Training in progress, epoch 2
Browse files- model.safetensors +1 -1
- run-1/checkpoint-35610/config.json +25 -0
- run-1/checkpoint-35610/model.safetensors +3 -0
- run-1/checkpoint-35610/optimizer.pt +3 -0
- run-1/checkpoint-35610/rng_state.pth +3 -0
- run-1/checkpoint-35610/scheduler.pt +3 -0
- run-1/checkpoint-35610/special_tokens_map.json +7 -0
- run-1/checkpoint-35610/tokenizer.json +0 -0
- run-1/checkpoint-35610/tokenizer_config.json +55 -0
- run-1/checkpoint-35610/trainer_state.json +470 -0
- run-1/checkpoint-35610/training_args.bin +3 -0
- run-1/checkpoint-35610/vocab.txt +0 -0
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 267832560
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:774d849cdf3ab02df9982467109ea2c22850b7ab5402af37c564a88d5573eb9a
|
| 3 |
size 267832560
|
run-1/checkpoint-35610/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"max_position_embeddings": 512,
|
| 13 |
+
"model_type": "distilbert",
|
| 14 |
+
"n_heads": 12,
|
| 15 |
+
"n_layers": 6,
|
| 16 |
+
"pad_token_id": 0,
|
| 17 |
+
"problem_type": "single_label_classification",
|
| 18 |
+
"qa_dropout": 0.1,
|
| 19 |
+
"seq_classif_dropout": 0.2,
|
| 20 |
+
"sinusoidal_pos_embds": false,
|
| 21 |
+
"tie_weights_": true,
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.37.2",
|
| 24 |
+
"vocab_size": 30522
|
| 25 |
+
}
|
run-1/checkpoint-35610/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:774d849cdf3ab02df9982467109ea2c22850b7ab5402af37c564a88d5573eb9a
|
| 3 |
+
size 267832560
|
run-1/checkpoint-35610/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29b4aefd5fd041329bebbe60f71e264638f13bf6e8a4eeaafda2a428d5bcc120
|
| 3 |
+
size 535727290
|
run-1/checkpoint-35610/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88b01b7b4cbc1d5872bb3be15b376ef122f14a5983ba4a3c7752bd00a13a02b7
|
| 3 |
+
size 14244
|
run-1/checkpoint-35610/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d071ae2c55220b3cfd148fa90da46a8c21d138051a053a7df8bbcd90c75f892
|
| 3 |
+
size 1064
|
run-1/checkpoint-35610/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
run-1/checkpoint-35610/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-1/checkpoint-35610/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
run-1/checkpoint-35610/trainer_state.json
ADDED
|
@@ -0,0 +1,470 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8587530820711519,
|
| 3 |
+
"best_model_checkpoint": "relevant_model/run-1/checkpoint-35610",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 35610,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"learning_rate": 4.101665655728474e-06,
|
| 14 |
+
"loss": 0.5111,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.06,
|
| 19 |
+
"learning_rate": 4.078498947704027e-06,
|
| 20 |
+
"loss": 0.4216,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.08,
|
| 25 |
+
"learning_rate": 4.0553322396795785e-06,
|
| 26 |
+
"loss": 0.4711,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.11,
|
| 31 |
+
"learning_rate": 4.0321655316551306e-06,
|
| 32 |
+
"loss": 0.4472,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.14,
|
| 37 |
+
"learning_rate": 4.0089988236306835e-06,
|
| 38 |
+
"loss": 0.4429,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.17,
|
| 43 |
+
"learning_rate": 3.985832115606236e-06,
|
| 44 |
+
"loss": 0.5083,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.2,
|
| 49 |
+
"learning_rate": 3.962665407581788e-06,
|
| 50 |
+
"loss": 0.469,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.22,
|
| 55 |
+
"learning_rate": 3.93949869955734e-06,
|
| 56 |
+
"loss": 0.4424,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.25,
|
| 61 |
+
"learning_rate": 3.916331991532892e-06,
|
| 62 |
+
"loss": 0.472,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.28,
|
| 67 |
+
"learning_rate": 3.893165283508445e-06,
|
| 68 |
+
"loss": 0.4344,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.31,
|
| 73 |
+
"learning_rate": 3.869998575483997e-06,
|
| 74 |
+
"loss": 0.4255,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.34,
|
| 79 |
+
"learning_rate": 3.846831867459549e-06,
|
| 80 |
+
"loss": 0.4293,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.37,
|
| 85 |
+
"learning_rate": 3.823665159435101e-06,
|
| 86 |
+
"loss": 0.4581,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.39,
|
| 91 |
+
"learning_rate": 3.8004984514106537e-06,
|
| 92 |
+
"loss": 0.4235,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.42,
|
| 97 |
+
"learning_rate": 3.777331743386206e-06,
|
| 98 |
+
"loss": 0.4334,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.45,
|
| 103 |
+
"learning_rate": 3.7541650353617583e-06,
|
| 104 |
+
"loss": 0.3703,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.48,
|
| 109 |
+
"learning_rate": 3.7309983273373104e-06,
|
| 110 |
+
"loss": 0.4415,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.51,
|
| 115 |
+
"learning_rate": 3.7078316193128626e-06,
|
| 116 |
+
"loss": 0.4234,
|
| 117 |
+
"step": 9000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.53,
|
| 121 |
+
"learning_rate": 3.684664911288415e-06,
|
| 122 |
+
"loss": 0.4184,
|
| 123 |
+
"step": 9500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.56,
|
| 127 |
+
"learning_rate": 3.661498203263967e-06,
|
| 128 |
+
"loss": 0.3912,
|
| 129 |
+
"step": 10000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.59,
|
| 133 |
+
"learning_rate": 3.6383314952395193e-06,
|
| 134 |
+
"loss": 0.4158,
|
| 135 |
+
"step": 10500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.62,
|
| 139 |
+
"learning_rate": 3.615164787215072e-06,
|
| 140 |
+
"loss": 0.3966,
|
| 141 |
+
"step": 11000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.65,
|
| 145 |
+
"learning_rate": 3.591998079190624e-06,
|
| 146 |
+
"loss": 0.4171,
|
| 147 |
+
"step": 11500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.67,
|
| 151 |
+
"learning_rate": 3.568831371166176e-06,
|
| 152 |
+
"loss": 0.381,
|
| 153 |
+
"step": 12000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.7,
|
| 157 |
+
"learning_rate": 3.5456646631417285e-06,
|
| 158 |
+
"loss": 0.3867,
|
| 159 |
+
"step": 12500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.73,
|
| 163 |
+
"learning_rate": 3.5224979551172806e-06,
|
| 164 |
+
"loss": 0.4438,
|
| 165 |
+
"step": 13000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.76,
|
| 169 |
+
"learning_rate": 3.4993312470928328e-06,
|
| 170 |
+
"loss": 0.3806,
|
| 171 |
+
"step": 13500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.79,
|
| 175 |
+
"learning_rate": 3.4761645390683853e-06,
|
| 176 |
+
"loss": 0.391,
|
| 177 |
+
"step": 14000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.81,
|
| 181 |
+
"learning_rate": 3.4529978310439374e-06,
|
| 182 |
+
"loss": 0.3947,
|
| 183 |
+
"step": 14500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.84,
|
| 187 |
+
"learning_rate": 3.42983112301949e-06,
|
| 188 |
+
"loss": 0.397,
|
| 189 |
+
"step": 15000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.87,
|
| 193 |
+
"learning_rate": 3.406664414995042e-06,
|
| 194 |
+
"loss": 0.4048,
|
| 195 |
+
"step": 15500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.9,
|
| 199 |
+
"learning_rate": 3.383497706970594e-06,
|
| 200 |
+
"loss": 0.4648,
|
| 201 |
+
"step": 16000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.93,
|
| 205 |
+
"learning_rate": 3.3603309989461466e-06,
|
| 206 |
+
"loss": 0.3751,
|
| 207 |
+
"step": 16500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.95,
|
| 211 |
+
"learning_rate": 3.3371642909216987e-06,
|
| 212 |
+
"loss": 0.3951,
|
| 213 |
+
"step": 17000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.98,
|
| 217 |
+
"learning_rate": 3.313997582897251e-06,
|
| 218 |
+
"loss": 0.4386,
|
| 219 |
+
"step": 17500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.0,
|
| 223 |
+
"eval_f1": 0.8416666666666667,
|
| 224 |
+
"eval_loss": 0.3926413059234619,
|
| 225 |
+
"eval_runtime": 7.7212,
|
| 226 |
+
"eval_samples_per_second": 512.357,
|
| 227 |
+
"eval_steps_per_second": 8.03,
|
| 228 |
+
"step": 17805
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.01,
|
| 232 |
+
"learning_rate": 3.2908308748728034e-06,
|
| 233 |
+
"loss": 0.3639,
|
| 234 |
+
"step": 18000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.04,
|
| 238 |
+
"learning_rate": 3.2676641668483555e-06,
|
| 239 |
+
"loss": 0.372,
|
| 240 |
+
"step": 18500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.07,
|
| 244 |
+
"learning_rate": 3.2444974588239076e-06,
|
| 245 |
+
"loss": 0.3249,
|
| 246 |
+
"step": 19000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.1,
|
| 250 |
+
"learning_rate": 3.22133075079946e-06,
|
| 251 |
+
"loss": 0.3586,
|
| 252 |
+
"step": 19500
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.12,
|
| 256 |
+
"learning_rate": 3.1981640427750122e-06,
|
| 257 |
+
"loss": 0.3595,
|
| 258 |
+
"step": 20000
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.15,
|
| 262 |
+
"learning_rate": 3.1749973347505643e-06,
|
| 263 |
+
"loss": 0.3577,
|
| 264 |
+
"step": 20500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.18,
|
| 268 |
+
"learning_rate": 3.151830626726117e-06,
|
| 269 |
+
"loss": 0.3505,
|
| 270 |
+
"step": 21000
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.21,
|
| 274 |
+
"learning_rate": 3.128663918701669e-06,
|
| 275 |
+
"loss": 0.3448,
|
| 276 |
+
"step": 21500
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.24,
|
| 280 |
+
"learning_rate": 3.105497210677221e-06,
|
| 281 |
+
"loss": 0.3726,
|
| 282 |
+
"step": 22000
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.26,
|
| 286 |
+
"learning_rate": 3.0823305026527736e-06,
|
| 287 |
+
"loss": 0.3522,
|
| 288 |
+
"step": 22500
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.29,
|
| 292 |
+
"learning_rate": 3.0591637946283257e-06,
|
| 293 |
+
"loss": 0.3814,
|
| 294 |
+
"step": 23000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.32,
|
| 298 |
+
"learning_rate": 3.0359970866038778e-06,
|
| 299 |
+
"loss": 0.3641,
|
| 300 |
+
"step": 23500
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.35,
|
| 304 |
+
"learning_rate": 3.0128303785794303e-06,
|
| 305 |
+
"loss": 0.343,
|
| 306 |
+
"step": 24000
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.38,
|
| 310 |
+
"learning_rate": 2.9896636705549824e-06,
|
| 311 |
+
"loss": 0.331,
|
| 312 |
+
"step": 24500
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.4,
|
| 316 |
+
"learning_rate": 2.966496962530535e-06,
|
| 317 |
+
"loss": 0.3737,
|
| 318 |
+
"step": 25000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.43,
|
| 322 |
+
"learning_rate": 2.943330254506087e-06,
|
| 323 |
+
"loss": 0.3437,
|
| 324 |
+
"step": 25500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.46,
|
| 328 |
+
"learning_rate": 2.920163546481639e-06,
|
| 329 |
+
"loss": 0.3648,
|
| 330 |
+
"step": 26000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.49,
|
| 334 |
+
"learning_rate": 2.8969968384571917e-06,
|
| 335 |
+
"loss": 0.3421,
|
| 336 |
+
"step": 26500
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.52,
|
| 340 |
+
"learning_rate": 2.8738301304327438e-06,
|
| 341 |
+
"loss": 0.3344,
|
| 342 |
+
"step": 27000
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.54,
|
| 346 |
+
"learning_rate": 2.850663422408296e-06,
|
| 347 |
+
"loss": 0.3533,
|
| 348 |
+
"step": 27500
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.57,
|
| 352 |
+
"learning_rate": 2.8274967143838484e-06,
|
| 353 |
+
"loss": 0.371,
|
| 354 |
+
"step": 28000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.6,
|
| 358 |
+
"learning_rate": 2.8043300063594005e-06,
|
| 359 |
+
"loss": 0.3526,
|
| 360 |
+
"step": 28500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.63,
|
| 364 |
+
"learning_rate": 2.7811632983349526e-06,
|
| 365 |
+
"loss": 0.3539,
|
| 366 |
+
"step": 29000
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.66,
|
| 370 |
+
"learning_rate": 2.757996590310505e-06,
|
| 371 |
+
"loss": 0.3692,
|
| 372 |
+
"step": 29500
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.68,
|
| 376 |
+
"learning_rate": 2.7348298822860572e-06,
|
| 377 |
+
"loss": 0.3104,
|
| 378 |
+
"step": 30000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.71,
|
| 382 |
+
"learning_rate": 2.7116631742616094e-06,
|
| 383 |
+
"loss": 0.3371,
|
| 384 |
+
"step": 30500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.74,
|
| 388 |
+
"learning_rate": 2.688496466237162e-06,
|
| 389 |
+
"loss": 0.3818,
|
| 390 |
+
"step": 31000
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.77,
|
| 394 |
+
"learning_rate": 2.665329758212714e-06,
|
| 395 |
+
"loss": 0.384,
|
| 396 |
+
"step": 31500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.8,
|
| 400 |
+
"learning_rate": 2.6421630501882657e-06,
|
| 401 |
+
"loss": 0.3249,
|
| 402 |
+
"step": 32000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.83,
|
| 406 |
+
"learning_rate": 2.6189963421638186e-06,
|
| 407 |
+
"loss": 0.3385,
|
| 408 |
+
"step": 32500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.85,
|
| 412 |
+
"learning_rate": 2.5958296341393703e-06,
|
| 413 |
+
"loss": 0.3837,
|
| 414 |
+
"step": 33000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.88,
|
| 418 |
+
"learning_rate": 2.5726629261149224e-06,
|
| 419 |
+
"loss": 0.3224,
|
| 420 |
+
"step": 33500
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.91,
|
| 424 |
+
"learning_rate": 2.549496218090475e-06,
|
| 425 |
+
"loss": 0.3555,
|
| 426 |
+
"step": 34000
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.94,
|
| 430 |
+
"learning_rate": 2.526329510066027e-06,
|
| 431 |
+
"loss": 0.3555,
|
| 432 |
+
"step": 34500
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.97,
|
| 436 |
+
"learning_rate": 2.50316280204158e-06,
|
| 437 |
+
"loss": 0.3487,
|
| 438 |
+
"step": 35000
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.99,
|
| 442 |
+
"learning_rate": 2.4799960940171317e-06,
|
| 443 |
+
"loss": 0.3847,
|
| 444 |
+
"step": 35500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.0,
|
| 448 |
+
"eval_f1": 0.8587530820711519,
|
| 449 |
+
"eval_loss": 0.37445908784866333,
|
| 450 |
+
"eval_runtime": 7.6778,
|
| 451 |
+
"eval_samples_per_second": 515.253,
|
| 452 |
+
"eval_steps_per_second": 8.075,
|
| 453 |
+
"step": 35610
|
| 454 |
+
}
|
| 455 |
+
],
|
| 456 |
+
"logging_steps": 500,
|
| 457 |
+
"max_steps": 89025,
|
| 458 |
+
"num_input_tokens_seen": 0,
|
| 459 |
+
"num_train_epochs": 5,
|
| 460 |
+
"save_steps": 500,
|
| 461 |
+
"total_flos": 5581990155809868.0,
|
| 462 |
+
"train_batch_size": 4,
|
| 463 |
+
"trial_name": null,
|
| 464 |
+
"trial_params": {
|
| 465 |
+
"learning_rate": 4.124832363752922e-06,
|
| 466 |
+
"num_train_epochs": 5,
|
| 467 |
+
"per_device_train_batch_size": 4,
|
| 468 |
+
"seed": 40
|
| 469 |
+
}
|
| 470 |
+
}
|
run-1/checkpoint-35610/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1edfb4d32c4b440688a42ad772fd577e72d0a24c0764a9f6c27730006d6a58ce
|
| 3 |
+
size 4664
|
run-1/checkpoint-35610/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|