Training in progress, step 3500
Browse files- model.safetensors +1 -1
- run-3/checkpoint-3000/config.json +27 -0
- run-3/checkpoint-3000/merges.txt +0 -0
- run-3/checkpoint-3000/model.safetensors +3 -0
- run-3/checkpoint-3000/optimizer.pt +3 -0
- run-3/checkpoint-3000/rng_state.pth +3 -0
- run-3/checkpoint-3000/scheduler.pt +3 -0
- run-3/checkpoint-3000/special_tokens_map.json +15 -0
- run-3/checkpoint-3000/tokenizer.json +0 -0
- run-3/checkpoint-3000/tokenizer_config.json +57 -0
- run-3/checkpoint-3000/trainer_state.json +138 -0
- run-3/checkpoint-3000/training_args.bin +3 -0
- run-3/checkpoint-3000/vocab.json +0 -0
- run-3/checkpoint-3500/config.json +27 -0
- run-3/checkpoint-3500/merges.txt +0 -0
- run-3/checkpoint-3500/model.safetensors +3 -0
- run-3/checkpoint-3500/optimizer.pt +3 -0
- run-3/checkpoint-3500/rng_state.pth +3 -0
- run-3/checkpoint-3500/scheduler.pt +3 -0
- run-3/checkpoint-3500/special_tokens_map.json +15 -0
- run-3/checkpoint-3500/tokenizer.json +0 -0
- run-3/checkpoint-3500/tokenizer_config.json +57 -0
- run-3/checkpoint-3500/trainer_state.json +154 -0
- run-3/checkpoint-3500/training_args.bin +3 -0
- run-3/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 sha256:26264ea451c03fe9975c481abd0203da843fbd8a43069b5cc7888b70c8674925
|
3 |
size 1421491284
|
run-3/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-3/checkpoint-3000/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-3000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7da275054ebf9605cbf61876ef5738f42fcbe00500a1f91e0113fdd9efcea52
|
3 |
+
size 1421491284
|
run-3/checkpoint-3000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34b8f9b99e598ee538538649e6727d5c7879b35f03367a21f534afa5e159591d
|
3 |
+
size 2843215085
|
run-3/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-3/checkpoint-3000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3edde44003cce4385c70f9b16f308a096851878ae283e0e05196f3b5a27464e8
|
3 |
+
size 1064
|
run-3/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-3/checkpoint-3000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/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-3/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": 0.6443178057670593,
|
14 |
+
"eval_loss": 0.6200888156890869,
|
15 |
+
"eval_runtime": 9.4558,
|
16 |
+
"eval_samples_per_second": 315.469,
|
17 |
+
"eval_steps_per_second": 19.776,
|
18 |
+
"step": 373
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.3404825737265416,
|
22 |
+
"grad_norm": 11.498894691467285,
|
23 |
+
"learning_rate": 1.0365748013479516e-05,
|
24 |
+
"loss": 0.6738,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_accuracy": 0.7539389729499817,
|
30 |
+
"eval_loss": 0.47277966141700745,
|
31 |
+
"eval_runtime": 9.3806,
|
32 |
+
"eval_samples_per_second": 317.998,
|
33 |
+
"eval_steps_per_second": 19.935,
|
34 |
+
"step": 746
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 2.680965147453083,
|
38 |
+
"grad_norm": 9.671843528747559,
|
39 |
+
"learning_rate": 8.761143057832532e-06,
|
40 |
+
"loss": 0.4763,
|
41 |
+
"step": 1000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 3.0,
|
45 |
+
"eval_accuracy": 0.7717063426971436,
|
46 |
+
"eval_loss": 0.5170367360115051,
|
47 |
+
"eval_runtime": 9.2678,
|
48 |
+
"eval_samples_per_second": 321.867,
|
49 |
+
"eval_steps_per_second": 20.177,
|
50 |
+
"step": 1119
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"eval_accuracy": 0.7787462472915649,
|
55 |
+
"eval_loss": 0.5018635392189026,
|
56 |
+
"eval_runtime": 9.2787,
|
57 |
+
"eval_samples_per_second": 321.49,
|
58 |
+
"eval_steps_per_second": 20.154,
|
59 |
+
"step": 1492
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.021447721179625,
|
63 |
+
"grad_norm": 22.328227996826172,
|
64 |
+
"learning_rate": 7.156538102185547e-06,
|
65 |
+
"loss": 0.2904,
|
66 |
+
"step": 1500
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 5.0,
|
70 |
+
"eval_accuracy": 0.7800871729850769,
|
71 |
+
"eval_loss": 0.6816526651382446,
|
72 |
+
"eval_runtime": 9.2909,
|
73 |
+
"eval_samples_per_second": 321.068,
|
74 |
+
"eval_steps_per_second": 20.127,
|
75 |
+
"step": 1865
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 5.361930294906166,
|
79 |
+
"grad_norm": 8.851292610168457,
|
80 |
+
"learning_rate": 5.551933146538564e-06,
|
81 |
+
"loss": 0.1552,
|
82 |
+
"step": 2000
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 6.0,
|
86 |
+
"eval_accuracy": 0.782433807849884,
|
87 |
+
"eval_loss": 0.8527898192405701,
|
88 |
+
"eval_runtime": 9.405,
|
89 |
+
"eval_samples_per_second": 317.172,
|
90 |
+
"eval_steps_per_second": 19.883,
|
91 |
+
"step": 2238
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 6.702412868632708,
|
95 |
+
"grad_norm": 20.3522891998291,
|
96 |
+
"learning_rate": 3.94732819089158e-06,
|
97 |
+
"loss": 0.1004,
|
98 |
+
"step": 2500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.0,
|
102 |
+
"eval_accuracy": 0.7747234106063843,
|
103 |
+
"eval_loss": 0.9924494624137878,
|
104 |
+
"eval_runtime": 9.2681,
|
105 |
+
"eval_samples_per_second": 321.856,
|
106 |
+
"eval_steps_per_second": 20.177,
|
107 |
+
"step": 2611
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 8.0,
|
111 |
+
"eval_accuracy": 0.7780757546424866,
|
112 |
+
"eval_loss": 1.0592091083526611,
|
113 |
+
"eval_runtime": 9.4254,
|
114 |
+
"eval_samples_per_second": 316.486,
|
115 |
+
"eval_steps_per_second": 19.84,
|
116 |
+
"step": 2984
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 8.04289544235925,
|
120 |
+
"grad_norm": 6.993451118469238,
|
121 |
+
"learning_rate": 2.342723235244596e-06,
|
122 |
+
"loss": 0.0685,
|
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": 1.1970352969126499e-05,
|
136 |
+
"per_device_train_batch_size": 32
|
137 |
+
}
|
138 |
+
}
|
run-3/checkpoint-3000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:727738f55918307e08ad76d17a0ae75bcbb428e0ca4edd47d017bd972c0f5a21
|
3 |
+
size 5048
|
run-3/checkpoint-3000/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/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-3/checkpoint-3500/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-3500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26264ea451c03fe9975c481abd0203da843fbd8a43069b5cc7888b70c8674925
|
3 |
+
size 1421491284
|
run-3/checkpoint-3500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8af2e1d4e010f7819381ba9771d47d24fd14b4458f8d37b1c02a63a88f064f84
|
3 |
+
size 2843215085
|
run-3/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-3/checkpoint-3500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db137ff925e36d19d33102340ab0477601d9b4e23d19b8cbfbbe42942a218e5a
|
3 |
+
size 1064
|
run-3/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-3/checkpoint-3500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/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-3/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": 0.6443178057670593,
|
14 |
+
"eval_loss": 0.6200888156890869,
|
15 |
+
"eval_runtime": 9.4558,
|
16 |
+
"eval_samples_per_second": 315.469,
|
17 |
+
"eval_steps_per_second": 19.776,
|
18 |
+
"step": 373
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.3404825737265416,
|
22 |
+
"grad_norm": 11.498894691467285,
|
23 |
+
"learning_rate": 1.0365748013479516e-05,
|
24 |
+
"loss": 0.6738,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_accuracy": 0.7539389729499817,
|
30 |
+
"eval_loss": 0.47277966141700745,
|
31 |
+
"eval_runtime": 9.3806,
|
32 |
+
"eval_samples_per_second": 317.998,
|
33 |
+
"eval_steps_per_second": 19.935,
|
34 |
+
"step": 746
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 2.680965147453083,
|
38 |
+
"grad_norm": 9.671843528747559,
|
39 |
+
"learning_rate": 8.761143057832532e-06,
|
40 |
+
"loss": 0.4763,
|
41 |
+
"step": 1000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 3.0,
|
45 |
+
"eval_accuracy": 0.7717063426971436,
|
46 |
+
"eval_loss": 0.5170367360115051,
|
47 |
+
"eval_runtime": 9.2678,
|
48 |
+
"eval_samples_per_second": 321.867,
|
49 |
+
"eval_steps_per_second": 20.177,
|
50 |
+
"step": 1119
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"eval_accuracy": 0.7787462472915649,
|
55 |
+
"eval_loss": 0.5018635392189026,
|
56 |
+
"eval_runtime": 9.2787,
|
57 |
+
"eval_samples_per_second": 321.49,
|
58 |
+
"eval_steps_per_second": 20.154,
|
59 |
+
"step": 1492
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.021447721179625,
|
63 |
+
"grad_norm": 22.328227996826172,
|
64 |
+
"learning_rate": 7.156538102185547e-06,
|
65 |
+
"loss": 0.2904,
|
66 |
+
"step": 1500
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 5.0,
|
70 |
+
"eval_accuracy": 0.7800871729850769,
|
71 |
+
"eval_loss": 0.6816526651382446,
|
72 |
+
"eval_runtime": 9.2909,
|
73 |
+
"eval_samples_per_second": 321.068,
|
74 |
+
"eval_steps_per_second": 20.127,
|
75 |
+
"step": 1865
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 5.361930294906166,
|
79 |
+
"grad_norm": 8.851292610168457,
|
80 |
+
"learning_rate": 5.551933146538564e-06,
|
81 |
+
"loss": 0.1552,
|
82 |
+
"step": 2000
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 6.0,
|
86 |
+
"eval_accuracy": 0.782433807849884,
|
87 |
+
"eval_loss": 0.8527898192405701,
|
88 |
+
"eval_runtime": 9.405,
|
89 |
+
"eval_samples_per_second": 317.172,
|
90 |
+
"eval_steps_per_second": 19.883,
|
91 |
+
"step": 2238
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 6.702412868632708,
|
95 |
+
"grad_norm": 20.3522891998291,
|
96 |
+
"learning_rate": 3.94732819089158e-06,
|
97 |
+
"loss": 0.1004,
|
98 |
+
"step": 2500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.0,
|
102 |
+
"eval_accuracy": 0.7747234106063843,
|
103 |
+
"eval_loss": 0.9924494624137878,
|
104 |
+
"eval_runtime": 9.2681,
|
105 |
+
"eval_samples_per_second": 321.856,
|
106 |
+
"eval_steps_per_second": 20.177,
|
107 |
+
"step": 2611
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 8.0,
|
111 |
+
"eval_accuracy": 0.7780757546424866,
|
112 |
+
"eval_loss": 1.0592091083526611,
|
113 |
+
"eval_runtime": 9.4254,
|
114 |
+
"eval_samples_per_second": 316.486,
|
115 |
+
"eval_steps_per_second": 19.84,
|
116 |
+
"step": 2984
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 8.04289544235925,
|
120 |
+
"grad_norm": 6.993451118469238,
|
121 |
+
"learning_rate": 2.342723235244596e-06,
|
122 |
+
"loss": 0.0685,
|
123 |
+
"step": 3000
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 9.0,
|
127 |
+
"eval_accuracy": 0.7794166803359985,
|
128 |
+
"eval_loss": 1.097713589668274,
|
129 |
+
"eval_runtime": 9.4231,
|
130 |
+
"eval_samples_per_second": 316.561,
|
131 |
+
"eval_steps_per_second": 19.845,
|
132 |
+
"step": 3357
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 9.383378016085791,
|
136 |
+
"grad_norm": 36.58711242675781,
|
137 |
+
"learning_rate": 7.381182795976126e-07,
|
138 |
+
"loss": 0.0513,
|
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": 1.1970352969126499e-05,
|
152 |
+
"per_device_train_batch_size": 32
|
153 |
+
}
|
154 |
+
}
|
run-3/checkpoint-3500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:727738f55918307e08ad76d17a0ae75bcbb428e0ca4edd47d017bd972c0f5a21
|
3 |
+
size 5048
|
run-3/checkpoint-3500/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|