diogopaes10
commited on
Commit
β’
b37b8ce
1
Parent(s):
5f1dc18
Training in progress, epoch 5
Browse files- {checkpoint-250 β checkpoint-1000}/added_tokens.json +0 -0
- {checkpoint-250 β checkpoint-1000}/config.json +0 -0
- {checkpoint-250 β checkpoint-1000}/optimizer.pt +2 -2
- {checkpoint-250 β checkpoint-1000}/pytorch_model.bin +1 -1
- {checkpoint-250 β checkpoint-1000}/rng_state.pth +1 -1
- {checkpoint-250 β checkpoint-1000}/scheduler.pt +1 -1
- {checkpoint-250 β checkpoint-1000}/special_tokens_map.json +0 -0
- {checkpoint-250 β checkpoint-1000}/spm.model +0 -0
- {checkpoint-250 β checkpoint-1000}/tokenizer.json +0 -0
- {checkpoint-250 β checkpoint-1000}/tokenizer_config.json +0 -0
- checkpoint-1000/trainer_state.json +152 -0
- {checkpoint-250 β checkpoint-1000}/training_args.bin +0 -0
- checkpoint-1250/added_tokens.json +3 -0
- checkpoint-1250/config.json +59 -0
- checkpoint-1250/optimizer.pt +3 -0
- checkpoint-1250/pytorch_model.bin +3 -0
- checkpoint-1250/rng_state.pth +3 -0
- checkpoint-1250/scheduler.pt +3 -0
- checkpoint-1250/special_tokens_map.json +9 -0
- checkpoint-1250/spm.model +3 -0
- checkpoint-1250/tokenizer.json +0 -0
- checkpoint-1250/tokenizer_config.json +16 -0
- checkpoint-1250/trainer_state.json +178 -0
- checkpoint-1250/training_args.bin +3 -0
- checkpoint-250/trainer_state.json +0 -48
- pytorch_model.bin +1 -1
- runs/Jul22_21-19-20_ab4276e44fca/events.out.tfevents.1690060770.ab4276e44fca.659.0 +2 -2
{checkpoint-250 β checkpoint-1000}/added_tokens.json
RENAMED
File without changes
|
{checkpoint-250 β checkpoint-1000}/config.json
RENAMED
File without changes
|
{checkpoint-250 β checkpoint-1000}/optimizer.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8933160b3231a03ba857db1c0b9a44a2a04c1b49248d1f369c856ad4887c531
|
3 |
+
size 1475557125
|
{checkpoint-250 β checkpoint-1000}/pytorch_model.bin
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 737788917
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f8aadd399eb31e54990d00c74b732c0319b275fdd1b9ad592f63b3d4dfae103
|
3 |
size 737788917
|
{checkpoint-250 β checkpoint-1000}/rng_state.pth
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da22004a4944e63e1dbfe1405f93c1d28411a5132dc640d3ac3c6859c3579dde
|
3 |
size 14575
|
{checkpoint-250 β checkpoint-1000}/scheduler.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72009b915e4ec650d135b73c75f2c43ff27dde3a223cbdb31d0e7105432803cc
|
3 |
size 627
|
{checkpoint-250 β checkpoint-1000}/special_tokens_map.json
RENAMED
File without changes
|
{checkpoint-250 β checkpoint-1000}/spm.model
RENAMED
File without changes
|
{checkpoint-250 β checkpoint-1000}/tokenizer.json
RENAMED
File without changes
|
{checkpoint-250 β checkpoint-1000}/tokenizer_config.json
RENAMED
File without changes
|
checkpoint-1000/trainer_state.json
ADDED
@@ -0,0 +1,152 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.0,
|
5 |
+
"global_step": 1000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 1.999466666666667e-05,
|
13 |
+
"loss": 2.308,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.75,
|
18 |
+
"learning_rate": 1.8997333333333335e-05,
|
19 |
+
"loss": 1.6916,
|
20 |
+
"step": 188
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.75,
|
24 |
+
"eval_accuracy": 0.6755,
|
25 |
+
"eval_disk_space_total": 78.1898422241211,
|
26 |
+
"eval_disk_space_used": 24.806385040283203,
|
27 |
+
"eval_f1": 0.6708054417489328,
|
28 |
+
"eval_gpu_ram_allocated": 2.089780330657959,
|
29 |
+
"eval_gpu_ram_cached": 25.85546875,
|
30 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
31 |
+
"eval_gpu_utilization": 50,
|
32 |
+
"eval_loss": 1.1062816381454468,
|
33 |
+
"eval_precision": 0.690043017889279,
|
34 |
+
"eval_recall": 0.6755,
|
35 |
+
"eval_runtime": 2.3912,
|
36 |
+
"eval_samples_per_second": 836.398,
|
37 |
+
"eval_steps_per_second": 26.347,
|
38 |
+
"eval_system_ram_total": 83.48074722290039,
|
39 |
+
"eval_system_ram_used": 4.019077301025391,
|
40 |
+
"step": 188
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 1.5,
|
44 |
+
"learning_rate": 1.8e-05,
|
45 |
+
"loss": 0.9694,
|
46 |
+
"step": 376
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 1.5,
|
50 |
+
"eval_accuracy": 0.7195,
|
51 |
+
"eval_disk_space_total": 78.1898422241211,
|
52 |
+
"eval_disk_space_used": 29.64177703857422,
|
53 |
+
"eval_f1": 0.7181081417115642,
|
54 |
+
"eval_gpu_ram_allocated": 2.0897774696350098,
|
55 |
+
"eval_gpu_ram_cached": 25.85546875,
|
56 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
57 |
+
"eval_gpu_utilization": 50,
|
58 |
+
"eval_loss": 0.9585903286933899,
|
59 |
+
"eval_precision": 0.719758443061289,
|
60 |
+
"eval_recall": 0.7195,
|
61 |
+
"eval_runtime": 2.3693,
|
62 |
+
"eval_samples_per_second": 844.141,
|
63 |
+
"eval_steps_per_second": 26.59,
|
64 |
+
"eval_system_ram_total": 83.48074722290039,
|
65 |
+
"eval_system_ram_used": 4.2536163330078125,
|
66 |
+
"step": 376
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 2.26,
|
70 |
+
"learning_rate": 1.6997333333333334e-05,
|
71 |
+
"loss": 0.8509,
|
72 |
+
"step": 564
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 2.26,
|
76 |
+
"eval_accuracy": 0.712,
|
77 |
+
"eval_disk_space_total": 78.1898422241211,
|
78 |
+
"eval_disk_space_used": 29.641841888427734,
|
79 |
+
"eval_f1": 0.7070168337920522,
|
80 |
+
"eval_gpu_ram_allocated": 2.089791774749756,
|
81 |
+
"eval_gpu_ram_cached": 25.85546875,
|
82 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
83 |
+
"eval_gpu_utilization": 46,
|
84 |
+
"eval_loss": 0.9747923016548157,
|
85 |
+
"eval_precision": 0.7160570316458433,
|
86 |
+
"eval_recall": 0.712,
|
87 |
+
"eval_runtime": 2.4432,
|
88 |
+
"eval_samples_per_second": 818.586,
|
89 |
+
"eval_steps_per_second": 25.785,
|
90 |
+
"eval_system_ram_total": 83.48074722290039,
|
91 |
+
"eval_system_ram_used": 4.160213470458984,
|
92 |
+
"step": 564
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 3.01,
|
96 |
+
"learning_rate": 1.5994666666666668e-05,
|
97 |
+
"loss": 0.7475,
|
98 |
+
"step": 752
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 3.01,
|
102 |
+
"eval_accuracy": 0.714,
|
103 |
+
"eval_disk_space_total": 78.1898422241211,
|
104 |
+
"eval_disk_space_used": 29.641963958740234,
|
105 |
+
"eval_f1": 0.7122032912823338,
|
106 |
+
"eval_gpu_ram_allocated": 2.089776039123535,
|
107 |
+
"eval_gpu_ram_cached": 25.85546875,
|
108 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
109 |
+
"eval_gpu_utilization": 50,
|
110 |
+
"eval_loss": 0.9446640014648438,
|
111 |
+
"eval_precision": 0.7148157467744413,
|
112 |
+
"eval_recall": 0.714,
|
113 |
+
"eval_runtime": 2.5063,
|
114 |
+
"eval_samples_per_second": 798.001,
|
115 |
+
"eval_steps_per_second": 25.137,
|
116 |
+
"eval_system_ram_total": 83.48074722290039,
|
117 |
+
"eval_system_ram_used": 4.160709381103516,
|
118 |
+
"step": 752
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 3.76,
|
122 |
+
"learning_rate": 1.4997333333333335e-05,
|
123 |
+
"loss": 0.5841,
|
124 |
+
"step": 940
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 3.76,
|
128 |
+
"eval_accuracy": 0.711,
|
129 |
+
"eval_disk_space_total": 78.1898422241211,
|
130 |
+
"eval_disk_space_used": 29.642024993896484,
|
131 |
+
"eval_f1": 0.7076606604060025,
|
132 |
+
"eval_gpu_ram_allocated": 2.089787483215332,
|
133 |
+
"eval_gpu_ram_cached": 25.85546875,
|
134 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
135 |
+
"eval_gpu_utilization": 47,
|
136 |
+
"eval_loss": 1.0064291954040527,
|
137 |
+
"eval_precision": 0.7225290812411572,
|
138 |
+
"eval_recall": 0.711,
|
139 |
+
"eval_runtime": 2.4755,
|
140 |
+
"eval_samples_per_second": 807.933,
|
141 |
+
"eval_steps_per_second": 25.45,
|
142 |
+
"eval_system_ram_total": 83.48074722290039,
|
143 |
+
"eval_system_ram_used": 4.188880920410156,
|
144 |
+
"step": 940
|
145 |
+
}
|
146 |
+
],
|
147 |
+
"max_steps": 3750,
|
148 |
+
"num_train_epochs": 15,
|
149 |
+
"total_flos": 1921836975330048.0,
|
150 |
+
"trial_name": null,
|
151 |
+
"trial_params": null
|
152 |
+
}
|
{checkpoint-250 β checkpoint-1000}/training_args.bin
RENAMED
File without changes
|
checkpoint-1250/added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[MASK]": 128000
|
3 |
+
}
|
checkpoint-1250/config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/deberta-v3-base",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaV2ForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"id2label": {
|
11 |
+
"0": "Society & Culture",
|
12 |
+
"1": "Science & Mathematics",
|
13 |
+
"2": "Health",
|
14 |
+
"3": "Education & Reference",
|
15 |
+
"4": "Computers & Internet",
|
16 |
+
"5": "Sports",
|
17 |
+
"6": "Business & Finance",
|
18 |
+
"7": "Entertainment & Music",
|
19 |
+
"8": "Family & Relationships",
|
20 |
+
"9": "Politics & Government"
|
21 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 3072,
|
24 |
+
"label2id": {
|
25 |
+
"Business & Finance": 6,
|
26 |
+
"Computers & Internet": 4,
|
27 |
+
"Education & Reference": 3,
|
28 |
+
"Entertainment & Music": 7,
|
29 |
+
"Family & Relationships": 8,
|
30 |
+
"Health": 2,
|
31 |
+
"Politics & Government": 9,
|
32 |
+
"Science & Mathematics": 1,
|
33 |
+
"Society & Culture": 0,
|
34 |
+
"Sports": 5
|
35 |
+
},
|
36 |
+
"layer_norm_eps": 1e-07,
|
37 |
+
"max_position_embeddings": 512,
|
38 |
+
"max_relative_positions": -1,
|
39 |
+
"model_type": "deberta-v2",
|
40 |
+
"norm_rel_ebd": "layer_norm",
|
41 |
+
"num_attention_heads": 12,
|
42 |
+
"num_hidden_layers": 12,
|
43 |
+
"pad_token_id": 0,
|
44 |
+
"pooler_dropout": 0,
|
45 |
+
"pooler_hidden_act": "gelu",
|
46 |
+
"pooler_hidden_size": 768,
|
47 |
+
"pos_att_type": [
|
48 |
+
"p2c",
|
49 |
+
"c2p"
|
50 |
+
],
|
51 |
+
"position_biased_input": false,
|
52 |
+
"position_buckets": 256,
|
53 |
+
"relative_attention": true,
|
54 |
+
"share_att_key": true,
|
55 |
+
"torch_dtype": "float32",
|
56 |
+
"transformers_version": "4.31.0",
|
57 |
+
"type_vocab_size": 0,
|
58 |
+
"vocab_size": 128100
|
59 |
+
}
|
checkpoint-1250/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a110d5b7bd9065a6e2aea20e66039c3ad94a36fb9ab062f65ed04c8052bc467
|
3 |
+
size 1475557125
|
checkpoint-1250/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c37c9b2cf82643ccb441b9f2e76d6a70dccdc2fd29cd95cea2aeac5989dcc044
|
3 |
+
size 737788917
|
checkpoint-1250/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c5494a563819f3435c3619722f6c611dd7e04ea13d2a4561f1cd488ab67b296
|
3 |
+
size 14575
|
checkpoint-1250/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29851d63b5f6f5b0335901be112937603be45604b6b61b539240790a7047e5b9
|
3 |
+
size 627
|
checkpoint-1250/special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"unk_token": "[UNK]"
|
9 |
+
}
|
checkpoint-1250/spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
3 |
+
size 2464616
|
checkpoint-1250/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1250/tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"cls_token": "[CLS]",
|
5 |
+
"do_lower_case": false,
|
6 |
+
"eos_token": "[SEP]",
|
7 |
+
"mask_token": "[MASK]",
|
8 |
+
"model_max_length": 1000000000000000019884624838656,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"sp_model_kwargs": {},
|
12 |
+
"split_by_punct": false,
|
13 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
14 |
+
"unk_token": "[UNK]",
|
15 |
+
"vocab_type": "spm"
|
16 |
+
}
|
checkpoint-1250/trainer_state.json
ADDED
@@ -0,0 +1,178 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"global_step": 1250,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 1.999466666666667e-05,
|
13 |
+
"loss": 2.308,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.75,
|
18 |
+
"learning_rate": 1.8997333333333335e-05,
|
19 |
+
"loss": 1.6916,
|
20 |
+
"step": 188
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.75,
|
24 |
+
"eval_accuracy": 0.6755,
|
25 |
+
"eval_disk_space_total": 78.1898422241211,
|
26 |
+
"eval_disk_space_used": 24.806385040283203,
|
27 |
+
"eval_f1": 0.6708054417489328,
|
28 |
+
"eval_gpu_ram_allocated": 2.089780330657959,
|
29 |
+
"eval_gpu_ram_cached": 25.85546875,
|
30 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
31 |
+
"eval_gpu_utilization": 50,
|
32 |
+
"eval_loss": 1.1062816381454468,
|
33 |
+
"eval_precision": 0.690043017889279,
|
34 |
+
"eval_recall": 0.6755,
|
35 |
+
"eval_runtime": 2.3912,
|
36 |
+
"eval_samples_per_second": 836.398,
|
37 |
+
"eval_steps_per_second": 26.347,
|
38 |
+
"eval_system_ram_total": 83.48074722290039,
|
39 |
+
"eval_system_ram_used": 4.019077301025391,
|
40 |
+
"step": 188
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 1.5,
|
44 |
+
"learning_rate": 1.8e-05,
|
45 |
+
"loss": 0.9694,
|
46 |
+
"step": 376
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 1.5,
|
50 |
+
"eval_accuracy": 0.7195,
|
51 |
+
"eval_disk_space_total": 78.1898422241211,
|
52 |
+
"eval_disk_space_used": 29.64177703857422,
|
53 |
+
"eval_f1": 0.7181081417115642,
|
54 |
+
"eval_gpu_ram_allocated": 2.0897774696350098,
|
55 |
+
"eval_gpu_ram_cached": 25.85546875,
|
56 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
57 |
+
"eval_gpu_utilization": 50,
|
58 |
+
"eval_loss": 0.9585903286933899,
|
59 |
+
"eval_precision": 0.719758443061289,
|
60 |
+
"eval_recall": 0.7195,
|
61 |
+
"eval_runtime": 2.3693,
|
62 |
+
"eval_samples_per_second": 844.141,
|
63 |
+
"eval_steps_per_second": 26.59,
|
64 |
+
"eval_system_ram_total": 83.48074722290039,
|
65 |
+
"eval_system_ram_used": 4.2536163330078125,
|
66 |
+
"step": 376
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 2.26,
|
70 |
+
"learning_rate": 1.6997333333333334e-05,
|
71 |
+
"loss": 0.8509,
|
72 |
+
"step": 564
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 2.26,
|
76 |
+
"eval_accuracy": 0.712,
|
77 |
+
"eval_disk_space_total": 78.1898422241211,
|
78 |
+
"eval_disk_space_used": 29.641841888427734,
|
79 |
+
"eval_f1": 0.7070168337920522,
|
80 |
+
"eval_gpu_ram_allocated": 2.089791774749756,
|
81 |
+
"eval_gpu_ram_cached": 25.85546875,
|
82 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
83 |
+
"eval_gpu_utilization": 46,
|
84 |
+
"eval_loss": 0.9747923016548157,
|
85 |
+
"eval_precision": 0.7160570316458433,
|
86 |
+
"eval_recall": 0.712,
|
87 |
+
"eval_runtime": 2.4432,
|
88 |
+
"eval_samples_per_second": 818.586,
|
89 |
+
"eval_steps_per_second": 25.785,
|
90 |
+
"eval_system_ram_total": 83.48074722290039,
|
91 |
+
"eval_system_ram_used": 4.160213470458984,
|
92 |
+
"step": 564
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 3.01,
|
96 |
+
"learning_rate": 1.5994666666666668e-05,
|
97 |
+
"loss": 0.7475,
|
98 |
+
"step": 752
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 3.01,
|
102 |
+
"eval_accuracy": 0.714,
|
103 |
+
"eval_disk_space_total": 78.1898422241211,
|
104 |
+
"eval_disk_space_used": 29.641963958740234,
|
105 |
+
"eval_f1": 0.7122032912823338,
|
106 |
+
"eval_gpu_ram_allocated": 2.089776039123535,
|
107 |
+
"eval_gpu_ram_cached": 25.85546875,
|
108 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
109 |
+
"eval_gpu_utilization": 50,
|
110 |
+
"eval_loss": 0.9446640014648438,
|
111 |
+
"eval_precision": 0.7148157467744413,
|
112 |
+
"eval_recall": 0.714,
|
113 |
+
"eval_runtime": 2.5063,
|
114 |
+
"eval_samples_per_second": 798.001,
|
115 |
+
"eval_steps_per_second": 25.137,
|
116 |
+
"eval_system_ram_total": 83.48074722290039,
|
117 |
+
"eval_system_ram_used": 4.160709381103516,
|
118 |
+
"step": 752
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 3.76,
|
122 |
+
"learning_rate": 1.4997333333333335e-05,
|
123 |
+
"loss": 0.5841,
|
124 |
+
"step": 940
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 3.76,
|
128 |
+
"eval_accuracy": 0.711,
|
129 |
+
"eval_disk_space_total": 78.1898422241211,
|
130 |
+
"eval_disk_space_used": 29.642024993896484,
|
131 |
+
"eval_f1": 0.7076606604060025,
|
132 |
+
"eval_gpu_ram_allocated": 2.089787483215332,
|
133 |
+
"eval_gpu_ram_cached": 25.85546875,
|
134 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
135 |
+
"eval_gpu_utilization": 47,
|
136 |
+
"eval_loss": 1.0064291954040527,
|
137 |
+
"eval_precision": 0.7225290812411572,
|
138 |
+
"eval_recall": 0.711,
|
139 |
+
"eval_runtime": 2.4755,
|
140 |
+
"eval_samples_per_second": 807.933,
|
141 |
+
"eval_steps_per_second": 25.45,
|
142 |
+
"eval_system_ram_total": 83.48074722290039,
|
143 |
+
"eval_system_ram_used": 4.188880920410156,
|
144 |
+
"step": 940
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 4.51,
|
148 |
+
"learning_rate": 1.3994666666666668e-05,
|
149 |
+
"loss": 0.4972,
|
150 |
+
"step": 1128
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 4.51,
|
154 |
+
"eval_accuracy": 0.714,
|
155 |
+
"eval_disk_space_total": 78.1898422241211,
|
156 |
+
"eval_disk_space_used": 29.642135620117188,
|
157 |
+
"eval_f1": 0.7109995031569997,
|
158 |
+
"eval_gpu_ram_allocated": 2.089801788330078,
|
159 |
+
"eval_gpu_ram_cached": 25.85546875,
|
160 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
161 |
+
"eval_gpu_utilization": 47,
|
162 |
+
"eval_loss": 1.0585097074508667,
|
163 |
+
"eval_precision": 0.7129473752365556,
|
164 |
+
"eval_recall": 0.714,
|
165 |
+
"eval_runtime": 2.3843,
|
166 |
+
"eval_samples_per_second": 838.824,
|
167 |
+
"eval_steps_per_second": 26.423,
|
168 |
+
"eval_system_ram_total": 83.48074722290039,
|
169 |
+
"eval_system_ram_used": 4.176631927490234,
|
170 |
+
"step": 1128
|
171 |
+
}
|
172 |
+
],
|
173 |
+
"max_steps": 3750,
|
174 |
+
"num_train_epochs": 15,
|
175 |
+
"total_flos": 2407649365164288.0,
|
176 |
+
"trial_name": null,
|
177 |
+
"trial_params": null
|
178 |
+
}
|
checkpoint-1250/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c483311c6e034a3b791b3aba6061603f3b239dec5f5cd88a867a5f6743909401
|
3 |
+
size 4091
|
checkpoint-250/trainer_state.json
DELETED
@@ -1,48 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": null,
|
3 |
-
"best_model_checkpoint": null,
|
4 |
-
"epoch": 1.0,
|
5 |
-
"global_step": 250,
|
6 |
-
"is_hyper_param_search": false,
|
7 |
-
"is_local_process_zero": true,
|
8 |
-
"is_world_process_zero": true,
|
9 |
-
"log_history": [
|
10 |
-
{
|
11 |
-
"epoch": 0.0,
|
12 |
-
"learning_rate": 1.999466666666667e-05,
|
13 |
-
"loss": 2.308,
|
14 |
-
"step": 1
|
15 |
-
},
|
16 |
-
{
|
17 |
-
"epoch": 0.75,
|
18 |
-
"learning_rate": 1.8997333333333335e-05,
|
19 |
-
"loss": 1.6916,
|
20 |
-
"step": 188
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"epoch": 0.75,
|
24 |
-
"eval_accuracy": 0.6755,
|
25 |
-
"eval_disk_space_total": 78.1898422241211,
|
26 |
-
"eval_disk_space_used": 24.806385040283203,
|
27 |
-
"eval_f1": 0.6708054417489328,
|
28 |
-
"eval_gpu_ram_allocated": 2.089780330657959,
|
29 |
-
"eval_gpu_ram_cached": 25.85546875,
|
30 |
-
"eval_gpu_ram_total": 39.56402587890625,
|
31 |
-
"eval_gpu_utilization": 50,
|
32 |
-
"eval_loss": 1.1062816381454468,
|
33 |
-
"eval_precision": 0.690043017889279,
|
34 |
-
"eval_recall": 0.6755,
|
35 |
-
"eval_runtime": 2.3912,
|
36 |
-
"eval_samples_per_second": 836.398,
|
37 |
-
"eval_steps_per_second": 26.347,
|
38 |
-
"eval_system_ram_total": 83.48074722290039,
|
39 |
-
"eval_system_ram_used": 4.019077301025391,
|
40 |
-
"step": 188
|
41 |
-
}
|
42 |
-
],
|
43 |
-
"max_steps": 3750,
|
44 |
-
"num_train_epochs": 15,
|
45 |
-
"total_flos": 478954442421888.0,
|
46 |
-
"trial_name": null,
|
47 |
-
"trial_params": null
|
48 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 737788917
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c37c9b2cf82643ccb441b9f2e76d6a70dccdc2fd29cd95cea2aeac5989dcc044
|
3 |
size 737788917
|
runs/Jul22_21-19-20_ab4276e44fca/events.out.tfevents.1690060770.ab4276e44fca.659.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91c406716727b3f9c785733bad33bcc6f1db69b8352ddbcb0f44eb1f3dc7eb58
|
3 |
+
size 11732
|