Hugging Face's logo

Shresthadev403
/
ner-bert-ingredients

Token Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files
xet
Metrics Community
Shresthadev403 commited on
Commit
53fc0f2
·
1 Parent(s): daaf981

End of training

Browse files
Files changed (15) hide show
  1. README.md +86 -0
  2. config.json +180 -0
  3. model.safetensors +3 -0
  4. runs/Jan05_06-13-05_414819e23027/events.out.tfevents.1704435192.414819e23027.9579.0 +3 -0
  5. runs/Jan05_06-14-19_414819e23027/events.out.tfevents.1704435268.414819e23027.9579.1 +3 -0
  6. runs/Jan05_06-16-09_414819e23027/events.out.tfevents.1704435377.414819e23027.9579.2 +3 -0
  7. runs/Jan05_06-17-23_414819e23027/events.out.tfevents.1704435452.414819e23027.9579.3 +3 -0
  8. runs/Jan05_06-18-41_414819e23027/events.out.tfevents.1704435530.414819e23027.9579.4 +3 -0
  9. runs/Jan05_06-28-56_414819e23027/events.out.tfevents.1704436145.414819e23027.9579.5 +3 -0
  10. runs/Jan05_07-21-44_414819e23027/events.out.tfevents.1704439312.414819e23027.9579.6 +3 -0
  11. runs/Jan05_07-23-52_414819e23027/events.out.tfevents.1704439445.414819e23027.9579.7 +3 -0
  12. runs/Jan05_07-33-16_414819e23027/events.out.tfevents.1704440006.414819e23027.9579.8 +3 -0
  13. runs/Jan05_07-36-33_414819e23027/events.out.tfevents.1704440204.414819e23027.9579.9 +3 -0
  14. trainer_state.json +448 -0
  15. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: bert-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: ner-bert-ingredients
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # ner-bert-ingredients
15
+
16
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 4.4971
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
+ - train_batch_size: 32
39
+ - eval_batch_size: 32
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 30
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:----:|:---------------:|
49
+ | 4.3432 | 1.0 | 1 | 4.3567 |
50
+ | 4.0861 | 2.0 | 2 | 4.3692 |
51
+ | 3.8656 | 3.0 | 3 | 4.3758 |
52
+ | 3.6664 | 4.0 | 4 | 4.3794 |
53
+ | 3.5134 | 5.0 | 5 | 4.3980 |
54
+ | 3.3284 | 6.0 | 6 | 4.4122 |
55
+ | 3.1759 | 7.0 | 7 | 4.4251 |
56
+ | 3.081 | 8.0 | 8 | 4.4369 |
57
+ | 2.9241 | 9.0 | 9 | 4.4459 |
58
+ | 2.7786 | 10.0 | 10 | 4.4513 |
59
+ | 2.6749 | 11.0 | 11 | 4.4566 |
60
+ | 2.5854 | 12.0 | 12 | 4.4633 |
61
+ | 2.4858 | 13.0 | 13 | 4.4685 |
62
+ | 2.4099 | 14.0 | 14 | 4.4731 |
63
+ | 2.3274 | 15.0 | 15 | 4.4766 |
64
+ | 2.248 | 16.0 | 16 | 4.4802 |
65
+ | 2.1441 | 17.0 | 17 | 4.4823 |
66
+ | 2.0917 | 18.0 | 18 | 4.4837 |
67
+ | 2.0482 | 19.0 | 19 | 4.4843 |
68
+ | 1.9734 | 20.0 | 20 | 4.4849 |
69
+ | 1.9277 | 21.0 | 21 | 4.4847 |
70
+ | 1.9198 | 22.0 | 22 | 4.4858 |
71
+ | 1.8629 | 23.0 | 23 | 4.4874 |
72
+ | 1.7521 | 24.0 | 24 | 4.4892 |
73
+ | 1.7454 | 25.0 | 25 | 4.4912 |
74
+ | 1.7226 | 26.0 | 26 | 4.4932 |
75
+ | 1.7192 | 27.0 | 27 | 4.4948 |
76
+ | 1.6892 | 28.0 | 28 | 4.4959 |
77
+ | 1.6849 | 29.0 | 29 | 4.4967 |
78
+ | 1.6504 | 30.0 | 30 | 4.4971 |
79
+
80
+
81
+ ### Framework versions
82
+
83
+ - Transformers 4.35.2
84
+ - Pytorch 2.1.0+cu121
85
+ - Datasets 2.16.1
86
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,180 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8",
22
+ "9": "LABEL_9",
23
+ "10": "LABEL_10",
24
+ "11": "LABEL_11",
25
+ "12": "LABEL_12",
26
+ "13": "LABEL_13",
27
+ "14": "LABEL_14",
28
+ "15": "LABEL_15",
29
+ "16": "LABEL_16",
30
+ "17": "LABEL_17",
31
+ "18": "LABEL_18",
32
+ "19": "LABEL_19",
33
+ "20": "LABEL_20",
34
+ "21": "LABEL_21",
35
+ "22": "LABEL_22",
36
+ "23": "LABEL_23",
37
+ "24": "LABEL_24",
38
+ "25": "LABEL_25",
39
+ "26": "LABEL_26",
40
+ "27": "LABEL_27",
41
+ "28": "LABEL_28",
42
+ "29": "LABEL_29",
43
+ "30": "LABEL_30",
44
+ "31": "LABEL_31",
45
+ "32": "LABEL_32",
46
+ "33": "LABEL_33",
47
+ "34": "LABEL_34",
48
+ "35": "LABEL_35",
49
+ "36": "LABEL_36",
50
+ "37": "LABEL_37",
51
+ "38": "LABEL_38",
52
+ "39": "LABEL_39",
53
+ "40": "LABEL_40",
54
+ "41": "LABEL_41",
55
+ "42": "LABEL_42",
56
+ "43": "LABEL_43",
57
+ "44": "LABEL_44",
58
+ "45": "LABEL_45",
59
+ "46": "LABEL_46",
60
+ "47": "LABEL_47",
61
+ "48": "LABEL_48",
62
+ "49": "LABEL_49",
63
+ "50": "LABEL_50",
64
+ "51": "LABEL_51",
65
+ "52": "LABEL_52",
66
+ "53": "LABEL_53",
67
+ "54": "LABEL_54",
68
+ "55": "LABEL_55",
69
+ "56": "LABEL_56",
70
+ "57": "LABEL_57",
71
+ "58": "LABEL_58",
72
+ "59": "LABEL_59",
73
+ "60": "LABEL_60",
74
+ "61": "LABEL_61",
75
+ "62": "LABEL_62",
76
+ "63": "LABEL_63",
77
+ "64": "LABEL_64",
78
+ "65": "LABEL_65",
79
+ "66": "LABEL_66",
80
+ "67": "LABEL_67",
81
+ "68": "LABEL_68",
82
+ "69": "LABEL_69",
83
+ "70": "LABEL_70",
84
+ "71": "LABEL_71",
85
+ "72": "LABEL_72",
86
+ "73": "LABEL_73",
87
+ "74": "LABEL_74"
88
+ },
89
+ "initializer_range": 0.02,
90
+ "intermediate_size": 3072,
91
+ "label2id": {
92
+ "LABEL_0": 0,
93
+ "LABEL_1": 1,
94
+ "LABEL_10": 10,
95
+ "LABEL_11": 11,
96
+ "LABEL_12": 12,
97
+ "LABEL_13": 13,
98
+ "LABEL_14": 14,
99
+ "LABEL_15": 15,
100
+ "LABEL_16": 16,
101
+ "LABEL_17": 17,
102
+ "LABEL_18": 18,
103
+ "LABEL_19": 19,
104
+ "LABEL_2": 2,
105
+ "LABEL_20": 20,
106
+ "LABEL_21": 21,
107
+ "LABEL_22": 22,
108
+ "LABEL_23": 23,
109
+ "LABEL_24": 24,
110
+ "LABEL_25": 25,
111
+ "LABEL_26": 26,
112
+ "LABEL_27": 27,
113
+ "LABEL_28": 28,
114
+ "LABEL_29": 29,
115
+ "LABEL_3": 3,
116
+ "LABEL_30": 30,
117
+ "LABEL_31": 31,
118
+ "LABEL_32": 32,
119
+ "LABEL_33": 33,
120
+ "LABEL_34": 34,
121
+ "LABEL_35": 35,
122
+ "LABEL_36": 36,
123
+ "LABEL_37": 37,
124
+ "LABEL_38": 38,
125
+ "LABEL_39": 39,
126
+ "LABEL_4": 4,
127
+ "LABEL_40": 40,
128
+ "LABEL_41": 41,
129
+ "LABEL_42": 42,
130
+ "LABEL_43": 43,
131
+ "LABEL_44": 44,
132
+ "LABEL_45": 45,
133
+ "LABEL_46": 46,
134
+ "LABEL_47": 47,
135
+ "LABEL_48": 48,
136
+ "LABEL_49": 49,
137
+ "LABEL_5": 5,
138
+ "LABEL_50": 50,
139
+ "LABEL_51": 51,
140
+ "LABEL_52": 52,
141
+ "LABEL_53": 53,
142
+ "LABEL_54": 54,
143
+ "LABEL_55": 55,
144
+ "LABEL_56": 56,
145
+ "LABEL_57": 57,
146
+ "LABEL_58": 58,
147
+ "LABEL_59": 59,
148
+ "LABEL_6": 6,
149
+ "LABEL_60": 60,
150
+ "LABEL_61": 61,
151
+ "LABEL_62": 62,
152
+ "LABEL_63": 63,
153
+ "LABEL_64": 64,
154
+ "LABEL_65": 65,
155
+ "LABEL_66": 66,
156
+ "LABEL_67": 67,
157
+ "LABEL_68": 68,
158
+ "LABEL_69": 69,
159
+ "LABEL_7": 7,
160
+ "LABEL_70": 70,
161
+ "LABEL_71": 71,
162
+ "LABEL_72": 72,
163
+ "LABEL_73": 73,
164
+ "LABEL_74": 74,
165
+ "LABEL_8": 8,
166
+ "LABEL_9": 9
167
+ },
168
+ "layer_norm_eps": 1e-12,
169
+ "max_position_embeddings": 512,
170
+ "model_type": "bert",
171
+ "num_attention_heads": 12,
172
+ "num_hidden_layers": 12,
173
+ "pad_token_id": 0,
174
+ "position_embedding_type": "absolute",
175
+ "torch_dtype": "float32",
176
+ "transformers_version": "4.35.2",
177
+ "type_vocab_size": 2,
178
+ "use_cache": true,
179
+ "vocab_size": 30522
180
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de247be48c1f31ac017bfe8064dec6d7e52035801c45ad80917840938222fc01
3
+ size 435820636
runs/Jan05_06-13-05_414819e23027/events.out.tfevents.1704435192.414819e23027.9579.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e31843086aa4e9d5c81c6645723b2ee902cea99a2d3e8416505911824534bf44
3
+ size 7331
runs/Jan05_06-14-19_414819e23027/events.out.tfevents.1704435268.414819e23027.9579.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c1c56d93e0b274312c0615dec0bf7592cefe44e3b7e188ae6bf6d387018816b
3
+ size 7679
runs/Jan05_06-16-09_414819e23027/events.out.tfevents.1704435377.414819e23027.9579.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f86c743867f0d961cda48a500f392ebd3af5758f0bb77f6d141d10d594471ecf
3
+ size 7333
runs/Jan05_06-17-23_414819e23027/events.out.tfevents.1704435452.414819e23027.9579.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf0681dba05f3bec94d1830007ec7122d95b58197ff55d91e0d92b1e4ddc084f
3
+ size 9063
runs/Jan05_06-18-41_414819e23027/events.out.tfevents.1704435530.414819e23027.9579.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a45b8eee920479bd329a997011fad7a0d2d3e0f4006b936522cc9c64b7b18478
3
+ size 9063
runs/Jan05_06-28-56_414819e23027/events.out.tfevents.1704436145.414819e23027.9579.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4f539bb9e2a0500c7e0e07527d82b267f34130035d0eef300ce771128208fe6
3
+ size 93401
runs/Jan05_07-21-44_414819e23027/events.out.tfevents.1704439312.414819e23027.9579.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db0bea5e2cb33cfaed3ae0f88142a09e6551dd93c93c1324aaf03a19cdf8a182
3
+ size 20279
runs/Jan05_07-23-52_414819e23027/events.out.tfevents.1704439445.414819e23027.9579.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd77abcf3f919fcca5503f2c698ed46582810f071371b73a5fd1183e76271f25
3
+ size 20279
runs/Jan05_07-33-16_414819e23027/events.out.tfevents.1704440006.414819e23027.9579.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9afbc9b461525222eb312575f7d84e61b22e8af9ff4ecae8b6831c5c3a5d2615
3
+ size 20296
runs/Jan05_07-36-33_414819e23027/events.out.tfevents.1704440204.414819e23027.9579.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:818ff0152710f1b8c6d057fea09523e61c626c8a72f505067ccfa98c8f971c25
3
+ size 20296
trainer_state.json ADDED
@@ -0,0 +1,448 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 30.0,
5
+ "eval_steps": 1,
6
+ "global_step": 30,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "learning_rate": 4.8333333333333334e-05,
14
+ "loss": 4.3432,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_loss": 4.35671854019165,
20
+ "eval_runtime": 0.1407,
21
+ "eval_samples_per_second": 14.211,
22
+ "eval_steps_per_second": 7.106,
23
+ "step": 1
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 4.666666666666667e-05,
28
+ "loss": 4.0861,
29
+ "step": 2
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_loss": 4.369217395782471,
34
+ "eval_runtime": 0.0817,
35
+ "eval_samples_per_second": 24.485,
36
+ "eval_steps_per_second": 12.242,
37
+ "step": 2
38
+ },
39
+ {
40
+ "epoch": 3.0,
41
+ "learning_rate": 4.5e-05,
42
+ "loss": 3.8656,
43
+ "step": 3
44
+ },
45
+ {
46
+ "epoch": 3.0,
47
+ "eval_loss": 4.375834941864014,
48
+ "eval_runtime": 0.0652,
49
+ "eval_samples_per_second": 30.668,
50
+ "eval_steps_per_second": 15.334,
51
+ "step": 3
52
+ },
53
+ {
54
+ "epoch": 4.0,
55
+ "learning_rate": 4.3333333333333334e-05,
56
+ "loss": 3.6664,
57
+ "step": 4
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "eval_loss": 4.3793864250183105,
62
+ "eval_runtime": 0.0448,
63
+ "eval_samples_per_second": 44.677,
64
+ "eval_steps_per_second": 22.339,
65
+ "step": 4
66
+ },
67
+ {
68
+ "epoch": 5.0,
69
+ "learning_rate": 4.166666666666667e-05,
70
+ "loss": 3.5134,
71
+ "step": 5
72
+ },
73
+ {
74
+ "epoch": 5.0,
75
+ "eval_loss": 4.3979878425598145,
76
+ "eval_runtime": 0.0481,
77
+ "eval_samples_per_second": 41.609,
78
+ "eval_steps_per_second": 20.805,
79
+ "step": 5
80
+ },
81
+ {
82
+ "epoch": 6.0,
83
+ "learning_rate": 4e-05,
84
+ "loss": 3.3284,
85
+ "step": 6
86
+ },
87
+ {
88
+ "epoch": 6.0,
89
+ "eval_loss": 4.412211894989014,
90
+ "eval_runtime": 0.0427,
91
+ "eval_samples_per_second": 46.82,
92
+ "eval_steps_per_second": 23.41,
93
+ "step": 6
94
+ },
95
+ {
96
+ "epoch": 7.0,
97
+ "learning_rate": 3.8333333333333334e-05,
98
+ "loss": 3.1759,
99
+ "step": 7
100
+ },
101
+ {
102
+ "epoch": 7.0,
103
+ "eval_loss": 4.425065994262695,
104
+ "eval_runtime": 0.0359,
105
+ "eval_samples_per_second": 55.731,
106
+ "eval_steps_per_second": 27.866,
107
+ "step": 7
108
+ },
109
+ {
110
+ "epoch": 8.0,
111
+ "learning_rate": 3.6666666666666666e-05,
112
+ "loss": 3.081,
113
+ "step": 8
114
+ },
115
+ {
116
+ "epoch": 8.0,
117
+ "eval_loss": 4.436896800994873,
118
+ "eval_runtime": 0.0511,
119
+ "eval_samples_per_second": 39.117,
120
+ "eval_steps_per_second": 19.559,
121
+ "step": 8
122
+ },
123
+ {
124
+ "epoch": 9.0,
125
+ "learning_rate": 3.5e-05,
126
+ "loss": 2.9241,
127
+ "step": 9
128
+ },
129
+ {
130
+ "epoch": 9.0,
131
+ "eval_loss": 4.445853233337402,
132
+ "eval_runtime": 0.0375,
133
+ "eval_samples_per_second": 53.324,
134
+ "eval_steps_per_second": 26.662,
135
+ "step": 9
136
+ },
137
+ {
138
+ "epoch": 10.0,
139
+ "learning_rate": 3.3333333333333335e-05,
140
+ "loss": 2.7786,
141
+ "step": 10
142
+ },
143
+ {
144
+ "epoch": 10.0,
145
+ "eval_loss": 4.451279640197754,
146
+ "eval_runtime": 0.0479,
147
+ "eval_samples_per_second": 41.751,
148
+ "eval_steps_per_second": 20.876,
149
+ "step": 10
150
+ },
151
+ {
152
+ "epoch": 11.0,
153
+ "learning_rate": 3.1666666666666666e-05,
154
+ "loss": 2.6749,
155
+ "step": 11
156
+ },
157
+ {
158
+ "epoch": 11.0,
159
+ "eval_loss": 4.456623554229736,
160
+ "eval_runtime": 0.0688,
161
+ "eval_samples_per_second": 29.049,
162
+ "eval_steps_per_second": 14.525,
163
+ "step": 11
164
+ },
165
+ {
166
+ "epoch": 12.0,
167
+ "learning_rate": 3e-05,
168
+ "loss": 2.5854,
169
+ "step": 12
170
+ },
171
+ {
172
+ "epoch": 12.0,
173
+ "eval_loss": 4.463347911834717,
174
+ "eval_runtime": 0.0454,
175
+ "eval_samples_per_second": 44.062,
176
+ "eval_steps_per_second": 22.031,
177
+ "step": 12
178
+ },
179
+ {
180
+ "epoch": 13.0,
181
+ "learning_rate": 2.8333333333333335e-05,
182
+ "loss": 2.4858,
183
+ "step": 13
184
+ },
185
+ {
186
+ "epoch": 13.0,
187
+ "eval_loss": 4.468521595001221,
188
+ "eval_runtime": 0.0386,
189
+ "eval_samples_per_second": 51.842,
190
+ "eval_steps_per_second": 25.921,
191
+ "step": 13
192
+ },
193
+ {
194
+ "epoch": 14.0,
195
+ "learning_rate": 2.6666666666666667e-05,
196
+ "loss": 2.4099,
197
+ "step": 14
198
+ },
199
+ {
200
+ "epoch": 14.0,
201
+ "eval_loss": 4.473144054412842,
202
+ "eval_runtime": 0.0612,
203
+ "eval_samples_per_second": 32.678,
204
+ "eval_steps_per_second": 16.339,
205
+ "step": 14
206
+ },
207
+ {
208
+ "epoch": 15.0,
209
+ "learning_rate": 2.5e-05,
210
+ "loss": 2.3274,
211
+ "step": 15
212
+ },
213
+ {
214
+ "epoch": 15.0,
215
+ "eval_loss": 4.47658634185791,
216
+ "eval_runtime": 0.0417,
217
+ "eval_samples_per_second": 48.005,
218
+ "eval_steps_per_second": 24.002,
219
+ "step": 15
220
+ },
221
+ {
222
+ "epoch": 16.0,
223
+ "learning_rate": 2.3333333333333336e-05,
224
+ "loss": 2.248,
225
+ "step": 16
226
+ },
227
+ {
228
+ "epoch": 16.0,
229
+ "eval_loss": 4.480152606964111,
230
+ "eval_runtime": 0.0428,
231
+ "eval_samples_per_second": 46.707,
232
+ "eval_steps_per_second": 23.354,
233
+ "step": 16
234
+ },
235
+ {
236
+ "epoch": 17.0,
237
+ "learning_rate": 2.1666666666666667e-05,
238
+ "loss": 2.1441,
239
+ "step": 17
240
+ },
241
+ {
242
+ "epoch": 17.0,
243
+ "eval_loss": 4.482294082641602,
244
+ "eval_runtime": 0.0416,
245
+ "eval_samples_per_second": 48.118,
246
+ "eval_steps_per_second": 24.059,
247
+ "step": 17
248
+ },
249
+ {
250
+ "epoch": 18.0,
251
+ "learning_rate": 2e-05,
252
+ "loss": 2.0917,
253
+ "step": 18
254
+ },
255
+ {
256
+ "epoch": 18.0,
257
+ "eval_loss": 4.483733654022217,
258
+ "eval_runtime": 0.0576,
259
+ "eval_samples_per_second": 34.736,
260
+ "eval_steps_per_second": 17.368,
261
+ "step": 18
262
+ },
263
+ {
264
+ "epoch": 19.0,
265
+ "learning_rate": 1.8333333333333333e-05,
266
+ "loss": 2.0482,
267
+ "step": 19
268
+ },
269
+ {
270
+ "epoch": 19.0,
271
+ "eval_loss": 4.484250068664551,
272
+ "eval_runtime": 0.0477,
273
+ "eval_samples_per_second": 41.952,
274
+ "eval_steps_per_second": 20.976,
275
+ "step": 19
276
+ },
277
+ {
278
+ "epoch": 20.0,
279
+ "learning_rate": 1.6666666666666667e-05,
280
+ "loss": 1.9734,
281
+ "step": 20
282
+ },
283
+ {
284
+ "epoch": 20.0,
285
+ "eval_loss": 4.484899520874023,
286
+ "eval_runtime": 0.0657,
287
+ "eval_samples_per_second": 30.45,
288
+ "eval_steps_per_second": 15.225,
289
+ "step": 20
290
+ },
291
+ {
292
+ "epoch": 21.0,
293
+ "learning_rate": 1.5e-05,
294
+ "loss": 1.9277,
295
+ "step": 21
296
+ },
297
+ {
298
+ "epoch": 21.0,
299
+ "eval_loss": 4.484712600708008,
300
+ "eval_runtime": 0.0571,
301
+ "eval_samples_per_second": 34.999,
302
+ "eval_steps_per_second": 17.5,
303
+ "step": 21
304
+ },
305
+ {
306
+ "epoch": 22.0,
307
+ "learning_rate": 1.3333333333333333e-05,
308
+ "loss": 1.9198,
309
+ "step": 22
310
+ },
311
+ {
312
+ "epoch": 22.0,
313
+ "eval_loss": 4.485757827758789,
314
+ "eval_runtime": 0.0438,
315
+ "eval_samples_per_second": 45.632,
316
+ "eval_steps_per_second": 22.816,
317
+ "step": 22
318
+ },
319
+ {
320
+ "epoch": 23.0,
321
+ "learning_rate": 1.1666666666666668e-05,
322
+ "loss": 1.8629,
323
+ "step": 23
324
+ },
325
+ {
326
+ "epoch": 23.0,
327
+ "eval_loss": 4.487393379211426,
328
+ "eval_runtime": 0.0494,
329
+ "eval_samples_per_second": 40.485,
330
+ "eval_steps_per_second": 20.243,
331
+ "step": 23
332
+ },
333
+ {
334
+ "epoch": 24.0,
335
+ "learning_rate": 1e-05,
336
+ "loss": 1.7521,
337
+ "step": 24
338
+ },
339
+ {
340
+ "epoch": 24.0,
341
+ "eval_loss": 4.489238262176514,
342
+ "eval_runtime": 0.0567,
343
+ "eval_samples_per_second": 35.285,
344
+ "eval_steps_per_second": 17.642,
345
+ "step": 24
346
+ },
347
+ {
348
+ "epoch": 25.0,
349
+ "learning_rate": 8.333333333333334e-06,
350
+ "loss": 1.7454,
351
+ "step": 25
352
+ },
353
+ {
354
+ "epoch": 25.0,
355
+ "eval_loss": 4.491191864013672,
356
+ "eval_runtime": 0.0523,
357
+ "eval_samples_per_second": 38.25,
358
+ "eval_steps_per_second": 19.125,
359
+ "step": 25
360
+ },
361
+ {
362
+ "epoch": 26.0,
363
+ "learning_rate": 6.666666666666667e-06,
364
+ "loss": 1.7226,
365
+ "step": 26
366
+ },
367
+ {
368
+ "epoch": 26.0,
369
+ "eval_loss": 4.493249893188477,
370
+ "eval_runtime": 0.0493,
371
+ "eval_samples_per_second": 40.552,
372
+ "eval_steps_per_second": 20.276,
373
+ "step": 26
374
+ },
375
+ {
376
+ "epoch": 27.0,
377
+ "learning_rate": 5e-06,
378
+ "loss": 1.7192,
379
+ "step": 27
380
+ },
381
+ {
382
+ "epoch": 27.0,
383
+ "eval_loss": 4.494760990142822,
384
+ "eval_runtime": 0.0643,
385
+ "eval_samples_per_second": 31.082,
386
+ "eval_steps_per_second": 15.541,
387
+ "step": 27
388
+ },
389
+ {
390
+ "epoch": 28.0,
391
+ "learning_rate": 3.3333333333333333e-06,
392
+ "loss": 1.6892,
393
+ "step": 28
394
+ },
395
+ {
396
+ "epoch": 28.0,
397
+ "eval_loss": 4.495946884155273,
398
+ "eval_runtime": 0.0648,
399
+ "eval_samples_per_second": 30.848,
400
+ "eval_steps_per_second": 15.424,
401
+ "step": 28
402
+ },
403
+ {
404
+ "epoch": 29.0,
405
+ "learning_rate": 1.6666666666666667e-06,
406
+ "loss": 1.6849,
407
+ "step": 29
408
+ },
409
+ {
410
+ "epoch": 29.0,
411
+ "eval_loss": 4.496687889099121,
412
+ "eval_runtime": 0.067,
413
+ "eval_samples_per_second": 29.867,
414
+ "eval_steps_per_second": 14.933,
415
+ "step": 29
416
+ },
417
+ {
418
+ "epoch": 30.0,
419
+ "learning_rate": 0.0,
420
+ "loss": 1.6504,
421
+ "step": 30
422
+ },
423
+ {
424
+ "epoch": 30.0,
425
+ "eval_loss": 4.497078895568848,
426
+ "eval_runtime": 0.0572,
427
+ "eval_samples_per_second": 34.952,
428
+ "eval_steps_per_second": 17.476,
429
+ "step": 30
430
+ },
431
+ {
432
+ "epoch": 30.0,
433
+ "step": 30,
434
+ "total_flos": 17281480572000.0,
435
+ "train_loss": 2.5141863663991293,
436
+ "train_runtime": 8.7375,
437
+ "train_samples_per_second": 27.468,
438
+ "train_steps_per_second": 3.433
439
+ }
440
+ ],
441
+ "logging_steps": 1,
442
+ "max_steps": 30,
443
+ "num_train_epochs": 30,
444
+ "save_steps": 500,
445
+ "total_flos": 17281480572000.0,
446
+ "trial_name": null,
447
+ "trial_params": null
448
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40e1c7011ce262396d659969b9361605bd6d32cbc09be30d8f7240d9d99ac2ba
3
+ size 4600