Muqeeth commited on
Commit
e114a20
·
verified ·
1 Parent(s): af58bb1

Training in progress, step 1823, checkpoint

Browse files
checkpoint-1823/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GPTNeoXForSequenceClassification"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": 0.1,
9
+ "eos_token_id": 0,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout": 0.0,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 4096,
18
+ "label2id": {
19
+ "LABEL_0": 0
20
+ },
21
+ "layer_norm_eps": 1e-05,
22
+ "max_position_embeddings": 2048,
23
+ "model_type": "gpt_neox",
24
+ "num_attention_heads": 16,
25
+ "num_hidden_layers": 24,
26
+ "pad_token_id": 1,
27
+ "partial_rotary_factor": 0.25,
28
+ "rope_scaling": null,
29
+ "rope_theta": 10000,
30
+ "rotary_emb_base": 10000,
31
+ "rotary_pct": 0.25,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.50.3",
35
+ "use_cache": true,
36
+ "use_parallel_residual": true,
37
+ "vocab_size": 50304
38
+ }
checkpoint-1823/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d68b9700db07b367a8a682014b413508c748fab1e7044afefdcffc584ef9e0f
3
+ size 1415329032
checkpoint-1823/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c62ab5f344340bc5dacc20d4605a8750f1034db018a719731fc42b434ae4cd6
3
+ size 2830833850
checkpoint-1823/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48ee9b73399c28d7e668360bf1d5a4d11095c4738bf96c13f7bb6fbff59f8ccb
3
+ size 14244
checkpoint-1823/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcd8826b159374e58c7cc3f33a47f5654fa56dc7c4fe435bc87e9b22fae67696
3
+ size 1064
checkpoint-1823/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|padding|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
checkpoint-1823/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1823/tokenizer_config.json ADDED
@@ -0,0 +1,219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|padding|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "50254": {
23
+ "content": " ",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "50255": {
31
+ "content": " ",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "50256": {
39
+ "content": " ",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "50257": {
47
+ "content": " ",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "50258": {
55
+ "content": " ",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "50259": {
63
+ "content": " ",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "50260": {
71
+ "content": " ",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "50261": {
79
+ "content": " ",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "50262": {
87
+ "content": " ",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "50263": {
95
+ "content": " ",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "50264": {
103
+ "content": " ",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "50265": {
111
+ "content": " ",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "50266": {
119
+ "content": " ",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "50267": {
127
+ "content": " ",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "50268": {
135
+ "content": " ",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "50269": {
143
+ "content": " ",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "50270": {
151
+ "content": " ",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "50271": {
159
+ "content": " ",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "50272": {
167
+ "content": " ",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "50273": {
175
+ "content": " ",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "50274": {
183
+ "content": " ",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "50275": {
191
+ "content": " ",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "50276": {
199
+ "content": " ",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ }
206
+ },
207
+ "bos_token": "<|endoftext|>",
208
+ "clean_up_tokenization_spaces": true,
209
+ "eos_token": "<|endoftext|>",
210
+ "extra_special_tokens": {},
211
+ "max_length": 580,
212
+ "model_max_length": 1000000000000000019884624838656,
213
+ "pad_token": "<|padding|>",
214
+ "stride": 0,
215
+ "tokenizer_class": "GPTNeoXTokenizer",
216
+ "truncation_side": "right",
217
+ "truncation_strategy": "longest_first",
218
+ "unk_token": "<|endoftext|>"
219
+ }
checkpoint-1823/trainer_state.json ADDED
@@ -0,0 +1,1344 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.9995202522102666,
6
+ "eval_steps": 365,
7
+ "global_step": 1823,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.005482831882667398,
14
+ "grad_norm": 1.8271640439809084e-13,
15
+ "learning_rate": 9.999257569732963e-06,
16
+ "loss": 0.0547,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.010965663765334796,
21
+ "grad_norm": 1.8681511551469146e-14,
22
+ "learning_rate": 9.997030499412933e-06,
23
+ "loss": 0.0,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.016448495648002194,
28
+ "grad_norm": 1.2511433729323063e-11,
29
+ "learning_rate": 9.993319450417669e-06,
30
+ "loss": 0.0,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.021931327530669592,
35
+ "grad_norm": 3.090452546650191e-11,
36
+ "learning_rate": 9.988125524825216e-06,
37
+ "loss": 0.0,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.02741415941333699,
42
+ "grad_norm": 1.458404726736688e-14,
43
+ "learning_rate": 9.981450265086598e-06,
44
+ "loss": 0.0,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.03289699129600439,
49
+ "grad_norm": 3.242672515051115e-14,
50
+ "learning_rate": 9.973295653567764e-06,
51
+ "loss": 0.0,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.038379823178671786,
56
+ "grad_norm": 2.718872761479918e-14,
57
+ "learning_rate": 9.963664111960875e-06,
58
+ "loss": 0.0,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.043862655061339184,
63
+ "grad_norm": 9.169036085943105e-10,
64
+ "learning_rate": 9.952558500565135e-06,
65
+ "loss": 0.0,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.04934548694400658,
70
+ "grad_norm": 6.057082835297933e-09,
71
+ "learning_rate": 9.939982117437356e-06,
72
+ "loss": 0.0,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.05482831882667398,
77
+ "grad_norm": 2.746146947174566e-06,
78
+ "learning_rate": 9.925938697412536e-06,
79
+ "loss": 0.0,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.06031115070934138,
84
+ "grad_norm": 2.1543860384554137e-07,
85
+ "learning_rate": 9.910432410994701e-06,
86
+ "loss": 0.0,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.06579398259200878,
91
+ "grad_norm": 1.2734583378914976e-06,
92
+ "learning_rate": 9.893467863118402e-06,
93
+ "loss": 0.0,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.07127681447467617,
98
+ "grad_norm": 3.238647128256389e-09,
99
+ "learning_rate": 9.87505009178116e-06,
100
+ "loss": 0.0,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.07675964635734357,
105
+ "grad_norm": 1.8630474585279444e-07,
106
+ "learning_rate": 9.855184566547333e-06,
107
+ "loss": 0.0,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.08224247824001096,
112
+ "grad_norm": 1.8918351329944016e-09,
113
+ "learning_rate": 9.833877186923803e-06,
114
+ "loss": 0.0,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.08772531012267837,
119
+ "grad_norm": 1.6541060188224321e-10,
120
+ "learning_rate": 9.811134280607988e-06,
121
+ "loss": 0.0,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.09320814200534576,
126
+ "grad_norm": 0.0067967576906085014,
127
+ "learning_rate": 9.786962601608689e-06,
128
+ "loss": 0.0015,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.09869097388801316,
133
+ "grad_norm": 7.394525164272636e-05,
134
+ "learning_rate": 9.761369328240347e-06,
135
+ "loss": 0.0,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.10417380577068056,
140
+ "grad_norm": 2.62540652329335e-07,
141
+ "learning_rate": 9.734362060991274e-06,
142
+ "loss": 0.0,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.10965663765334796,
147
+ "grad_norm": 4.609726822479843e-09,
148
+ "learning_rate": 9.70594882026652e-06,
149
+ "loss": 0.0,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.11513946953601535,
154
+ "grad_norm": 8.970529319363152e-10,
155
+ "learning_rate": 9.676138044006051e-06,
156
+ "loss": 0.0,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.12062230141868276,
161
+ "grad_norm": 7.758627629250725e-10,
162
+ "learning_rate": 9.644938585178894e-06,
163
+ "loss": 0.0,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.12610513330135015,
168
+ "grad_norm": 3.484149357912969e-10,
169
+ "learning_rate": 9.61235970915407e-06,
170
+ "loss": 0.0,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.13158796518401755,
175
+ "grad_norm": 3.5987784974267356e-10,
176
+ "learning_rate": 9.57841109094903e-06,
177
+ "loss": 0.0,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.13707079706668493,
182
+ "grad_norm": 2.9926486289078014e-10,
183
+ "learning_rate": 9.543102812356446e-06,
184
+ "loss": 0.0,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.14255362894935233,
189
+ "grad_norm": 2.17573001282112e-10,
190
+ "learning_rate": 9.506445358950199e-06,
191
+ "loss": 0.0,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.14803646083201974,
196
+ "grad_norm": 1.5743054082584251e-10,
197
+ "learning_rate": 9.468449616971458e-06,
198
+ "loss": 0.0,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.15351929271468714,
203
+ "grad_norm": 3.0337881185005244e-07,
204
+ "learning_rate": 9.429126870095766e-06,
205
+ "loss": 0.0,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.15900212459735452,
210
+ "grad_norm": 2.075781768695606e-10,
211
+ "learning_rate": 9.388488796082113e-06,
212
+ "loss": 0.0,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.16448495648002193,
217
+ "grad_norm": 2.6534453922977264e-07,
218
+ "learning_rate": 9.346547463304953e-06,
219
+ "loss": 0.0,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.16996778836268933,
224
+ "grad_norm": 2.213984316767892e-06,
225
+ "learning_rate": 9.303315327170244e-06,
226
+ "loss": 0.0,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.17545062024535674,
231
+ "grad_norm": 1.0965933022744068e-10,
232
+ "learning_rate": 9.258805226416536e-06,
233
+ "loss": 0.0,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.1809334521280241,
238
+ "grad_norm": 9.682482593476038e-11,
239
+ "learning_rate": 9.213030379302223e-06,
240
+ "loss": 0.0,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.18641628401069152,
245
+ "grad_norm": 1.8911376631347565e-10,
246
+ "learning_rate": 9.166004379680094e-06,
247
+ "loss": 0.0,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.19189911589335892,
252
+ "grad_norm": 2.287967731939844e-10,
253
+ "learning_rate": 9.11774119296033e-06,
254
+ "loss": 0.0,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.19738194777602633,
259
+ "grad_norm": 1.6538861946635564e-10,
260
+ "learning_rate": 9.068255151963174e-06,
261
+ "loss": 0.0,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.20012336371736,
266
+ "eval_accuracy": 1.0,
267
+ "eval_loss": 8.152250430271124e-09,
268
+ "eval_runtime": 172.1258,
269
+ "eval_samples_per_second": 37.455,
270
+ "eval_steps_per_second": 4.683,
271
+ "step": 365
272
+ },
273
+ {
274
+ "epoch": 0.2028647796586937,
275
+ "grad_norm": 1.5171223139986978e-06,
276
+ "learning_rate": 9.017560952662478e-06,
277
+ "loss": 0.0,
278
+ "step": 370
279
+ },
280
+ {
281
+ "epoch": 0.2083476115413611,
282
+ "grad_norm": 1.40862849162815e-10,
283
+ "learning_rate": 8.965673649821411e-06,
284
+ "loss": 0.0,
285
+ "step": 380
286
+ },
287
+ {
288
+ "epoch": 0.21383044342402852,
289
+ "grad_norm": 1.6394713364675795e-10,
290
+ "learning_rate": 8.912608652521618e-06,
291
+ "loss": 0.0,
292
+ "step": 390
293
+ },
294
+ {
295
+ "epoch": 0.21931327530669592,
296
+ "grad_norm": 9.934635752939514e-11,
297
+ "learning_rate": 8.858381719587143e-06,
298
+ "loss": 0.0,
299
+ "step": 400
300
+ },
301
+ {
302
+ "epoch": 0.2247961071893633,
303
+ "grad_norm": 1.0912845627153445e-10,
304
+ "learning_rate": 8.803008954904504e-06,
305
+ "loss": 0.0,
306
+ "step": 410
307
+ },
308
+ {
309
+ "epoch": 0.2302789390720307,
310
+ "grad_norm": 4.275700121070258e-05,
311
+ "learning_rate": 8.74650680264029e-06,
312
+ "loss": 0.0001,
313
+ "step": 420
314
+ },
315
+ {
316
+ "epoch": 0.2357617709546981,
317
+ "grad_norm": 3.5764787753578275e-05,
318
+ "learning_rate": 8.688892042357703e-06,
319
+ "loss": 0.0,
320
+ "step": 430
321
+ },
322
+ {
323
+ "epoch": 0.2412446028373655,
324
+ "grad_norm": 8.193592657335103e-05,
325
+ "learning_rate": 8.63018178403348e-06,
326
+ "loss": 0.0,
327
+ "step": 440
328
+ },
329
+ {
330
+ "epoch": 0.2467274347200329,
331
+ "grad_norm": 9.473233149037696e-06,
332
+ "learning_rate": 8.570393462976731e-06,
333
+ "loss": 0.0,
334
+ "step": 450
335
+ },
336
+ {
337
+ "epoch": 0.2522102666027003,
338
+ "grad_norm": 0.00011029987945221364,
339
+ "learning_rate": 8.509544834651124e-06,
340
+ "loss": 0.0,
341
+ "step": 460
342
+ },
343
+ {
344
+ "epoch": 0.2576930984853677,
345
+ "grad_norm": 6.70829012960894e-06,
346
+ "learning_rate": 8.44765396940201e-06,
347
+ "loss": 0.0,
348
+ "step": 470
349
+ },
350
+ {
351
+ "epoch": 0.2631759303680351,
352
+ "grad_norm": 6.388377641997067e-06,
353
+ "learning_rate": 8.384739247090032e-06,
354
+ "loss": 0.0,
355
+ "step": 480
356
+ },
357
+ {
358
+ "epoch": 0.2686587622507025,
359
+ "grad_norm": 5.076117304270156e-06,
360
+ "learning_rate": 8.320819351632828e-06,
361
+ "loss": 0.0,
362
+ "step": 490
363
+ },
364
+ {
365
+ "epoch": 0.27414159413336986,
366
+ "grad_norm": 8.84547353052767e-06,
367
+ "learning_rate": 8.255913265456416e-06,
368
+ "loss": 0.0,
369
+ "step": 500
370
+ },
371
+ {
372
+ "epoch": 0.27962442601603726,
373
+ "grad_norm": 3.398100943741156e-06,
374
+ "learning_rate": 8.190040263857955e-06,
375
+ "loss": 0.0,
376
+ "step": 510
377
+ },
378
+ {
379
+ "epoch": 0.28510725789870467,
380
+ "grad_norm": 8.591404366597999e-06,
381
+ "learning_rate": 8.123219909281511e-06,
382
+ "loss": 0.0,
383
+ "step": 520
384
+ },
385
+ {
386
+ "epoch": 0.2905900897813721,
387
+ "grad_norm": 3.0375645110325422e-06,
388
+ "learning_rate": 8.05547204550856e-06,
389
+ "loss": 0.0,
390
+ "step": 530
391
+ },
392
+ {
393
+ "epoch": 0.2960729216640395,
394
+ "grad_norm": 3.1508220672549214e-06,
395
+ "learning_rate": 7.986816791764942e-06,
396
+ "loss": 0.0,
397
+ "step": 540
398
+ },
399
+ {
400
+ "epoch": 0.3015557535467069,
401
+ "grad_norm": 4.118597907165622e-09,
402
+ "learning_rate": 7.917274536746002e-06,
403
+ "loss": 0.0,
404
+ "step": 550
405
+ },
406
+ {
407
+ "epoch": 0.3070385854293743,
408
+ "grad_norm": 6.056056697789636e-12,
409
+ "learning_rate": 7.846865932561727e-06,
410
+ "loss": 0.0,
411
+ "step": 560
412
+ },
413
+ {
414
+ "epoch": 0.3125214173120417,
415
+ "grad_norm": 1.4811193160824132e-08,
416
+ "learning_rate": 7.775611888603641e-06,
417
+ "loss": 0.0,
418
+ "step": 570
419
+ },
420
+ {
421
+ "epoch": 0.31800424919470904,
422
+ "grad_norm": 1.5655763144217794e-11,
423
+ "learning_rate": 7.703533565335293e-06,
424
+ "loss": 0.0,
425
+ "step": 580
426
+ },
427
+ {
428
+ "epoch": 0.32348708107737645,
429
+ "grad_norm": 2.8082117187189226e-10,
430
+ "learning_rate": 7.630652368008202e-06,
431
+ "loss": 0.0,
432
+ "step": 590
433
+ },
434
+ {
435
+ "epoch": 0.32896991296004385,
436
+ "grad_norm": 1.598878668351844e-10,
437
+ "learning_rate": 7.556989940305087e-06,
438
+ "loss": 0.0,
439
+ "step": 600
440
+ },
441
+ {
442
+ "epoch": 0.33445274484271126,
443
+ "grad_norm": 2.0122902455455005e-08,
444
+ "learning_rate": 7.482568157912293e-06,
445
+ "loss": 0.0,
446
+ "step": 610
447
+ },
448
+ {
449
+ "epoch": 0.33993557672537866,
450
+ "grad_norm": 4.7687648101202296e-12,
451
+ "learning_rate": 7.407409122023334e-06,
452
+ "loss": 0.0,
453
+ "step": 620
454
+ },
455
+ {
456
+ "epoch": 0.34541840860804607,
457
+ "grad_norm": 4.5280151156346093e-11,
458
+ "learning_rate": 7.3315351527754405e-06,
459
+ "loss": 0.0,
460
+ "step": 630
461
+ },
462
+ {
463
+ "epoch": 0.3509012404907135,
464
+ "grad_norm": 1.5659229291031806e-07,
465
+ "learning_rate": 7.254968782621115e-06,
466
+ "loss": 0.0,
467
+ "step": 640
468
+ },
469
+ {
470
+ "epoch": 0.3563840723733809,
471
+ "grad_norm": 1.5579940115806323e-11,
472
+ "learning_rate": 7.177732749636612e-06,
473
+ "loss": 0.0,
474
+ "step": 650
475
+ },
476
+ {
477
+ "epoch": 0.3618669042560482,
478
+ "grad_norm": 9.450333493532526e-08,
479
+ "learning_rate": 7.099849990769371e-06,
480
+ "loss": 0.0,
481
+ "step": 660
482
+ },
483
+ {
484
+ "epoch": 0.36734973613871563,
485
+ "grad_norm": 4.771372630330006e-09,
486
+ "learning_rate": 7.021343635026373e-06,
487
+ "loss": 0.0,
488
+ "step": 670
489
+ },
490
+ {
491
+ "epoch": 0.37283256802138304,
492
+ "grad_norm": 9.640462733662147e-11,
493
+ "learning_rate": 6.9422369966054856e-06,
494
+ "loss": 0.0,
495
+ "step": 680
496
+ },
497
+ {
498
+ "epoch": 0.37831539990405044,
499
+ "grad_norm": 5.622925458581562e-10,
500
+ "learning_rate": 6.862553567971782e-06,
501
+ "loss": 0.0,
502
+ "step": 690
503
+ },
504
+ {
505
+ "epoch": 0.38379823178671785,
506
+ "grad_norm": 1.4773490590591631e-12,
507
+ "learning_rate": 6.782317012880941e-06,
508
+ "loss": 0.0,
509
+ "step": 700
510
+ },
511
+ {
512
+ "epoch": 0.38928106366938525,
513
+ "grad_norm": 1.792624208796223e-11,
514
+ "learning_rate": 6.7015511593517735e-06,
515
+ "loss": 0.0,
516
+ "step": 710
517
+ },
518
+ {
519
+ "epoch": 0.39476389555205266,
520
+ "grad_norm": 1.1963580126561624e-10,
521
+ "learning_rate": 6.6202799925899595e-06,
522
+ "loss": 0.0,
523
+ "step": 720
524
+ },
525
+ {
526
+ "epoch": 0.40024672743472,
527
+ "grad_norm": 4.0963617047029555e-12,
528
+ "learning_rate": 6.5385276478651164e-06,
529
+ "loss": 0.0,
530
+ "step": 730
531
+ },
532
+ {
533
+ "epoch": 0.40024672743472,
534
+ "eval_accuracy": 1.0,
535
+ "eval_loss": 1.5134760111834566e-10,
536
+ "eval_runtime": 172.6946,
537
+ "eval_samples_per_second": 37.332,
538
+ "eval_steps_per_second": 4.667,
539
+ "step": 730
540
+ },
541
+ {
542
+ "epoch": 0.4057295593173874,
543
+ "grad_norm": 1.4070650027064868e-11,
544
+ "learning_rate": 6.456318403343291e-06,
545
+ "loss": 0.0,
546
+ "step": 740
547
+ },
548
+ {
549
+ "epoch": 0.4112123912000548,
550
+ "grad_norm": 1.0772934627700792e-10,
551
+ "learning_rate": 6.373676672877034e-06,
552
+ "loss": 0.0,
553
+ "step": 750
554
+ },
555
+ {
556
+ "epoch": 0.4166952230827222,
557
+ "grad_norm": 3.4152651817720425e-09,
558
+ "learning_rate": 6.2906269987551505e-06,
559
+ "loss": 0.0,
560
+ "step": 760
561
+ },
562
+ {
563
+ "epoch": 0.4221780549653896,
564
+ "grad_norm": 2.17619100517652e-09,
565
+ "learning_rate": 6.207194044414333e-06,
566
+ "loss": 0.0,
567
+ "step": 770
568
+ },
569
+ {
570
+ "epoch": 0.42766088684805703,
571
+ "grad_norm": 1.4359431612515072e-12,
572
+ "learning_rate": 6.123402587114811e-06,
573
+ "loss": 0.0,
574
+ "step": 780
575
+ },
576
+ {
577
+ "epoch": 0.43314371873072444,
578
+ "grad_norm": 1.1758019417048432e-13,
579
+ "learning_rate": 6.0392775105821936e-06,
580
+ "loss": 0.0,
581
+ "step": 790
582
+ },
583
+ {
584
+ "epoch": 0.43862655061339184,
585
+ "grad_norm": 2.0359106067679988e-10,
586
+ "learning_rate": 5.954843797617691e-06,
587
+ "loss": 0.0,
588
+ "step": 800
589
+ },
590
+ {
591
+ "epoch": 0.4441093824960592,
592
+ "grad_norm": 5.402939762255698e-10,
593
+ "learning_rate": 5.870126522678933e-06,
594
+ "loss": 0.0,
595
+ "step": 810
596
+ },
597
+ {
598
+ "epoch": 0.4495922143787266,
599
+ "grad_norm": 4.365914921256042e-11,
600
+ "learning_rate": 5.785150844433537e-06,
601
+ "loss": 0.0,
602
+ "step": 820
603
+ },
604
+ {
605
+ "epoch": 0.455075046261394,
606
+ "grad_norm": 6.805337001390688e-13,
607
+ "learning_rate": 5.699941998287703e-06,
608
+ "loss": 0.0,
609
+ "step": 830
610
+ },
611
+ {
612
+ "epoch": 0.4605578781440614,
613
+ "grad_norm": 2.589694138386417e-13,
614
+ "learning_rate": 5.614525288891989e-06,
615
+ "loss": 0.0,
616
+ "step": 840
617
+ },
618
+ {
619
+ "epoch": 0.4660407100267288,
620
+ "grad_norm": 2.5609280029925685e-08,
621
+ "learning_rate": 5.528926082626542e-06,
622
+ "loss": 0.0,
623
+ "step": 850
624
+ },
625
+ {
626
+ "epoch": 0.4715235419093962,
627
+ "grad_norm": 1.1285481013242893e-12,
628
+ "learning_rate": 5.443169800067987e-06,
629
+ "loss": 0.0,
630
+ "step": 860
631
+ },
632
+ {
633
+ "epoch": 0.4770063737920636,
634
+ "grad_norm": 1.6540750713556207e-10,
635
+ "learning_rate": 5.3572819084402305e-06,
636
+ "loss": 0.0,
637
+ "step": 870
638
+ },
639
+ {
640
+ "epoch": 0.482489205674731,
641
+ "grad_norm": 1.1919898401657747e-10,
642
+ "learning_rate": 5.271287914051397e-06,
643
+ "loss": 0.0,
644
+ "step": 880
645
+ },
646
+ {
647
+ "epoch": 0.4879720375573984,
648
+ "grad_norm": 2.92970747488297e-12,
649
+ "learning_rate": 5.185213354719173e-06,
650
+ "loss": 0.0,
651
+ "step": 890
652
+ },
653
+ {
654
+ "epoch": 0.4934548694400658,
655
+ "grad_norm": 2.3761615938755476e-11,
656
+ "learning_rate": 5.09908379218679e-06,
657
+ "loss": 0.0,
658
+ "step": 900
659
+ },
660
+ {
661
+ "epoch": 0.4989377013227332,
662
+ "grad_norm": 4.64755833817776e-09,
663
+ "learning_rate": 5.012924804531889e-06,
664
+ "loss": 0.0,
665
+ "step": 910
666
+ },
667
+ {
668
+ "epoch": 0.5044205332054006,
669
+ "grad_norm": 3.9917269489819773e-10,
670
+ "learning_rate": 4.926761978570556e-06,
671
+ "loss": 0.0,
672
+ "step": 920
673
+ },
674
+ {
675
+ "epoch": 0.509903365088068,
676
+ "grad_norm": 2.794019737795139e-10,
677
+ "learning_rate": 4.840620902258745e-06,
678
+ "loss": 0.0,
679
+ "step": 930
680
+ },
681
+ {
682
+ "epoch": 0.5153861969707354,
683
+ "grad_norm": 5.130761451255239e-07,
684
+ "learning_rate": 4.754527157093374e-06,
685
+ "loss": 0.0,
686
+ "step": 940
687
+ },
688
+ {
689
+ "epoch": 0.5208690288534028,
690
+ "grad_norm": 1.3340023530261647e-11,
691
+ "learning_rate": 4.668506310515325e-06,
692
+ "loss": 0.0,
693
+ "step": 950
694
+ },
695
+ {
696
+ "epoch": 0.5263518607360702,
697
+ "grad_norm": 1.227000584469451e-10,
698
+ "learning_rate": 4.582583908316639e-06,
699
+ "loss": 0.0,
700
+ "step": 960
701
+ },
702
+ {
703
+ "epoch": 0.5318346926187376,
704
+ "grad_norm": 1.3804829675223562e-12,
705
+ "learning_rate": 4.496785467054119e-06,
706
+ "loss": 0.0,
707
+ "step": 970
708
+ },
709
+ {
710
+ "epoch": 0.537317524501405,
711
+ "grad_norm": 1.4683420495112398e-12,
712
+ "learning_rate": 4.411136466471628e-06,
713
+ "loss": 0.0,
714
+ "step": 980
715
+ },
716
+ {
717
+ "epoch": 0.5428003563840724,
718
+ "grad_norm": 1.9661270389548235e-09,
719
+ "learning_rate": 4.325662341933316e-06,
720
+ "loss": 0.0,
721
+ "step": 990
722
+ },
723
+ {
724
+ "epoch": 0.5482831882667397,
725
+ "grad_norm": 2.592374981347234e-09,
726
+ "learning_rate": 4.240388476870025e-06,
727
+ "loss": 0.0,
728
+ "step": 1000
729
+ },
730
+ {
731
+ "epoch": 0.5537660201494071,
732
+ "grad_norm": 1.8693929054475894e-13,
733
+ "learning_rate": 4.155340195241118e-06,
734
+ "loss": 0.0,
735
+ "step": 1010
736
+ },
737
+ {
738
+ "epoch": 0.5592488520320745,
739
+ "grad_norm": 2.1399457761361873e-09,
740
+ "learning_rate": 4.070542754013973e-06,
741
+ "loss": 0.0,
742
+ "step": 1020
743
+ },
744
+ {
745
+ "epoch": 0.5647316839147419,
746
+ "grad_norm": 8.234736781354002e-10,
747
+ "learning_rate": 3.98602133566336e-06,
748
+ "loss": 0.0,
749
+ "step": 1030
750
+ },
751
+ {
752
+ "epoch": 0.5702145157974093,
753
+ "grad_norm": 6.851032761934217e-12,
754
+ "learning_rate": 3.901801040692963e-06,
755
+ "loss": 0.0,
756
+ "step": 1040
757
+ },
758
+ {
759
+ "epoch": 0.5756973476800767,
760
+ "grad_norm": 2.0872885364564553e-10,
761
+ "learning_rate": 3.817906880181213e-06,
762
+ "loss": 0.0,
763
+ "step": 1050
764
+ },
765
+ {
766
+ "epoch": 0.5811801795627441,
767
+ "grad_norm": 4.878079717940409e-09,
768
+ "learning_rate": 3.734363768353707e-06,
769
+ "loss": 0.0,
770
+ "step": 1060
771
+ },
772
+ {
773
+ "epoch": 0.5866630114454116,
774
+ "grad_norm": 1.1738454652743258e-10,
775
+ "learning_rate": 3.6511965151843754e-06,
776
+ "loss": 0.0,
777
+ "step": 1070
778
+ },
779
+ {
780
+ "epoch": 0.592145843328079,
781
+ "grad_norm": 1.119752957023934e-09,
782
+ "learning_rate": 3.568429819027609e-06,
783
+ "loss": 0.0,
784
+ "step": 1080
785
+ },
786
+ {
787
+ "epoch": 0.5976286752107464,
788
+ "grad_norm": 8.4299603031468e-07,
789
+ "learning_rate": 3.4860882592835386e-06,
790
+ "loss": 0.0,
791
+ "step": 1090
792
+ },
793
+ {
794
+ "epoch": 0.6003700911520801,
795
+ "eval_accuracy": 1.0,
796
+ "eval_loss": 1.301232038786182e-10,
797
+ "eval_runtime": 170.5676,
798
+ "eval_samples_per_second": 37.797,
799
+ "eval_steps_per_second": 4.725,
800
+ "step": 1095
801
+ },
802
+ {
803
+ "epoch": 0.6031115070934138,
804
+ "grad_norm": 2.746873475206746e-12,
805
+ "learning_rate": 3.4041962890986395e-06,
806
+ "loss": 0.0,
807
+ "step": 1100
808
+ },
809
+ {
810
+ "epoch": 0.6085943389760812,
811
+ "grad_norm": 6.488060089182568e-12,
812
+ "learning_rate": 3.3227782281038322e-06,
813
+ "loss": 0.0,
814
+ "step": 1110
815
+ },
816
+ {
817
+ "epoch": 0.6140771708587486,
818
+ "grad_norm": 2.261536069525505e-09,
819
+ "learning_rate": 3.2418582551922207e-06,
820
+ "loss": 0.0,
821
+ "step": 1120
822
+ },
823
+ {
824
+ "epoch": 0.619560002741416,
825
+ "grad_norm": 8.609309931628673e-10,
826
+ "learning_rate": 3.161460401338644e-06,
827
+ "loss": 0.0,
828
+ "step": 1130
829
+ },
830
+ {
831
+ "epoch": 0.6250428346240834,
832
+ "grad_norm": 1.8204505611296717e-11,
833
+ "learning_rate": 3.0816085424631446e-06,
834
+ "loss": 0.0,
835
+ "step": 1140
836
+ },
837
+ {
838
+ "epoch": 0.6305256665067507,
839
+ "grad_norm": 3.812865648211705e-11,
840
+ "learning_rate": 3.002326392340486e-06,
841
+ "loss": 0.0,
842
+ "step": 1150
843
+ },
844
+ {
845
+ "epoch": 0.6360084983894181,
846
+ "grad_norm": 3.348888278232459e-13,
847
+ "learning_rate": 2.9236374955578216e-06,
848
+ "loss": 0.0,
849
+ "step": 1160
850
+ },
851
+ {
852
+ "epoch": 0.6414913302720855,
853
+ "grad_norm": 9.471730777477205e-08,
854
+ "learning_rate": 2.8455652205226146e-06,
855
+ "loss": 0.0,
856
+ "step": 1170
857
+ },
858
+ {
859
+ "epoch": 0.6469741621547529,
860
+ "grad_norm": 1.2743735103640241e-12,
861
+ "learning_rate": 2.7681327525228633e-06,
862
+ "loss": 0.0,
863
+ "step": 1180
864
+ },
865
+ {
866
+ "epoch": 0.6524569940374203,
867
+ "grad_norm": 1.312070541104049e-08,
868
+ "learning_rate": 2.6913630868417275e-06,
869
+ "loss": 0.0,
870
+ "step": 1190
871
+ },
872
+ {
873
+ "epoch": 0.6579398259200877,
874
+ "grad_norm": 1.1591673801381042e-11,
875
+ "learning_rate": 2.615279021928564e-06,
876
+ "loss": 0.0,
877
+ "step": 1200
878
+ },
879
+ {
880
+ "epoch": 0.6634226578027551,
881
+ "grad_norm": 1.2137901794773143e-10,
882
+ "learning_rate": 2.539903152628423e-06,
883
+ "loss": 0.0,
884
+ "step": 1210
885
+ },
886
+ {
887
+ "epoch": 0.6689054896854225,
888
+ "grad_norm": 2.375248886465897e-10,
889
+ "learning_rate": 2.4652578634720147e-06,
890
+ "loss": 0.0,
891
+ "step": 1220
892
+ },
893
+ {
894
+ "epoch": 0.6743883215680899,
895
+ "grad_norm": 1.3065516446530978e-09,
896
+ "learning_rate": 2.3913653220281256e-06,
897
+ "loss": 0.0,
898
+ "step": 1230
899
+ },
900
+ {
901
+ "epoch": 0.6798711534507573,
902
+ "grad_norm": 1.0660168060783182e-11,
903
+ "learning_rate": 2.3182474723204634e-06,
904
+ "loss": 0.0003,
905
+ "step": 1240
906
+ },
907
+ {
908
+ "epoch": 0.6853539853334247,
909
+ "grad_norm": 1.7096091209367614e-09,
910
+ "learning_rate": 2.2459260283109025e-06,
911
+ "loss": 0.0,
912
+ "step": 1250
913
+ },
914
+ {
915
+ "epoch": 0.6908368172160921,
916
+ "grad_norm": 1.6090853094397062e-08,
917
+ "learning_rate": 2.1744224674510384e-06,
918
+ "loss": 0.0,
919
+ "step": 1260
920
+ },
921
+ {
922
+ "epoch": 0.6963196490987595,
923
+ "grad_norm": 3.779675683546202e-09,
924
+ "learning_rate": 2.1037580243039864e-06,
925
+ "loss": 0.0,
926
+ "step": 1270
927
+ },
928
+ {
929
+ "epoch": 0.701802480981427,
930
+ "grad_norm": 8.770736137364565e-09,
931
+ "learning_rate": 2.0339536842383013e-06,
932
+ "loss": 0.0,
933
+ "step": 1280
934
+ },
935
+ {
936
+ "epoch": 0.7072853128640944,
937
+ "grad_norm": 7.484961095372e-09,
938
+ "learning_rate": 1.9650301771959203e-06,
939
+ "loss": 0.0,
940
+ "step": 1290
941
+ },
942
+ {
943
+ "epoch": 0.7127681447467618,
944
+ "grad_norm": 1.883010858350076e-09,
945
+ "learning_rate": 1.8970079715359358e-06,
946
+ "loss": 0.0,
947
+ "step": 1300
948
+ },
949
+ {
950
+ "epoch": 0.718250976629429,
951
+ "grad_norm": 1.3645068408507655e-09,
952
+ "learning_rate": 1.8299072679560764e-06,
953
+ "loss": 0.0,
954
+ "step": 1310
955
+ },
956
+ {
957
+ "epoch": 0.7237338085120965,
958
+ "grad_norm": 7.935481605159111e-09,
959
+ "learning_rate": 1.7637479934936492e-06,
960
+ "loss": 0.0,
961
+ "step": 1320
962
+ },
963
+ {
964
+ "epoch": 0.7292166403947639,
965
+ "grad_norm": 3.995001662815412e-09,
966
+ "learning_rate": 1.698549795607779e-06,
967
+ "loss": 0.0,
968
+ "step": 1330
969
+ },
970
+ {
971
+ "epoch": 0.7346994722774313,
972
+ "grad_norm": 3.9588501921095087e-10,
973
+ "learning_rate": 1.634332036344652e-06,
974
+ "loss": 0.0,
975
+ "step": 1340
976
+ },
977
+ {
978
+ "epoch": 0.7401823041600987,
979
+ "grad_norm": 7.819238589945599e-08,
980
+ "learning_rate": 1.571113786587531e-06,
981
+ "loss": 0.0,
982
+ "step": 1350
983
+ },
984
+ {
985
+ "epoch": 0.7456651360427661,
986
+ "grad_norm": 6.14655548680787e-10,
987
+ "learning_rate": 1.508913820393238e-06,
988
+ "loss": 0.0,
989
+ "step": 1360
990
+ },
991
+ {
992
+ "epoch": 0.7511479679254335,
993
+ "grad_norm": 8.140911234022497e-08,
994
+ "learning_rate": 1.4477506094167743e-06,
995
+ "loss": 0.0,
996
+ "step": 1370
997
+ },
998
+ {
999
+ "epoch": 0.7566307998081009,
1000
+ "grad_norm": 5.628587596007151e-10,
1001
+ "learning_rate": 1.387642317425766e-06,
1002
+ "loss": 0.0,
1003
+ "step": 1380
1004
+ },
1005
+ {
1006
+ "epoch": 0.7621136316907683,
1007
+ "grad_norm": 9.740036555072606e-11,
1008
+ "learning_rate": 1.328606794906319e-06,
1009
+ "loss": 0.0,
1010
+ "step": 1390
1011
+ },
1012
+ {
1013
+ "epoch": 0.7675964635734357,
1014
+ "grad_norm": 1.1645804676163607e-07,
1015
+ "learning_rate": 1.270661573761936e-06,
1016
+ "loss": 0.0,
1017
+ "step": 1400
1018
+ },
1019
+ {
1020
+ "epoch": 0.7730792954561031,
1021
+ "grad_norm": 7.708293447983294e-10,
1022
+ "learning_rate": 1.2138238621070187e-06,
1023
+ "loss": 0.0,
1024
+ "step": 1410
1025
+ },
1026
+ {
1027
+ "epoch": 0.7785621273387705,
1028
+ "grad_norm": 3.555227889862067e-09,
1029
+ "learning_rate": 1.1581105391565456e-06,
1030
+ "loss": 0.0,
1031
+ "step": 1420
1032
+ },
1033
+ {
1034
+ "epoch": 0.7840449592214379,
1035
+ "grad_norm": 5.142852810280374e-09,
1036
+ "learning_rate": 1.1035381502134085e-06,
1037
+ "loss": 0.0,
1038
+ "step": 1430
1039
+ },
1040
+ {
1041
+ "epoch": 0.7895277911041053,
1042
+ "grad_norm": 2.3604476706573507e-10,
1043
+ "learning_rate": 1.0501229017549264e-06,
1044
+ "loss": 0.0,
1045
+ "step": 1440
1046
+ },
1047
+ {
1048
+ "epoch": 0.7950106229867727,
1049
+ "grad_norm": 5.834436822560463e-10,
1050
+ "learning_rate": 9.978806566199721e-07,
1051
+ "loss": 0.0,
1052
+ "step": 1450
1053
+ },
1054
+ {
1055
+ "epoch": 0.80049345486944,
1056
+ "grad_norm": 5.675169778562861e-10,
1057
+ "learning_rate": 9.468269292981458e-07,
1058
+ "loss": 0.0,
1059
+ "step": 1460
1060
+ },
1061
+ {
1062
+ "epoch": 0.80049345486944,
1063
+ "eval_accuracy": 1.0,
1064
+ "eval_loss": 2.4157550959635898e-11,
1065
+ "eval_runtime": 172.6444,
1066
+ "eval_samples_per_second": 37.343,
1067
+ "eval_steps_per_second": 4.669,
1068
+ "step": 1460
1069
+ },
1070
+ {
1071
+ "epoch": 0.8059762867521074,
1072
+ "grad_norm": 6.742395974868032e-09,
1073
+ "learning_rate": 8.969768813224128e-07,
1074
+ "loss": 0.0,
1075
+ "step": 1470
1076
+ },
1077
+ {
1078
+ "epoch": 0.8114591186347748,
1079
+ "grad_norm": 1.1905292029990022e-10,
1080
+ "learning_rate": 8.483453167665412e-07,
1081
+ "loss": 0.0,
1082
+ "step": 1480
1083
+ },
1084
+ {
1085
+ "epoch": 0.8169419505174422,
1086
+ "grad_norm": 2.7659869950014127e-09,
1087
+ "learning_rate": 8.009466778487207e-07,
1088
+ "loss": 0.0,
1089
+ "step": 1490
1090
+ },
1091
+ {
1092
+ "epoch": 0.8224247824001096,
1093
+ "grad_norm": 4.819477705808595e-09,
1094
+ "learning_rate": 7.547950406426069e-07,
1095
+ "loss": 0.0,
1096
+ "step": 1500
1097
+ },
1098
+ {
1099
+ "epoch": 0.827907614282777,
1100
+ "grad_norm": 4.073986925590134e-09,
1101
+ "learning_rate": 7.099041108971366e-07,
1102
+ "loss": 0.0,
1103
+ "step": 1510
1104
+ },
1105
+ {
1106
+ "epoch": 0.8333904461654444,
1107
+ "grad_norm": 1.316788900140864e-09,
1108
+ "learning_rate": 6.662872199662901e-07,
1109
+ "loss": 0.0,
1110
+ "step": 1520
1111
+ },
1112
+ {
1113
+ "epoch": 0.8388732780481118,
1114
+ "grad_norm": 1.0290546192948113e-09,
1115
+ "learning_rate": 6.239573208500626e-07,
1116
+ "loss": 0.0,
1117
+ "step": 1530
1118
+ },
1119
+ {
1120
+ "epoch": 0.8443561099307793,
1121
+ "grad_norm": 1.4087077282454175e-08,
1122
+ "learning_rate": 5.829269843477736e-07,
1123
+ "loss": 0.0,
1124
+ "step": 1540
1125
+ },
1126
+ {
1127
+ "epoch": 0.8498389418134467,
1128
+ "grad_norm": 4.590867408449384e-10,
1129
+ "learning_rate": 5.432083953248984e-07,
1130
+ "loss": 0.0,
1131
+ "step": 1550
1132
+ },
1133
+ {
1134
+ "epoch": 0.8553217736961141,
1135
+ "grad_norm": 3.087105682197944e-08,
1136
+ "learning_rate": 5.048133490944995e-07,
1137
+ "loss": 0.0,
1138
+ "step": 1560
1139
+ },
1140
+ {
1141
+ "epoch": 0.8608046055787815,
1142
+ "grad_norm": 3.0670661566034596e-09,
1143
+ "learning_rate": 4.6775324791434704e-07,
1144
+ "loss": 0.0,
1145
+ "step": 1570
1146
+ },
1147
+ {
1148
+ "epoch": 0.8662874374614489,
1149
+ "grad_norm": 3.477520937877898e-09,
1150
+ "learning_rate": 4.320390976007677e-07,
1151
+ "loss": 0.0,
1152
+ "step": 1580
1153
+ },
1154
+ {
1155
+ "epoch": 0.8717702693441163,
1156
+ "grad_norm": 1.1442693320651287e-10,
1157
+ "learning_rate": 3.976815042602211e-07,
1158
+ "loss": 0.0,
1159
+ "step": 1590
1160
+ },
1161
+ {
1162
+ "epoch": 0.8772531012267837,
1163
+ "grad_norm": 4.2184575832493465e-09,
1164
+ "learning_rate": 3.646906711395898e-07,
1165
+ "loss": 0.0,
1166
+ "step": 1600
1167
+ },
1168
+ {
1169
+ "epoch": 0.882735933109451,
1170
+ "grad_norm": 5.359482857514308e-10,
1171
+ "learning_rate": 3.3307639559608807e-07,
1172
+ "loss": 0.0,
1173
+ "step": 1610
1174
+ },
1175
+ {
1176
+ "epoch": 0.8882187649921184,
1177
+ "grad_norm": 3.928372627193255e-10,
1178
+ "learning_rate": 3.02848066187732e-07,
1179
+ "loss": 0.0,
1180
+ "step": 1620
1181
+ },
1182
+ {
1183
+ "epoch": 0.8937015968747858,
1184
+ "grad_norm": 8.331213763312917e-08,
1185
+ "learning_rate": 2.7401465988518894e-07,
1186
+ "loss": 0.0,
1187
+ "step": 1630
1188
+ },
1189
+ {
1190
+ "epoch": 0.8991844287574532,
1191
+ "grad_norm": 9.844909776290933e-09,
1192
+ "learning_rate": 2.465847394058779e-07,
1193
+ "loss": 0.0,
1194
+ "step": 1640
1195
+ },
1196
+ {
1197
+ "epoch": 0.9046672606401206,
1198
+ "grad_norm": 2.0618541596295614e-10,
1199
+ "learning_rate": 2.2056645067107197e-07,
1200
+ "loss": 0.0,
1201
+ "step": 1650
1202
+ },
1203
+ {
1204
+ "epoch": 0.910150092522788,
1205
+ "grad_norm": 8.006903473578575e-10,
1206
+ "learning_rate": 1.9596752038679223e-07,
1207
+ "loss": 0.0,
1208
+ "step": 1660
1209
+ },
1210
+ {
1211
+ "epoch": 0.9156329244054554,
1212
+ "grad_norm": 3.338698761901071e-10,
1213
+ "learning_rate": 1.727952537491917e-07,
1214
+ "loss": 0.0,
1215
+ "step": 1670
1216
+ },
1217
+ {
1218
+ "epoch": 0.9211157562881228,
1219
+ "grad_norm": 2.3249064895480842e-09,
1220
+ "learning_rate": 1.5105653227511286e-07,
1221
+ "loss": 0.0,
1222
+ "step": 1680
1223
+ },
1224
+ {
1225
+ "epoch": 0.9265985881707902,
1226
+ "grad_norm": 2.8821448339044764e-08,
1227
+ "learning_rate": 1.307578117584707e-07,
1228
+ "loss": 0.0,
1229
+ "step": 1690
1230
+ },
1231
+ {
1232
+ "epoch": 0.9320814200534576,
1233
+ "grad_norm": 1.7130765694872707e-09,
1234
+ "learning_rate": 1.1190512035306356e-07,
1235
+ "loss": 0.0,
1236
+ "step": 1700
1237
+ },
1238
+ {
1239
+ "epoch": 0.937564251936125,
1240
+ "grad_norm": 1.5305934297771273e-09,
1241
+ "learning_rate": 9.450405678237685e-08,
1242
+ "loss": 0.0,
1243
+ "step": 1710
1244
+ },
1245
+ {
1246
+ "epoch": 0.9430470838187924,
1247
+ "grad_norm": 2.3416841798962196e-09,
1248
+ "learning_rate": 7.85597886769196e-08,
1249
+ "loss": 0.0,
1250
+ "step": 1720
1251
+ },
1252
+ {
1253
+ "epoch": 0.9485299157014598,
1254
+ "grad_norm": 2.2962311163610138e-07,
1255
+ "learning_rate": 6.407705103958383e-08,
1256
+ "loss": 0.0,
1257
+ "step": 1730
1258
+ },
1259
+ {
1260
+ "epoch": 0.9540127475841272,
1261
+ "grad_norm": 3.0744815027183847e-10,
1262
+ "learning_rate": 5.106014483947708e-08,
1263
+ "loss": 0.0,
1264
+ "step": 1740
1265
+ },
1266
+ {
1267
+ "epoch": 0.9594955794667946,
1268
+ "grad_norm": 1.7505968896713853e-09,
1269
+ "learning_rate": 3.951293573465853e-08,
1270
+ "loss": 0.0,
1271
+ "step": 1750
1272
+ },
1273
+ {
1274
+ "epoch": 0.964978411349462,
1275
+ "grad_norm": 4.694804614513437e-11,
1276
+ "learning_rate": 2.9438852924142948e-08,
1277
+ "loss": 0.0,
1278
+ "step": 1760
1279
+ },
1280
+ {
1281
+ "epoch": 0.9704612432321293,
1282
+ "grad_norm": 2.355823869315543e-10,
1283
+ "learning_rate": 2.0840888129528002e-08,
1284
+ "loss": 0.0,
1285
+ "step": 1770
1286
+ },
1287
+ {
1288
+ "epoch": 0.9759440751147967,
1289
+ "grad_norm": 1.5761986160711672e-10,
1290
+ "learning_rate": 1.3721594706532226e-08,
1291
+ "loss": 0.0,
1292
+ "step": 1780
1293
+ },
1294
+ {
1295
+ "epoch": 0.9814269069974642,
1296
+ "grad_norm": 3.816250093713336e-10,
1297
+ "learning_rate": 8.083086886722658e-09,
1298
+ "loss": 0.0,
1299
+ "step": 1790
1300
+ },
1301
+ {
1302
+ "epoch": 0.9869097388801316,
1303
+ "grad_norm": 5.1638181730595534e-08,
1304
+ "learning_rate": 3.9270391496459835e-09,
1305
+ "loss": 0.0,
1306
+ "step": 1800
1307
+ },
1308
+ {
1309
+ "epoch": 0.992392570762799,
1310
+ "grad_norm": 2.3921026937046008e-08,
1311
+ "learning_rate": 1.2546857255546496e-09,
1312
+ "loss": 0.0,
1313
+ "step": 1810
1314
+ },
1315
+ {
1316
+ "epoch": 0.9978754026454664,
1317
+ "grad_norm": 1.7885470882106347e-08,
1318
+ "learning_rate": 6.682022887505302e-11,
1319
+ "loss": 0.0,
1320
+ "step": 1820
1321
+ }
1322
+ ],
1323
+ "logging_steps": 10,
1324
+ "max_steps": 1823,
1325
+ "num_input_tokens_seen": 0,
1326
+ "num_train_epochs": 1,
1327
+ "save_steps": 365,
1328
+ "stateful_callbacks": {
1329
+ "TrainerControl": {
1330
+ "args": {
1331
+ "should_epoch_stop": false,
1332
+ "should_evaluate": false,
1333
+ "should_log": false,
1334
+ "should_save": true,
1335
+ "should_training_stop": true
1336
+ },
1337
+ "attributes": {}
1338
+ }
1339
+ },
1340
+ "total_flos": 0.0,
1341
+ "train_batch_size": 8,
1342
+ "trial_name": null,
1343
+ "trial_params": null
1344
+ }
checkpoint-1823/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:926a7444a45d48efd4563a99c4488539f509a3f974643781d5e8dfc252c071a0
3
+ size 5624