Training in progress, step 3500
Browse files- model.safetensors +1 -1
- run-4/checkpoint-3000/config.json +27 -0
- run-4/checkpoint-3000/merges.txt +0 -0
- run-4/checkpoint-3000/model.safetensors +3 -0
- run-4/checkpoint-3000/optimizer.pt +3 -0
- run-4/checkpoint-3000/rng_state.pth +3 -0
- run-4/checkpoint-3000/scheduler.pt +3 -0
- run-4/checkpoint-3000/special_tokens_map.json +15 -0
- run-4/checkpoint-3000/tokenizer.json +0 -0
- run-4/checkpoint-3000/tokenizer_config.json +57 -0
- run-4/checkpoint-3000/trainer_state.json +138 -0
- run-4/checkpoint-3000/training_args.bin +3 -0
- run-4/checkpoint-3000/vocab.json +0 -0
- run-4/checkpoint-3500/config.json +27 -0
- run-4/checkpoint-3500/merges.txt +0 -0
- run-4/checkpoint-3500/model.safetensors +3 -0
- run-4/checkpoint-3500/optimizer.pt +3 -0
- run-4/checkpoint-3500/rng_state.pth +3 -0
- run-4/checkpoint-3500/scheduler.pt +3 -0
- run-4/checkpoint-3500/special_tokens_map.json +15 -0
- run-4/checkpoint-3500/tokenizer.json +0 -0
- run-4/checkpoint-3500/tokenizer_config.json +57 -0
- run-4/checkpoint-3500/trainer_state.json +154 -0
- run-4/checkpoint-3500/training_args.bin +3 -0
- run-4/checkpoint-3500/vocab.json +0 -0
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1421491284
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f7d25481e681f44ba27d8739c8e323e06580f610b8d3af37a2d8c34237721c9
|
3 |
size 1421491284
|
run-4/checkpoint-3000/config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-large",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForMultipleChoice"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 1024,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 24,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.40.1",
|
24 |
+
"type_vocab_size": 1,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 50265
|
27 |
+
}
|
run-4/checkpoint-3000/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/checkpoint-3000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a4ade2943d946a6d71dba6fe2b47738ed94311a0d8886d6af14a53dea3ff71e
|
3 |
+
size 1421491284
|
run-4/checkpoint-3000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f74c14c100b5319487b15924161b31dbe6af2835763d98549df3cd1b4ba500a
|
3 |
+
size 2843215085
|
run-4/checkpoint-3000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39d877b28a8cd06c07aabb601fbd8f6ea1d4177967208aba352cb58683f5b319
|
3 |
+
size 14244
|
run-4/checkpoint-3000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:392812e78d7d500c6b36e07a2042cf14ebc2132ecad0d73592464a51b325c06d
|
3 |
+
size 1064
|
run-4/checkpoint-3000/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 |
+
}
|
run-4/checkpoint-3000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/checkpoint-3000/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 |
+
}
|
run-4/checkpoint-3000/trainer_state.json
ADDED
@@ -0,0 +1,138 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 8.04289544235925,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 3000,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.7321488261222839,
|
14 |
+
"eval_loss": 0.5215846300125122,
|
15 |
+
"eval_runtime": 9.3633,
|
16 |
+
"eval_samples_per_second": 318.585,
|
17 |
+
"eval_steps_per_second": 19.972,
|
18 |
+
"step": 373
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.3404825737265416,
|
22 |
+
"grad_norm": 13.217938423156738,
|
23 |
+
"learning_rate": 2.418286940875578e-06,
|
24 |
+
"loss": 0.5967,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_accuracy": 0.7723767757415771,
|
30 |
+
"eval_loss": 0.45723703503608704,
|
31 |
+
"eval_runtime": 9.2866,
|
32 |
+
"eval_samples_per_second": 321.216,
|
33 |
+
"eval_steps_per_second": 20.137,
|
34 |
+
"step": 746
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 2.680965147453083,
|
38 |
+
"grad_norm": 15.163392066955566,
|
39 |
+
"learning_rate": 2.043939117210628e-06,
|
40 |
+
"loss": 0.4683,
|
41 |
+
"step": 1000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 3.0,
|
45 |
+
"eval_accuracy": 0.796513557434082,
|
46 |
+
"eval_loss": 0.4389999508857727,
|
47 |
+
"eval_runtime": 9.2689,
|
48 |
+
"eval_samples_per_second": 321.829,
|
49 |
+
"eval_steps_per_second": 20.175,
|
50 |
+
"step": 1119
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"eval_accuracy": 0.8055648803710938,
|
55 |
+
"eval_loss": 0.45021912455558777,
|
56 |
+
"eval_runtime": 9.4524,
|
57 |
+
"eval_samples_per_second": 315.58,
|
58 |
+
"eval_steps_per_second": 19.783,
|
59 |
+
"step": 1492
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.021447721179625,
|
63 |
+
"grad_norm": 33.55284118652344,
|
64 |
+
"learning_rate": 1.6695912935456774e-06,
|
65 |
+
"loss": 0.3783,
|
66 |
+
"step": 1500
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 5.0,
|
70 |
+
"eval_accuracy": 0.8079115152359009,
|
71 |
+
"eval_loss": 0.4486864507198334,
|
72 |
+
"eval_runtime": 9.329,
|
73 |
+
"eval_samples_per_second": 319.756,
|
74 |
+
"eval_steps_per_second": 20.045,
|
75 |
+
"step": 1865
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 5.361930294906166,
|
79 |
+
"grad_norm": 17.95193862915039,
|
80 |
+
"learning_rate": 1.2952434698807272e-06,
|
81 |
+
"loss": 0.3049,
|
82 |
+
"step": 2000
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 6.0,
|
86 |
+
"eval_accuracy": 0.8139457106590271,
|
87 |
+
"eval_loss": 0.44699645042419434,
|
88 |
+
"eval_runtime": 9.3232,
|
89 |
+
"eval_samples_per_second": 319.955,
|
90 |
+
"eval_steps_per_second": 20.058,
|
91 |
+
"step": 2238
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 6.702412868632708,
|
95 |
+
"grad_norm": 19.94598388671875,
|
96 |
+
"learning_rate": 9.208956462157772e-07,
|
97 |
+
"loss": 0.2663,
|
98 |
+
"step": 2500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.0,
|
102 |
+
"eval_accuracy": 0.8162923455238342,
|
103 |
+
"eval_loss": 0.4586087167263031,
|
104 |
+
"eval_runtime": 9.3905,
|
105 |
+
"eval_samples_per_second": 317.661,
|
106 |
+
"eval_steps_per_second": 19.914,
|
107 |
+
"step": 2611
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 8.0,
|
111 |
+
"eval_accuracy": 0.8169627785682678,
|
112 |
+
"eval_loss": 0.46715453267097473,
|
113 |
+
"eval_runtime": 9.458,
|
114 |
+
"eval_samples_per_second": 315.395,
|
115 |
+
"eval_steps_per_second": 19.772,
|
116 |
+
"step": 2984
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 8.04289544235925,
|
120 |
+
"grad_norm": 21.875141143798828,
|
121 |
+
"learning_rate": 5.465478225508271e-07,
|
122 |
+
"loss": 0.2394,
|
123 |
+
"step": 3000
|
124 |
+
}
|
125 |
+
],
|
126 |
+
"logging_steps": 500,
|
127 |
+
"max_steps": 3730,
|
128 |
+
"num_input_tokens_seen": 0,
|
129 |
+
"num_train_epochs": 10,
|
130 |
+
"save_steps": 500,
|
131 |
+
"total_flos": 1.6826244219836316e+16,
|
132 |
+
"train_batch_size": 32,
|
133 |
+
"trial_name": null,
|
134 |
+
"trial_params": {
|
135 |
+
"learning_rate": 2.7926347645405278e-06,
|
136 |
+
"per_device_train_batch_size": 32
|
137 |
+
}
|
138 |
+
}
|
run-4/checkpoint-3000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7db8a7a0dfed6f985d34492a77fc54ac5788fe514ba2cde45d3b63947da0c296
|
3 |
+
size 5048
|
run-4/checkpoint-3000/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/checkpoint-3500/config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-large",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForMultipleChoice"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 1024,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 24,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.40.1",
|
24 |
+
"type_vocab_size": 1,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 50265
|
27 |
+
}
|
run-4/checkpoint-3500/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/checkpoint-3500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f7d25481e681f44ba27d8739c8e323e06580f610b8d3af37a2d8c34237721c9
|
3 |
+
size 1421491284
|
run-4/checkpoint-3500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f05dc77f0e86a22e4e4c336bc492006ea90ba165f24bc269d1da22bb8ca4b9c5
|
3 |
+
size 2843215085
|
run-4/checkpoint-3500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89fcfe9c1b5080b260fd4f680dbc672465e21ae3377576806ff2322f72cb0630
|
3 |
+
size 14244
|
run-4/checkpoint-3500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24b707ef72de5b8d53eeae53cb7eb60b47e56ba3da28baa61c94cbfe7a768fb8
|
3 |
+
size 1064
|
run-4/checkpoint-3500/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 |
+
}
|
run-4/checkpoint-3500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/checkpoint-3500/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 |
+
}
|
run-4/checkpoint-3500/trainer_state.json
ADDED
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 9.383378016085791,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 3500,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.7321488261222839,
|
14 |
+
"eval_loss": 0.5215846300125122,
|
15 |
+
"eval_runtime": 9.3633,
|
16 |
+
"eval_samples_per_second": 318.585,
|
17 |
+
"eval_steps_per_second": 19.972,
|
18 |
+
"step": 373
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.3404825737265416,
|
22 |
+
"grad_norm": 13.217938423156738,
|
23 |
+
"learning_rate": 2.418286940875578e-06,
|
24 |
+
"loss": 0.5967,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_accuracy": 0.7723767757415771,
|
30 |
+
"eval_loss": 0.45723703503608704,
|
31 |
+
"eval_runtime": 9.2866,
|
32 |
+
"eval_samples_per_second": 321.216,
|
33 |
+
"eval_steps_per_second": 20.137,
|
34 |
+
"step": 746
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 2.680965147453083,
|
38 |
+
"grad_norm": 15.163392066955566,
|
39 |
+
"learning_rate": 2.043939117210628e-06,
|
40 |
+
"loss": 0.4683,
|
41 |
+
"step": 1000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 3.0,
|
45 |
+
"eval_accuracy": 0.796513557434082,
|
46 |
+
"eval_loss": 0.4389999508857727,
|
47 |
+
"eval_runtime": 9.2689,
|
48 |
+
"eval_samples_per_second": 321.829,
|
49 |
+
"eval_steps_per_second": 20.175,
|
50 |
+
"step": 1119
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"eval_accuracy": 0.8055648803710938,
|
55 |
+
"eval_loss": 0.45021912455558777,
|
56 |
+
"eval_runtime": 9.4524,
|
57 |
+
"eval_samples_per_second": 315.58,
|
58 |
+
"eval_steps_per_second": 19.783,
|
59 |
+
"step": 1492
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.021447721179625,
|
63 |
+
"grad_norm": 33.55284118652344,
|
64 |
+
"learning_rate": 1.6695912935456774e-06,
|
65 |
+
"loss": 0.3783,
|
66 |
+
"step": 1500
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 5.0,
|
70 |
+
"eval_accuracy": 0.8079115152359009,
|
71 |
+
"eval_loss": 0.4486864507198334,
|
72 |
+
"eval_runtime": 9.329,
|
73 |
+
"eval_samples_per_second": 319.756,
|
74 |
+
"eval_steps_per_second": 20.045,
|
75 |
+
"step": 1865
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 5.361930294906166,
|
79 |
+
"grad_norm": 17.95193862915039,
|
80 |
+
"learning_rate": 1.2952434698807272e-06,
|
81 |
+
"loss": 0.3049,
|
82 |
+
"step": 2000
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 6.0,
|
86 |
+
"eval_accuracy": 0.8139457106590271,
|
87 |
+
"eval_loss": 0.44699645042419434,
|
88 |
+
"eval_runtime": 9.3232,
|
89 |
+
"eval_samples_per_second": 319.955,
|
90 |
+
"eval_steps_per_second": 20.058,
|
91 |
+
"step": 2238
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 6.702412868632708,
|
95 |
+
"grad_norm": 19.94598388671875,
|
96 |
+
"learning_rate": 9.208956462157772e-07,
|
97 |
+
"loss": 0.2663,
|
98 |
+
"step": 2500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.0,
|
102 |
+
"eval_accuracy": 0.8162923455238342,
|
103 |
+
"eval_loss": 0.4586087167263031,
|
104 |
+
"eval_runtime": 9.3905,
|
105 |
+
"eval_samples_per_second": 317.661,
|
106 |
+
"eval_steps_per_second": 19.914,
|
107 |
+
"step": 2611
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 8.0,
|
111 |
+
"eval_accuracy": 0.8169627785682678,
|
112 |
+
"eval_loss": 0.46715453267097473,
|
113 |
+
"eval_runtime": 9.458,
|
114 |
+
"eval_samples_per_second": 315.395,
|
115 |
+
"eval_steps_per_second": 19.772,
|
116 |
+
"step": 2984
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 8.04289544235925,
|
120 |
+
"grad_norm": 21.875141143798828,
|
121 |
+
"learning_rate": 5.465478225508271e-07,
|
122 |
+
"loss": 0.2394,
|
123 |
+
"step": 3000
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 9.0,
|
127 |
+
"eval_accuracy": 0.8183037042617798,
|
128 |
+
"eval_loss": 0.4889311194419861,
|
129 |
+
"eval_runtime": 9.4511,
|
130 |
+
"eval_samples_per_second": 315.626,
|
131 |
+
"eval_steps_per_second": 19.786,
|
132 |
+
"step": 3357
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 9.383378016085791,
|
136 |
+
"grad_norm": 31.631711959838867,
|
137 |
+
"learning_rate": 1.7219999888587704e-07,
|
138 |
+
"loss": 0.2114,
|
139 |
+
"step": 3500
|
140 |
+
}
|
141 |
+
],
|
142 |
+
"logging_steps": 500,
|
143 |
+
"max_steps": 3730,
|
144 |
+
"num_input_tokens_seen": 0,
|
145 |
+
"num_train_epochs": 10,
|
146 |
+
"save_steps": 500,
|
147 |
+
"total_flos": 1.9626746750006364e+16,
|
148 |
+
"train_batch_size": 32,
|
149 |
+
"trial_name": null,
|
150 |
+
"trial_params": {
|
151 |
+
"learning_rate": 2.7926347645405278e-06,
|
152 |
+
"per_device_train_batch_size": 32
|
153 |
+
}
|
154 |
+
}
|
run-4/checkpoint-3500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7db8a7a0dfed6f985d34492a77fc54ac5788fe514ba2cde45d3b63947da0c296
|
3 |
+
size 5048
|
run-4/checkpoint-3500/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|