Upload folder using huggingface_hub
Browse files- config.json +39 -0
- model.safetensors +3 -0
- optimizer_state_dict.pth +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +53 -0
- trainer_state.json +393 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "pGenomeOcean/GenomeOcean-100M",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "pGenomeOcean/GenomeOcean-100M--configuration_mistral.MistralConfig",
|
9 |
+
"AutoModel": "pGenomeOcean/GenomeOcean-100M--modeling_mistral.MistralModel",
|
10 |
+
"AutoModelForCausalLM": "pGenomeOcean/GenomeOcean-100M--modeling_mistral.MistralForCausalLM",
|
11 |
+
"AutoModelForMaskedLM": "pGenomeOcean/GenomeOcean-100M--modeling_mistral.MistralForMaskedLM",
|
12 |
+
"AutoModelForSequenceClassification": "pGenomeOcean/GenomeOcean-100M--modeling_mistral.MistralForSequenceClassification"
|
13 |
+
},
|
14 |
+
"bos_token_id": 1,
|
15 |
+
"classifier_dropout": 0.1,
|
16 |
+
"eos_token_id": 2,
|
17 |
+
"hidden_act": "silu",
|
18 |
+
"hidden_size": 768,
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"is_causal": true,
|
22 |
+
"max_position_embeddings": 32768,
|
23 |
+
"model_type": "mistral",
|
24 |
+
"num_attention_heads": 8,
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"num_key_value_heads": 8,
|
27 |
+
"output_router_logits": false,
|
28 |
+
"pad_token_id": 3,
|
29 |
+
"problem_type": "single_label_classification",
|
30 |
+
"rms_norm_eps": 1e-05,
|
31 |
+
"rope_theta": 1000000.0,
|
32 |
+
"router_aux_loss_coef": 0.02,
|
33 |
+
"sliding_window": null,
|
34 |
+
"tie_word_embeddings": false,
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.45.2",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 4096
|
39 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a2a513c24d9eb874f36600423a45fe0feb9e4f7877f5e097fe449f8f3470cb0
|
3 |
+
size 465662960
|
optimizer_state_dict.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33e81476fc21e91ac44ee8d6dcef26aaac377e0e51083154daac7fea0cd3be5e
|
3 |
+
size 931398901
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[UNK]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[CLS]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[SEP]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[PAD]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
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 |
+
"mask_token": "[MASK]",
|
47 |
+
"model_max_length": 256,
|
48 |
+
"pad_token": "[PAD]",
|
49 |
+
"padding_side": "right",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
52 |
+
"unk_token": "[UNK]"
|
53 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,393 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.11086247861385345,
|
3 |
+
"best_model_checkpoint": "output_pipe/prom_300_notata/origin/checkpoint-1000",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 200,
|
6 |
+
"global_step": 2656,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.15060240963855423,
|
13 |
+
"grad_norm": 22.862253189086914,
|
14 |
+
"learning_rate": 2.9470452801227934e-05,
|
15 |
+
"loss": 0.3165,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.30120481927710846,
|
20 |
+
"grad_norm": 15.997178077697754,
|
21 |
+
"learning_rate": 2.831926323867997e-05,
|
22 |
+
"loss": 0.174,
|
23 |
+
"step": 200
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.30120481927710846,
|
27 |
+
"eval_accuracy": 0.9440361786319955,
|
28 |
+
"eval_f1": 0.9440350340667568,
|
29 |
+
"eval_loss": 0.13831785321235657,
|
30 |
+
"eval_matthews_correlation": 0.8884885605641855,
|
31 |
+
"eval_precision": 0.9443041112978641,
|
32 |
+
"eval_recall": 0.9441844573233038,
|
33 |
+
"eval_runtime": 1.5317,
|
34 |
+
"eval_samples_per_second": 3464.713,
|
35 |
+
"eval_steps_per_second": 54.187,
|
36 |
+
"step": 200
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 0.45180722891566266,
|
40 |
+
"grad_norm": 9.916468620300293,
|
41 |
+
"learning_rate": 2.7168073676132003e-05,
|
42 |
+
"loss": 0.1727,
|
43 |
+
"step": 300
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 0.6024096385542169,
|
47 |
+
"grad_norm": 8.223430633544922,
|
48 |
+
"learning_rate": 2.6016884113584036e-05,
|
49 |
+
"loss": 0.1306,
|
50 |
+
"step": 400
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.6024096385542169,
|
54 |
+
"eval_accuracy": 0.9470510646316186,
|
55 |
+
"eval_f1": 0.9469116079894582,
|
56 |
+
"eval_loss": 0.1320875585079193,
|
57 |
+
"eval_matthews_correlation": 0.8970111970995432,
|
58 |
+
"eval_precision": 0.9503975774077025,
|
59 |
+
"eval_recall": 0.946621567301194,
|
60 |
+
"eval_runtime": 1.5336,
|
61 |
+
"eval_samples_per_second": 3460.585,
|
62 |
+
"eval_steps_per_second": 54.123,
|
63 |
+
"step": 400
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.7530120481927711,
|
67 |
+
"grad_norm": 8.465655326843262,
|
68 |
+
"learning_rate": 2.4865694551036073e-05,
|
69 |
+
"loss": 0.1449,
|
70 |
+
"step": 500
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 0.9036144578313253,
|
74 |
+
"grad_norm": 8.037919998168945,
|
75 |
+
"learning_rate": 2.3714504988488106e-05,
|
76 |
+
"loss": 0.1268,
|
77 |
+
"step": 600
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 0.9036144578313253,
|
81 |
+
"eval_accuracy": 0.9502543810062182,
|
82 |
+
"eval_f1": 0.9502384353255368,
|
83 |
+
"eval_loss": 0.1223142221570015,
|
84 |
+
"eval_matthews_correlation": 0.9019972975694879,
|
85 |
+
"eval_precision": 0.9514557669338246,
|
86 |
+
"eval_recall": 0.9505419934872148,
|
87 |
+
"eval_runtime": 1.5394,
|
88 |
+
"eval_samples_per_second": 3447.515,
|
89 |
+
"eval_steps_per_second": 53.918,
|
90 |
+
"step": 600
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 1.0542168674698795,
|
94 |
+
"grad_norm": 5.252899646759033,
|
95 |
+
"learning_rate": 2.256331542594014e-05,
|
96 |
+
"loss": 0.0967,
|
97 |
+
"step": 700
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 1.2048192771084336,
|
101 |
+
"grad_norm": 2.8755605220794678,
|
102 |
+
"learning_rate": 2.1412125863392172e-05,
|
103 |
+
"loss": 0.0793,
|
104 |
+
"step": 800
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 1.2048192771084336,
|
108 |
+
"eval_accuracy": 0.9534576973808178,
|
109 |
+
"eval_f1": 0.9534544978603143,
|
110 |
+
"eval_loss": 0.12600094079971313,
|
111 |
+
"eval_matthews_correlation": 0.9075729094229542,
|
112 |
+
"eval_precision": 0.9539269039717451,
|
113 |
+
"eval_recall": 0.9536460489075334,
|
114 |
+
"eval_runtime": 1.546,
|
115 |
+
"eval_samples_per_second": 3432.697,
|
116 |
+
"eval_steps_per_second": 53.686,
|
117 |
+
"step": 800
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 1.355421686746988,
|
121 |
+
"grad_norm": 15.925186157226562,
|
122 |
+
"learning_rate": 2.026093630084421e-05,
|
123 |
+
"loss": 0.0632,
|
124 |
+
"step": 900
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 1.5060240963855422,
|
128 |
+
"grad_norm": 5.883889198303223,
|
129 |
+
"learning_rate": 1.9109746738296238e-05,
|
130 |
+
"loss": 0.0664,
|
131 |
+
"step": 1000
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 1.5060240963855422,
|
135 |
+
"eval_accuracy": 0.9634445072545694,
|
136 |
+
"eval_f1": 0.9634296411014179,
|
137 |
+
"eval_loss": 0.11086247861385345,
|
138 |
+
"eval_matthews_correlation": 0.9270444420166869,
|
139 |
+
"eval_precision": 0.9637054919711341,
|
140 |
+
"eval_recall": 0.9633390224799887,
|
141 |
+
"eval_runtime": 1.5519,
|
142 |
+
"eval_samples_per_second": 3419.769,
|
143 |
+
"eval_steps_per_second": 53.484,
|
144 |
+
"step": 1000
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 1.6566265060240963,
|
148 |
+
"grad_norm": 9.317992210388184,
|
149 |
+
"learning_rate": 1.7958557175748274e-05,
|
150 |
+
"loss": 0.0651,
|
151 |
+
"step": 1100
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 1.8072289156626506,
|
155 |
+
"grad_norm": 7.534521102905273,
|
156 |
+
"learning_rate": 1.6807367613200308e-05,
|
157 |
+
"loss": 0.0644,
|
158 |
+
"step": 1200
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 1.8072289156626506,
|
162 |
+
"eval_accuracy": 0.9570378745053703,
|
163 |
+
"eval_f1": 0.9570372017874856,
|
164 |
+
"eval_loss": 0.14527226984500885,
|
165 |
+
"eval_matthews_correlation": 0.9144670396513508,
|
166 |
+
"eval_precision": 0.9572853548448508,
|
167 |
+
"eval_recall": 0.9571816906821948,
|
168 |
+
"eval_runtime": 1.5434,
|
169 |
+
"eval_samples_per_second": 3438.416,
|
170 |
+
"eval_steps_per_second": 53.776,
|
171 |
+
"step": 1200
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 1.9578313253012047,
|
175 |
+
"grad_norm": 7.254329681396484,
|
176 |
+
"learning_rate": 1.565617805065234e-05,
|
177 |
+
"loss": 0.0635,
|
178 |
+
"step": 1300
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 2.108433734939759,
|
182 |
+
"grad_norm": 6.914297580718994,
|
183 |
+
"learning_rate": 1.4504988488104375e-05,
|
184 |
+
"loss": 0.0374,
|
185 |
+
"step": 1400
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 2.108433734939759,
|
189 |
+
"eval_accuracy": 0.9628792161296401,
|
190 |
+
"eval_f1": 0.9628401830979684,
|
191 |
+
"eval_loss": 0.18788941204547882,
|
192 |
+
"eval_matthews_correlation": 0.9266187165348982,
|
193 |
+
"eval_precision": 0.9639729425818305,
|
194 |
+
"eval_recall": 0.9626467230259594,
|
195 |
+
"eval_runtime": 1.5439,
|
196 |
+
"eval_samples_per_second": 3437.375,
|
197 |
+
"eval_steps_per_second": 53.76,
|
198 |
+
"step": 1400
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 2.2590361445783134,
|
202 |
+
"grad_norm": 0.7644485235214233,
|
203 |
+
"learning_rate": 1.3353798925556408e-05,
|
204 |
+
"loss": 0.0279,
|
205 |
+
"step": 1500
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 2.4096385542168672,
|
209 |
+
"grad_norm": 8.384675979614258,
|
210 |
+
"learning_rate": 1.2202609363008443e-05,
|
211 |
+
"loss": 0.0164,
|
212 |
+
"step": 1600
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 2.4096385542168672,
|
216 |
+
"eval_accuracy": 0.9657056717542868,
|
217 |
+
"eval_f1": 0.9656756314944064,
|
218 |
+
"eval_loss": 0.16530963778495789,
|
219 |
+
"eval_matthews_correlation": 0.9320662060488338,
|
220 |
+
"eval_precision": 0.9665640323608415,
|
221 |
+
"eval_recall": 0.9655027778622123,
|
222 |
+
"eval_runtime": 1.5424,
|
223 |
+
"eval_samples_per_second": 3440.766,
|
224 |
+
"eval_steps_per_second": 53.813,
|
225 |
+
"step": 1600
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 2.5602409638554215,
|
229 |
+
"grad_norm": 18.41074562072754,
|
230 |
+
"learning_rate": 1.1051419800460476e-05,
|
231 |
+
"loss": 0.0179,
|
232 |
+
"step": 1700
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 2.710843373493976,
|
236 |
+
"grad_norm": 0.21532420814037323,
|
237 |
+
"learning_rate": 9.90023023791251e-06,
|
238 |
+
"loss": 0.0251,
|
239 |
+
"step": 1800
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 2.710843373493976,
|
243 |
+
"eval_accuracy": 0.9591106086301112,
|
244 |
+
"eval_f1": 0.95910930195127,
|
245 |
+
"eval_loss": 0.22635453939437866,
|
246 |
+
"eval_matthews_correlation": 0.9187108433086283,
|
247 |
+
"eval_precision": 0.9594386335644487,
|
248 |
+
"eval_recall": 0.9592722248152282,
|
249 |
+
"eval_runtime": 1.5425,
|
250 |
+
"eval_samples_per_second": 3440.442,
|
251 |
+
"eval_steps_per_second": 53.808,
|
252 |
+
"step": 1800
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"epoch": 2.86144578313253,
|
256 |
+
"grad_norm": 5.3087263107299805,
|
257 |
+
"learning_rate": 8.749040675364544e-06,
|
258 |
+
"loss": 0.0224,
|
259 |
+
"step": 1900
|
260 |
+
},
|
261 |
+
{
|
262 |
+
"epoch": 3.0120481927710845,
|
263 |
+
"grad_norm": 0.07524475455284119,
|
264 |
+
"learning_rate": 7.597851112816577e-06,
|
265 |
+
"loss": 0.0179,
|
266 |
+
"step": 2000
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 3.0120481927710845,
|
270 |
+
"eval_accuracy": 0.9692858488788393,
|
271 |
+
"eval_f1": 0.9692716697192839,
|
272 |
+
"eval_loss": 0.17637819051742554,
|
273 |
+
"eval_matthews_correlation": 0.9387831838919006,
|
274 |
+
"eval_precision": 0.9696159708142937,
|
275 |
+
"eval_recall": 0.9691673202840899,
|
276 |
+
"eval_runtime": 1.5414,
|
277 |
+
"eval_samples_per_second": 3442.9,
|
278 |
+
"eval_steps_per_second": 53.846,
|
279 |
+
"step": 2000
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 3.1626506024096384,
|
283 |
+
"grad_norm": 0.002716244664043188,
|
284 |
+
"learning_rate": 6.446661550268611e-06,
|
285 |
+
"loss": 0.0032,
|
286 |
+
"step": 2100
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 3.3132530120481927,
|
290 |
+
"grad_norm": 0.0046457210555672646,
|
291 |
+
"learning_rate": 5.295471987720644e-06,
|
292 |
+
"loss": 0.0037,
|
293 |
+
"step": 2200
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 3.3132530120481927,
|
297 |
+
"eval_accuracy": 0.9677784058790277,
|
298 |
+
"eval_f1": 0.9677761908263713,
|
299 |
+
"eval_loss": 0.21041572093963623,
|
300 |
+
"eval_matthews_correlation": 0.9355606983847059,
|
301 |
+
"eval_precision": 0.9677642707707517,
|
302 |
+
"eval_recall": 0.9677964281666167,
|
303 |
+
"eval_runtime": 1.5409,
|
304 |
+
"eval_samples_per_second": 3444.045,
|
305 |
+
"eval_steps_per_second": 53.864,
|
306 |
+
"step": 2200
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 3.463855421686747,
|
310 |
+
"grad_norm": 7.352254390716553,
|
311 |
+
"learning_rate": 4.144282425172678e-06,
|
312 |
+
"loss": 0.0021,
|
313 |
+
"step": 2300
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 3.6144578313253013,
|
317 |
+
"grad_norm": 0.1295173019170761,
|
318 |
+
"learning_rate": 2.993092862624712e-06,
|
319 |
+
"loss": 0.0014,
|
320 |
+
"step": 2400
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 3.6144578313253013,
|
324 |
+
"eval_accuracy": 0.9683436970039571,
|
325 |
+
"eval_f1": 0.9683377061336159,
|
326 |
+
"eval_loss": 0.22055356204509735,
|
327 |
+
"eval_matthews_correlation": 0.936697700228757,
|
328 |
+
"eval_precision": 0.9683925624578065,
|
329 |
+
"eval_recall": 0.9683051418503684,
|
330 |
+
"eval_runtime": 1.5412,
|
331 |
+
"eval_samples_per_second": 3443.434,
|
332 |
+
"eval_steps_per_second": 53.854,
|
333 |
+
"step": 2400
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 3.765060240963855,
|
337 |
+
"grad_norm": 0.0010891439160332084,
|
338 |
+
"learning_rate": 1.8419033000767458e-06,
|
339 |
+
"loss": 0.0035,
|
340 |
+
"step": 2500
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 3.9156626506024095,
|
344 |
+
"grad_norm": 0.010914706625044346,
|
345 |
+
"learning_rate": 6.907137375287798e-07,
|
346 |
+
"loss": 0.0026,
|
347 |
+
"step": 2600
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 3.9156626506024095,
|
351 |
+
"eval_accuracy": 0.9690974185038628,
|
352 |
+
"eval_f1": 0.9690902179184598,
|
353 |
+
"eval_loss": 0.21992520987987518,
|
354 |
+
"eval_matthews_correlation": 0.938226978614608,
|
355 |
+
"eval_precision": 0.9691836691199455,
|
356 |
+
"eval_recall": 0.9690433199920572,
|
357 |
+
"eval_runtime": 1.5378,
|
358 |
+
"eval_samples_per_second": 3450.927,
|
359 |
+
"eval_steps_per_second": 53.972,
|
360 |
+
"step": 2600
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 4.0,
|
364 |
+
"step": 2656,
|
365 |
+
"total_flos": 8308929553956864.0,
|
366 |
+
"train_loss": 0.06583031266366682,
|
367 |
+
"train_runtime": 193.8482,
|
368 |
+
"train_samples_per_second": 875.984,
|
369 |
+
"train_steps_per_second": 13.701
|
370 |
+
}
|
371 |
+
],
|
372 |
+
"logging_steps": 100,
|
373 |
+
"max_steps": 2656,
|
374 |
+
"num_input_tokens_seen": 0,
|
375 |
+
"num_train_epochs": 4,
|
376 |
+
"save_steps": 200,
|
377 |
+
"stateful_callbacks": {
|
378 |
+
"TrainerControl": {
|
379 |
+
"args": {
|
380 |
+
"should_epoch_stop": false,
|
381 |
+
"should_evaluate": false,
|
382 |
+
"should_log": false,
|
383 |
+
"should_save": true,
|
384 |
+
"should_training_stop": true
|
385 |
+
},
|
386 |
+
"attributes": {}
|
387 |
+
}
|
388 |
+
},
|
389 |
+
"total_flos": 8308929553956864.0,
|
390 |
+
"train_batch_size": 64,
|
391 |
+
"trial_name": null,
|
392 |
+
"trial_params": null
|
393 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:532e6dbf3707e11b6466d45804268d083767dcd336699ed2b97d1d6f4fc9c6b6
|
3 |
+
size 5368
|