Training in progress, step 7000, checkpoint
Browse files- checkpoint-7000/added_tokens.json +5 -0
- checkpoint-7000/config.json +46 -0
- checkpoint-7000/merges.txt +0 -0
- checkpoint-7000/optimizer.pt +3 -0
- checkpoint-7000/pytorch_model.bin +3 -0
- checkpoint-7000/rng_state.pth +3 -0
- checkpoint-7000/scheduler.pt +3 -0
- checkpoint-7000/special_tokens_map.json +6 -0
- checkpoint-7000/tokenizer_config.json +7 -0
- checkpoint-7000/trainer_state.json +130 -0
- checkpoint-7000/training_args.bin +3 -0
- checkpoint-7000/vocab.json +0 -0
checkpoint-7000/added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<bos>": 40478,
|
3 |
+
"<eos>": 40479,
|
4 |
+
"<pad>": 40480
|
5 |
+
}
|
checkpoint-7000/config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openai-gpt",
|
3 |
+
"afn": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"OpenAIGPTForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"embd_pdrop": 0.1,
|
9 |
+
"id2label": {
|
10 |
+
"0": "entailment",
|
11 |
+
"1": "neutral",
|
12 |
+
"2": "contradiction"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"label2id": {
|
16 |
+
"contradiction": 2,
|
17 |
+
"entailment": 0,
|
18 |
+
"neutral": 1
|
19 |
+
},
|
20 |
+
"layer_norm_epsilon": 1e-05,
|
21 |
+
"model_type": "openai-gpt",
|
22 |
+
"n_ctx": 512,
|
23 |
+
"n_embd": 768,
|
24 |
+
"n_head": 12,
|
25 |
+
"n_layer": 4,
|
26 |
+
"n_positions": 512,
|
27 |
+
"n_special": 0,
|
28 |
+
"pad_token_id": 40480,
|
29 |
+
"predict_special_tokens": true,
|
30 |
+
"problem_type": "single_label_classification",
|
31 |
+
"resid_pdrop": 0.1,
|
32 |
+
"summary_activation": null,
|
33 |
+
"summary_first_dropout": 0.1,
|
34 |
+
"summary_proj_to_labels": true,
|
35 |
+
"summary_type": "last",
|
36 |
+
"summary_use_proj": true,
|
37 |
+
"task_specific_params": {
|
38 |
+
"text-generation": {
|
39 |
+
"do_sample": true,
|
40 |
+
"max_length": 50
|
41 |
+
}
|
42 |
+
},
|
43 |
+
"torch_dtype": "float32",
|
44 |
+
"transformers_version": "4.33.0.dev0",
|
45 |
+
"vocab_size": 40481
|
46 |
+
}
|
checkpoint-7000/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-7000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14c729561ca75fd01d81a6244812b98bbb93833aa7077a3c51e54d2e0f51bc78
|
3 |
+
size 478721221
|
checkpoint-7000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b73b59b7aefd0f5535db76159e8d4736b9dbbd1c5fce8cf5414bcf880a9bc065
|
3 |
+
size 239361994
|
checkpoint-7000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54d4d809a86eec009490a82bfbd54585a6d99c583692caf10c1c26f42d8d025a
|
3 |
+
size 14575
|
checkpoint-7000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d75ee43d1f6a35f9b09b256ffb801f98eae6c121f4f6a1c453c396f2eaf76ed
|
3 |
+
size 627
|
checkpoint-7000/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<bos>",
|
3 |
+
"eos_token": "<eos>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
checkpoint-7000/tokenizer_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"model_max_length": 512,
|
4 |
+
"padding_side": "left",
|
5 |
+
"tokenizer_class": "OpenAIGPTTokenizer",
|
6 |
+
"unk_token": "<unk>"
|
7 |
+
}
|
checkpoint-7000/trainer_state.json
ADDED
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.0985721349716187,
|
3 |
+
"best_model_checkpoint": "/kaggle/output/checkpoint-7000",
|
4 |
+
"epoch": 0.28520208604954367,
|
5 |
+
"eval_steps": 1000,
|
6 |
+
"global_step": 7000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 2.7777777777777777e-11,
|
14 |
+
"loss": 1.2184,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.04,
|
19 |
+
"learning_rate": 2.7750000000000004e-08,
|
20 |
+
"loss": 1.1394,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.04,
|
25 |
+
"eval_accuracy": 0.3327345309381238,
|
26 |
+
"eval_loss": 1.1149410009384155,
|
27 |
+
"eval_runtime": 20.6803,
|
28 |
+
"eval_samples_per_second": 242.26,
|
29 |
+
"eval_steps_per_second": 30.319,
|
30 |
+
"step": 1000
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.08,
|
34 |
+
"learning_rate": 5.5527777777777784e-08,
|
35 |
+
"loss": 1.1141,
|
36 |
+
"step": 2000
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 0.08,
|
40 |
+
"eval_accuracy": 0.3401197604790419,
|
41 |
+
"eval_loss": 1.104099988937378,
|
42 |
+
"eval_runtime": 20.8477,
|
43 |
+
"eval_samples_per_second": 240.314,
|
44 |
+
"eval_steps_per_second": 30.075,
|
45 |
+
"step": 2000
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.12,
|
49 |
+
"learning_rate": 8.330555555555556e-08,
|
50 |
+
"loss": 1.116,
|
51 |
+
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.12,
|
55 |
+
"eval_accuracy": 0.3407185628742515,
|
56 |
+
"eval_loss": 1.1040862798690796,
|
57 |
+
"eval_runtime": 20.6818,
|
58 |
+
"eval_samples_per_second": 242.242,
|
59 |
+
"eval_steps_per_second": 30.317,
|
60 |
+
"step": 3000
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 0.16,
|
64 |
+
"learning_rate": 1.1108333333333333e-07,
|
65 |
+
"loss": 1.1158,
|
66 |
+
"step": 4000
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.16,
|
70 |
+
"eval_accuracy": 0.32894211576846305,
|
71 |
+
"eval_loss": 1.1020556688308716,
|
72 |
+
"eval_runtime": 20.8541,
|
73 |
+
"eval_samples_per_second": 240.241,
|
74 |
+
"eval_steps_per_second": 30.066,
|
75 |
+
"step": 4000
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.2,
|
79 |
+
"learning_rate": 1.3883333333333335e-07,
|
80 |
+
"loss": 1.1135,
|
81 |
+
"step": 5000
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.2,
|
85 |
+
"eval_accuracy": 0.34271457085828344,
|
86 |
+
"eval_loss": 1.1008552312850952,
|
87 |
+
"eval_runtime": 20.8055,
|
88 |
+
"eval_samples_per_second": 240.802,
|
89 |
+
"eval_steps_per_second": 30.136,
|
90 |
+
"step": 5000
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 0.24,
|
94 |
+
"learning_rate": 1.6658333333333335e-07,
|
95 |
+
"loss": 1.1121,
|
96 |
+
"step": 6000
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 0.24,
|
100 |
+
"eval_accuracy": 0.3395209580838323,
|
101 |
+
"eval_loss": 1.1004050970077515,
|
102 |
+
"eval_runtime": 20.8985,
|
103 |
+
"eval_samples_per_second": 239.731,
|
104 |
+
"eval_steps_per_second": 30.002,
|
105 |
+
"step": 6000
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.29,
|
109 |
+
"learning_rate": 1.9436111111111112e-07,
|
110 |
+
"loss": 1.1089,
|
111 |
+
"step": 7000
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.29,
|
115 |
+
"eval_accuracy": 0.35788423153692617,
|
116 |
+
"eval_loss": 1.0985721349716187,
|
117 |
+
"eval_runtime": 20.84,
|
118 |
+
"eval_samples_per_second": 240.403,
|
119 |
+
"eval_steps_per_second": 30.086,
|
120 |
+
"step": 7000
|
121 |
+
}
|
122 |
+
],
|
123 |
+
"logging_steps": 1000,
|
124 |
+
"max_steps": 10000000,
|
125 |
+
"num_train_epochs": 408,
|
126 |
+
"save_steps": 1000,
|
127 |
+
"total_flos": 4877759545344000.0,
|
128 |
+
"trial_name": null,
|
129 |
+
"trial_params": null
|
130 |
+
}
|
checkpoint-7000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d42437e01c6a8e691de275f2b2ef4e9ee68d60c829bca2508adb832bd55170f9
|
3 |
+
size 4027
|
checkpoint-7000/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|