LRJ1981 commited on
Commit
d84355a
1 Parent(s): 1ec6dd6

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - autotrain
5
+ - text2text-generation
6
+ widget:
7
+ - text: "I love AutoTrain"
8
+ datasets:
9
+ - autotrain-tlvon-zmjgo/autotrain-data
10
+ ---
11
+
12
+ # Model Trained Using AutoTrain
13
+
14
+ - Problem type: Seq2Seq
15
+
16
+ ## Validation Metrics
17
+ loss: 0.007954709231853485
18
+
19
+ rouge1: 99.4349
20
+
21
+ rouge2: 99.1573
22
+
23
+ rougeL: 99.4066
24
+
25
+ rougeLsum: 99.4213
26
+
27
+ gen_len: 458.5909
28
+
29
+ runtime: 309.674
30
+
31
+ samples_per_second: 0.639
32
+
33
+ steps_per_second: 0.161
34
+
35
+ : 10.0
checkpoint-3960/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "LRJ1981/RITO_Version1.0",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "swish",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": false,
8
+ "architectures": [
9
+ "MarianMTModel"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bad_words_ids": [
13
+ [
14
+ 58929
15
+ ]
16
+ ],
17
+ "bos_token_id": 0,
18
+ "classif_dropout": 0.0,
19
+ "classifier_dropout": 0.0,
20
+ "d_model": 512,
21
+ "decoder_attention_heads": 8,
22
+ "decoder_ffn_dim": 2048,
23
+ "decoder_layerdrop": 0.0,
24
+ "decoder_layers": 6,
25
+ "decoder_start_token_id": 58929,
26
+ "decoder_vocab_size": 58930,
27
+ "dropout": 0.1,
28
+ "encoder_attention_heads": 8,
29
+ "encoder_ffn_dim": 2048,
30
+ "encoder_layerdrop": 0.0,
31
+ "encoder_layers": 6,
32
+ "eos_token_id": 0,
33
+ "forced_eos_token_id": 0,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1",
37
+ "2": "LABEL_2"
38
+ },
39
+ "init_std": 0.02,
40
+ "is_encoder_decoder": true,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1,
44
+ "LABEL_2": 2
45
+ },
46
+ "max_length": 512,
47
+ "max_position_embeddings": 512,
48
+ "model_type": "marian",
49
+ "normalize_before": false,
50
+ "normalize_embedding": false,
51
+ "num_beams": 4,
52
+ "num_hidden_layers": 6,
53
+ "pad_token_id": 58929,
54
+ "scale_embedding": true,
55
+ "share_encoder_decoder_embeddings": true,
56
+ "static_position_embeddings": true,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.40.1",
59
+ "use_cache": false,
60
+ "vocab_size": 58930
61
+ }
checkpoint-3960/generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 58929
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 58929,
9
+ "eos_token_id": 0,
10
+ "forced_eos_token_id": 0,
11
+ "max_length": 512,
12
+ "num_beams": 4,
13
+ "pad_token_id": 58929,
14
+ "renormalize_logits": true,
15
+ "transformers_version": "4.40.1"
16
+ }
checkpoint-3960/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:228e10fd25241d25cc33e05e56b2285fcfc0d0187b49b6f5cad8df731aa62c1a
3
+ size 297507400
checkpoint-3960/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8374b7ff7e61bbb7eb6a9a777ae4330da14856c6d87d644e5faa027825da32ca
3
+ size 594696826
checkpoint-3960/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8368c7749135143bebe5e5d7ad08096a32f84dddb6d96bd5dcb1b199375fba9f
3
+ size 14244
checkpoint-3960/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:921350592575b293a33c90b0ed0ee9e71aa05363acc57c0e05d22c0f0949ebae
3
+ size 1064
checkpoint-3960/source.spm ADDED
Binary file (820 kB). View file
 
checkpoint-3960/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-3960/target.spm ADDED
Binary file (788 kB). View file
 
checkpoint-3960/tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "</s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "58929": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "clean_up_tokenization_spaces": true,
29
+ "eos_token": "</s>",
30
+ "model_max_length": 512,
31
+ "pad_token": "<pad>",
32
+ "separate_vocabs": false,
33
+ "source_lang": "da",
34
+ "sp_model_kwargs": {},
35
+ "target_lang": "en",
36
+ "tokenizer_class": "MarianTokenizer",
37
+ "unk_token": "<unk>"
38
+ }
checkpoint-3960/trainer_state.json ADDED
@@ -0,0 +1,1607 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.007954709231853485,
3
+ "best_model_checkpoint": "autotrain-tlvon-zmjgo/checkpoint-3960",
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3960,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.047979797979797977,
13
+ "grad_norm": 69.1661148071289,
14
+ "learning_rate": 7.575757575757576e-07,
15
+ "loss": 9.6544,
16
+ "step": 19
17
+ },
18
+ {
19
+ "epoch": 0.09595959595959595,
20
+ "grad_norm": 59.700984954833984,
21
+ "learning_rate": 1.6666666666666667e-06,
22
+ "loss": 8.2669,
23
+ "step": 38
24
+ },
25
+ {
26
+ "epoch": 0.14393939393939395,
27
+ "grad_norm": 22.565589904785156,
28
+ "learning_rate": 2.6262626262626263e-06,
29
+ "loss": 6.1057,
30
+ "step": 57
31
+ },
32
+ {
33
+ "epoch": 0.1919191919191919,
34
+ "grad_norm": 12.696467399597168,
35
+ "learning_rate": 3.5858585858585863e-06,
36
+ "loss": 4.9529,
37
+ "step": 76
38
+ },
39
+ {
40
+ "epoch": 0.2398989898989899,
41
+ "grad_norm": 11.562800407409668,
42
+ "learning_rate": 4.5454545454545455e-06,
43
+ "loss": 4.3771,
44
+ "step": 95
45
+ },
46
+ {
47
+ "epoch": 0.2878787878787879,
48
+ "grad_norm": 7.8888840675354,
49
+ "learning_rate": 5.5050505050505056e-06,
50
+ "loss": 4.027,
51
+ "step": 114
52
+ },
53
+ {
54
+ "epoch": 0.33585858585858586,
55
+ "grad_norm": 11.868915557861328,
56
+ "learning_rate": 6.464646464646465e-06,
57
+ "loss": 3.3608,
58
+ "step": 133
59
+ },
60
+ {
61
+ "epoch": 0.3838383838383838,
62
+ "grad_norm": 6.647916793823242,
63
+ "learning_rate": 7.424242424242425e-06,
64
+ "loss": 3.3761,
65
+ "step": 152
66
+ },
67
+ {
68
+ "epoch": 0.4318181818181818,
69
+ "grad_norm": 5.503500938415527,
70
+ "learning_rate": 8.383838383838384e-06,
71
+ "loss": 3.3234,
72
+ "step": 171
73
+ },
74
+ {
75
+ "epoch": 0.4797979797979798,
76
+ "grad_norm": 7.909439563751221,
77
+ "learning_rate": 9.343434343434344e-06,
78
+ "loss": 2.9671,
79
+ "step": 190
80
+ },
81
+ {
82
+ "epoch": 0.5277777777777778,
83
+ "grad_norm": 6.679018020629883,
84
+ "learning_rate": 1.0303030303030304e-05,
85
+ "loss": 2.9742,
86
+ "step": 209
87
+ },
88
+ {
89
+ "epoch": 0.5757575757575758,
90
+ "grad_norm": 7.1399664878845215,
91
+ "learning_rate": 1.1262626262626264e-05,
92
+ "loss": 2.8917,
93
+ "step": 228
94
+ },
95
+ {
96
+ "epoch": 0.6237373737373737,
97
+ "grad_norm": 6.230110168457031,
98
+ "learning_rate": 1.2222222222222222e-05,
99
+ "loss": 2.9786,
100
+ "step": 247
101
+ },
102
+ {
103
+ "epoch": 0.6717171717171717,
104
+ "grad_norm": 5.975085735321045,
105
+ "learning_rate": 1.318181818181818e-05,
106
+ "loss": 2.5503,
107
+ "step": 266
108
+ },
109
+ {
110
+ "epoch": 0.7196969696969697,
111
+ "grad_norm": 6.412594318389893,
112
+ "learning_rate": 1.4141414141414141e-05,
113
+ "loss": 2.6222,
114
+ "step": 285
115
+ },
116
+ {
117
+ "epoch": 0.7676767676767676,
118
+ "grad_norm": 5.266932487487793,
119
+ "learning_rate": 1.5101010101010103e-05,
120
+ "loss": 2.4747,
121
+ "step": 304
122
+ },
123
+ {
124
+ "epoch": 0.8156565656565656,
125
+ "grad_norm": 6.42549991607666,
126
+ "learning_rate": 1.606060606060606e-05,
127
+ "loss": 2.4522,
128
+ "step": 323
129
+ },
130
+ {
131
+ "epoch": 0.8636363636363636,
132
+ "grad_norm": 5.953466892242432,
133
+ "learning_rate": 1.7020202020202023e-05,
134
+ "loss": 2.4671,
135
+ "step": 342
136
+ },
137
+ {
138
+ "epoch": 0.9116161616161617,
139
+ "grad_norm": 5.912783145904541,
140
+ "learning_rate": 1.797979797979798e-05,
141
+ "loss": 2.1904,
142
+ "step": 361
143
+ },
144
+ {
145
+ "epoch": 0.9595959595959596,
146
+ "grad_norm": 6.379250526428223,
147
+ "learning_rate": 1.893939393939394e-05,
148
+ "loss": 2.2119,
149
+ "step": 380
150
+ },
151
+ {
152
+ "epoch": 1.0,
153
+ "eval_gen_len": 433.9545,
154
+ "eval_loss": 1.9540973901748657,
155
+ "eval_rouge1": 61.8945,
156
+ "eval_rouge2": 45.0914,
157
+ "eval_rougeL": 55.0215,
158
+ "eval_rougeLsum": 60.5887,
159
+ "eval_runtime": 309.9067,
160
+ "eval_samples_per_second": 0.639,
161
+ "eval_steps_per_second": 0.161,
162
+ "step": 396
163
+ },
164
+ {
165
+ "epoch": 1.0075757575757576,
166
+ "grad_norm": 5.456070899963379,
167
+ "learning_rate": 1.98989898989899e-05,
168
+ "loss": 2.1641,
169
+ "step": 399
170
+ },
171
+ {
172
+ "epoch": 1.0555555555555556,
173
+ "grad_norm": 6.323323726654053,
174
+ "learning_rate": 2.085858585858586e-05,
175
+ "loss": 1.8417,
176
+ "step": 418
177
+ },
178
+ {
179
+ "epoch": 1.1035353535353536,
180
+ "grad_norm": 5.177259922027588,
181
+ "learning_rate": 2.1818181818181818e-05,
182
+ "loss": 2.1193,
183
+ "step": 437
184
+ },
185
+ {
186
+ "epoch": 1.1515151515151516,
187
+ "grad_norm": 4.9402689933776855,
188
+ "learning_rate": 2.277777777777778e-05,
189
+ "loss": 2.0342,
190
+ "step": 456
191
+ },
192
+ {
193
+ "epoch": 1.1994949494949494,
194
+ "grad_norm": 5.041110515594482,
195
+ "learning_rate": 2.3737373737373738e-05,
196
+ "loss": 1.9017,
197
+ "step": 475
198
+ },
199
+ {
200
+ "epoch": 1.2474747474747474,
201
+ "grad_norm": 5.8411946296691895,
202
+ "learning_rate": 2.46969696969697e-05,
203
+ "loss": 1.9286,
204
+ "step": 494
205
+ },
206
+ {
207
+ "epoch": 1.2954545454545454,
208
+ "grad_norm": 4.762038707733154,
209
+ "learning_rate": 2.5656565656565658e-05,
210
+ "loss": 1.9661,
211
+ "step": 513
212
+ },
213
+ {
214
+ "epoch": 1.3434343434343434,
215
+ "grad_norm": 5.631948947906494,
216
+ "learning_rate": 2.6616161616161616e-05,
217
+ "loss": 1.6384,
218
+ "step": 532
219
+ },
220
+ {
221
+ "epoch": 1.3914141414141414,
222
+ "grad_norm": 8.481356620788574,
223
+ "learning_rate": 2.7575757575757578e-05,
224
+ "loss": 1.628,
225
+ "step": 551
226
+ },
227
+ {
228
+ "epoch": 1.4393939393939394,
229
+ "grad_norm": 5.706149101257324,
230
+ "learning_rate": 2.8535353535353536e-05,
231
+ "loss": 1.7007,
232
+ "step": 570
233
+ },
234
+ {
235
+ "epoch": 1.4873737373737375,
236
+ "grad_norm": 5.414116382598877,
237
+ "learning_rate": 2.9494949494949498e-05,
238
+ "loss": 1.5938,
239
+ "step": 589
240
+ },
241
+ {
242
+ "epoch": 1.5353535353535355,
243
+ "grad_norm": 4.6547441482543945,
244
+ "learning_rate": 3.0454545454545456e-05,
245
+ "loss": 1.6564,
246
+ "step": 608
247
+ },
248
+ {
249
+ "epoch": 1.5833333333333335,
250
+ "grad_norm": 5.299274444580078,
251
+ "learning_rate": 3.141414141414142e-05,
252
+ "loss": 1.5271,
253
+ "step": 627
254
+ },
255
+ {
256
+ "epoch": 1.6313131313131313,
257
+ "grad_norm": 5.234986305236816,
258
+ "learning_rate": 3.237373737373737e-05,
259
+ "loss": 1.4951,
260
+ "step": 646
261
+ },
262
+ {
263
+ "epoch": 1.6792929292929293,
264
+ "grad_norm": 4.347626209259033,
265
+ "learning_rate": 3.3333333333333335e-05,
266
+ "loss": 1.2796,
267
+ "step": 665
268
+ },
269
+ {
270
+ "epoch": 1.7272727272727273,
271
+ "grad_norm": 4.5906596183776855,
272
+ "learning_rate": 3.429292929292929e-05,
273
+ "loss": 1.3838,
274
+ "step": 684
275
+ },
276
+ {
277
+ "epoch": 1.7752525252525253,
278
+ "grad_norm": 5.531446933746338,
279
+ "learning_rate": 3.525252525252525e-05,
280
+ "loss": 1.5017,
281
+ "step": 703
282
+ },
283
+ {
284
+ "epoch": 1.823232323232323,
285
+ "grad_norm": 2.8456931114196777,
286
+ "learning_rate": 3.621212121212122e-05,
287
+ "loss": 1.3426,
288
+ "step": 722
289
+ },
290
+ {
291
+ "epoch": 1.871212121212121,
292
+ "grad_norm": 4.428695201873779,
293
+ "learning_rate": 3.7171717171717175e-05,
294
+ "loss": 1.4338,
295
+ "step": 741
296
+ },
297
+ {
298
+ "epoch": 1.9191919191919191,
299
+ "grad_norm": 5.436211585998535,
300
+ "learning_rate": 3.8131313131313133e-05,
301
+ "loss": 1.4004,
302
+ "step": 760
303
+ },
304
+ {
305
+ "epoch": 1.9671717171717171,
306
+ "grad_norm": 5.241793632507324,
307
+ "learning_rate": 3.909090909090909e-05,
308
+ "loss": 1.2884,
309
+ "step": 779
310
+ },
311
+ {
312
+ "epoch": 2.0,
313
+ "eval_gen_len": 452.298,
314
+ "eval_loss": 1.0236088037490845,
315
+ "eval_rouge1": 73.1042,
316
+ "eval_rouge2": 58.8087,
317
+ "eval_rougeL": 67.5013,
318
+ "eval_rougeLsum": 71.9232,
319
+ "eval_runtime": 307.9407,
320
+ "eval_samples_per_second": 0.643,
321
+ "eval_steps_per_second": 0.162,
322
+ "step": 792
323
+ },
324
+ {
325
+ "epoch": 2.015151515151515,
326
+ "grad_norm": 6.048191547393799,
327
+ "learning_rate": 4.005050505050506e-05,
328
+ "loss": 1.1874,
329
+ "step": 798
330
+ },
331
+ {
332
+ "epoch": 2.063131313131313,
333
+ "grad_norm": 4.456089019775391,
334
+ "learning_rate": 4.101010101010101e-05,
335
+ "loss": 1.2008,
336
+ "step": 817
337
+ },
338
+ {
339
+ "epoch": 2.111111111111111,
340
+ "grad_norm": 4.898771286010742,
341
+ "learning_rate": 4.196969696969697e-05,
342
+ "loss": 1.1192,
343
+ "step": 836
344
+ },
345
+ {
346
+ "epoch": 2.159090909090909,
347
+ "grad_norm": 4.564539909362793,
348
+ "learning_rate": 4.292929292929293e-05,
349
+ "loss": 1.0235,
350
+ "step": 855
351
+ },
352
+ {
353
+ "epoch": 2.207070707070707,
354
+ "grad_norm": 3.8853230476379395,
355
+ "learning_rate": 4.388888888888889e-05,
356
+ "loss": 1.0205,
357
+ "step": 874
358
+ },
359
+ {
360
+ "epoch": 2.255050505050505,
361
+ "grad_norm": 5.523693084716797,
362
+ "learning_rate": 4.484848484848485e-05,
363
+ "loss": 1.1685,
364
+ "step": 893
365
+ },
366
+ {
367
+ "epoch": 2.303030303030303,
368
+ "grad_norm": 4.635316848754883,
369
+ "learning_rate": 4.5808080808080814e-05,
370
+ "loss": 0.9885,
371
+ "step": 912
372
+ },
373
+ {
374
+ "epoch": 2.351010101010101,
375
+ "grad_norm": 4.56376314163208,
376
+ "learning_rate": 4.676767676767677e-05,
377
+ "loss": 0.9086,
378
+ "step": 931
379
+ },
380
+ {
381
+ "epoch": 2.398989898989899,
382
+ "grad_norm": 4.306213855743408,
383
+ "learning_rate": 4.772727272727273e-05,
384
+ "loss": 0.9958,
385
+ "step": 950
386
+ },
387
+ {
388
+ "epoch": 2.446969696969697,
389
+ "grad_norm": 3.2135376930236816,
390
+ "learning_rate": 4.868686868686869e-05,
391
+ "loss": 0.8709,
392
+ "step": 969
393
+ },
394
+ {
395
+ "epoch": 2.494949494949495,
396
+ "grad_norm": 6.685573101043701,
397
+ "learning_rate": 4.964646464646465e-05,
398
+ "loss": 0.931,
399
+ "step": 988
400
+ },
401
+ {
402
+ "epoch": 2.542929292929293,
403
+ "grad_norm": 3.9406039714813232,
404
+ "learning_rate": 4.993265993265993e-05,
405
+ "loss": 0.8775,
406
+ "step": 1007
407
+ },
408
+ {
409
+ "epoch": 2.590909090909091,
410
+ "grad_norm": 5.393746852874756,
411
+ "learning_rate": 4.9826038159371496e-05,
412
+ "loss": 0.8857,
413
+ "step": 1026
414
+ },
415
+ {
416
+ "epoch": 2.638888888888889,
417
+ "grad_norm": 5.132722854614258,
418
+ "learning_rate": 4.971941638608306e-05,
419
+ "loss": 0.8471,
420
+ "step": 1045
421
+ },
422
+ {
423
+ "epoch": 2.686868686868687,
424
+ "grad_norm": 4.663482189178467,
425
+ "learning_rate": 4.9612794612794616e-05,
426
+ "loss": 0.7213,
427
+ "step": 1064
428
+ },
429
+ {
430
+ "epoch": 2.734848484848485,
431
+ "grad_norm": 4.11750602722168,
432
+ "learning_rate": 4.950617283950618e-05,
433
+ "loss": 0.8061,
434
+ "step": 1083
435
+ },
436
+ {
437
+ "epoch": 2.782828282828283,
438
+ "grad_norm": 4.041347026824951,
439
+ "learning_rate": 4.9399551066217736e-05,
440
+ "loss": 0.7509,
441
+ "step": 1102
442
+ },
443
+ {
444
+ "epoch": 2.830808080808081,
445
+ "grad_norm": 4.211297988891602,
446
+ "learning_rate": 4.92929292929293e-05,
447
+ "loss": 0.6744,
448
+ "step": 1121
449
+ },
450
+ {
451
+ "epoch": 2.878787878787879,
452
+ "grad_norm": 3.244640827178955,
453
+ "learning_rate": 4.9186307519640855e-05,
454
+ "loss": 0.7003,
455
+ "step": 1140
456
+ },
457
+ {
458
+ "epoch": 2.926767676767677,
459
+ "grad_norm": 5.315489768981934,
460
+ "learning_rate": 4.907968574635242e-05,
461
+ "loss": 0.7851,
462
+ "step": 1159
463
+ },
464
+ {
465
+ "epoch": 2.974747474747475,
466
+ "grad_norm": 4.3310651779174805,
467
+ "learning_rate": 4.8973063973063975e-05,
468
+ "loss": 0.6508,
469
+ "step": 1178
470
+ },
471
+ {
472
+ "epoch": 3.0,
473
+ "eval_gen_len": 446.7525,
474
+ "eval_loss": 0.4764357805252075,
475
+ "eval_rouge1": 81.6804,
476
+ "eval_rouge2": 72.1296,
477
+ "eval_rougeL": 77.6939,
478
+ "eval_rougeLsum": 80.7121,
479
+ "eval_runtime": 314.0103,
480
+ "eval_samples_per_second": 0.631,
481
+ "eval_steps_per_second": 0.159,
482
+ "step": 1188
483
+ },
484
+ {
485
+ "epoch": 3.022727272727273,
486
+ "grad_norm": 4.33705997467041,
487
+ "learning_rate": 4.886644219977554e-05,
488
+ "loss": 0.6099,
489
+ "step": 1197
490
+ },
491
+ {
492
+ "epoch": 3.0707070707070705,
493
+ "grad_norm": 3.1699767112731934,
494
+ "learning_rate": 4.8759820426487094e-05,
495
+ "loss": 0.5929,
496
+ "step": 1216
497
+ },
498
+ {
499
+ "epoch": 3.1186868686868685,
500
+ "grad_norm": 4.443921089172363,
501
+ "learning_rate": 4.865319865319866e-05,
502
+ "loss": 0.5826,
503
+ "step": 1235
504
+ },
505
+ {
506
+ "epoch": 3.1666666666666665,
507
+ "grad_norm": 2.6721291542053223,
508
+ "learning_rate": 4.8546576879910214e-05,
509
+ "loss": 0.5011,
510
+ "step": 1254
511
+ },
512
+ {
513
+ "epoch": 3.2146464646464645,
514
+ "grad_norm": 3.757880687713623,
515
+ "learning_rate": 4.843995510662178e-05,
516
+ "loss": 0.5661,
517
+ "step": 1273
518
+ },
519
+ {
520
+ "epoch": 3.2626262626262625,
521
+ "grad_norm": 3.813979387283325,
522
+ "learning_rate": 4.8333333333333334e-05,
523
+ "loss": 0.5751,
524
+ "step": 1292
525
+ },
526
+ {
527
+ "epoch": 3.3106060606060606,
528
+ "grad_norm": 3.1598410606384277,
529
+ "learning_rate": 4.82267115600449e-05,
530
+ "loss": 0.4737,
531
+ "step": 1311
532
+ },
533
+ {
534
+ "epoch": 3.3585858585858586,
535
+ "grad_norm": 3.785410165786743,
536
+ "learning_rate": 4.812008978675645e-05,
537
+ "loss": 0.517,
538
+ "step": 1330
539
+ },
540
+ {
541
+ "epoch": 3.4065656565656566,
542
+ "grad_norm": 3.080495834350586,
543
+ "learning_rate": 4.8013468013468016e-05,
544
+ "loss": 0.5221,
545
+ "step": 1349
546
+ },
547
+ {
548
+ "epoch": 3.4545454545454546,
549
+ "grad_norm": 3.909271001815796,
550
+ "learning_rate": 4.790684624017957e-05,
551
+ "loss": 0.4863,
552
+ "step": 1368
553
+ },
554
+ {
555
+ "epoch": 3.5025252525252526,
556
+ "grad_norm": 4.788086891174316,
557
+ "learning_rate": 4.7800224466891136e-05,
558
+ "loss": 0.4692,
559
+ "step": 1387
560
+ },
561
+ {
562
+ "epoch": 3.5505050505050506,
563
+ "grad_norm": 3.4247238636016846,
564
+ "learning_rate": 4.769360269360269e-05,
565
+ "loss": 0.4108,
566
+ "step": 1406
567
+ },
568
+ {
569
+ "epoch": 3.5984848484848486,
570
+ "grad_norm": 4.0106587409973145,
571
+ "learning_rate": 4.7586980920314256e-05,
572
+ "loss": 0.4493,
573
+ "step": 1425
574
+ },
575
+ {
576
+ "epoch": 3.6464646464646466,
577
+ "grad_norm": 3.134174108505249,
578
+ "learning_rate": 4.748035914702582e-05,
579
+ "loss": 0.4723,
580
+ "step": 1444
581
+ },
582
+ {
583
+ "epoch": 3.6944444444444446,
584
+ "grad_norm": 3.621345043182373,
585
+ "learning_rate": 4.7373737373737375e-05,
586
+ "loss": 0.4259,
587
+ "step": 1463
588
+ },
589
+ {
590
+ "epoch": 3.742424242424242,
591
+ "grad_norm": 3.506635904312134,
592
+ "learning_rate": 4.726711560044894e-05,
593
+ "loss": 0.4028,
594
+ "step": 1482
595
+ },
596
+ {
597
+ "epoch": 3.7904040404040407,
598
+ "grad_norm": 3.2687313556671143,
599
+ "learning_rate": 4.7160493827160495e-05,
600
+ "loss": 0.3411,
601
+ "step": 1501
602
+ },
603
+ {
604
+ "epoch": 3.8383838383838382,
605
+ "grad_norm": 2.7574453353881836,
606
+ "learning_rate": 4.705387205387206e-05,
607
+ "loss": 0.3987,
608
+ "step": 1520
609
+ },
610
+ {
611
+ "epoch": 3.8863636363636362,
612
+ "grad_norm": 3.152305841445923,
613
+ "learning_rate": 4.6947250280583614e-05,
614
+ "loss": 0.3134,
615
+ "step": 1539
616
+ },
617
+ {
618
+ "epoch": 3.9343434343434343,
619
+ "grad_norm": 3.0011281967163086,
620
+ "learning_rate": 4.684062850729518e-05,
621
+ "loss": 0.4049,
622
+ "step": 1558
623
+ },
624
+ {
625
+ "epoch": 3.9823232323232323,
626
+ "grad_norm": 3.843477487564087,
627
+ "learning_rate": 4.6734006734006734e-05,
628
+ "loss": 0.3601,
629
+ "step": 1577
630
+ },
631
+ {
632
+ "epoch": 4.0,
633
+ "eval_gen_len": 450.1111,
634
+ "eval_loss": 0.200236514210701,
635
+ "eval_rouge1": 88.8764,
636
+ "eval_rouge2": 82.5347,
637
+ "eval_rougeL": 86.0051,
638
+ "eval_rougeLsum": 88.1546,
639
+ "eval_runtime": 311.9983,
640
+ "eval_samples_per_second": 0.635,
641
+ "eval_steps_per_second": 0.16,
642
+ "step": 1584
643
+ },
644
+ {
645
+ "epoch": 4.03030303030303,
646
+ "grad_norm": 3.5295767784118652,
647
+ "learning_rate": 4.66273849607183e-05,
648
+ "loss": 0.2928,
649
+ "step": 1596
650
+ },
651
+ {
652
+ "epoch": 4.078282828282829,
653
+ "grad_norm": 2.5708324909210205,
654
+ "learning_rate": 4.6520763187429854e-05,
655
+ "loss": 0.3198,
656
+ "step": 1615
657
+ },
658
+ {
659
+ "epoch": 4.126262626262626,
660
+ "grad_norm": 3.164304256439209,
661
+ "learning_rate": 4.641414141414142e-05,
662
+ "loss": 0.2895,
663
+ "step": 1634
664
+ },
665
+ {
666
+ "epoch": 4.174242424242424,
667
+ "grad_norm": 2.5397143363952637,
668
+ "learning_rate": 4.630751964085297e-05,
669
+ "loss": 0.277,
670
+ "step": 1653
671
+ },
672
+ {
673
+ "epoch": 4.222222222222222,
674
+ "grad_norm": 2.639850616455078,
675
+ "learning_rate": 4.6200897867564537e-05,
676
+ "loss": 0.2605,
677
+ "step": 1672
678
+ },
679
+ {
680
+ "epoch": 4.27020202020202,
681
+ "grad_norm": 2.7750766277313232,
682
+ "learning_rate": 4.609427609427609e-05,
683
+ "loss": 0.2702,
684
+ "step": 1691
685
+ },
686
+ {
687
+ "epoch": 4.318181818181818,
688
+ "grad_norm": 3.7487545013427734,
689
+ "learning_rate": 4.5987654320987656e-05,
690
+ "loss": 0.2904,
691
+ "step": 1710
692
+ },
693
+ {
694
+ "epoch": 4.366161616161616,
695
+ "grad_norm": 2.997239351272583,
696
+ "learning_rate": 4.588103254769921e-05,
697
+ "loss": 0.2802,
698
+ "step": 1729
699
+ },
700
+ {
701
+ "epoch": 4.414141414141414,
702
+ "grad_norm": 3.394998788833618,
703
+ "learning_rate": 4.5774410774410776e-05,
704
+ "loss": 0.2538,
705
+ "step": 1748
706
+ },
707
+ {
708
+ "epoch": 4.462121212121212,
709
+ "grad_norm": 2.767073392868042,
710
+ "learning_rate": 4.566778900112233e-05,
711
+ "loss": 0.2537,
712
+ "step": 1767
713
+ },
714
+ {
715
+ "epoch": 4.51010101010101,
716
+ "grad_norm": 2.4357552528381348,
717
+ "learning_rate": 4.5561167227833895e-05,
718
+ "loss": 0.2404,
719
+ "step": 1786
720
+ },
721
+ {
722
+ "epoch": 4.558080808080808,
723
+ "grad_norm": 3.32743763923645,
724
+ "learning_rate": 4.545454545454546e-05,
725
+ "loss": 0.2273,
726
+ "step": 1805
727
+ },
728
+ {
729
+ "epoch": 4.606060606060606,
730
+ "grad_norm": 4.112804889678955,
731
+ "learning_rate": 4.5347923681257015e-05,
732
+ "loss": 0.2373,
733
+ "step": 1824
734
+ },
735
+ {
736
+ "epoch": 4.654040404040404,
737
+ "grad_norm": 2.256756067276001,
738
+ "learning_rate": 4.524130190796858e-05,
739
+ "loss": 0.2387,
740
+ "step": 1843
741
+ },
742
+ {
743
+ "epoch": 4.702020202020202,
744
+ "grad_norm": 2.8960530757904053,
745
+ "learning_rate": 4.5134680134680135e-05,
746
+ "loss": 0.2507,
747
+ "step": 1862
748
+ },
749
+ {
750
+ "epoch": 4.75,
751
+ "grad_norm": 2.621000289916992,
752
+ "learning_rate": 4.50280583613917e-05,
753
+ "loss": 0.1899,
754
+ "step": 1881
755
+ },
756
+ {
757
+ "epoch": 4.797979797979798,
758
+ "grad_norm": 2.6264095306396484,
759
+ "learning_rate": 4.4921436588103254e-05,
760
+ "loss": 0.1921,
761
+ "step": 1900
762
+ },
763
+ {
764
+ "epoch": 4.845959595959596,
765
+ "grad_norm": 2.770009994506836,
766
+ "learning_rate": 4.481481481481482e-05,
767
+ "loss": 0.1819,
768
+ "step": 1919
769
+ },
770
+ {
771
+ "epoch": 4.893939393939394,
772
+ "grad_norm": 2.9698147773742676,
773
+ "learning_rate": 4.4708193041526374e-05,
774
+ "loss": 0.1877,
775
+ "step": 1938
776
+ },
777
+ {
778
+ "epoch": 4.941919191919192,
779
+ "grad_norm": 2.6372764110565186,
780
+ "learning_rate": 4.460157126823794e-05,
781
+ "loss": 0.1848,
782
+ "step": 1957
783
+ },
784
+ {
785
+ "epoch": 4.98989898989899,
786
+ "grad_norm": 3.164541006088257,
787
+ "learning_rate": 4.4494949494949493e-05,
788
+ "loss": 0.1663,
789
+ "step": 1976
790
+ },
791
+ {
792
+ "epoch": 5.0,
793
+ "eval_gen_len": 456.2828,
794
+ "eval_loss": 0.07814756035804749,
795
+ "eval_rouge1": 94.3866,
796
+ "eval_rouge2": 91.5001,
797
+ "eval_rougeL": 93.1131,
798
+ "eval_rougeLsum": 94.0657,
799
+ "eval_runtime": 313.1525,
800
+ "eval_samples_per_second": 0.632,
801
+ "eval_steps_per_second": 0.16,
802
+ "step": 1980
803
+ },
804
+ {
805
+ "epoch": 5.037878787878788,
806
+ "grad_norm": 1.722895622253418,
807
+ "learning_rate": 4.438832772166106e-05,
808
+ "loss": 0.1759,
809
+ "step": 1995
810
+ },
811
+ {
812
+ "epoch": 5.085858585858586,
813
+ "grad_norm": 5.62981653213501,
814
+ "learning_rate": 4.428170594837261e-05,
815
+ "loss": 0.1636,
816
+ "step": 2014
817
+ },
818
+ {
819
+ "epoch": 5.133838383838384,
820
+ "grad_norm": 2.8217477798461914,
821
+ "learning_rate": 4.4175084175084176e-05,
822
+ "loss": 0.1606,
823
+ "step": 2033
824
+ },
825
+ {
826
+ "epoch": 5.181818181818182,
827
+ "grad_norm": 2.2173731327056885,
828
+ "learning_rate": 4.406846240179573e-05,
829
+ "loss": 0.1439,
830
+ "step": 2052
831
+ },
832
+ {
833
+ "epoch": 5.22979797979798,
834
+ "grad_norm": 2.4998719692230225,
835
+ "learning_rate": 4.3961840628507296e-05,
836
+ "loss": 0.1621,
837
+ "step": 2071
838
+ },
839
+ {
840
+ "epoch": 5.277777777777778,
841
+ "grad_norm": 2.240722894668579,
842
+ "learning_rate": 4.385521885521885e-05,
843
+ "loss": 0.1453,
844
+ "step": 2090
845
+ },
846
+ {
847
+ "epoch": 5.325757575757576,
848
+ "grad_norm": 2.2540104389190674,
849
+ "learning_rate": 4.3748597081930415e-05,
850
+ "loss": 0.1277,
851
+ "step": 2109
852
+ },
853
+ {
854
+ "epoch": 5.373737373737374,
855
+ "grad_norm": 2.4170944690704346,
856
+ "learning_rate": 4.364197530864197e-05,
857
+ "loss": 0.1447,
858
+ "step": 2128
859
+ },
860
+ {
861
+ "epoch": 5.421717171717171,
862
+ "grad_norm": 2.999178409576416,
863
+ "learning_rate": 4.3535353535353535e-05,
864
+ "loss": 0.1436,
865
+ "step": 2147
866
+ },
867
+ {
868
+ "epoch": 5.46969696969697,
869
+ "grad_norm": 1.2877140045166016,
870
+ "learning_rate": 4.34287317620651e-05,
871
+ "loss": 0.1567,
872
+ "step": 2166
873
+ },
874
+ {
875
+ "epoch": 5.517676767676767,
876
+ "grad_norm": 2.6238033771514893,
877
+ "learning_rate": 4.332210998877666e-05,
878
+ "loss": 0.1196,
879
+ "step": 2185
880
+ },
881
+ {
882
+ "epoch": 5.565656565656566,
883
+ "grad_norm": 3.2489261627197266,
884
+ "learning_rate": 4.321548821548822e-05,
885
+ "loss": 0.1403,
886
+ "step": 2204
887
+ },
888
+ {
889
+ "epoch": 5.613636363636363,
890
+ "grad_norm": 2.750288963317871,
891
+ "learning_rate": 4.310886644219978e-05,
892
+ "loss": 0.1422,
893
+ "step": 2223
894
+ },
895
+ {
896
+ "epoch": 5.661616161616162,
897
+ "grad_norm": 2.125354290008545,
898
+ "learning_rate": 4.300224466891134e-05,
899
+ "loss": 0.1209,
900
+ "step": 2242
901
+ },
902
+ {
903
+ "epoch": 5.709595959595959,
904
+ "grad_norm": 2.956669330596924,
905
+ "learning_rate": 4.28956228956229e-05,
906
+ "loss": 0.1261,
907
+ "step": 2261
908
+ },
909
+ {
910
+ "epoch": 5.757575757575758,
911
+ "grad_norm": 2.4984519481658936,
912
+ "learning_rate": 4.278900112233446e-05,
913
+ "loss": 0.1688,
914
+ "step": 2280
915
+ },
916
+ {
917
+ "epoch": 5.805555555555555,
918
+ "grad_norm": 1.8321527242660522,
919
+ "learning_rate": 4.268237934904602e-05,
920
+ "loss": 0.1242,
921
+ "step": 2299
922
+ },
923
+ {
924
+ "epoch": 5.853535353535354,
925
+ "grad_norm": 2.03973650932312,
926
+ "learning_rate": 4.257575757575758e-05,
927
+ "loss": 0.1083,
928
+ "step": 2318
929
+ },
930
+ {
931
+ "epoch": 5.901515151515151,
932
+ "grad_norm": 3.7561116218566895,
933
+ "learning_rate": 4.246913580246914e-05,
934
+ "loss": 0.1553,
935
+ "step": 2337
936
+ },
937
+ {
938
+ "epoch": 5.94949494949495,
939
+ "grad_norm": 4.251192092895508,
940
+ "learning_rate": 4.23625140291807e-05,
941
+ "loss": 0.1083,
942
+ "step": 2356
943
+ },
944
+ {
945
+ "epoch": 5.997474747474747,
946
+ "grad_norm": 1.9990973472595215,
947
+ "learning_rate": 4.225589225589226e-05,
948
+ "loss": 0.1058,
949
+ "step": 2375
950
+ },
951
+ {
952
+ "epoch": 6.0,
953
+ "eval_gen_len": 457.202,
954
+ "eval_loss": 0.04152845963835716,
955
+ "eval_rouge1": 96.8862,
956
+ "eval_rouge2": 95.3951,
957
+ "eval_rougeL": 96.2693,
958
+ "eval_rougeLsum": 96.7116,
959
+ "eval_runtime": 311.7737,
960
+ "eval_samples_per_second": 0.635,
961
+ "eval_steps_per_second": 0.16,
962
+ "step": 2376
963
+ },
964
+ {
965
+ "epoch": 6.045454545454546,
966
+ "grad_norm": 0.8384280204772949,
967
+ "learning_rate": 4.214927048260382e-05,
968
+ "loss": 0.108,
969
+ "step": 2394
970
+ },
971
+ {
972
+ "epoch": 6.093434343434343,
973
+ "grad_norm": 2.411668539047241,
974
+ "learning_rate": 4.204264870931538e-05,
975
+ "loss": 0.1004,
976
+ "step": 2413
977
+ },
978
+ {
979
+ "epoch": 6.141414141414141,
980
+ "grad_norm": 1.1796258687973022,
981
+ "learning_rate": 4.193602693602694e-05,
982
+ "loss": 0.1045,
983
+ "step": 2432
984
+ },
985
+ {
986
+ "epoch": 6.1893939393939394,
987
+ "grad_norm": 1.7287437915802002,
988
+ "learning_rate": 4.18294051627385e-05,
989
+ "loss": 0.0994,
990
+ "step": 2451
991
+ },
992
+ {
993
+ "epoch": 6.237373737373737,
994
+ "grad_norm": 1.7795087099075317,
995
+ "learning_rate": 4.172278338945006e-05,
996
+ "loss": 0.0972,
997
+ "step": 2470
998
+ },
999
+ {
1000
+ "epoch": 6.2853535353535355,
1001
+ "grad_norm": 1.167188048362732,
1002
+ "learning_rate": 4.161616161616162e-05,
1003
+ "loss": 0.0983,
1004
+ "step": 2489
1005
+ },
1006
+ {
1007
+ "epoch": 6.333333333333333,
1008
+ "grad_norm": 2.2238261699676514,
1009
+ "learning_rate": 4.150953984287318e-05,
1010
+ "loss": 0.0924,
1011
+ "step": 2508
1012
+ },
1013
+ {
1014
+ "epoch": 6.3813131313131315,
1015
+ "grad_norm": 2.0129451751708984,
1016
+ "learning_rate": 4.140291806958474e-05,
1017
+ "loss": 0.1008,
1018
+ "step": 2527
1019
+ },
1020
+ {
1021
+ "epoch": 6.429292929292929,
1022
+ "grad_norm": 2.159029006958008,
1023
+ "learning_rate": 4.12962962962963e-05,
1024
+ "loss": 0.0844,
1025
+ "step": 2546
1026
+ },
1027
+ {
1028
+ "epoch": 6.4772727272727275,
1029
+ "grad_norm": 1.6442041397094727,
1030
+ "learning_rate": 4.118967452300786e-05,
1031
+ "loss": 0.089,
1032
+ "step": 2565
1033
+ },
1034
+ {
1035
+ "epoch": 6.525252525252525,
1036
+ "grad_norm": 1.7517181634902954,
1037
+ "learning_rate": 4.108305274971942e-05,
1038
+ "loss": 0.0901,
1039
+ "step": 2584
1040
+ },
1041
+ {
1042
+ "epoch": 6.5732323232323235,
1043
+ "grad_norm": 1.2451421022415161,
1044
+ "learning_rate": 4.097643097643098e-05,
1045
+ "loss": 0.0792,
1046
+ "step": 2603
1047
+ },
1048
+ {
1049
+ "epoch": 6.621212121212121,
1050
+ "grad_norm": 1.7869890928268433,
1051
+ "learning_rate": 4.086980920314254e-05,
1052
+ "loss": 0.0915,
1053
+ "step": 2622
1054
+ },
1055
+ {
1056
+ "epoch": 6.66919191919192,
1057
+ "grad_norm": 2.2728748321533203,
1058
+ "learning_rate": 4.07631874298541e-05,
1059
+ "loss": 0.0844,
1060
+ "step": 2641
1061
+ },
1062
+ {
1063
+ "epoch": 6.717171717171717,
1064
+ "grad_norm": 1.853063702583313,
1065
+ "learning_rate": 4.065656565656566e-05,
1066
+ "loss": 0.0857,
1067
+ "step": 2660
1068
+ },
1069
+ {
1070
+ "epoch": 6.765151515151516,
1071
+ "grad_norm": 1.8357278108596802,
1072
+ "learning_rate": 4.0549943883277216e-05,
1073
+ "loss": 0.0785,
1074
+ "step": 2679
1075
+ },
1076
+ {
1077
+ "epoch": 6.813131313131313,
1078
+ "grad_norm": 2.4003820419311523,
1079
+ "learning_rate": 4.044332210998878e-05,
1080
+ "loss": 0.0928,
1081
+ "step": 2698
1082
+ },
1083
+ {
1084
+ "epoch": 6.861111111111111,
1085
+ "grad_norm": 3.2185213565826416,
1086
+ "learning_rate": 4.0336700336700336e-05,
1087
+ "loss": 0.0846,
1088
+ "step": 2717
1089
+ },
1090
+ {
1091
+ "epoch": 6.909090909090909,
1092
+ "grad_norm": 2.1494338512420654,
1093
+ "learning_rate": 4.02300785634119e-05,
1094
+ "loss": 0.0779,
1095
+ "step": 2736
1096
+ },
1097
+ {
1098
+ "epoch": 6.957070707070707,
1099
+ "grad_norm": 1.4656015634536743,
1100
+ "learning_rate": 4.012345679012346e-05,
1101
+ "loss": 0.0701,
1102
+ "step": 2755
1103
+ },
1104
+ {
1105
+ "epoch": 7.0,
1106
+ "eval_gen_len": 457.0758,
1107
+ "eval_loss": 0.023281894624233246,
1108
+ "eval_rouge1": 98.2551,
1109
+ "eval_rouge2": 97.419,
1110
+ "eval_rougeL": 97.9827,
1111
+ "eval_rougeLsum": 98.1479,
1112
+ "eval_runtime": 308.2542,
1113
+ "eval_samples_per_second": 0.642,
1114
+ "eval_steps_per_second": 0.162,
1115
+ "step": 2772
1116
+ },
1117
+ {
1118
+ "epoch": 7.005050505050505,
1119
+ "grad_norm": 2.010523796081543,
1120
+ "learning_rate": 4.001683501683502e-05,
1121
+ "loss": 0.0752,
1122
+ "step": 2774
1123
+ },
1124
+ {
1125
+ "epoch": 7.053030303030303,
1126
+ "grad_norm": 2.3323521614074707,
1127
+ "learning_rate": 3.991021324354658e-05,
1128
+ "loss": 0.0637,
1129
+ "step": 2793
1130
+ },
1131
+ {
1132
+ "epoch": 7.101010101010101,
1133
+ "grad_norm": 1.684549331665039,
1134
+ "learning_rate": 3.980359147025814e-05,
1135
+ "loss": 0.0711,
1136
+ "step": 2812
1137
+ },
1138
+ {
1139
+ "epoch": 7.148989898989899,
1140
+ "grad_norm": 1.6758151054382324,
1141
+ "learning_rate": 3.96969696969697e-05,
1142
+ "loss": 0.0709,
1143
+ "step": 2831
1144
+ },
1145
+ {
1146
+ "epoch": 7.196969696969697,
1147
+ "grad_norm": 1.9380394220352173,
1148
+ "learning_rate": 3.959034792368126e-05,
1149
+ "loss": 0.0665,
1150
+ "step": 2850
1151
+ },
1152
+ {
1153
+ "epoch": 7.244949494949495,
1154
+ "grad_norm": 1.988451361656189,
1155
+ "learning_rate": 3.948372615039282e-05,
1156
+ "loss": 0.0693,
1157
+ "step": 2869
1158
+ },
1159
+ {
1160
+ "epoch": 7.292929292929293,
1161
+ "grad_norm": 1.2491166591644287,
1162
+ "learning_rate": 3.937710437710438e-05,
1163
+ "loss": 0.0721,
1164
+ "step": 2888
1165
+ },
1166
+ {
1167
+ "epoch": 7.340909090909091,
1168
+ "grad_norm": 1.4535962343215942,
1169
+ "learning_rate": 3.927048260381594e-05,
1170
+ "loss": 0.0659,
1171
+ "step": 2907
1172
+ },
1173
+ {
1174
+ "epoch": 7.388888888888889,
1175
+ "grad_norm": 1.9495213031768799,
1176
+ "learning_rate": 3.91638608305275e-05,
1177
+ "loss": 0.085,
1178
+ "step": 2926
1179
+ },
1180
+ {
1181
+ "epoch": 7.436868686868687,
1182
+ "grad_norm": 2.000051259994507,
1183
+ "learning_rate": 3.905723905723906e-05,
1184
+ "loss": 0.0694,
1185
+ "step": 2945
1186
+ },
1187
+ {
1188
+ "epoch": 7.484848484848484,
1189
+ "grad_norm": 2.803647518157959,
1190
+ "learning_rate": 3.895061728395062e-05,
1191
+ "loss": 0.0713,
1192
+ "step": 2964
1193
+ },
1194
+ {
1195
+ "epoch": 7.532828282828283,
1196
+ "grad_norm": 1.7719061374664307,
1197
+ "learning_rate": 3.884399551066218e-05,
1198
+ "loss": 0.0626,
1199
+ "step": 2983
1200
+ },
1201
+ {
1202
+ "epoch": 7.58080808080808,
1203
+ "grad_norm": 2.1927216053009033,
1204
+ "learning_rate": 3.8737373737373737e-05,
1205
+ "loss": 0.0668,
1206
+ "step": 3002
1207
+ },
1208
+ {
1209
+ "epoch": 7.628787878787879,
1210
+ "grad_norm": 1.1310573816299438,
1211
+ "learning_rate": 3.86307519640853e-05,
1212
+ "loss": 0.0521,
1213
+ "step": 3021
1214
+ },
1215
+ {
1216
+ "epoch": 7.6767676767676765,
1217
+ "grad_norm": 1.4547724723815918,
1218
+ "learning_rate": 3.8524130190796856e-05,
1219
+ "loss": 0.0556,
1220
+ "step": 3040
1221
+ },
1222
+ {
1223
+ "epoch": 7.724747474747475,
1224
+ "grad_norm": 2.3777520656585693,
1225
+ "learning_rate": 3.841750841750842e-05,
1226
+ "loss": 0.053,
1227
+ "step": 3059
1228
+ },
1229
+ {
1230
+ "epoch": 7.7727272727272725,
1231
+ "grad_norm": 2.8660731315612793,
1232
+ "learning_rate": 3.8310886644219976e-05,
1233
+ "loss": 0.0662,
1234
+ "step": 3078
1235
+ },
1236
+ {
1237
+ "epoch": 7.820707070707071,
1238
+ "grad_norm": 1.2403335571289062,
1239
+ "learning_rate": 3.820426487093154e-05,
1240
+ "loss": 0.0513,
1241
+ "step": 3097
1242
+ },
1243
+ {
1244
+ "epoch": 7.8686868686868685,
1245
+ "grad_norm": 1.2479897737503052,
1246
+ "learning_rate": 3.8097643097643095e-05,
1247
+ "loss": 0.0529,
1248
+ "step": 3116
1249
+ },
1250
+ {
1251
+ "epoch": 7.916666666666667,
1252
+ "grad_norm": 0.8943136930465698,
1253
+ "learning_rate": 3.799102132435466e-05,
1254
+ "loss": 0.0493,
1255
+ "step": 3135
1256
+ },
1257
+ {
1258
+ "epoch": 7.9646464646464645,
1259
+ "grad_norm": 2.092480421066284,
1260
+ "learning_rate": 3.788439955106622e-05,
1261
+ "loss": 0.0613,
1262
+ "step": 3154
1263
+ },
1264
+ {
1265
+ "epoch": 8.0,
1266
+ "eval_gen_len": 456.2626,
1267
+ "eval_loss": 0.014666617847979069,
1268
+ "eval_rouge1": 98.8857,
1269
+ "eval_rouge2": 98.3456,
1270
+ "eval_rougeL": 98.7777,
1271
+ "eval_rougeLsum": 98.8775,
1272
+ "eval_runtime": 309.5854,
1273
+ "eval_samples_per_second": 0.64,
1274
+ "eval_steps_per_second": 0.162,
1275
+ "step": 3168
1276
+ },
1277
+ {
1278
+ "epoch": 8.012626262626263,
1279
+ "grad_norm": 0.7548523545265198,
1280
+ "learning_rate": 3.777777777777778e-05,
1281
+ "loss": 0.0606,
1282
+ "step": 3173
1283
+ },
1284
+ {
1285
+ "epoch": 8.06060606060606,
1286
+ "grad_norm": 1.4151593446731567,
1287
+ "learning_rate": 3.767115600448934e-05,
1288
+ "loss": 0.047,
1289
+ "step": 3192
1290
+ },
1291
+ {
1292
+ "epoch": 8.108585858585858,
1293
+ "grad_norm": 1.26515531539917,
1294
+ "learning_rate": 3.75645342312009e-05,
1295
+ "loss": 0.0535,
1296
+ "step": 3211
1297
+ },
1298
+ {
1299
+ "epoch": 8.156565656565657,
1300
+ "grad_norm": 1.318965196609497,
1301
+ "learning_rate": 3.745791245791246e-05,
1302
+ "loss": 0.0496,
1303
+ "step": 3230
1304
+ },
1305
+ {
1306
+ "epoch": 8.204545454545455,
1307
+ "grad_norm": 1.5114891529083252,
1308
+ "learning_rate": 3.735129068462402e-05,
1309
+ "loss": 0.0434,
1310
+ "step": 3249
1311
+ },
1312
+ {
1313
+ "epoch": 8.252525252525253,
1314
+ "grad_norm": 1.121440052986145,
1315
+ "learning_rate": 3.724466891133558e-05,
1316
+ "loss": 0.0447,
1317
+ "step": 3268
1318
+ },
1319
+ {
1320
+ "epoch": 8.30050505050505,
1321
+ "grad_norm": 0.9955199360847473,
1322
+ "learning_rate": 3.713804713804714e-05,
1323
+ "loss": 0.0478,
1324
+ "step": 3287
1325
+ },
1326
+ {
1327
+ "epoch": 8.348484848484848,
1328
+ "grad_norm": 2.078119993209839,
1329
+ "learning_rate": 3.70314253647587e-05,
1330
+ "loss": 0.0494,
1331
+ "step": 3306
1332
+ },
1333
+ {
1334
+ "epoch": 8.396464646464647,
1335
+ "grad_norm": 1.3387614488601685,
1336
+ "learning_rate": 3.692480359147026e-05,
1337
+ "loss": 0.0402,
1338
+ "step": 3325
1339
+ },
1340
+ {
1341
+ "epoch": 8.444444444444445,
1342
+ "grad_norm": 2.1103882789611816,
1343
+ "learning_rate": 3.681818181818182e-05,
1344
+ "loss": 0.0457,
1345
+ "step": 3344
1346
+ },
1347
+ {
1348
+ "epoch": 8.492424242424242,
1349
+ "grad_norm": 1.5628422498703003,
1350
+ "learning_rate": 3.6711560044893376e-05,
1351
+ "loss": 0.0462,
1352
+ "step": 3363
1353
+ },
1354
+ {
1355
+ "epoch": 8.54040404040404,
1356
+ "grad_norm": 1.7333801984786987,
1357
+ "learning_rate": 3.660493827160494e-05,
1358
+ "loss": 0.0466,
1359
+ "step": 3382
1360
+ },
1361
+ {
1362
+ "epoch": 8.58838383838384,
1363
+ "grad_norm": 1.3456194400787354,
1364
+ "learning_rate": 3.6498316498316496e-05,
1365
+ "loss": 0.0402,
1366
+ "step": 3401
1367
+ },
1368
+ {
1369
+ "epoch": 8.636363636363637,
1370
+ "grad_norm": 1.2034332752227783,
1371
+ "learning_rate": 3.639169472502806e-05,
1372
+ "loss": 0.0459,
1373
+ "step": 3420
1374
+ },
1375
+ {
1376
+ "epoch": 8.684343434343434,
1377
+ "grad_norm": 0.502601683139801,
1378
+ "learning_rate": 3.6285072951739616e-05,
1379
+ "loss": 0.0465,
1380
+ "step": 3439
1381
+ },
1382
+ {
1383
+ "epoch": 8.732323232323232,
1384
+ "grad_norm": 1.651060938835144,
1385
+ "learning_rate": 3.617845117845118e-05,
1386
+ "loss": 0.0401,
1387
+ "step": 3458
1388
+ },
1389
+ {
1390
+ "epoch": 8.780303030303031,
1391
+ "grad_norm": 1.1892279386520386,
1392
+ "learning_rate": 3.6071829405162735e-05,
1393
+ "loss": 0.0357,
1394
+ "step": 3477
1395
+ },
1396
+ {
1397
+ "epoch": 8.828282828282829,
1398
+ "grad_norm": 1.0248866081237793,
1399
+ "learning_rate": 3.59652076318743e-05,
1400
+ "loss": 0.0368,
1401
+ "step": 3496
1402
+ },
1403
+ {
1404
+ "epoch": 8.876262626262626,
1405
+ "grad_norm": 1.235990285873413,
1406
+ "learning_rate": 3.5858585858585855e-05,
1407
+ "loss": 0.0354,
1408
+ "step": 3515
1409
+ },
1410
+ {
1411
+ "epoch": 8.924242424242424,
1412
+ "grad_norm": 1.156433343887329,
1413
+ "learning_rate": 3.575196408529742e-05,
1414
+ "loss": 0.0366,
1415
+ "step": 3534
1416
+ },
1417
+ {
1418
+ "epoch": 8.972222222222221,
1419
+ "grad_norm": 1.7279999256134033,
1420
+ "learning_rate": 3.564534231200898e-05,
1421
+ "loss": 0.042,
1422
+ "step": 3553
1423
+ },
1424
+ {
1425
+ "epoch": 9.0,
1426
+ "eval_gen_len": 458.904,
1427
+ "eval_loss": 0.010045090690255165,
1428
+ "eval_rouge1": 99.2356,
1429
+ "eval_rouge2": 98.9142,
1430
+ "eval_rougeL": 99.1626,
1431
+ "eval_rougeLsum": 99.2057,
1432
+ "eval_runtime": 310.3859,
1433
+ "eval_samples_per_second": 0.638,
1434
+ "eval_steps_per_second": 0.161,
1435
+ "step": 3564
1436
+ },
1437
+ {
1438
+ "epoch": 9.02020202020202,
1439
+ "grad_norm": 1.298857569694519,
1440
+ "learning_rate": 3.553872053872054e-05,
1441
+ "loss": 0.0423,
1442
+ "step": 3572
1443
+ },
1444
+ {
1445
+ "epoch": 9.068181818181818,
1446
+ "grad_norm": 1.124570608139038,
1447
+ "learning_rate": 3.54320987654321e-05,
1448
+ "loss": 0.0309,
1449
+ "step": 3591
1450
+ },
1451
+ {
1452
+ "epoch": 9.116161616161616,
1453
+ "grad_norm": 1.5465493202209473,
1454
+ "learning_rate": 3.532547699214366e-05,
1455
+ "loss": 0.0365,
1456
+ "step": 3610
1457
+ },
1458
+ {
1459
+ "epoch": 9.164141414141413,
1460
+ "grad_norm": 1.208004117012024,
1461
+ "learning_rate": 3.521885521885522e-05,
1462
+ "loss": 0.035,
1463
+ "step": 3629
1464
+ },
1465
+ {
1466
+ "epoch": 9.212121212121213,
1467
+ "grad_norm": 1.7865431308746338,
1468
+ "learning_rate": 3.511223344556678e-05,
1469
+ "loss": 0.0376,
1470
+ "step": 3648
1471
+ },
1472
+ {
1473
+ "epoch": 9.26010101010101,
1474
+ "grad_norm": 0.8254820108413696,
1475
+ "learning_rate": 3.500561167227834e-05,
1476
+ "loss": 0.0327,
1477
+ "step": 3667
1478
+ },
1479
+ {
1480
+ "epoch": 9.308080808080808,
1481
+ "grad_norm": 1.0625301599502563,
1482
+ "learning_rate": 3.48989898989899e-05,
1483
+ "loss": 0.0363,
1484
+ "step": 3686
1485
+ },
1486
+ {
1487
+ "epoch": 9.356060606060606,
1488
+ "grad_norm": 1.4023059606552124,
1489
+ "learning_rate": 3.4792368125701466e-05,
1490
+ "loss": 0.0386,
1491
+ "step": 3705
1492
+ },
1493
+ {
1494
+ "epoch": 9.404040404040405,
1495
+ "grad_norm": 1.9438424110412598,
1496
+ "learning_rate": 3.468574635241302e-05,
1497
+ "loss": 0.0345,
1498
+ "step": 3724
1499
+ },
1500
+ {
1501
+ "epoch": 9.452020202020202,
1502
+ "grad_norm": 0.7543076872825623,
1503
+ "learning_rate": 3.4579124579124586e-05,
1504
+ "loss": 0.0369,
1505
+ "step": 3743
1506
+ },
1507
+ {
1508
+ "epoch": 9.5,
1509
+ "grad_norm": 1.4393041133880615,
1510
+ "learning_rate": 3.447250280583614e-05,
1511
+ "loss": 0.0327,
1512
+ "step": 3762
1513
+ },
1514
+ {
1515
+ "epoch": 9.547979797979798,
1516
+ "grad_norm": 0.8074661493301392,
1517
+ "learning_rate": 3.4365881032547706e-05,
1518
+ "loss": 0.0317,
1519
+ "step": 3781
1520
+ },
1521
+ {
1522
+ "epoch": 9.595959595959595,
1523
+ "grad_norm": 1.5561342239379883,
1524
+ "learning_rate": 3.425925925925926e-05,
1525
+ "loss": 0.037,
1526
+ "step": 3800
1527
+ },
1528
+ {
1529
+ "epoch": 9.643939393939394,
1530
+ "grad_norm": 2.0807337760925293,
1531
+ "learning_rate": 3.4152637485970825e-05,
1532
+ "loss": 0.0365,
1533
+ "step": 3819
1534
+ },
1535
+ {
1536
+ "epoch": 9.691919191919192,
1537
+ "grad_norm": 0.9361720681190491,
1538
+ "learning_rate": 3.404601571268238e-05,
1539
+ "loss": 0.0289,
1540
+ "step": 3838
1541
+ },
1542
+ {
1543
+ "epoch": 9.73989898989899,
1544
+ "grad_norm": 0.8103030323982239,
1545
+ "learning_rate": 3.3939393939393945e-05,
1546
+ "loss": 0.0294,
1547
+ "step": 3857
1548
+ },
1549
+ {
1550
+ "epoch": 9.787878787878787,
1551
+ "grad_norm": 1.4826786518096924,
1552
+ "learning_rate": 3.38327721661055e-05,
1553
+ "loss": 0.0274,
1554
+ "step": 3876
1555
+ },
1556
+ {
1557
+ "epoch": 9.835858585858587,
1558
+ "grad_norm": 1.5168986320495605,
1559
+ "learning_rate": 3.3726150392817064e-05,
1560
+ "loss": 0.0323,
1561
+ "step": 3895
1562
+ },
1563
+ {
1564
+ "epoch": 9.883838383838384,
1565
+ "grad_norm": 1.7513259649276733,
1566
+ "learning_rate": 3.361952861952862e-05,
1567
+ "loss": 0.0312,
1568
+ "step": 3914
1569
+ },
1570
+ {
1571
+ "epoch": 9.931818181818182,
1572
+ "grad_norm": 1.0549064874649048,
1573
+ "learning_rate": 3.3512906846240184e-05,
1574
+ "loss": 0.0294,
1575
+ "step": 3933
1576
+ },
1577
+ {
1578
+ "epoch": 9.97979797979798,
1579
+ "grad_norm": 1.206652045249939,
1580
+ "learning_rate": 3.340628507295174e-05,
1581
+ "loss": 0.0295,
1582
+ "step": 3952
1583
+ },
1584
+ {
1585
+ "epoch": 10.0,
1586
+ "eval_gen_len": 458.5909,
1587
+ "eval_loss": 0.007954709231853485,
1588
+ "eval_rouge1": 99.4349,
1589
+ "eval_rouge2": 99.1573,
1590
+ "eval_rougeL": 99.4066,
1591
+ "eval_rougeLsum": 99.4213,
1592
+ "eval_runtime": 308.7546,
1593
+ "eval_samples_per_second": 0.641,
1594
+ "eval_steps_per_second": 0.162,
1595
+ "step": 3960
1596
+ }
1597
+ ],
1598
+ "logging_steps": 19,
1599
+ "max_steps": 9900,
1600
+ "num_input_tokens_seen": 0,
1601
+ "num_train_epochs": 25,
1602
+ "save_steps": 500,
1603
+ "total_flos": 1017429232582656.0,
1604
+ "train_batch_size": 2,
1605
+ "trial_name": null,
1606
+ "trial_params": null
1607
+ }
checkpoint-3960/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62a6bb28bb360013bcfdc07feeb3365525520a2ae613255247c1fd2e2eb4289c
3
+ size 5176
checkpoint-3960/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "LRJ1981/RITO_Version1.0",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "swish",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": false,
8
+ "architectures": [
9
+ "MarianMTModel"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bad_words_ids": [
13
+ [
14
+ 58929
15
+ ]
16
+ ],
17
+ "bos_token_id": 0,
18
+ "classif_dropout": 0.0,
19
+ "classifier_dropout": 0.0,
20
+ "d_model": 512,
21
+ "decoder_attention_heads": 8,
22
+ "decoder_ffn_dim": 2048,
23
+ "decoder_layerdrop": 0.0,
24
+ "decoder_layers": 6,
25
+ "decoder_start_token_id": 58929,
26
+ "decoder_vocab_size": 58930,
27
+ "dropout": 0.1,
28
+ "encoder_attention_heads": 8,
29
+ "encoder_ffn_dim": 2048,
30
+ "encoder_layerdrop": 0.0,
31
+ "encoder_layers": 6,
32
+ "eos_token_id": 0,
33
+ "forced_eos_token_id": 0,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1",
37
+ "2": "LABEL_2"
38
+ },
39
+ "init_std": 0.02,
40
+ "is_encoder_decoder": true,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1,
44
+ "LABEL_2": 2
45
+ },
46
+ "max_length": 512,
47
+ "max_position_embeddings": 512,
48
+ "model_type": "marian",
49
+ "normalize_before": false,
50
+ "normalize_embedding": false,
51
+ "num_beams": 4,
52
+ "num_hidden_layers": 6,
53
+ "pad_token_id": 58929,
54
+ "scale_embedding": true,
55
+ "share_encoder_decoder_embeddings": true,
56
+ "static_position_embeddings": true,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.40.1",
59
+ "use_cache": true,
60
+ "vocab_size": 58930
61
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 58929
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 58929,
9
+ "eos_token_id": 0,
10
+ "forced_eos_token_id": 0,
11
+ "max_length": 512,
12
+ "num_beams": 4,
13
+ "pad_token_id": 58929,
14
+ "renormalize_logits": true,
15
+ "transformers_version": "4.40.1"
16
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:228e10fd25241d25cc33e05e56b2285fcfc0d0187b49b6f5cad8df731aa62c1a
3
+ size 297507400
runs/May14_09-07-39_r-lrj1981-rito-bvamzz15-af43e-hz6l9/events.out.tfevents.1715677662.r-lrj1981-rito-bvamzz15-af43e-hz6l9.68.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ee2bf2254e91636e5960332311aaaff932f1ce10bff081cafde0af44df7ffa9
3
- size 44816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7704529355274a806d9bd3fcc6b67f1c052166c53c80ad1acb453c573e295ede
3
+ size 55082
runs/May14_09-07-39_r-lrj1981-rito-bvamzz15-af43e-hz6l9/events.out.tfevents.1715681569.r-lrj1981-rito-bvamzz15-af43e-hz6l9.68.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f06c87b5564f40634291c39edfcd8f9dd8f81f7598c0e8a632cb655f925f60eb
3
+ size 613
source.spm ADDED
Binary file (820 kB). View file
 
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
target.spm ADDED
Binary file (788 kB). View file
 
tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "</s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "58929": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "clean_up_tokenization_spaces": true,
29
+ "eos_token": "</s>",
30
+ "model_max_length": 512,
31
+ "pad_token": "<pad>",
32
+ "separate_vocabs": false,
33
+ "source_lang": "da",
34
+ "sp_model_kwargs": {},
35
+ "target_lang": "en",
36
+ "tokenizer_class": "MarianTokenizer",
37
+ "unk_token": "<unk>"
38
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62a6bb28bb360013bcfdc07feeb3365525520a2ae613255247c1fd2e2eb4289c
3
+ size 5176
training_params.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "autotrain-tlvon-zmjgo/autotrain-data",
3
+ "model": "LRJ1981/RITO_Version1.0",
4
+ "username": "LRJ1981",
5
+ "seed": 42,
6
+ "train_split": "train",
7
+ "valid_split": "validation",
8
+ "project_name": "autotrain-tlvon-zmjgo",
9
+ "push_to_hub": true,
10
+ "text_column": "autotrain_text",
11
+ "target_column": "autotrain_label",
12
+ "lr": 5e-05,
13
+ "epochs": 25,
14
+ "max_seq_length": 512,
15
+ "max_target_length": 512,
16
+ "batch_size": 2,
17
+ "warmup_ratio": 0.1,
18
+ "gradient_accumulation": 1,
19
+ "optimizer": "adamw_torch",
20
+ "scheduler": "linear",
21
+ "weight_decay": 0.0,
22
+ "max_grad_norm": 1.0,
23
+ "logging_steps": -1,
24
+ "evaluation_strategy": "epoch",
25
+ "auto_find_batch_size": false,
26
+ "mixed_precision": "fp16",
27
+ "save_total_limit": 1,
28
+ "peft": false,
29
+ "quantization": "int4",
30
+ "lora_r": 16,
31
+ "lora_alpha": 32,
32
+ "lora_dropout": 0.05,
33
+ "target_modules": "all-linear",
34
+ "log": "tensorboard"
35
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff