3.3,
|
| 775 |
+
"eval_accuracy": 0.7386666666666667,
|
| 776 |
+
"eval_combined_score": 0.6626504648943422,
|
| 777 |
+
"eval_f1": 0.6276400817995911,
|
| 778 |
+
"eval_loss": 0.7692281603813171,
|
| 779 |
+
"eval_precision": 0.5456284444444445,
|
| 780 |
+
"eval_recall": 0.7386666666666667,
|
| 781 |
+
"eval_runtime": 6.6464,
|
| 782 |
+
"eval_samples_per_second": 225.686,
|
| 783 |
+
"eval_steps_per_second": 7.071,
|
| 784 |
+
"step": 620
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 3.35,
|
| 788 |
+
"learning_rate": 0.0004445430346051464,
|
| 789 |
+
"loss": 0.8531,
|
| 790 |
+
"step": 630
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 3.4,
|
| 794 |
+
"learning_rate": 0.00044365572315882877,
|
| 795 |
+
"loss": 0.7526,
|
| 796 |
+
"step": 640
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 3.4,
|
| 800 |
+
"eval_accuracy": 0.7386666666666667,
|
| 801 |
+
"eval_combined_score": 0.6626504648943422,
|
| 802 |
+
"eval_f1": 0.6276400817995911,
|
| 803 |
+
"eval_loss": 0.7548736929893494,
|
| 804 |
+
"eval_precision": 0.5456284444444445,
|
| 805 |
+
"eval_recall": 0.7386666666666667,
|
| 806 |
+
"eval_runtime": 6.5723,
|
| 807 |
+
"eval_samples_per_second": 228.23,
|
| 808 |
+
"eval_steps_per_second": 7.151,
|
| 809 |
+
"step": 640
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 3.46,
|
| 813 |
+
"learning_rate": 0.0004427684117125111,
|
| 814 |
+
"loss": 0.8442,
|
| 815 |
+
"step": 650
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 3.51,
|
| 819 |
+
"learning_rate": 0.00044188110026619344,
|
| 820 |
+
"loss": 0.9005,
|
| 821 |
+
"step": 660
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 3.51,
|
| 825 |
+
"eval_accuracy": 0.7386666666666667,
|
| 826 |
+
"eval_combined_score": 0.6626504648943422,
|
| 827 |
+
"eval_f1": 0.6276400817995911,
|
| 828 |
+
"eval_loss": 0.8103847503662109,
|
| 829 |
+
"eval_precision": 0.5456284444444445,
|
| 830 |
+
"eval_recall": 0.7386666666666667,
|
| 831 |
+
"eval_runtime": 6.4776,
|
| 832 |
+
"eval_samples_per_second": 231.566,
|
| 833 |
+
"eval_steps_per_second": 7.256,
|
| 834 |
+
"step": 660
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 3.56,
|
| 838 |
+
"learning_rate": 0.0004409937888198758,
|
| 839 |
+
"loss": 0.8343,
|
| 840 |
+
"step": 670
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 3.62,
|
| 844 |
+
"learning_rate": 0.0004401064773735581,
|
| 845 |
+
"loss": 0.7993,
|
| 846 |
+
"step": 680
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 3.62,
|
| 850 |
+
"eval_accuracy": 0.7386666666666667,
|
| 851 |
+
"eval_combined_score": 0.6626504648943422,
|
| 852 |
+
"eval_f1": 0.6276400817995911,
|
| 853 |
+
"eval_loss": 0.8053144812583923,
|
| 854 |
+
"eval_precision": 0.5456284444444445,
|
| 855 |
+
"eval_recall": 0.7386666666666667,
|
| 856 |
+
"eval_runtime": 6.3285,
|
| 857 |
+
"eval_samples_per_second": 237.021,
|
| 858 |
+
"eval_steps_per_second": 7.427,
|
| 859 |
+
"step": 680
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 3.67,
|
| 863 |
+
"learning_rate": 0.0004392191659272405,
|
| 864 |
+
"loss": 0.8369,
|
| 865 |
+
"step": 690
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 3.72,
|
| 869 |
+
"learning_rate": 0.00043833185448092284,
|
| 870 |
+
"loss": 0.7966,
|
| 871 |
+
"step": 700
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 3.72,
|
| 875 |
+
"eval_accuracy": 0.7386666666666667,
|
| 876 |
+
"eval_combined_score": 0.6626504648943422,
|
| 877 |
+
"eval_f1": 0.6276400817995911,
|
| 878 |
+
"eval_loss": 0.7448229193687439,
|
| 879 |
+
"eval_precision": 0.5456284444444445,
|
| 880 |
+
"eval_recall": 0.7386666666666667,
|
| 881 |
+
"eval_runtime": 6.3865,
|
| 882 |
+
"eval_samples_per_second": 234.871,
|
| 883 |
+
"eval_steps_per_second": 7.359,
|
| 884 |
+
"step": 700
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 3.78,
|
| 888 |
+
"learning_rate": 0.0004374445430346052,
|
| 889 |
+
"loss": 0.7612,
|
| 890 |
+
"step": 710
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 3.83,
|
| 894 |
+
"learning_rate": 0.00043655723158828746,
|
| 895 |
+
"loss": 0.7656,
|
| 896 |
+
"step": 720
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 3.83,
|
| 900 |
+
"eval_accuracy": 0.7386666666666667,
|
| 901 |
+
"eval_combined_score": 0.6626504648943422,
|
| 902 |
+
"eval_f1": 0.6276400817995911,
|
| 903 |
+
"eval_loss": 0.7586243748664856,
|
| 904 |
+
"eval_precision": 0.5456284444444445,
|
| 905 |
+
"eval_recall": 0.7386666666666667,
|
| 906 |
+
"eval_runtime": 6.3473,
|
| 907 |
+
"eval_samples_per_second": 236.32,
|
| 908 |
+
"eval_steps_per_second": 7.405,
|
| 909 |
+
"step": 720
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 3.88,
|
| 913 |
+
"learning_rate": 0.0004356699201419698,
|
| 914 |
+
"loss": 0.6469,
|
| 915 |
+
"step": 730
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 3.94,
|
| 919 |
+
"learning_rate": 0.0004347826086956522,
|
| 920 |
+
"loss": 0.6889,
|
| 921 |
+
"step": 740
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 3.94,
|
| 925 |
+
"eval_accuracy": 0.7386666666666667,
|
| 926 |
+
"eval_combined_score": 0.6626504648943422,
|
| 927 |
+
"eval_f1": 0.6276400817995911,
|
| 928 |
+
"eval_loss": 0.7640272378921509,
|
| 929 |
+
"eval_precision": 0.5456284444444445,
|
| 930 |
+
"eval_recall": 0.7386666666666667,
|
| 931 |
+
"eval_runtime": 6.3581,
|
| 932 |
+
"eval_samples_per_second": 235.92,
|
| 933 |
+
"eval_steps_per_second": 7.392,
|
| 934 |
+
"step": 740
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 3.99,
|
| 938 |
+
"learning_rate": 0.0004338952972493345,
|
| 939 |
+
"loss": 0.7086,
|
| 940 |
+
"step": 750
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 4.04,
|
| 944 |
+
"learning_rate": 0.00043300798580301686,
|
| 945 |
+
"loss": 0.8226,
|
| 946 |
+
"step": 760
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 4.04,
|
| 950 |
+
"eval_accuracy": 0.7386666666666667,
|
| 951 |
+
"eval_combined_score": 0.6626504648943422,
|
| 952 |
+
"eval_f1": 0.6276400817995911,
|
| 953 |
+
"eval_loss": 0.8118994235992432,
|
| 954 |
+
"eval_precision": 0.5456284444444445,
|
| 955 |
+
"eval_recall": 0.7386666666666667,
|
| 956 |
+
"eval_runtime": 6.3396,
|
| 957 |
+
"eval_samples_per_second": 236.61,
|
| 958 |
+
"eval_steps_per_second": 7.414,
|
| 959 |
+
"step": 760
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 4.1,
|
| 963 |
+
"learning_rate": 0.0004321206743566992,
|
| 964 |
+
"loss": 1.0159,
|
| 965 |
+
"step": 770
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 4.15,
|
| 969 |
+
"learning_rate": 0.0004312333629103816,
|
| 970 |
+
"loss": 0.8907,
|
| 971 |
+
"step": 780
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 4.15,
|
| 975 |
+
"eval_accuracy": 0.7386666666666667,
|
| 976 |
+
"eval_combined_score": 0.6626504648943422,
|
| 977 |
+
"eval_f1": 0.6276400817995911,
|
| 978 |
+
"eval_loss": 0.7906585335731506,
|
| 979 |
+
"eval_precision": 0.5456284444444445,
|
| 980 |
+
"eval_recall": 0.7386666666666667,
|
| 981 |
+
"eval_runtime": 6.4149,
|
| 982 |
+
"eval_samples_per_second": 233.829,
|
| 983 |
+
"eval_steps_per_second": 7.327,
|
| 984 |
+
"step": 780
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 4.2,
|
| 988 |
+
"learning_rate": 0.00043034605146406393,
|
| 989 |
+
"loss": 0.6486,
|
| 990 |
+
"step": 790
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 4.26,
|
| 994 |
+
"learning_rate": 0.00042945874001774627,
|
| 995 |
+
"loss": 0.8749,
|
| 996 |
+
"step": 800
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 4.26,
|
| 1000 |
+
"eval_accuracy": 0.7386666666666667,
|
| 1001 |
+
"eval_combined_score": 0.6626504648943422,
|
| 1002 |
+
"eval_f1": 0.6276400817995911,
|
| 1003 |
+
"eval_loss": 0.7677525877952576,
|
| 1004 |
+
"eval_precision": 0.5456284444444445,
|
| 1005 |
+
"eval_recall": 0.7386666666666667,
|
| 1006 |
+
"eval_runtime": 6.3008,
|
| 1007 |
+
"eval_samples_per_second": 238.066,
|
| 1008 |
+
"eval_steps_per_second": 7.459,
|
| 1009 |
+
"step": 800
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 4.31,
|
| 1013 |
+
"learning_rate": 0.00042857142857142855,
|
| 1014 |
+
"loss": 0.6891,
|
| 1015 |
+
"step": 810
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 4.36,
|
| 1019 |
+
"learning_rate": 0.0004276841171251109,
|
| 1020 |
+
"loss": 0.749,
|
| 1021 |
+
"step": 820
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 4.36,
|
| 1025 |
+
"eval_accuracy": 0.7386666666666667,
|
| 1026 |
+
"eval_combined_score": 0.6626504648943422,
|
| 1027 |
+
"eval_f1": 0.6276400817995911,
|
| 1028 |
+
"eval_loss": 0.7736731767654419,
|
| 1029 |
+
"eval_precision": 0.5456284444444445,
|
| 1030 |
+
"eval_recall": 0.7386666666666667,
|
| 1031 |
+
"eval_runtime": 6.384,
|
| 1032 |
+
"eval_samples_per_second": 234.964,
|
| 1033 |
+
"eval_steps_per_second": 7.362,
|
| 1034 |
+
"step": 820
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 4.41,
|
| 1038 |
+
"learning_rate": 0.0004267968056787933,
|
| 1039 |
+
"loss": 0.7781,
|
| 1040 |
+
"step": 830
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 4.47,
|
| 1044 |
+
"learning_rate": 0.0004259094942324756,
|
| 1045 |
+
"loss": 0.7333,
|
| 1046 |
+
"step": 840
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 4.47,
|
| 1050 |
+
"eval_accuracy": 0.7386666666666667,
|
| 1051 |
+
"eval_combined_score": 0.6626504648943422,
|
| 1052 |
+
"eval_f1": 0.6276400817995911,
|
| 1053 |
+
"eval_loss": 0.8354427218437195,
|
| 1054 |
+
"eval_precision": 0.5456284444444445,
|
| 1055 |
+
"eval_recall": 0.7386666666666667,
|
| 1056 |
+
"eval_runtime": 6.1708,
|
| 1057 |
+
"eval_samples_per_second": 243.081,
|
| 1058 |
+
"eval_steps_per_second": 7.617,
|
| 1059 |
+
"step": 840
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 4.52,
|
| 1063 |
+
"learning_rate": 0.00042502218278615795,
|
| 1064 |
+
"loss": 1.1763,
|
| 1065 |
+
"step": 850
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 4.57,
|
| 1069 |
+
"learning_rate": 0.0004241348713398403,
|
| 1070 |
+
"loss": 0.9287,
|
| 1071 |
+
"step": 860
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 4.57,
|
| 1075 |
+
"eval_accuracy": 0.7386666666666667,
|
| 1076 |
+
"eval_combined_score": 0.6626504648943422,
|
| 1077 |
+
"eval_f1": 0.6276400817995911,
|
| 1078 |
+
"eval_loss": 0.7903938889503479,
|
| 1079 |
+
"eval_precision": 0.5456284444444445,
|
| 1080 |
+
"eval_recall": 0.7386666666666667,
|
| 1081 |
+
"eval_runtime": 6.1862,
|
| 1082 |
+
"eval_samples_per_second": 242.475,
|
| 1083 |
+
"eval_steps_per_second": 7.598,
|
| 1084 |
+
"step": 860
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 4.63,
|
| 1088 |
+
"learning_rate": 0.0004232475598935226,
|
| 1089 |
+
"loss": 0.7707,
|
| 1090 |
+
"step": 870
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 4.68,
|
| 1094 |
+
"learning_rate": 0.000422360248447205,
|
| 1095 |
+
"loss": 0.8231,
|
| 1096 |
+
"step": 880
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 4.68,
|
| 1100 |
+
"eval_accuracy": 0.7386666666666667,
|
| 1101 |
+
"eval_combined_score": 0.6626504648943422,
|
| 1102 |
+
"eval_f1": 0.6276400817995911,
|
| 1103 |
+
"eval_loss": 0.7689003944396973,
|
| 1104 |
+
"eval_precision": 0.5456284444444445,
|
| 1105 |
+
"eval_recall": 0.7386666666666667,
|
| 1106 |
+
"eval_runtime": 6.0616,
|
| 1107 |
+
"eval_samples_per_second": 247.459,
|
| 1108 |
+
"eval_steps_per_second": 7.754,
|
| 1109 |
+
"step": 880
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 4.73,
|
| 1113 |
+
"learning_rate": 0.00042147293700088735,
|
| 1114 |
+
"loss": 0.723,
|
| 1115 |
+
"step": 890
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 4.79,
|
| 1119 |
+
"learning_rate": 0.00042058562555456964,
|
| 1120 |
+
"loss": 0.7486,
|
| 1121 |
+
"step": 900
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 4.79,
|
| 1125 |
+
"eval_accuracy": 0.7386666666666667,
|
| 1126 |
+
"eval_combined_score": 0.6626504648943422,
|
| 1127 |
+
"eval_f1": 0.6276400817995911,
|
| 1128 |
+
"eval_loss": 0.7458215951919556,
|
| 1129 |
+
"eval_precision": 0.5456284444444445,
|
| 1130 |
+
"eval_recall": 0.7386666666666667,
|
| 1131 |
+
"eval_runtime": 6.0863,
|
| 1132 |
+
"eval_samples_per_second": 246.454,
|
| 1133 |
+
"eval_steps_per_second": 7.722,
|
| 1134 |
+
"step": 900
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 4.84,
|
| 1138 |
+
"learning_rate": 0.000419698314108252,
|
| 1139 |
+
"loss": 0.6488,
|
| 1140 |
+
"step": 910
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 4.89,
|
| 1144 |
+
"learning_rate": 0.0004188110026619343,
|
| 1145 |
+
"loss": 0.8551,
|
| 1146 |
+
"step": 920
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 4.89,
|
| 1150 |
+
"eval_accuracy": 0.7386666666666667,
|
| 1151 |
+
"eval_combined_score": 0.6626504648943422,
|
| 1152 |
+
"eval_f1": 0.6276400817995911,
|
| 1153 |
+
"eval_loss": 0.7851412892341614,
|
| 1154 |
+
"eval_precision": 0.5456284444444445,
|
| 1155 |
+
"eval_recall": 0.7386666666666667,
|
| 1156 |
+
"eval_runtime": 5.9684,
|
| 1157 |
+
"eval_samples_per_second": 251.326,
|
| 1158 |
+
"eval_steps_per_second": 7.875,
|
| 1159 |
+
"step": 920
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 4.95,
|
| 1163 |
+
"learning_rate": 0.0004179236912156167,
|
| 1164 |
+
"loss": 0.7437,
|
| 1165 |
+
"step": 930
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 5.0,
|
| 1169 |
+
"learning_rate": 0.00041703637976929904,
|
| 1170 |
+
"loss": 0.7452,
|
| 1171 |
+
"step": 940
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 5.0,
|
| 1175 |
+
"eval_accuracy": 0.7386666666666667,
|
| 1176 |
+
"eval_combined_score": 0.6626504648943422,
|
| 1177 |
+
"eval_f1": 0.6276400817995911,
|
| 1178 |
+
"eval_loss": 0.7961435317993164,
|
| 1179 |
+
"eval_precision": 0.5456284444444445,
|
| 1180 |
+
"eval_recall": 0.7386666666666667,
|
| 1181 |
+
"eval_runtime": 6.0838,
|
| 1182 |
+
"eval_samples_per_second": 246.558,
|
| 1183 |
+
"eval_steps_per_second": 7.725,
|
| 1184 |
+
"step": 940
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 5.05,
|
| 1188 |
+
"learning_rate": 0.0004161490683229814,
|
| 1189 |
+
"loss": 0.8069,
|
| 1190 |
+
"step": 950
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 5.11,
|
| 1194 |
+
"learning_rate": 0.0004152617568766637,
|
| 1195 |
+
"loss": 0.7453,
|
| 1196 |
+
"step": 960
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 5.11,
|
| 1200 |
+
"eval_accuracy": 0.7386666666666667,
|
| 1201 |
+
"eval_combined_score": 0.6626504648943422,
|
| 1202 |
+
"eval_f1": 0.6276400817995911,
|
| 1203 |
+
"eval_loss": 0.7462239861488342,
|
| 1204 |
+
"eval_precision": 0.5456284444444445,
|
| 1205 |
+
"eval_recall": 0.7386666666666667,
|
| 1206 |
+
"eval_runtime": 6.1042,
|
| 1207 |
+
"eval_samples_per_second": 245.731,
|
| 1208 |
+
"eval_steps_per_second": 7.7,
|
| 1209 |
+
"step": 960
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 5.16,
|
| 1213 |
+
"learning_rate": 0.0004143744454303461,
|
| 1214 |
+
"loss": 0.5743,
|
| 1215 |
+
"step": 970
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 5.21,
|
| 1219 |
+
"learning_rate": 0.00041348713398402844,
|
| 1220 |
+
"loss": 0.7784,
|
| 1221 |
+
"step": 980
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 5.21,
|
| 1225 |
+
"eval_accuracy": 0.7386666666666667,
|
| 1226 |
+
"eval_combined_score": 0.6626504648943422,
|
| 1227 |
+
"eval_f1": 0.6276400817995911,
|
| 1228 |
+
"eval_loss": 0.7713678479194641,
|
| 1229 |
+
"eval_precision": 0.5456284444444445,
|
| 1230 |
+
"eval_recall": 0.7386666666666667,
|
| 1231 |
+
"eval_runtime": 6.0898,
|
| 1232 |
+
"eval_samples_per_second": 246.314,
|
| 1233 |
+
"eval_steps_per_second": 7.718,
|
| 1234 |
+
"step": 980
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 5.27,
|
| 1238 |
+
"learning_rate": 0.0004125998225377107,
|
| 1239 |
+
"loss": 0.7916,
|
| 1240 |
+
"step": 990
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 5.32,
|
| 1244 |
+
"learning_rate": 0.00041171251109139306,
|
| 1245 |
+
"loss": 0.7943,
|
| 1246 |
+
"step": 1000
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 5.32,
|
| 1250 |
+
"eval_accuracy": 0.7386666666666667,
|
| 1251 |
+
"eval_combined_score": 0.6626504648943422,
|
| 1252 |
+
"eval_f1": 0.6276400817995911,
|
| 1253 |
+
"eval_loss": 0.7590846419334412,
|
| 1254 |
+
"eval_precision": 0.5456284444444445,
|
| 1255 |
+
"eval_recall": 0.7386666666666667,
|
| 1256 |
+
"eval_runtime": 6.0172,
|
| 1257 |
+
"eval_samples_per_second": 249.284,
|
| 1258 |
+
"eval_steps_per_second": 7.811,
|
| 1259 |
+
"step": 1000
|
| 1260 |
+
}
|
| 1261 |
+
],
|
| 1262 |
+
"logging_steps": 10,
|
| 1263 |
+
"max_steps": 5640,
|
| 1264 |
+
"num_train_epochs": 30,
|
| 1265 |
+
"save_steps": 100,
|
| 1266 |
+
"total_flos": 2099644999925760.0,
|
| 1267 |
+
"trial_name": null,
|
| 1268 |
+
"trial_params": null
|
| 1269 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5774ca6e2ea30af0574f0df2eee8b6bf7c47cb150d6cc3a84e7f1fdeba63d725
|
| 3 |
+
size 4472
|
checkpoint-1000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|