Hugging Face's logo

samuellimabraz
/
t5-small-qlora-finetune-tweetsumm

PEFT
Safetensors
Generated from Trainer
Eval Results
Model card Files Community
samuellimabraz commited on
Commit
d7f4ba3
•
1 Parent(s): 3226d8a

End of training

Browse files
Files changed (11) hide show
  1. README.md +96 -0
  2. adapter_config.json +29 -0
  3. adapter_model.safetensors +3 -0
  4. all_results.json +12 -0
  5. special_tokens_map.json +125 -0
  6. spiece.model +3 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +937 -0
  9. train_results.json +12 -0
  10. trainer_state.json +2400 -0
  11. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: google-t5/t5-small
3
+ datasets:
4
+ - Andyrasika/TweetSumm-tuned
5
+ library_name: peft
6
+ license: apache-2.0
7
+ metrics:
8
+ - rouge
9
+ - f1
10
+ - precision
11
+ - recall
12
+ tags:
13
+ - generated_from_trainer
14
+ model-index:
15
+ - name: t5-small-QLoRA-TweetSumm-1724713795
16
+ results:
17
+ - task:
18
+ type: summarization
19
+ name: Summarization
20
+ dataset:
21
+ name: Andyrasika/TweetSumm-tuned
22
+ type: Andyrasika/TweetSumm-tuned
23
+ metrics:
24
+ - type: rouge
25
+ value: 0.4298
26
+ name: Rouge1
27
+ - type: f1
28
+ value: 0.887
29
+ name: F1
30
+ - type: precision
31
+ value: 0.8838
32
+ name: Precision
33
+ - type: recall
34
+ value: 0.8904
35
+ name: Recall
36
+ ---
37
+
38
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
39
+ should probably proofread and complete it, then remove this comment. -->
40
+
41
+ # t5-small-QLoRA-TweetSumm-1724713795
42
+
43
+ This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on the Andyrasika/TweetSumm-tuned dataset.
44
+ It achieves the following results on the evaluation set:
45
+ - Loss: 2.0940
46
+ - Rouge1: 0.4298
47
+ - Rouge2: 0.1915
48
+ - Rougel: 0.3559
49
+ - Rougelsum: 0.3956
50
+ - Gen Len: 47.8091
51
+ - F1: 0.887
52
+ - Precision: 0.8838
53
+ - Recall: 0.8904
54
+
55
+ ## Model description
56
+
57
+ More information needed
58
+
59
+ ## Intended uses & limitations
60
+
61
+ More information needed
62
+
63
+ ## Training and evaluation data
64
+
65
+ More information needed
66
+
67
+ ## Training procedure
68
+
69
+ ### Training hyperparameters
70
+
71
+ The following hyperparameters were used during training:
72
+ - learning_rate: 0.0005
73
+ - train_batch_size: 8
74
+ - eval_batch_size: 8
75
+ - seed: 42
76
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
77
+ - lr_scheduler_type: linear
78
+ - num_epochs: 3
79
+ - mixed_precision_training: Native AMP
80
+
81
+ ### Training results
82
+
83
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | F1 | Precision | Recall |
84
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|:------:|:---------:|:------:|
85
+ | 2.3641 | 1.0 | 110 | 2.2019 | 0.4172 | 0.1774 | 0.3518 | 0.386 | 47.7636 | 0.8828 | 0.8806 | 0.8852 |
86
+ | 2.2228 | 2.0 | 220 | 2.1040 | 0.419 | 0.1789 | 0.3477 | 0.3827 | 48.1182 | 0.8846 | 0.882 | 0.8875 |
87
+ | 2.0174 | 3.0 | 330 | 2.0940 | 0.4298 | 0.1915 | 0.3559 | 0.3956 | 47.8091 | 0.887 | 0.8838 | 0.8904 |
88
+
89
+
90
+ ### Framework versions
91
+
92
+ - PEFT 0.12.1.dev0
93
+ - Transformers 4.44.0
94
+ - Pytorch 2.4.0
95
+ - Datasets 2.21.0
96
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "google-t5/t5-small",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 64,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q",
24
+ "v"
25
+ ],
26
+ "task_type": "SEQ_2_SEQ_LM",
27
+ "use_dora": false,
28
+ "use_rslora": true
29
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1451b4d601a00441e67b38f1ddf6acd02703eb79396e65fd5544236a6c18923d
3
+ size 4728656
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "all_params": 45957632,
3
+ "epoch": 3.0,
4
+ "memory_footprint": 136644608,
5
+ "total_flos": 366452498497536.0,
6
+ "train_loss": 2.2660372549837287,
7
+ "train_runtime": 171.2707,
8
+ "train_samples_per_second": 15.397,
9
+ "train_steps_per_second": 1.927,
10
+ "trainable_params": 1179648,
11
+ "trainable_params_percent": 2.5668163233475565
12
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,937 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<unk>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32000": {
28
+ "content": "<extra_id_99>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32001": {
36
+ "content": "<extra_id_98>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32002": {
44
+ "content": "<extra_id_97>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32003": {
52
+ "content": "<extra_id_96>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "32004": {
60
+ "content": "<extra_id_95>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "32005": {
68
+ "content": "<extra_id_94>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "32006": {
76
+ "content": "<extra_id_93>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "32007": {
84
+ "content": "<extra_id_92>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "32008": {
92
+ "content": "<extra_id_91>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "32009": {
100
+ "content": "<extra_id_90>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "32010": {
108
+ "content": "<extra_id_89>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "32011": {
116
+ "content": "<extra_id_88>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "32012": {
124
+ "content": "<extra_id_87>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "32013": {
132
+ "content": "<extra_id_86>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "32014": {
140
+ "content": "<extra_id_85>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "32015": {
148
+ "content": "<extra_id_84>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "32016": {
156
+ "content": "<extra_id_83>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "32017": {
164
+ "content": "<extra_id_82>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "32018": {
172
+ "content": "<extra_id_81>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "32019": {
180
+ "content": "<extra_id_80>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "32020": {
188
+ "content": "<extra_id_79>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "32021": {
196
+ "content": "<extra_id_78>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "32022": {
204
+ "content": "<extra_id_77>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "32023": {
212
+ "content": "<extra_id_76>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "32024": {
220
+ "content": "<extra_id_75>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "32025": {
228
+ "content": "<extra_id_74>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "32026": {
236
+ "content": "<extra_id_73>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "32027": {
244
+ "content": "<extra_id_72>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "32028": {
252
+ "content": "<extra_id_71>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "32029": {
260
+ "content": "<extra_id_70>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "32030": {
268
+ "content": "<extra_id_69>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "32031": {
276
+ "content": "<extra_id_68>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "32032": {
284
+ "content": "<extra_id_67>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "32033": {
292
+ "content": "<extra_id_66>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "32034": {
300
+ "content": "<extra_id_65>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "32035": {
308
+ "content": "<extra_id_64>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "32036": {
316
+ "content": "<extra_id_63>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "32037": {
324
+ "content": "<extra_id_62>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "32038": {
332
+ "content": "<extra_id_61>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "32039": {
340
+ "content": "<extra_id_60>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "32040": {
348
+ "content": "<extra_id_59>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "32041": {
356
+ "content": "<extra_id_58>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "32042": {
364
+ "content": "<extra_id_57>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "32043": {
372
+ "content": "<extra_id_56>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "32044": {
380
+ "content": "<extra_id_55>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "32045": {
388
+ "content": "<extra_id_54>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "32046": {
396
+ "content": "<extra_id_53>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "32047": {
404
+ "content": "<extra_id_52>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "32048": {
412
+ "content": "<extra_id_51>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "32049": {
420
+ "content": "<extra_id_50>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "32050": {
428
+ "content": "<extra_id_49>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "32051": {
436
+ "content": "<extra_id_48>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "32052": {
444
+ "content": "<extra_id_47>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "32053": {
452
+ "content": "<extra_id_46>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "32054": {
460
+ "content": "<extra_id_45>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "32055": {
468
+ "content": "<extra_id_44>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "32056": {
476
+ "content": "<extra_id_43>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "32057": {
484
+ "content": "<extra_id_42>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "32058": {
492
+ "content": "<extra_id_41>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "32059": {
500
+ "content": "<extra_id_40>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "32060": {
508
+ "content": "<extra_id_39>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "32061": {
516
+ "content": "<extra_id_38>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "32062": {
524
+ "content": "<extra_id_37>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "32063": {
532
+ "content": "<extra_id_36>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "32064": {
540
+ "content": "<extra_id_35>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "32065": {
548
+ "content": "<extra_id_34>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "32066": {
556
+ "content": "<extra_id_33>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "32067": {
564
+ "content": "<extra_id_32>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "32068": {
572
+ "content": "<extra_id_31>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "32069": {
580
+ "content": "<extra_id_30>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "32070": {
588
+ "content": "<extra_id_29>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "32071": {
596
+ "content": "<extra_id_28>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "32072": {
604
+ "content": "<extra_id_27>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "32073": {
612
+ "content": "<extra_id_26>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "32074": {
620
+ "content": "<extra_id_25>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "32075": {
628
+ "content": "<extra_id_24>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "32076": {
636
+ "content": "<extra_id_23>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "32077": {
644
+ "content": "<extra_id_22>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "32078": {
652
+ "content": "<extra_id_21>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "32079": {
660
+ "content": "<extra_id_20>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "32080": {
668
+ "content": "<extra_id_19>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "32081": {
676
+ "content": "<extra_id_18>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "32082": {
684
+ "content": "<extra_id_17>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "32083": {
692
+ "content": "<extra_id_16>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "32084": {
700
+ "content": "<extra_id_15>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "32085": {
708
+ "content": "<extra_id_14>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "32086": {
716
+ "content": "<extra_id_13>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "32087": {
724
+ "content": "<extra_id_12>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "32088": {
732
+ "content": "<extra_id_11>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "32089": {
740
+ "content": "<extra_id_10>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "32090": {
748
+ "content": "<extra_id_9>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "32091": {
756
+ "content": "<extra_id_8>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "32092": {
764
+ "content": "<extra_id_7>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "32093": {
772
+ "content": "<extra_id_6>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "32094": {
780
+ "content": "<extra_id_5>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "32095": {
788
+ "content": "<extra_id_4>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "32096": {
796
+ "content": "<extra_id_3>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "32097": {
804
+ "content": "<extra_id_2>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "32098": {
812
+ "content": "<extra_id_1>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "32099": {
820
+ "content": "<extra_id_0>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ }
827
+ },
828
+ "additional_special_tokens": [
829
+ "<extra_id_0>",
830
+ "<extra_id_1>",
831
+ "<extra_id_2>",
832
+ "<extra_id_3>",
833
+ "<extra_id_4>",
834
+ "<extra_id_5>",
835
+ "<extra_id_6>",
836
+ "<extra_id_7>",
837
+ "<extra_id_8>",
838
+ "<extra_id_9>",
839
+ "<extra_id_10>",
840
+ "<extra_id_11>",
841
+ "<extra_id_12>",
842
+ "<extra_id_13>",
843
+ "<extra_id_14>",
844
+ "<extra_id_15>",
845
+ "<extra_id_16>",
846
+ "<extra_id_17>",
847
+ "<extra_id_18>",
848
+ "<extra_id_19>",
849
+ "<extra_id_20>",
850
+ "<extra_id_21>",
851
+ "<extra_id_22>",
852
+ "<extra_id_23>",
853
+ "<extra_id_24>",
854
+ "<extra_id_25>",
855
+ "<extra_id_26>",
856
+ "<extra_id_27>",
857
+ "<extra_id_28>",
858
+ "<extra_id_29>",
859
+ "<extra_id_30>",
860
+ "<extra_id_31>",
861
+ "<extra_id_32>",
862
+ "<extra_id_33>",
863
+ "<extra_id_34>",
864
+ "<extra_id_35>",
865
+ "<extra_id_36>",
866
+ "<extra_id_37>",
867
+ "<extra_id_38>",
868
+ "<extra_id_39>",
869
+ "<extra_id_40>",
870
+ "<extra_id_41>",
871
+ "<extra_id_42>",
872
+ "<extra_id_43>",
873
+ "<extra_id_44>",
874
+ "<extra_id_45>",
875
+ "<extra_id_46>",
876
+ "<extra_id_47>",
877
+ "<extra_id_48>",
878
+ "<extra_id_49>",
879
+ "<extra_id_50>",
880
+ "<extra_id_51>",
881
+ "<extra_id_52>",
882
+ "<extra_id_53>",
883
+ "<extra_id_54>",
884
+ "<extra_id_55>",
885
+ "<extra_id_56>",
886
+ "<extra_id_57>",
887
+ "<extra_id_58>",
888
+ "<extra_id_59>",
889
+ "<extra_id_60>",
890
+ "<extra_id_61>",
891
+ "<extra_id_62>",
892
+ "<extra_id_63>",
893
+ "<extra_id_64>",
894
+ "<extra_id_65>",
895
+ "<extra_id_66>",
896
+ "<extra_id_67>",
897
+ "<extra_id_68>",
898
+ "<extra_id_69>",
899
+ "<extra_id_70>",
900
+ "<extra_id_71>",
901
+ "<extra_id_72>",
902
+ "<extra_id_73>",
903
+ "<extra_id_74>",
904
+ "<extra_id_75>",
905
+ "<extra_id_76>",
906
+ "<extra_id_77>",
907
+ "<extra_id_78>",
908
+ "<extra_id_79>",
909
+ "<extra_id_80>",
910
+ "<extra_id_81>",
911
+ "<extra_id_82>",
912
+ "<extra_id_83>",
913
+ "<extra_id_84>",
914
+ "<extra_id_85>",
915
+ "<extra_id_86>",
916
+ "<extra_id_87>",
917
+ "<extra_id_88>",
918
+ "<extra_id_89>",
919
+ "<extra_id_90>",
920
+ "<extra_id_91>",
921
+ "<extra_id_92>",
922
+ "<extra_id_93>",
923
+ "<extra_id_94>",
924
+ "<extra_id_95>",
925
+ "<extra_id_96>",
926
+ "<extra_id_97>",
927
+ "<extra_id_98>",
928
+ "<extra_id_99>"
929
+ ],
930
+ "clean_up_tokenization_spaces": true,
931
+ "eos_token": "</s>",
932
+ "extra_ids": 100,
933
+ "model_max_length": 512,
934
+ "pad_token": "<pad>",
935
+ "tokenizer_class": "T5Tokenizer",
936
+ "unk_token": "<unk>"
937
+ }
train_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "all_params": 45957632,
3
+ "epoch": 3.0,
4
+ "memory_footprint": 136644608,
5
+ "total_flos": 366452498497536.0,
6
+ "train_loss": 2.2660372549837287,
7
+ "train_runtime": 171.2707,
8
+ "train_samples_per_second": 15.397,
9
+ "train_steps_per_second": 1.927,
10
+ "trainable_params": 1179648,
11
+ "trainable_params_percent": 2.5668163233475565
12
+ }
trainer_state.json ADDED
@@ -0,0 +1,2400 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 330,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.00909090909090909,
13
+ "grad_norm": 3.072246789932251,
14
+ "learning_rate": 0.0004984848484848485,
15
+ "loss": 3.4024,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.01818181818181818,
20
+ "grad_norm": 2.9938416481018066,
21
+ "learning_rate": 0.000496969696969697,
22
+ "loss": 3.4175,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.02727272727272727,
27
+ "grad_norm": 2.8850042819976807,
28
+ "learning_rate": 0.0004954545454545455,
29
+ "loss": 3.406,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.03636363636363636,
34
+ "grad_norm": 3.1597700119018555,
35
+ "learning_rate": 0.000493939393939394,
36
+ "loss": 3.1781,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.045454545454545456,
41
+ "grad_norm": 2.873157262802124,
42
+ "learning_rate": 0.0004924242424242425,
43
+ "loss": 3.3714,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.05454545454545454,
48
+ "grad_norm": 2.6407289505004883,
49
+ "learning_rate": 0.0004909090909090909,
50
+ "loss": 3.2687,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.06363636363636363,
55
+ "grad_norm": 2.6007120609283447,
56
+ "learning_rate": 0.0004893939393939393,
57
+ "loss": 2.4782,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.07272727272727272,
62
+ "grad_norm": 3.4426627159118652,
63
+ "learning_rate": 0.00048787878787878784,
64
+ "loss": 3.4055,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.08181818181818182,
69
+ "grad_norm": 2.847586154937744,
70
+ "learning_rate": 0.0004863636363636364,
71
+ "loss": 2.997,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.09090909090909091,
76
+ "grad_norm": 2.890317916870117,
77
+ "learning_rate": 0.0004848484848484849,
78
+ "loss": 2.5766,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.1,
83
+ "grad_norm": 2.904961109161377,
84
+ "learning_rate": 0.00048333333333333334,
85
+ "loss": 2.8253,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.10909090909090909,
90
+ "grad_norm": 3.9057822227478027,
91
+ "learning_rate": 0.00048181818181818184,
92
+ "loss": 3.203,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.11818181818181818,
97
+ "grad_norm": 3.1521217823028564,
98
+ "learning_rate": 0.0004803030303030303,
99
+ "loss": 2.6697,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.12727272727272726,
104
+ "grad_norm": 2.8621177673339844,
105
+ "learning_rate": 0.0004787878787878788,
106
+ "loss": 2.7983,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.13636363636363635,
111
+ "grad_norm": 3.0851597785949707,
112
+ "learning_rate": 0.0004772727272727273,
113
+ "loss": 2.9337,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.14545454545454545,
118
+ "grad_norm": 3.1367125511169434,
119
+ "learning_rate": 0.0004757575757575758,
120
+ "loss": 2.7065,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.15454545454545454,
125
+ "grad_norm": 3.4545798301696777,
126
+ "learning_rate": 0.0004742424242424243,
127
+ "loss": 2.5313,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.16363636363636364,
132
+ "grad_norm": 3.1472649574279785,
133
+ "learning_rate": 0.0004727272727272727,
134
+ "loss": 2.823,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.17272727272727273,
139
+ "grad_norm": 3.5677640438079834,
140
+ "learning_rate": 0.0004712121212121212,
141
+ "loss": 3.0701,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.18181818181818182,
146
+ "grad_norm": 2.7954583168029785,
147
+ "learning_rate": 0.0004696969696969697,
148
+ "loss": 2.717,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.19090909090909092,
153
+ "grad_norm": 2.7427642345428467,
154
+ "learning_rate": 0.0004681818181818182,
155
+ "loss": 2.5426,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.2,
160
+ "grad_norm": 2.8571345806121826,
161
+ "learning_rate": 0.00046666666666666666,
162
+ "loss": 2.7008,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.20909090909090908,
167
+ "grad_norm": NaN,
168
+ "learning_rate": 0.00046666666666666666,
169
+ "loss": 2.7254,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.21818181818181817,
174
+ "grad_norm": 2.6938774585723877,
175
+ "learning_rate": 0.00046515151515151516,
176
+ "loss": 2.0546,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.22727272727272727,
181
+ "grad_norm": 3.1118974685668945,
182
+ "learning_rate": 0.00046363636363636366,
183
+ "loss": 2.5798,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.23636363636363636,
188
+ "grad_norm": 2.9915614128112793,
189
+ "learning_rate": 0.0004621212121212121,
190
+ "loss": 2.2886,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.24545454545454545,
195
+ "grad_norm": 3.370804786682129,
196
+ "learning_rate": 0.00046060606060606066,
197
+ "loss": 3.0413,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.2545454545454545,
202
+ "grad_norm": 3.392153739929199,
203
+ "learning_rate": 0.0004590909090909091,
204
+ "loss": 3.1874,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.2636363636363636,
209
+ "grad_norm": 2.894507646560669,
210
+ "learning_rate": 0.0004575757575757576,
211
+ "loss": 2.8216,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.2727272727272727,
216
+ "grad_norm": 2.8790500164031982,
217
+ "learning_rate": 0.00045606060606060605,
218
+ "loss": 2.5802,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.2818181818181818,
223
+ "grad_norm": 2.648164987564087,
224
+ "learning_rate": 0.00045454545454545455,
225
+ "loss": 2.5944,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.2909090909090909,
230
+ "grad_norm": 2.658068895339966,
231
+ "learning_rate": 0.000453030303030303,
232
+ "loss": 2.8305,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.3,
237
+ "grad_norm": 3.077828884124756,
238
+ "learning_rate": 0.00045151515151515154,
239
+ "loss": 2.5191,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.3090909090909091,
244
+ "grad_norm": 2.7916836738586426,
245
+ "learning_rate": 0.00045000000000000004,
246
+ "loss": 2.548,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.3181818181818182,
251
+ "grad_norm": 2.780879497528076,
252
+ "learning_rate": 0.0004484848484848485,
253
+ "loss": 2.6919,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.32727272727272727,
258
+ "grad_norm": 2.858031988143921,
259
+ "learning_rate": 0.000446969696969697,
260
+ "loss": 2.2139,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.33636363636363636,
265
+ "grad_norm": 2.5262515544891357,
266
+ "learning_rate": 0.00044545454545454543,
267
+ "loss": 2.6746,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.34545454545454546,
272
+ "grad_norm": 2.7128827571868896,
273
+ "learning_rate": 0.000443939393939394,
274
+ "loss": 2.9608,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.35454545454545455,
279
+ "grad_norm": 2.1641690731048584,
280
+ "learning_rate": 0.00044242424242424243,
281
+ "loss": 2.3184,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.36363636363636365,
286
+ "grad_norm": 2.511988878250122,
287
+ "learning_rate": 0.00044090909090909093,
288
+ "loss": 2.2914,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.37272727272727274,
293
+ "grad_norm": 2.837374448776245,
294
+ "learning_rate": 0.0004393939393939394,
295
+ "loss": 2.8177,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.38181818181818183,
300
+ "grad_norm": 2.4641802310943604,
301
+ "learning_rate": 0.00043787878787878787,
302
+ "loss": 3.0899,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.39090909090909093,
307
+ "grad_norm": 2.5493505001068115,
308
+ "learning_rate": 0.00043636363636363637,
309
+ "loss": 2.6168,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.4,
314
+ "grad_norm": 2.844992160797119,
315
+ "learning_rate": 0.00043484848484848487,
316
+ "loss": 2.0643,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.4090909090909091,
321
+ "grad_norm": 2.301405429840088,
322
+ "learning_rate": 0.00043333333333333337,
323
+ "loss": 2.1776,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.41818181818181815,
328
+ "grad_norm": 2.246461868286133,
329
+ "learning_rate": 0.0004318181818181818,
330
+ "loss": 2.1135,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.42727272727272725,
335
+ "grad_norm": 2.560056686401367,
336
+ "learning_rate": 0.0004303030303030303,
337
+ "loss": 2.8383,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.43636363636363634,
342
+ "grad_norm": 2.7504286766052246,
343
+ "learning_rate": 0.00042878787878787876,
344
+ "loss": 2.369,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.44545454545454544,
349
+ "grad_norm": 2.3253281116485596,
350
+ "learning_rate": 0.00042727272727272726,
351
+ "loss": 2.1502,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.45454545454545453,
356
+ "grad_norm": 2.799269676208496,
357
+ "learning_rate": 0.0004257575757575758,
358
+ "loss": 2.6997,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.4636363636363636,
363
+ "grad_norm": 2.5673718452453613,
364
+ "learning_rate": 0.00042424242424242425,
365
+ "loss": 2.8942,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.4727272727272727,
370
+ "grad_norm": 2.344376802444458,
371
+ "learning_rate": 0.00042272727272727275,
372
+ "loss": 2.7204,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.4818181818181818,
377
+ "grad_norm": 2.5352869033813477,
378
+ "learning_rate": 0.0004212121212121212,
379
+ "loss": 2.5996,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.4909090909090909,
384
+ "grad_norm": 2.6235299110412598,
385
+ "learning_rate": 0.0004196969696969697,
386
+ "loss": 2.7003,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.5,
391
+ "grad_norm": 2.1709656715393066,
392
+ "learning_rate": 0.00041818181818181814,
393
+ "loss": 2.2072,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.509090909090909,
398
+ "grad_norm": 2.1792054176330566,
399
+ "learning_rate": 0.0004166666666666667,
400
+ "loss": 1.994,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.5181818181818182,
405
+ "grad_norm": 2.7915806770324707,
406
+ "learning_rate": 0.0004151515151515152,
407
+ "loss": 2.7364,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.5272727272727272,
412
+ "grad_norm": 2.67014217376709,
413
+ "learning_rate": 0.00041363636363636364,
414
+ "loss": 2.419,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.5363636363636364,
419
+ "grad_norm": 2.3936879634857178,
420
+ "learning_rate": 0.00041212121212121214,
421
+ "loss": 2.594,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.5454545454545454,
426
+ "grad_norm": 2.2096967697143555,
427
+ "learning_rate": 0.0004106060606060606,
428
+ "loss": 2.1546,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.5545454545454546,
433
+ "grad_norm": 2.4055185317993164,
434
+ "learning_rate": 0.00040909090909090913,
435
+ "loss": 2.6045,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.5636363636363636,
440
+ "grad_norm": 2.4559690952301025,
441
+ "learning_rate": 0.0004075757575757576,
442
+ "loss": 2.3182,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.5727272727272728,
447
+ "grad_norm": 2.608903408050537,
448
+ "learning_rate": 0.0004060606060606061,
449
+ "loss": 2.3894,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.5818181818181818,
454
+ "grad_norm": 2.3189706802368164,
455
+ "learning_rate": 0.0004045454545454546,
456
+ "loss": 2.0284,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.5909090909090909,
461
+ "grad_norm": 2.2709004878997803,
462
+ "learning_rate": 0.000403030303030303,
463
+ "loss": 2.1272,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.6,
468
+ "grad_norm": 2.2770652770996094,
469
+ "learning_rate": 0.0004015151515151515,
470
+ "loss": 2.2473,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.6090909090909091,
475
+ "grad_norm": 2.5721359252929688,
476
+ "learning_rate": 0.0004,
477
+ "loss": 3.1117,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.6181818181818182,
482
+ "grad_norm": 2.5537078380584717,
483
+ "learning_rate": 0.0003984848484848485,
484
+ "loss": 2.3253,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.6272727272727273,
489
+ "grad_norm": 2.4199492931365967,
490
+ "learning_rate": 0.00039696969696969696,
491
+ "loss": 2.3951,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.6363636363636364,
496
+ "grad_norm": 2.334942579269409,
497
+ "learning_rate": 0.00039545454545454546,
498
+ "loss": 1.9247,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.6454545454545455,
503
+ "grad_norm": 4.504452705383301,
504
+ "learning_rate": 0.0003939393939393939,
505
+ "loss": 2.286,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.6545454545454545,
510
+ "grad_norm": 2.5388824939727783,
511
+ "learning_rate": 0.0003924242424242424,
512
+ "loss": 2.4846,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.6636363636363637,
517
+ "grad_norm": NaN,
518
+ "learning_rate": 0.0003924242424242424,
519
+ "loss": 2.3651,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.6727272727272727,
524
+ "grad_norm": 2.6247713565826416,
525
+ "learning_rate": 0.00039090909090909096,
526
+ "loss": 2.4366,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.6818181818181818,
531
+ "grad_norm": 2.6662254333496094,
532
+ "learning_rate": 0.0003893939393939394,
533
+ "loss": 2.4153,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.6909090909090909,
538
+ "grad_norm": 2.6559085845947266,
539
+ "learning_rate": 0.0003878787878787879,
540
+ "loss": 2.2564,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.7,
545
+ "grad_norm": 2.5082592964172363,
546
+ "learning_rate": 0.00038636363636363635,
547
+ "loss": 2.2927,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.7090909090909091,
552
+ "grad_norm": 2.240920066833496,
553
+ "learning_rate": 0.00038484848484848485,
554
+ "loss": 2.1802,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.7181818181818181,
559
+ "grad_norm": 2.321823835372925,
560
+ "learning_rate": 0.00038333333333333334,
561
+ "loss": 2.2249,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.7272727272727273,
566
+ "grad_norm": 2.708307981491089,
567
+ "learning_rate": 0.00038181818181818184,
568
+ "loss": 2.074,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.7363636363636363,
573
+ "grad_norm": 3.075338840484619,
574
+ "learning_rate": 0.00038030303030303034,
575
+ "loss": 2.4737,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.7454545454545455,
580
+ "grad_norm": 2.4267024993896484,
581
+ "learning_rate": 0.0003787878787878788,
582
+ "loss": 2.2937,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.7545454545454545,
587
+ "grad_norm": 2.877577543258667,
588
+ "learning_rate": 0.0003772727272727273,
589
+ "loss": 2.5973,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.7636363636363637,
594
+ "grad_norm": 2.5287859439849854,
595
+ "learning_rate": 0.00037575757575757573,
596
+ "loss": 2.2226,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.7727272727272727,
601
+ "grad_norm": 2.423067331314087,
602
+ "learning_rate": 0.0003742424242424243,
603
+ "loss": 1.9636,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.7818181818181819,
608
+ "grad_norm": 2.6509439945220947,
609
+ "learning_rate": 0.00037272727272727273,
610
+ "loss": 2.8285,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.7909090909090909,
615
+ "grad_norm": 2.527987480163574,
616
+ "learning_rate": 0.00037121212121212123,
617
+ "loss": 2.267,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.8,
622
+ "grad_norm": 2.641253709793091,
623
+ "learning_rate": 0.00036969696969696967,
624
+ "loss": 3.0696,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.8090909090909091,
629
+ "grad_norm": 2.3204126358032227,
630
+ "learning_rate": 0.00036818181818181817,
631
+ "loss": 2.621,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.8181818181818182,
636
+ "grad_norm": 2.6353261470794678,
637
+ "learning_rate": 0.00036666666666666667,
638
+ "loss": 2.3641,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.8272727272727273,
643
+ "grad_norm": 2.0846307277679443,
644
+ "learning_rate": 0.00036515151515151517,
645
+ "loss": 2.4313,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.8363636363636363,
650
+ "grad_norm": 2.263862371444702,
651
+ "learning_rate": 0.00036363636363636367,
652
+ "loss": 2.1305,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.8454545454545455,
657
+ "grad_norm": 2.4628946781158447,
658
+ "learning_rate": 0.0003621212121212121,
659
+ "loss": 2.3846,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.8545454545454545,
664
+ "grad_norm": 2.1154558658599854,
665
+ "learning_rate": 0.0003606060606060606,
666
+ "loss": 2.0915,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.8636363636363636,
671
+ "grad_norm": 2.421992540359497,
672
+ "learning_rate": 0.00035909090909090906,
673
+ "loss": 1.966,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.8727272727272727,
678
+ "grad_norm": 2.6157567501068115,
679
+ "learning_rate": 0.0003575757575757576,
680
+ "loss": 2.0816,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.8818181818181818,
685
+ "grad_norm": 2.487288236618042,
686
+ "learning_rate": 0.0003560606060606061,
687
+ "loss": 2.0444,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.8909090909090909,
692
+ "grad_norm": 2.3463704586029053,
693
+ "learning_rate": 0.00035454545454545455,
694
+ "loss": 2.3975,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.9,
699
+ "grad_norm": 2.7266664505004883,
700
+ "learning_rate": 0.00035303030303030305,
701
+ "loss": 2.2822,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.9090909090909091,
706
+ "grad_norm": 2.4807024002075195,
707
+ "learning_rate": 0.0003515151515151515,
708
+ "loss": 2.1119,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.9181818181818182,
713
+ "grad_norm": 2.7550277709960938,
714
+ "learning_rate": 0.00035,
715
+ "loss": 2.2461,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.9272727272727272,
720
+ "grad_norm": 2.43615984916687,
721
+ "learning_rate": 0.0003484848484848485,
722
+ "loss": 2.559,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.9363636363636364,
727
+ "grad_norm": 3.006021499633789,
728
+ "learning_rate": 0.000346969696969697,
729
+ "loss": 2.2031,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.9454545454545454,
734
+ "grad_norm": 2.3321893215179443,
735
+ "learning_rate": 0.00034545454545454544,
736
+ "loss": 2.2653,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.9545454545454546,
741
+ "grad_norm": 2.7566874027252197,
742
+ "learning_rate": 0.00034393939393939394,
743
+ "loss": 2.1273,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.9636363636363636,
748
+ "grad_norm": 2.574964761734009,
749
+ "learning_rate": 0.00034242424242424244,
750
+ "loss": 2.1953,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.9727272727272728,
755
+ "grad_norm": 2.2862184047698975,
756
+ "learning_rate": 0.0003409090909090909,
757
+ "loss": 1.9793,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.9818181818181818,
762
+ "grad_norm": 2.3291995525360107,
763
+ "learning_rate": 0.00033939393939393943,
764
+ "loss": 2.0028,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.990909090909091,
769
+ "grad_norm": 2.4766077995300293,
770
+ "learning_rate": 0.0003378787878787879,
771
+ "loss": 2.6716,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 1.0,
776
+ "grad_norm": 2.5020952224731445,
777
+ "learning_rate": 0.0003363636363636364,
778
+ "loss": 2.3641,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 1.0,
783
+ "eval_f1": 0.8828,
784
+ "eval_gen_len": 47.7636,
785
+ "eval_loss": 2.201944589614868,
786
+ "eval_precision": 0.8806,
787
+ "eval_recall": 0.8852,
788
+ "eval_rouge1": 0.4172,
789
+ "eval_rouge2": 0.1774,
790
+ "eval_rougeL": 0.3518,
791
+ "eval_rougeLsum": 0.386,
792
+ "eval_runtime": 22.5664,
793
+ "eval_samples_per_second": 4.874,
794
+ "eval_steps_per_second": 0.62,
795
+ "step": 110
796
+ },
797
+ {
798
+ "epoch": 1.009090909090909,
799
+ "grad_norm": 2.647275686264038,
800
+ "learning_rate": 0.0003348484848484848,
801
+ "loss": 2.3777,
802
+ "step": 111
803
+ },
804
+ {
805
+ "epoch": 1.018181818181818,
806
+ "grad_norm": 2.123640298843384,
807
+ "learning_rate": 0.0003333333333333333,
808
+ "loss": 1.861,
809
+ "step": 112
810
+ },
811
+ {
812
+ "epoch": 1.0272727272727273,
813
+ "grad_norm": 2.4780056476593018,
814
+ "learning_rate": 0.0003318181818181819,
815
+ "loss": 2.2539,
816
+ "step": 113
817
+ },
818
+ {
819
+ "epoch": 1.0363636363636364,
820
+ "grad_norm": 2.6516036987304688,
821
+ "learning_rate": 0.0003303030303030303,
822
+ "loss": 2.806,
823
+ "step": 114
824
+ },
825
+ {
826
+ "epoch": 1.0454545454545454,
827
+ "grad_norm": 2.273198366165161,
828
+ "learning_rate": 0.0003287878787878788,
829
+ "loss": 1.894,
830
+ "step": 115
831
+ },
832
+ {
833
+ "epoch": 1.0545454545454545,
834
+ "grad_norm": 2.6385703086853027,
835
+ "learning_rate": 0.00032727272727272726,
836
+ "loss": 2.3756,
837
+ "step": 116
838
+ },
839
+ {
840
+ "epoch": 1.0636363636363637,
841
+ "grad_norm": 2.1708078384399414,
842
+ "learning_rate": 0.00032575757575757576,
843
+ "loss": 1.7245,
844
+ "step": 117
845
+ },
846
+ {
847
+ "epoch": 1.0727272727272728,
848
+ "grad_norm": 2.353435516357422,
849
+ "learning_rate": 0.0003242424242424242,
850
+ "loss": 2.2521,
851
+ "step": 118
852
+ },
853
+ {
854
+ "epoch": 1.0818181818181818,
855
+ "grad_norm": 2.38700532913208,
856
+ "learning_rate": 0.00032272727272727276,
857
+ "loss": 2.4595,
858
+ "step": 119
859
+ },
860
+ {
861
+ "epoch": 1.0909090909090908,
862
+ "grad_norm": 2.301133632659912,
863
+ "learning_rate": 0.00032121212121212126,
864
+ "loss": 2.5753,
865
+ "step": 120
866
+ },
867
+ {
868
+ "epoch": 1.1,
869
+ "grad_norm": 2.515345811843872,
870
+ "learning_rate": 0.0003196969696969697,
871
+ "loss": 2.1911,
872
+ "step": 121
873
+ },
874
+ {
875
+ "epoch": 1.1090909090909091,
876
+ "grad_norm": 2.5848662853240967,
877
+ "learning_rate": 0.0003181818181818182,
878
+ "loss": 2.0735,
879
+ "step": 122
880
+ },
881
+ {
882
+ "epoch": 1.1181818181818182,
883
+ "grad_norm": 3.129497528076172,
884
+ "learning_rate": 0.00031666666666666665,
885
+ "loss": 2.4778,
886
+ "step": 123
887
+ },
888
+ {
889
+ "epoch": 1.1272727272727272,
890
+ "grad_norm": 2.623422145843506,
891
+ "learning_rate": 0.00031515151515151515,
892
+ "loss": 2.3883,
893
+ "step": 124
894
+ },
895
+ {
896
+ "epoch": 1.1363636363636362,
897
+ "grad_norm": 2.2395179271698,
898
+ "learning_rate": 0.00031363636363636365,
899
+ "loss": 2.2265,
900
+ "step": 125
901
+ },
902
+ {
903
+ "epoch": 1.1454545454545455,
904
+ "grad_norm": 2.5940821170806885,
905
+ "learning_rate": 0.00031212121212121214,
906
+ "loss": 2.2186,
907
+ "step": 126
908
+ },
909
+ {
910
+ "epoch": 1.1545454545454545,
911
+ "grad_norm": 3.4867501258850098,
912
+ "learning_rate": 0.0003106060606060606,
913
+ "loss": 2.1858,
914
+ "step": 127
915
+ },
916
+ {
917
+ "epoch": 1.1636363636363636,
918
+ "grad_norm": 2.4735608100891113,
919
+ "learning_rate": 0.0003090909090909091,
920
+ "loss": 2.1304,
921
+ "step": 128
922
+ },
923
+ {
924
+ "epoch": 1.1727272727272728,
925
+ "grad_norm": 2.619661331176758,
926
+ "learning_rate": 0.0003075757575757576,
927
+ "loss": 2.5575,
928
+ "step": 129
929
+ },
930
+ {
931
+ "epoch": 1.1818181818181819,
932
+ "grad_norm": 2.6737751960754395,
933
+ "learning_rate": 0.00030606060606060603,
934
+ "loss": 2.5957,
935
+ "step": 130
936
+ },
937
+ {
938
+ "epoch": 1.190909090909091,
939
+ "grad_norm": 2.519474506378174,
940
+ "learning_rate": 0.0003045454545454546,
941
+ "loss": 2.1605,
942
+ "step": 131
943
+ },
944
+ {
945
+ "epoch": 1.2,
946
+ "grad_norm": 2.309298276901245,
947
+ "learning_rate": 0.00030303030303030303,
948
+ "loss": 2.3122,
949
+ "step": 132
950
+ },
951
+ {
952
+ "epoch": 1.209090909090909,
953
+ "grad_norm": 2.2344257831573486,
954
+ "learning_rate": 0.00030151515151515153,
955
+ "loss": 1.9541,
956
+ "step": 133
957
+ },
958
+ {
959
+ "epoch": 1.2181818181818183,
960
+ "grad_norm": 2.624655246734619,
961
+ "learning_rate": 0.0003,
962
+ "loss": 2.2801,
963
+ "step": 134
964
+ },
965
+ {
966
+ "epoch": 1.2272727272727273,
967
+ "grad_norm": 2.513366222381592,
968
+ "learning_rate": 0.00029848484848484847,
969
+ "loss": 2.5152,
970
+ "step": 135
971
+ },
972
+ {
973
+ "epoch": 1.2363636363636363,
974
+ "grad_norm": 2.4093875885009766,
975
+ "learning_rate": 0.000296969696969697,
976
+ "loss": 2.2779,
977
+ "step": 136
978
+ },
979
+ {
980
+ "epoch": 1.2454545454545454,
981
+ "grad_norm": 2.115041971206665,
982
+ "learning_rate": 0.00029545454545454547,
983
+ "loss": 1.7012,
984
+ "step": 137
985
+ },
986
+ {
987
+ "epoch": 1.2545454545454544,
988
+ "grad_norm": 2.436295509338379,
989
+ "learning_rate": 0.00029393939393939397,
990
+ "loss": 2.0279,
991
+ "step": 138
992
+ },
993
+ {
994
+ "epoch": 1.2636363636363637,
995
+ "grad_norm": 2.2901837825775146,
996
+ "learning_rate": 0.0002924242424242424,
997
+ "loss": 2.2395,
998
+ "step": 139
999
+ },
1000
+ {
1001
+ "epoch": 1.2727272727272727,
1002
+ "grad_norm": 2.7776708602905273,
1003
+ "learning_rate": 0.0002909090909090909,
1004
+ "loss": 2.5537,
1005
+ "step": 140
1006
+ },
1007
+ {
1008
+ "epoch": 1.2818181818181817,
1009
+ "grad_norm": 2.3812379837036133,
1010
+ "learning_rate": 0.00028939393939393936,
1011
+ "loss": 2.4604,
1012
+ "step": 141
1013
+ },
1014
+ {
1015
+ "epoch": 1.290909090909091,
1016
+ "grad_norm": 2.4496119022369385,
1017
+ "learning_rate": 0.0002878787878787879,
1018
+ "loss": 1.9706,
1019
+ "step": 142
1020
+ },
1021
+ {
1022
+ "epoch": 1.3,
1023
+ "grad_norm": 2.4268991947174072,
1024
+ "learning_rate": 0.00028636363636363636,
1025
+ "loss": 2.5722,
1026
+ "step": 143
1027
+ },
1028
+ {
1029
+ "epoch": 1.309090909090909,
1030
+ "grad_norm": 2.3241193294525146,
1031
+ "learning_rate": 0.00028484848484848485,
1032
+ "loss": 1.9134,
1033
+ "step": 144
1034
+ },
1035
+ {
1036
+ "epoch": 1.3181818181818181,
1037
+ "grad_norm": 2.587451219558716,
1038
+ "learning_rate": 0.00028333333333333335,
1039
+ "loss": 2.5717,
1040
+ "step": 145
1041
+ },
1042
+ {
1043
+ "epoch": 1.3272727272727272,
1044
+ "grad_norm": 2.5142734050750732,
1045
+ "learning_rate": 0.0002818181818181818,
1046
+ "loss": 2.2671,
1047
+ "step": 146
1048
+ },
1049
+ {
1050
+ "epoch": 1.3363636363636364,
1051
+ "grad_norm": 2.3716535568237305,
1052
+ "learning_rate": 0.0002803030303030303,
1053
+ "loss": 2.1641,
1054
+ "step": 147
1055
+ },
1056
+ {
1057
+ "epoch": 1.3454545454545455,
1058
+ "grad_norm": 2.928048849105835,
1059
+ "learning_rate": 0.0002787878787878788,
1060
+ "loss": 2.4632,
1061
+ "step": 148
1062
+ },
1063
+ {
1064
+ "epoch": 1.3545454545454545,
1065
+ "grad_norm": 2.8642890453338623,
1066
+ "learning_rate": 0.0002772727272727273,
1067
+ "loss": 2.0992,
1068
+ "step": 149
1069
+ },
1070
+ {
1071
+ "epoch": 1.3636363636363638,
1072
+ "grad_norm": 2.571286201477051,
1073
+ "learning_rate": 0.00027575757575757574,
1074
+ "loss": 2.0022,
1075
+ "step": 150
1076
+ },
1077
+ {
1078
+ "epoch": 1.3727272727272728,
1079
+ "grad_norm": 2.6257894039154053,
1080
+ "learning_rate": 0.00027424242424242424,
1081
+ "loss": 2.3255,
1082
+ "step": 151
1083
+ },
1084
+ {
1085
+ "epoch": 1.3818181818181818,
1086
+ "grad_norm": 2.7065744400024414,
1087
+ "learning_rate": 0.00027272727272727274,
1088
+ "loss": 2.3697,
1089
+ "step": 152
1090
+ },
1091
+ {
1092
+ "epoch": 1.3909090909090909,
1093
+ "grad_norm": 2.388538122177124,
1094
+ "learning_rate": 0.00027121212121212124,
1095
+ "loss": 2.1528,
1096
+ "step": 153
1097
+ },
1098
+ {
1099
+ "epoch": 1.4,
1100
+ "grad_norm": 3.155831813812256,
1101
+ "learning_rate": 0.00026969696969696974,
1102
+ "loss": 2.2429,
1103
+ "step": 154
1104
+ },
1105
+ {
1106
+ "epoch": 1.4090909090909092,
1107
+ "grad_norm": 2.4925553798675537,
1108
+ "learning_rate": 0.0002681818181818182,
1109
+ "loss": 2.3352,
1110
+ "step": 155
1111
+ },
1112
+ {
1113
+ "epoch": 1.4181818181818182,
1114
+ "grad_norm": 2.4231719970703125,
1115
+ "learning_rate": 0.0002666666666666667,
1116
+ "loss": 2.2673,
1117
+ "step": 156
1118
+ },
1119
+ {
1120
+ "epoch": 1.4272727272727272,
1121
+ "grad_norm": 2.527735710144043,
1122
+ "learning_rate": 0.0002651515151515151,
1123
+ "loss": 1.7499,
1124
+ "step": 157
1125
+ },
1126
+ {
1127
+ "epoch": 1.4363636363636363,
1128
+ "grad_norm": 2.4436838626861572,
1129
+ "learning_rate": 0.0002636363636363636,
1130
+ "loss": 2.2615,
1131
+ "step": 158
1132
+ },
1133
+ {
1134
+ "epoch": 1.4454545454545453,
1135
+ "grad_norm": 2.401718854904175,
1136
+ "learning_rate": 0.0002621212121212122,
1137
+ "loss": 2.2756,
1138
+ "step": 159
1139
+ },
1140
+ {
1141
+ "epoch": 1.4545454545454546,
1142
+ "grad_norm": 2.2467689514160156,
1143
+ "learning_rate": 0.0002606060606060606,
1144
+ "loss": 2.3878,
1145
+ "step": 160
1146
+ },
1147
+ {
1148
+ "epoch": 1.4636363636363636,
1149
+ "grad_norm": 2.4564456939697266,
1150
+ "learning_rate": 0.0002590909090909091,
1151
+ "loss": 2.2045,
1152
+ "step": 161
1153
+ },
1154
+ {
1155
+ "epoch": 1.4727272727272727,
1156
+ "grad_norm": 2.67653751373291,
1157
+ "learning_rate": 0.00025757575757575756,
1158
+ "loss": 1.7914,
1159
+ "step": 162
1160
+ },
1161
+ {
1162
+ "epoch": 1.481818181818182,
1163
+ "grad_norm": 2.8810715675354004,
1164
+ "learning_rate": 0.00025606060606060606,
1165
+ "loss": 2.6104,
1166
+ "step": 163
1167
+ },
1168
+ {
1169
+ "epoch": 1.490909090909091,
1170
+ "grad_norm": 2.9596915245056152,
1171
+ "learning_rate": 0.0002545454545454545,
1172
+ "loss": 1.9902,
1173
+ "step": 164
1174
+ },
1175
+ {
1176
+ "epoch": 1.5,
1177
+ "grad_norm": 2.1952764987945557,
1178
+ "learning_rate": 0.00025303030303030306,
1179
+ "loss": 1.717,
1180
+ "step": 165
1181
+ },
1182
+ {
1183
+ "epoch": 1.509090909090909,
1184
+ "grad_norm": 2.576174259185791,
1185
+ "learning_rate": 0.0002515151515151515,
1186
+ "loss": 2.3907,
1187
+ "step": 166
1188
+ },
1189
+ {
1190
+ "epoch": 1.518181818181818,
1191
+ "grad_norm": 2.540867567062378,
1192
+ "learning_rate": 0.00025,
1193
+ "loss": 2.2214,
1194
+ "step": 167
1195
+ },
1196
+ {
1197
+ "epoch": 1.5272727272727273,
1198
+ "grad_norm": 2.2856028079986572,
1199
+ "learning_rate": 0.0002484848484848485,
1200
+ "loss": 1.8133,
1201
+ "step": 168
1202
+ },
1203
+ {
1204
+ "epoch": 1.5363636363636364,
1205
+ "grad_norm": 2.8178927898406982,
1206
+ "learning_rate": 0.000246969696969697,
1207
+ "loss": 2.199,
1208
+ "step": 169
1209
+ },
1210
+ {
1211
+ "epoch": 1.5454545454545454,
1212
+ "grad_norm": 2.3742241859436035,
1213
+ "learning_rate": 0.00024545454545454545,
1214
+ "loss": 1.9071,
1215
+ "step": 170
1216
+ },
1217
+ {
1218
+ "epoch": 1.5545454545454547,
1219
+ "grad_norm": 2.286177396774292,
1220
+ "learning_rate": 0.00024393939393939392,
1221
+ "loss": 2.3051,
1222
+ "step": 171
1223
+ },
1224
+ {
1225
+ "epoch": 1.5636363636363635,
1226
+ "grad_norm": 2.524489164352417,
1227
+ "learning_rate": 0.00024242424242424245,
1228
+ "loss": 2.0333,
1229
+ "step": 172
1230
+ },
1231
+ {
1232
+ "epoch": 1.5727272727272728,
1233
+ "grad_norm": 3.2371888160705566,
1234
+ "learning_rate": 0.00024090909090909092,
1235
+ "loss": 2.056,
1236
+ "step": 173
1237
+ },
1238
+ {
1239
+ "epoch": 1.5818181818181818,
1240
+ "grad_norm": 2.74900221824646,
1241
+ "learning_rate": 0.0002393939393939394,
1242
+ "loss": 2.3619,
1243
+ "step": 174
1244
+ },
1245
+ {
1246
+ "epoch": 1.5909090909090908,
1247
+ "grad_norm": 2.49453067779541,
1248
+ "learning_rate": 0.0002378787878787879,
1249
+ "loss": 2.191,
1250
+ "step": 175
1251
+ },
1252
+ {
1253
+ "epoch": 1.6,
1254
+ "grad_norm": 2.836361885070801,
1255
+ "learning_rate": 0.00023636363636363636,
1256
+ "loss": 2.4605,
1257
+ "step": 176
1258
+ },
1259
+ {
1260
+ "epoch": 1.6090909090909091,
1261
+ "grad_norm": 3.4644951820373535,
1262
+ "learning_rate": 0.00023484848484848486,
1263
+ "loss": 2.116,
1264
+ "step": 177
1265
+ },
1266
+ {
1267
+ "epoch": 1.6181818181818182,
1268
+ "grad_norm": 3.0246944427490234,
1269
+ "learning_rate": 0.00023333333333333333,
1270
+ "loss": 2.1507,
1271
+ "step": 178
1272
+ },
1273
+ {
1274
+ "epoch": 1.6272727272727274,
1275
+ "grad_norm": 2.28613018989563,
1276
+ "learning_rate": 0.00023181818181818183,
1277
+ "loss": 2.0915,
1278
+ "step": 179
1279
+ },
1280
+ {
1281
+ "epoch": 1.6363636363636362,
1282
+ "grad_norm": 2.576760768890381,
1283
+ "learning_rate": 0.00023030303030303033,
1284
+ "loss": 2.2536,
1285
+ "step": 180
1286
+ },
1287
+ {
1288
+ "epoch": 1.6454545454545455,
1289
+ "grad_norm": 2.953038454055786,
1290
+ "learning_rate": 0.0002287878787878788,
1291
+ "loss": 2.0687,
1292
+ "step": 181
1293
+ },
1294
+ {
1295
+ "epoch": 1.6545454545454545,
1296
+ "grad_norm": 2.397510528564453,
1297
+ "learning_rate": 0.00022727272727272727,
1298
+ "loss": 1.7358,
1299
+ "step": 182
1300
+ },
1301
+ {
1302
+ "epoch": 1.6636363636363636,
1303
+ "grad_norm": 3.0446624755859375,
1304
+ "learning_rate": 0.00022575757575757577,
1305
+ "loss": 2.0852,
1306
+ "step": 183
1307
+ },
1308
+ {
1309
+ "epoch": 1.6727272727272728,
1310
+ "grad_norm": 2.5387020111083984,
1311
+ "learning_rate": 0.00022424242424242424,
1312
+ "loss": 2.6556,
1313
+ "step": 184
1314
+ },
1315
+ {
1316
+ "epoch": 1.6818181818181817,
1317
+ "grad_norm": 2.7849063873291016,
1318
+ "learning_rate": 0.00022272727272727272,
1319
+ "loss": 2.2982,
1320
+ "step": 185
1321
+ },
1322
+ {
1323
+ "epoch": 1.690909090909091,
1324
+ "grad_norm": 2.275547504425049,
1325
+ "learning_rate": 0.00022121212121212121,
1326
+ "loss": 2.247,
1327
+ "step": 186
1328
+ },
1329
+ {
1330
+ "epoch": 1.7,
1331
+ "grad_norm": 2.217078685760498,
1332
+ "learning_rate": 0.0002196969696969697,
1333
+ "loss": 2.01,
1334
+ "step": 187
1335
+ },
1336
+ {
1337
+ "epoch": 1.709090909090909,
1338
+ "grad_norm": 2.437875747680664,
1339
+ "learning_rate": 0.00021818181818181818,
1340
+ "loss": 2.3097,
1341
+ "step": 188
1342
+ },
1343
+ {
1344
+ "epoch": 1.7181818181818183,
1345
+ "grad_norm": 1.9528652429580688,
1346
+ "learning_rate": 0.00021666666666666668,
1347
+ "loss": 1.7132,
1348
+ "step": 189
1349
+ },
1350
+ {
1351
+ "epoch": 1.7272727272727273,
1352
+ "grad_norm": 2.658073663711548,
1353
+ "learning_rate": 0.00021515151515151516,
1354
+ "loss": 2.2414,
1355
+ "step": 190
1356
+ },
1357
+ {
1358
+ "epoch": 1.7363636363636363,
1359
+ "grad_norm": 2.47921085357666,
1360
+ "learning_rate": 0.00021363636363636363,
1361
+ "loss": 2.1501,
1362
+ "step": 191
1363
+ },
1364
+ {
1365
+ "epoch": 1.7454545454545456,
1366
+ "grad_norm": 2.813053607940674,
1367
+ "learning_rate": 0.00021212121212121213,
1368
+ "loss": 2.2338,
1369
+ "step": 192
1370
+ },
1371
+ {
1372
+ "epoch": 1.7545454545454544,
1373
+ "grad_norm": 2.383352041244507,
1374
+ "learning_rate": 0.0002106060606060606,
1375
+ "loss": 2.0248,
1376
+ "step": 193
1377
+ },
1378
+ {
1379
+ "epoch": 1.7636363636363637,
1380
+ "grad_norm": 2.23240327835083,
1381
+ "learning_rate": 0.00020909090909090907,
1382
+ "loss": 2.4407,
1383
+ "step": 194
1384
+ },
1385
+ {
1386
+ "epoch": 1.7727272727272727,
1387
+ "grad_norm": 2.3927600383758545,
1388
+ "learning_rate": 0.0002075757575757576,
1389
+ "loss": 2.1969,
1390
+ "step": 195
1391
+ },
1392
+ {
1393
+ "epoch": 1.7818181818181817,
1394
+ "grad_norm": 2.6979734897613525,
1395
+ "learning_rate": 0.00020606060606060607,
1396
+ "loss": 2.3632,
1397
+ "step": 196
1398
+ },
1399
+ {
1400
+ "epoch": 1.790909090909091,
1401
+ "grad_norm": 3.1346116065979004,
1402
+ "learning_rate": 0.00020454545454545457,
1403
+ "loss": 1.7359,
1404
+ "step": 197
1405
+ },
1406
+ {
1407
+ "epoch": 1.8,
1408
+ "grad_norm": 2.7446019649505615,
1409
+ "learning_rate": 0.00020303030303030304,
1410
+ "loss": 2.2057,
1411
+ "step": 198
1412
+ },
1413
+ {
1414
+ "epoch": 1.809090909090909,
1415
+ "grad_norm": 2.7223236560821533,
1416
+ "learning_rate": 0.0002015151515151515,
1417
+ "loss": 2.4566,
1418
+ "step": 199
1419
+ },
1420
+ {
1421
+ "epoch": 1.8181818181818183,
1422
+ "grad_norm": 2.570932388305664,
1423
+ "learning_rate": 0.0002,
1424
+ "loss": 2.2638,
1425
+ "step": 200
1426
+ },
1427
+ {
1428
+ "epoch": 1.8272727272727272,
1429
+ "grad_norm": 2.2431604862213135,
1430
+ "learning_rate": 0.00019848484848484848,
1431
+ "loss": 2.1802,
1432
+ "step": 201
1433
+ },
1434
+ {
1435
+ "epoch": 1.8363636363636364,
1436
+ "grad_norm": 3.257647752761841,
1437
+ "learning_rate": 0.00019696969696969695,
1438
+ "loss": 2.2361,
1439
+ "step": 202
1440
+ },
1441
+ {
1442
+ "epoch": 1.8454545454545455,
1443
+ "grad_norm": 2.444171905517578,
1444
+ "learning_rate": 0.00019545454545454548,
1445
+ "loss": 1.8914,
1446
+ "step": 203
1447
+ },
1448
+ {
1449
+ "epoch": 1.8545454545454545,
1450
+ "grad_norm": 2.2748937606811523,
1451
+ "learning_rate": 0.00019393939393939395,
1452
+ "loss": 2.0162,
1453
+ "step": 204
1454
+ },
1455
+ {
1456
+ "epoch": 1.8636363636363638,
1457
+ "grad_norm": 2.450481653213501,
1458
+ "learning_rate": 0.00019242424242424242,
1459
+ "loss": 1.8713,
1460
+ "step": 205
1461
+ },
1462
+ {
1463
+ "epoch": 1.8727272727272726,
1464
+ "grad_norm": 2.7834432125091553,
1465
+ "learning_rate": 0.00019090909090909092,
1466
+ "loss": 2.1062,
1467
+ "step": 206
1468
+ },
1469
+ {
1470
+ "epoch": 1.8818181818181818,
1471
+ "grad_norm": 2.4121110439300537,
1472
+ "learning_rate": 0.0001893939393939394,
1473
+ "loss": 2.0578,
1474
+ "step": 207
1475
+ },
1476
+ {
1477
+ "epoch": 1.8909090909090909,
1478
+ "grad_norm": 2.533564567565918,
1479
+ "learning_rate": 0.00018787878787878787,
1480
+ "loss": 2.0605,
1481
+ "step": 208
1482
+ },
1483
+ {
1484
+ "epoch": 1.9,
1485
+ "grad_norm": 2.543336868286133,
1486
+ "learning_rate": 0.00018636363636363636,
1487
+ "loss": 2.083,
1488
+ "step": 209
1489
+ },
1490
+ {
1491
+ "epoch": 1.9090909090909092,
1492
+ "grad_norm": 3.0417320728302,
1493
+ "learning_rate": 0.00018484848484848484,
1494
+ "loss": 2.1015,
1495
+ "step": 210
1496
+ },
1497
+ {
1498
+ "epoch": 1.9181818181818182,
1499
+ "grad_norm": 3.0233654975891113,
1500
+ "learning_rate": 0.00018333333333333334,
1501
+ "loss": 2.1515,
1502
+ "step": 211
1503
+ },
1504
+ {
1505
+ "epoch": 1.9272727272727272,
1506
+ "grad_norm": 3.2592718601226807,
1507
+ "learning_rate": 0.00018181818181818183,
1508
+ "loss": 2.3158,
1509
+ "step": 212
1510
+ },
1511
+ {
1512
+ "epoch": 1.9363636363636365,
1513
+ "grad_norm": 2.5174355506896973,
1514
+ "learning_rate": 0.0001803030303030303,
1515
+ "loss": 2.0665,
1516
+ "step": 213
1517
+ },
1518
+ {
1519
+ "epoch": 1.9454545454545453,
1520
+ "grad_norm": 2.331172466278076,
1521
+ "learning_rate": 0.0001787878787878788,
1522
+ "loss": 2.2434,
1523
+ "step": 214
1524
+ },
1525
+ {
1526
+ "epoch": 1.9545454545454546,
1527
+ "grad_norm": 2.3686776161193848,
1528
+ "learning_rate": 0.00017727272727272728,
1529
+ "loss": 2.3329,
1530
+ "step": 215
1531
+ },
1532
+ {
1533
+ "epoch": 1.9636363636363636,
1534
+ "grad_norm": 2.747772693634033,
1535
+ "learning_rate": 0.00017575757575757575,
1536
+ "loss": 2.4027,
1537
+ "step": 216
1538
+ },
1539
+ {
1540
+ "epoch": 1.9727272727272727,
1541
+ "grad_norm": 3.5569443702697754,
1542
+ "learning_rate": 0.00017424242424242425,
1543
+ "loss": 2.0921,
1544
+ "step": 217
1545
+ },
1546
+ {
1547
+ "epoch": 1.981818181818182,
1548
+ "grad_norm": 2.4337990283966064,
1549
+ "learning_rate": 0.00017272727272727272,
1550
+ "loss": 1.8793,
1551
+ "step": 218
1552
+ },
1553
+ {
1554
+ "epoch": 1.990909090909091,
1555
+ "grad_norm": 3.418469190597534,
1556
+ "learning_rate": 0.00017121212121212122,
1557
+ "loss": 2.6085,
1558
+ "step": 219
1559
+ },
1560
+ {
1561
+ "epoch": 2.0,
1562
+ "grad_norm": 2.9401915073394775,
1563
+ "learning_rate": 0.00016969696969696972,
1564
+ "loss": 2.2228,
1565
+ "step": 220
1566
+ },
1567
+ {
1568
+ "epoch": 2.0,
1569
+ "eval_f1": 0.8846,
1570
+ "eval_gen_len": 48.1182,
1571
+ "eval_loss": 2.1040308475494385,
1572
+ "eval_precision": 0.882,
1573
+ "eval_recall": 0.8875,
1574
+ "eval_rouge1": 0.419,
1575
+ "eval_rouge2": 0.1789,
1576
+ "eval_rougeL": 0.3477,
1577
+ "eval_rougeLsum": 0.3827,
1578
+ "eval_runtime": 22.661,
1579
+ "eval_samples_per_second": 4.854,
1580
+ "eval_steps_per_second": 0.618,
1581
+ "step": 220
1582
+ },
1583
+ {
1584
+ "epoch": 2.0090909090909093,
1585
+ "grad_norm": 2.243396520614624,
1586
+ "learning_rate": 0.0001681818181818182,
1587
+ "loss": 1.6725,
1588
+ "step": 221
1589
+ },
1590
+ {
1591
+ "epoch": 2.018181818181818,
1592
+ "grad_norm": 2.3622076511383057,
1593
+ "learning_rate": 0.00016666666666666666,
1594
+ "loss": 2.0792,
1595
+ "step": 222
1596
+ },
1597
+ {
1598
+ "epoch": 2.0272727272727273,
1599
+ "grad_norm": 2.4615345001220703,
1600
+ "learning_rate": 0.00016515151515151516,
1601
+ "loss": 2.1534,
1602
+ "step": 223
1603
+ },
1604
+ {
1605
+ "epoch": 2.036363636363636,
1606
+ "grad_norm": 3.332016706466675,
1607
+ "learning_rate": 0.00016363636363636363,
1608
+ "loss": 2.151,
1609
+ "step": 224
1610
+ },
1611
+ {
1612
+ "epoch": 2.0454545454545454,
1613
+ "grad_norm": 2.830742597579956,
1614
+ "learning_rate": 0.0001621212121212121,
1615
+ "loss": 2.4115,
1616
+ "step": 225
1617
+ },
1618
+ {
1619
+ "epoch": 2.0545454545454547,
1620
+ "grad_norm": 2.9332048892974854,
1621
+ "learning_rate": 0.00016060606060606063,
1622
+ "loss": 2.8091,
1623
+ "step": 226
1624
+ },
1625
+ {
1626
+ "epoch": 2.0636363636363635,
1627
+ "grad_norm": 3.2479031085968018,
1628
+ "learning_rate": 0.0001590909090909091,
1629
+ "loss": 2.1244,
1630
+ "step": 227
1631
+ },
1632
+ {
1633
+ "epoch": 2.0727272727272728,
1634
+ "grad_norm": 2.493685007095337,
1635
+ "learning_rate": 0.00015757575757575757,
1636
+ "loss": 2.1421,
1637
+ "step": 228
1638
+ },
1639
+ {
1640
+ "epoch": 2.081818181818182,
1641
+ "grad_norm": 2.0491628646850586,
1642
+ "learning_rate": 0.00015606060606060607,
1643
+ "loss": 1.7688,
1644
+ "step": 229
1645
+ },
1646
+ {
1647
+ "epoch": 2.090909090909091,
1648
+ "grad_norm": 2.582287549972534,
1649
+ "learning_rate": 0.00015454545454545454,
1650
+ "loss": 2.0157,
1651
+ "step": 230
1652
+ },
1653
+ {
1654
+ "epoch": 2.1,
1655
+ "grad_norm": 2.326449155807495,
1656
+ "learning_rate": 0.00015303030303030302,
1657
+ "loss": 1.833,
1658
+ "step": 231
1659
+ },
1660
+ {
1661
+ "epoch": 2.109090909090909,
1662
+ "grad_norm": 2.128833770751953,
1663
+ "learning_rate": 0.00015151515151515152,
1664
+ "loss": 1.7071,
1665
+ "step": 232
1666
+ },
1667
+ {
1668
+ "epoch": 2.118181818181818,
1669
+ "grad_norm": 2.6494805812835693,
1670
+ "learning_rate": 0.00015,
1671
+ "loss": 1.8511,
1672
+ "step": 233
1673
+ },
1674
+ {
1675
+ "epoch": 2.1272727272727274,
1676
+ "grad_norm": 2.407592296600342,
1677
+ "learning_rate": 0.0001484848484848485,
1678
+ "loss": 1.8951,
1679
+ "step": 234
1680
+ },
1681
+ {
1682
+ "epoch": 2.1363636363636362,
1683
+ "grad_norm": 2.171020030975342,
1684
+ "learning_rate": 0.00014696969696969698,
1685
+ "loss": 1.8288,
1686
+ "step": 235
1687
+ },
1688
+ {
1689
+ "epoch": 2.1454545454545455,
1690
+ "grad_norm": 2.6327128410339355,
1691
+ "learning_rate": 0.00014545454545454546,
1692
+ "loss": 2.3277,
1693
+ "step": 236
1694
+ },
1695
+ {
1696
+ "epoch": 2.1545454545454543,
1697
+ "grad_norm": 2.796823740005493,
1698
+ "learning_rate": 0.00014393939393939396,
1699
+ "loss": 1.9495,
1700
+ "step": 237
1701
+ },
1702
+ {
1703
+ "epoch": 2.1636363636363636,
1704
+ "grad_norm": 2.510796308517456,
1705
+ "learning_rate": 0.00014242424242424243,
1706
+ "loss": 2.0122,
1707
+ "step": 238
1708
+ },
1709
+ {
1710
+ "epoch": 2.172727272727273,
1711
+ "grad_norm": 2.5371253490448,
1712
+ "learning_rate": 0.0001409090909090909,
1713
+ "loss": 2.1992,
1714
+ "step": 239
1715
+ },
1716
+ {
1717
+ "epoch": 2.1818181818181817,
1718
+ "grad_norm": 2.458181858062744,
1719
+ "learning_rate": 0.0001393939393939394,
1720
+ "loss": 2.5883,
1721
+ "step": 240
1722
+ },
1723
+ {
1724
+ "epoch": 2.190909090909091,
1725
+ "grad_norm": 2.3969123363494873,
1726
+ "learning_rate": 0.00013787878787878787,
1727
+ "loss": 1.7977,
1728
+ "step": 241
1729
+ },
1730
+ {
1731
+ "epoch": 2.2,
1732
+ "grad_norm": 2.271862506866455,
1733
+ "learning_rate": 0.00013636363636363637,
1734
+ "loss": 1.4961,
1735
+ "step": 242
1736
+ },
1737
+ {
1738
+ "epoch": 2.209090909090909,
1739
+ "grad_norm": 2.7577078342437744,
1740
+ "learning_rate": 0.00013484848484848487,
1741
+ "loss": 2.6418,
1742
+ "step": 243
1743
+ },
1744
+ {
1745
+ "epoch": 2.2181818181818183,
1746
+ "grad_norm": 3.0357556343078613,
1747
+ "learning_rate": 0.00013333333333333334,
1748
+ "loss": 2.2361,
1749
+ "step": 244
1750
+ },
1751
+ {
1752
+ "epoch": 2.227272727272727,
1753
+ "grad_norm": 3.5949878692626953,
1754
+ "learning_rate": 0.0001318181818181818,
1755
+ "loss": 2.1915,
1756
+ "step": 245
1757
+ },
1758
+ {
1759
+ "epoch": 2.2363636363636363,
1760
+ "grad_norm": 2.8536949157714844,
1761
+ "learning_rate": 0.0001303030303030303,
1762
+ "loss": 2.2827,
1763
+ "step": 246
1764
+ },
1765
+ {
1766
+ "epoch": 2.2454545454545456,
1767
+ "grad_norm": 2.9661660194396973,
1768
+ "learning_rate": 0.00012878787878787878,
1769
+ "loss": 2.2646,
1770
+ "step": 247
1771
+ },
1772
+ {
1773
+ "epoch": 2.2545454545454544,
1774
+ "grad_norm": 2.6501827239990234,
1775
+ "learning_rate": 0.00012727272727272725,
1776
+ "loss": 2.2011,
1777
+ "step": 248
1778
+ },
1779
+ {
1780
+ "epoch": 2.2636363636363637,
1781
+ "grad_norm": 2.4860503673553467,
1782
+ "learning_rate": 0.00012575757575757575,
1783
+ "loss": 2.4671,
1784
+ "step": 249
1785
+ },
1786
+ {
1787
+ "epoch": 2.2727272727272725,
1788
+ "grad_norm": 2.6340763568878174,
1789
+ "learning_rate": 0.00012424242424242425,
1790
+ "loss": 2.5151,
1791
+ "step": 250
1792
+ },
1793
+ {
1794
+ "epoch": 2.2818181818181817,
1795
+ "grad_norm": 1.978316307067871,
1796
+ "learning_rate": 0.00012272727272727272,
1797
+ "loss": 1.6343,
1798
+ "step": 251
1799
+ },
1800
+ {
1801
+ "epoch": 2.290909090909091,
1802
+ "grad_norm": 2.898264169692993,
1803
+ "learning_rate": 0.00012121212121212122,
1804
+ "loss": 1.6661,
1805
+ "step": 252
1806
+ },
1807
+ {
1808
+ "epoch": 2.3,
1809
+ "grad_norm": 2.3824710845947266,
1810
+ "learning_rate": 0.0001196969696969697,
1811
+ "loss": 2.0863,
1812
+ "step": 253
1813
+ },
1814
+ {
1815
+ "epoch": 2.309090909090909,
1816
+ "grad_norm": 2.5257728099823,
1817
+ "learning_rate": 0.00011818181818181818,
1818
+ "loss": 2.2026,
1819
+ "step": 254
1820
+ },
1821
+ {
1822
+ "epoch": 2.3181818181818183,
1823
+ "grad_norm": 2.5643668174743652,
1824
+ "learning_rate": 0.00011666666666666667,
1825
+ "loss": 1.994,
1826
+ "step": 255
1827
+ },
1828
+ {
1829
+ "epoch": 2.327272727272727,
1830
+ "grad_norm": 3.254385471343994,
1831
+ "learning_rate": 0.00011515151515151516,
1832
+ "loss": 2.1402,
1833
+ "step": 256
1834
+ },
1835
+ {
1836
+ "epoch": 2.3363636363636364,
1837
+ "grad_norm": 2.2531135082244873,
1838
+ "learning_rate": 0.00011363636363636364,
1839
+ "loss": 2.4741,
1840
+ "step": 257
1841
+ },
1842
+ {
1843
+ "epoch": 2.3454545454545457,
1844
+ "grad_norm": 4.917692184448242,
1845
+ "learning_rate": 0.00011212121212121212,
1846
+ "loss": 2.0093,
1847
+ "step": 258
1848
+ },
1849
+ {
1850
+ "epoch": 2.3545454545454545,
1851
+ "grad_norm": 2.2988479137420654,
1852
+ "learning_rate": 0.00011060606060606061,
1853
+ "loss": 2.2858,
1854
+ "step": 259
1855
+ },
1856
+ {
1857
+ "epoch": 2.3636363636363638,
1858
+ "grad_norm": 2.2871227264404297,
1859
+ "learning_rate": 0.00010909090909090909,
1860
+ "loss": 2.325,
1861
+ "step": 260
1862
+ },
1863
+ {
1864
+ "epoch": 2.3727272727272726,
1865
+ "grad_norm": 2.498077392578125,
1866
+ "learning_rate": 0.00010757575757575758,
1867
+ "loss": 1.8679,
1868
+ "step": 261
1869
+ },
1870
+ {
1871
+ "epoch": 2.381818181818182,
1872
+ "grad_norm": 2.622990608215332,
1873
+ "learning_rate": 0.00010606060606060606,
1874
+ "loss": 1.9478,
1875
+ "step": 262
1876
+ },
1877
+ {
1878
+ "epoch": 2.390909090909091,
1879
+ "grad_norm": 4.280647277832031,
1880
+ "learning_rate": 0.00010454545454545454,
1881
+ "loss": 1.4923,
1882
+ "step": 263
1883
+ },
1884
+ {
1885
+ "epoch": 2.4,
1886
+ "grad_norm": 2.2783660888671875,
1887
+ "learning_rate": 0.00010303030303030303,
1888
+ "loss": 2.3224,
1889
+ "step": 264
1890
+ },
1891
+ {
1892
+ "epoch": 2.409090909090909,
1893
+ "grad_norm": 2.2206008434295654,
1894
+ "learning_rate": 0.00010151515151515152,
1895
+ "loss": 1.9765,
1896
+ "step": 265
1897
+ },
1898
+ {
1899
+ "epoch": 2.418181818181818,
1900
+ "grad_norm": 2.0535147190093994,
1901
+ "learning_rate": 0.0001,
1902
+ "loss": 1.99,
1903
+ "step": 266
1904
+ },
1905
+ {
1906
+ "epoch": 2.4272727272727272,
1907
+ "grad_norm": 2.354729652404785,
1908
+ "learning_rate": 9.848484848484848e-05,
1909
+ "loss": 2.2821,
1910
+ "step": 267
1911
+ },
1912
+ {
1913
+ "epoch": 2.4363636363636365,
1914
+ "grad_norm": 2.695911169052124,
1915
+ "learning_rate": 9.696969696969698e-05,
1916
+ "loss": 1.9721,
1917
+ "step": 268
1918
+ },
1919
+ {
1920
+ "epoch": 2.4454545454545453,
1921
+ "grad_norm": 2.2769014835357666,
1922
+ "learning_rate": 9.545454545454546e-05,
1923
+ "loss": 2.0998,
1924
+ "step": 269
1925
+ },
1926
+ {
1927
+ "epoch": 2.4545454545454546,
1928
+ "grad_norm": 2.3782975673675537,
1929
+ "learning_rate": 9.393939393939393e-05,
1930
+ "loss": 2.1317,
1931
+ "step": 270
1932
+ },
1933
+ {
1934
+ "epoch": 2.463636363636364,
1935
+ "grad_norm": 2.41587495803833,
1936
+ "learning_rate": 9.242424242424242e-05,
1937
+ "loss": 2.0085,
1938
+ "step": 271
1939
+ },
1940
+ {
1941
+ "epoch": 2.4727272727272727,
1942
+ "grad_norm": 2.0826306343078613,
1943
+ "learning_rate": 9.090909090909092e-05,
1944
+ "loss": 1.7122,
1945
+ "step": 272
1946
+ },
1947
+ {
1948
+ "epoch": 2.481818181818182,
1949
+ "grad_norm": 3.2027394771575928,
1950
+ "learning_rate": 8.93939393939394e-05,
1951
+ "loss": 1.9247,
1952
+ "step": 273
1953
+ },
1954
+ {
1955
+ "epoch": 2.4909090909090907,
1956
+ "grad_norm": 2.588639974594116,
1957
+ "learning_rate": 8.787878787878787e-05,
1958
+ "loss": 2.3237,
1959
+ "step": 274
1960
+ },
1961
+ {
1962
+ "epoch": 2.5,
1963
+ "grad_norm": 2.358501672744751,
1964
+ "learning_rate": 8.636363636363636e-05,
1965
+ "loss": 2.1826,
1966
+ "step": 275
1967
+ },
1968
+ {
1969
+ "epoch": 2.509090909090909,
1970
+ "grad_norm": 2.538494348526001,
1971
+ "learning_rate": 8.484848484848486e-05,
1972
+ "loss": 1.9181,
1973
+ "step": 276
1974
+ },
1975
+ {
1976
+ "epoch": 2.518181818181818,
1977
+ "grad_norm": 2.2839136123657227,
1978
+ "learning_rate": 8.333333333333333e-05,
1979
+ "loss": 1.9576,
1980
+ "step": 277
1981
+ },
1982
+ {
1983
+ "epoch": 2.5272727272727273,
1984
+ "grad_norm": 2.2792277336120605,
1985
+ "learning_rate": 8.181818181818182e-05,
1986
+ "loss": 2.0411,
1987
+ "step": 278
1988
+ },
1989
+ {
1990
+ "epoch": 2.536363636363636,
1991
+ "grad_norm": 3.6436235904693604,
1992
+ "learning_rate": 8.030303030303031e-05,
1993
+ "loss": 2.3181,
1994
+ "step": 279
1995
+ },
1996
+ {
1997
+ "epoch": 2.5454545454545454,
1998
+ "grad_norm": 2.2795042991638184,
1999
+ "learning_rate": 7.878787878787879e-05,
2000
+ "loss": 1.9551,
2001
+ "step": 280
2002
+ },
2003
+ {
2004
+ "epoch": 2.5545454545454547,
2005
+ "grad_norm": 2.5352325439453125,
2006
+ "learning_rate": 7.727272727272727e-05,
2007
+ "loss": 1.9835,
2008
+ "step": 281
2009
+ },
2010
+ {
2011
+ "epoch": 2.5636363636363635,
2012
+ "grad_norm": 2.5468242168426514,
2013
+ "learning_rate": 7.575757575757576e-05,
2014
+ "loss": 1.9274,
2015
+ "step": 282
2016
+ },
2017
+ {
2018
+ "epoch": 2.5727272727272728,
2019
+ "grad_norm": 2.5645673274993896,
2020
+ "learning_rate": 7.424242424242426e-05,
2021
+ "loss": 2.0234,
2022
+ "step": 283
2023
+ },
2024
+ {
2025
+ "epoch": 2.581818181818182,
2026
+ "grad_norm": 2.5357186794281006,
2027
+ "learning_rate": 7.272727272727273e-05,
2028
+ "loss": 2.0772,
2029
+ "step": 284
2030
+ },
2031
+ {
2032
+ "epoch": 2.590909090909091,
2033
+ "grad_norm": 2.257965564727783,
2034
+ "learning_rate": 7.121212121212121e-05,
2035
+ "loss": 2.123,
2036
+ "step": 285
2037
+ },
2038
+ {
2039
+ "epoch": 2.6,
2040
+ "grad_norm": 2.6818959712982178,
2041
+ "learning_rate": 6.96969696969697e-05,
2042
+ "loss": 1.8595,
2043
+ "step": 286
2044
+ },
2045
+ {
2046
+ "epoch": 2.6090909090909093,
2047
+ "grad_norm": 2.531693458557129,
2048
+ "learning_rate": 6.818181818181818e-05,
2049
+ "loss": 1.9458,
2050
+ "step": 287
2051
+ },
2052
+ {
2053
+ "epoch": 2.618181818181818,
2054
+ "grad_norm": 2.8416342735290527,
2055
+ "learning_rate": 6.666666666666667e-05,
2056
+ "loss": 2.209,
2057
+ "step": 288
2058
+ },
2059
+ {
2060
+ "epoch": 2.6272727272727274,
2061
+ "grad_norm": 2.5356521606445312,
2062
+ "learning_rate": 6.515151515151516e-05,
2063
+ "loss": 1.8766,
2064
+ "step": 289
2065
+ },
2066
+ {
2067
+ "epoch": 2.6363636363636362,
2068
+ "grad_norm": 2.3233187198638916,
2069
+ "learning_rate": 6.363636363636363e-05,
2070
+ "loss": 2.1223,
2071
+ "step": 290
2072
+ },
2073
+ {
2074
+ "epoch": 2.6454545454545455,
2075
+ "grad_norm": 2.911799907684326,
2076
+ "learning_rate": 6.212121212121213e-05,
2077
+ "loss": 2.217,
2078
+ "step": 291
2079
+ },
2080
+ {
2081
+ "epoch": 2.6545454545454543,
2082
+ "grad_norm": 2.856112241744995,
2083
+ "learning_rate": 6.060606060606061e-05,
2084
+ "loss": 2.7215,
2085
+ "step": 292
2086
+ },
2087
+ {
2088
+ "epoch": 2.6636363636363636,
2089
+ "grad_norm": 2.6321911811828613,
2090
+ "learning_rate": 5.909090909090909e-05,
2091
+ "loss": 2.0893,
2092
+ "step": 293
2093
+ },
2094
+ {
2095
+ "epoch": 2.672727272727273,
2096
+ "grad_norm": 2.3121089935302734,
2097
+ "learning_rate": 5.757575757575758e-05,
2098
+ "loss": 2.0218,
2099
+ "step": 294
2100
+ },
2101
+ {
2102
+ "epoch": 2.6818181818181817,
2103
+ "grad_norm": 2.717296600341797,
2104
+ "learning_rate": 5.606060606060606e-05,
2105
+ "loss": 2.532,
2106
+ "step": 295
2107
+ },
2108
+ {
2109
+ "epoch": 2.690909090909091,
2110
+ "grad_norm": 2.3445937633514404,
2111
+ "learning_rate": 5.4545454545454546e-05,
2112
+ "loss": 2.1638,
2113
+ "step": 296
2114
+ },
2115
+ {
2116
+ "epoch": 2.7,
2117
+ "grad_norm": 2.4560205936431885,
2118
+ "learning_rate": 5.303030303030303e-05,
2119
+ "loss": 2.1792,
2120
+ "step": 297
2121
+ },
2122
+ {
2123
+ "epoch": 2.709090909090909,
2124
+ "grad_norm": 2.5110905170440674,
2125
+ "learning_rate": 5.151515151515152e-05,
2126
+ "loss": 1.7745,
2127
+ "step": 298
2128
+ },
2129
+ {
2130
+ "epoch": 2.7181818181818183,
2131
+ "grad_norm": 2.1710031032562256,
2132
+ "learning_rate": 5e-05,
2133
+ "loss": 1.7763,
2134
+ "step": 299
2135
+ },
2136
+ {
2137
+ "epoch": 2.7272727272727275,
2138
+ "grad_norm": 2.8132150173187256,
2139
+ "learning_rate": 4.848484848484849e-05,
2140
+ "loss": 2.7144,
2141
+ "step": 300
2142
+ },
2143
+ {
2144
+ "epoch": 2.7363636363636363,
2145
+ "grad_norm": 2.755683422088623,
2146
+ "learning_rate": 4.6969696969696966e-05,
2147
+ "loss": 1.8518,
2148
+ "step": 301
2149
+ },
2150
+ {
2151
+ "epoch": 2.7454545454545456,
2152
+ "grad_norm": 3.0009915828704834,
2153
+ "learning_rate": 4.545454545454546e-05,
2154
+ "loss": 1.9233,
2155
+ "step": 302
2156
+ },
2157
+ {
2158
+ "epoch": 2.7545454545454544,
2159
+ "grad_norm": 2.8329362869262695,
2160
+ "learning_rate": 4.393939393939394e-05,
2161
+ "loss": 1.9821,
2162
+ "step": 303
2163
+ },
2164
+ {
2165
+ "epoch": 2.7636363636363637,
2166
+ "grad_norm": 2.642076253890991,
2167
+ "learning_rate": 4.242424242424243e-05,
2168
+ "loss": 1.8232,
2169
+ "step": 304
2170
+ },
2171
+ {
2172
+ "epoch": 2.7727272727272725,
2173
+ "grad_norm": 2.3849098682403564,
2174
+ "learning_rate": 4.090909090909091e-05,
2175
+ "loss": 1.5814,
2176
+ "step": 305
2177
+ },
2178
+ {
2179
+ "epoch": 2.7818181818181817,
2180
+ "grad_norm": 2.4465572834014893,
2181
+ "learning_rate": 3.939393939393939e-05,
2182
+ "loss": 2.0538,
2183
+ "step": 306
2184
+ },
2185
+ {
2186
+ "epoch": 2.790909090909091,
2187
+ "grad_norm": 3.058110475540161,
2188
+ "learning_rate": 3.787878787878788e-05,
2189
+ "loss": 2.4959,
2190
+ "step": 307
2191
+ },
2192
+ {
2193
+ "epoch": 2.8,
2194
+ "grad_norm": 2.4234743118286133,
2195
+ "learning_rate": 3.6363636363636364e-05,
2196
+ "loss": 1.9271,
2197
+ "step": 308
2198
+ },
2199
+ {
2200
+ "epoch": 2.809090909090909,
2201
+ "grad_norm": 2.6342692375183105,
2202
+ "learning_rate": 3.484848484848485e-05,
2203
+ "loss": 2.4818,
2204
+ "step": 309
2205
+ },
2206
+ {
2207
+ "epoch": 2.8181818181818183,
2208
+ "grad_norm": 3.9711482524871826,
2209
+ "learning_rate": 3.3333333333333335e-05,
2210
+ "loss": 1.7856,
2211
+ "step": 310
2212
+ },
2213
+ {
2214
+ "epoch": 2.827272727272727,
2215
+ "grad_norm": 2.6276450157165527,
2216
+ "learning_rate": 3.1818181818181814e-05,
2217
+ "loss": 2.3267,
2218
+ "step": 311
2219
+ },
2220
+ {
2221
+ "epoch": 2.8363636363636364,
2222
+ "grad_norm": 2.395639181137085,
2223
+ "learning_rate": 3.0303030303030306e-05,
2224
+ "loss": 2.0063,
2225
+ "step": 312
2226
+ },
2227
+ {
2228
+ "epoch": 2.8454545454545457,
2229
+ "grad_norm": 3.2870113849639893,
2230
+ "learning_rate": 2.878787878787879e-05,
2231
+ "loss": 2.1394,
2232
+ "step": 313
2233
+ },
2234
+ {
2235
+ "epoch": 2.8545454545454545,
2236
+ "grad_norm": 2.2852306365966797,
2237
+ "learning_rate": 2.7272727272727273e-05,
2238
+ "loss": 1.905,
2239
+ "step": 314
2240
+ },
2241
+ {
2242
+ "epoch": 2.8636363636363638,
2243
+ "grad_norm": 2.724724292755127,
2244
+ "learning_rate": 2.575757575757576e-05,
2245
+ "loss": 1.8821,
2246
+ "step": 315
2247
+ },
2248
+ {
2249
+ "epoch": 2.8727272727272726,
2250
+ "grad_norm": 3.5306527614593506,
2251
+ "learning_rate": 2.4242424242424244e-05,
2252
+ "loss": 2.2191,
2253
+ "step": 316
2254
+ },
2255
+ {
2256
+ "epoch": 2.881818181818182,
2257
+ "grad_norm": 2.3539886474609375,
2258
+ "learning_rate": 2.272727272727273e-05,
2259
+ "loss": 2.0281,
2260
+ "step": 317
2261
+ },
2262
+ {
2263
+ "epoch": 2.8909090909090907,
2264
+ "grad_norm": 2.4188969135284424,
2265
+ "learning_rate": 2.1212121212121215e-05,
2266
+ "loss": 2.5453,
2267
+ "step": 318
2268
+ },
2269
+ {
2270
+ "epoch": 2.9,
2271
+ "grad_norm": 2.5099847316741943,
2272
+ "learning_rate": 1.9696969696969697e-05,
2273
+ "loss": 2.3246,
2274
+ "step": 319
2275
+ },
2276
+ {
2277
+ "epoch": 2.909090909090909,
2278
+ "grad_norm": 2.6091346740722656,
2279
+ "learning_rate": 1.8181818181818182e-05,
2280
+ "loss": 1.7609,
2281
+ "step": 320
2282
+ },
2283
+ {
2284
+ "epoch": 2.918181818181818,
2285
+ "grad_norm": 2.5419886112213135,
2286
+ "learning_rate": 1.6666666666666667e-05,
2287
+ "loss": 2.2443,
2288
+ "step": 321
2289
+ },
2290
+ {
2291
+ "epoch": 2.9272727272727272,
2292
+ "grad_norm": 2.336390972137451,
2293
+ "learning_rate": 1.5151515151515153e-05,
2294
+ "loss": 1.734,
2295
+ "step": 322
2296
+ },
2297
+ {
2298
+ "epoch": 2.9363636363636365,
2299
+ "grad_norm": 2.4999842643737793,
2300
+ "learning_rate": 1.3636363636363637e-05,
2301
+ "loss": 1.9539,
2302
+ "step": 323
2303
+ },
2304
+ {
2305
+ "epoch": 2.9454545454545453,
2306
+ "grad_norm": 2.4849205017089844,
2307
+ "learning_rate": 1.2121212121212122e-05,
2308
+ "loss": 2.2472,
2309
+ "step": 324
2310
+ },
2311
+ {
2312
+ "epoch": 2.9545454545454546,
2313
+ "grad_norm": 2.6928179264068604,
2314
+ "learning_rate": 1.0606060606060607e-05,
2315
+ "loss": 2.0897,
2316
+ "step": 325
2317
+ },
2318
+ {
2319
+ "epoch": 2.963636363636364,
2320
+ "grad_norm": 2.8431129455566406,
2321
+ "learning_rate": 9.090909090909091e-06,
2322
+ "loss": 2.443,
2323
+ "step": 326
2324
+ },
2325
+ {
2326
+ "epoch": 2.9727272727272727,
2327
+ "grad_norm": 2.494403839111328,
2328
+ "learning_rate": 7.5757575757575764e-06,
2329
+ "loss": 1.8585,
2330
+ "step": 327
2331
+ },
2332
+ {
2333
+ "epoch": 2.981818181818182,
2334
+ "grad_norm": 2.491305112838745,
2335
+ "learning_rate": 6.060606060606061e-06,
2336
+ "loss": 1.8932,
2337
+ "step": 328
2338
+ },
2339
+ {
2340
+ "epoch": 2.990909090909091,
2341
+ "grad_norm": 2.3088715076446533,
2342
+ "learning_rate": 4.5454545454545455e-06,
2343
+ "loss": 1.7301,
2344
+ "step": 329
2345
+ },
2346
+ {
2347
+ "epoch": 3.0,
2348
+ "grad_norm": 2.533508539199829,
2349
+ "learning_rate": 3.0303030303030305e-06,
2350
+ "loss": 2.0174,
2351
+ "step": 330
2352
+ },
2353
+ {
2354
+ "epoch": 3.0,
2355
+ "eval_f1": 0.887,
2356
+ "eval_gen_len": 47.8091,
2357
+ "eval_loss": 2.0939812660217285,
2358
+ "eval_precision": 0.8838,
2359
+ "eval_recall": 0.8904,
2360
+ "eval_rouge1": 0.4298,
2361
+ "eval_rouge2": 0.1915,
2362
+ "eval_rougeL": 0.3559,
2363
+ "eval_rougeLsum": 0.3956,
2364
+ "eval_runtime": 22.6842,
2365
+ "eval_samples_per_second": 4.849,
2366
+ "eval_steps_per_second": 0.617,
2367
+ "step": 330
2368
+ },
2369
+ {
2370
+ "epoch": 3.0,
2371
+ "step": 330,
2372
+ "total_flos": 366452498497536.0,
2373
+ "train_loss": 2.2660372549837287,
2374
+ "train_runtime": 171.2707,
2375
+ "train_samples_per_second": 15.397,
2376
+ "train_steps_per_second": 1.927
2377
+ }
2378
+ ],
2379
+ "logging_steps": 1,
2380
+ "max_steps": 330,
2381
+ "num_input_tokens_seen": 0,
2382
+ "num_train_epochs": 3,
2383
+ "save_steps": 500,
2384
+ "stateful_callbacks": {
2385
+ "TrainerControl": {
2386
+ "args": {
2387
+ "should_epoch_stop": false,
2388
+ "should_evaluate": false,
2389
+ "should_log": false,
2390
+ "should_save": true,
2391
+ "should_training_stop": true
2392
+ },
2393
+ "attributes": {}
2394
+ }
2395
+ },
2396
+ "total_flos": 366452498497536.0,
2397
+ "train_batch_size": 8,
2398
+ "trial_name": null,
2399
+ "trial_params": null
2400
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a67a5baecd02877a6fb9798fa84814097f6966a77a10da923d73b510054b26d5
3
+ size 5432