SyedA5688 commited on
Commit
b896d4b
1 Parent(s): 4687be9

initial commit

Browse files
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-410m",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 0,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 1024,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 4096,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 4096,
18
+ "model_type": "gpt_neox",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_layers": 24,
21
+ "rope_scaling": null,
22
+ "rotary_emb_base": 10000,
23
+ "rotary_pct": 0.25,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.41.0",
27
+ "use_cache": false,
28
+ "use_parallel_residual": true,
29
+ "vocab_size": 50304
30
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.41.0",
6
+ "use_cache": false
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f577cb1e096bd60402864246a00ab4c134732c86c1fea778f75b25e22005de34
3
+ size 1621370224
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2455962b40b4d11fc51a4a05cd856f8de69d57ee9739b17e08471d4403b6dd9
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33817259d0fe142b1457dacebf6aeed9e5ee493ae600ebf9ed24a8d94a22bf61
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,214 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 1000000000000000019884624838656,
211
+ "pad_token": "<|endoftext|>",
212
+ "tokenizer_class": "GPTNeoXTokenizer",
213
+ "unk_token": "<|endoftext|>"
214
+ }
trainer_state.json ADDED
@@ -0,0 +1,1083 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.805204153060913,
3
+ "best_model_checkpoint": "/home/sr2464/scratch/C2S_Files/C2S_training_runs/multicell_v2_pretraining_runs/finetuning-EleutherAI/pythia-410m-multicell_v2_pretraining-2024-07-28_14-10-44/checkpoint-7000",
4
+ "epoch": 0.024296135179068302,
5
+ "eval_steps": 100,
6
+ "global_step": 7000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.00034708764541526143,
13
+ "grad_norm": 12.638826370239258,
14
+ "learning_rate": 3.470776065528252e-07,
15
+ "loss": 4.1006,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.00034708764541526143,
20
+ "eval_loss": 3.750605821609497,
21
+ "eval_runtime": 28.5808,
22
+ "eval_samples_per_second": 16.69,
23
+ "eval_steps_per_second": 0.35,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.0006941752908305229,
28
+ "grad_norm": 7.417098522186279,
29
+ "learning_rate": 6.941552131056504e-07,
30
+ "loss": 3.4941,
31
+ "step": 200
32
+ },
33
+ {
34
+ "epoch": 0.0006941752908305229,
35
+ "eval_loss": 3.152513265609741,
36
+ "eval_runtime": 27.3056,
37
+ "eval_samples_per_second": 17.469,
38
+ "eval_steps_per_second": 0.366,
39
+ "step": 200
40
+ },
41
+ {
42
+ "epoch": 0.0010412629362457843,
43
+ "grad_norm": 5.065331935882568,
44
+ "learning_rate": 1.0412328196584756e-06,
45
+ "loss": 3.0197,
46
+ "step": 300
47
+ },
48
+ {
49
+ "epoch": 0.0010412629362457843,
50
+ "eval_loss": 2.8438754081726074,
51
+ "eval_runtime": 27.3207,
52
+ "eval_samples_per_second": 17.459,
53
+ "eval_steps_per_second": 0.366,
54
+ "step": 300
55
+ },
56
+ {
57
+ "epoch": 0.0013883505816610457,
58
+ "grad_norm": 5.113323211669922,
59
+ "learning_rate": 1.3883104262113009e-06,
60
+ "loss": 2.7915,
61
+ "step": 400
62
+ },
63
+ {
64
+ "epoch": 0.0013883505816610457,
65
+ "eval_loss": 2.6905336380004883,
66
+ "eval_runtime": 27.6367,
67
+ "eval_samples_per_second": 17.26,
68
+ "eval_steps_per_second": 0.362,
69
+ "step": 400
70
+ },
71
+ {
72
+ "epoch": 0.0017354382270763071,
73
+ "grad_norm": 6.473913192749023,
74
+ "learning_rate": 1.7353880327641261e-06,
75
+ "loss": 2.6697,
76
+ "step": 500
77
+ },
78
+ {
79
+ "epoch": 0.0017354382270763071,
80
+ "eval_loss": 2.609987735748291,
81
+ "eval_runtime": 27.5233,
82
+ "eval_samples_per_second": 17.331,
83
+ "eval_steps_per_second": 0.363,
84
+ "step": 500
85
+ },
86
+ {
87
+ "epoch": 0.0020825258724915686,
88
+ "grad_norm": 6.615407466888428,
89
+ "learning_rate": 2.082465639316951e-06,
90
+ "loss": 2.5959,
91
+ "step": 600
92
+ },
93
+ {
94
+ "epoch": 0.0020825258724915686,
95
+ "eval_loss": 2.5381109714508057,
96
+ "eval_runtime": 27.411,
97
+ "eval_samples_per_second": 17.402,
98
+ "eval_steps_per_second": 0.365,
99
+ "step": 600
100
+ },
101
+ {
102
+ "epoch": 0.00242961351790683,
103
+ "grad_norm": 8.234296798706055,
104
+ "learning_rate": 2.429543245869777e-06,
105
+ "loss": 2.5239,
106
+ "step": 700
107
+ },
108
+ {
109
+ "epoch": 0.00242961351790683,
110
+ "eval_loss": 2.4786229133605957,
111
+ "eval_runtime": 27.9876,
112
+ "eval_samples_per_second": 17.043,
113
+ "eval_steps_per_second": 0.357,
114
+ "step": 700
115
+ },
116
+ {
117
+ "epoch": 0.0027767011633220914,
118
+ "grad_norm": 3.987603187561035,
119
+ "learning_rate": 2.7766208524226017e-06,
120
+ "loss": 2.4544,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 0.0027767011633220914,
125
+ "eval_loss": 2.4083495140075684,
126
+ "eval_runtime": 27.5819,
127
+ "eval_samples_per_second": 17.294,
128
+ "eval_steps_per_second": 0.363,
129
+ "step": 800
130
+ },
131
+ {
132
+ "epoch": 0.003123788808737353,
133
+ "grad_norm": 3.854851484298706,
134
+ "learning_rate": 3.123698458975427e-06,
135
+ "loss": 2.3861,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.003123788808737353,
140
+ "eval_loss": 2.336987257003784,
141
+ "eval_runtime": 27.6168,
142
+ "eval_samples_per_second": 17.272,
143
+ "eval_steps_per_second": 0.362,
144
+ "step": 900
145
+ },
146
+ {
147
+ "epoch": 0.0034708764541526143,
148
+ "grad_norm": 3.7287888526916504,
149
+ "learning_rate": 3.4707760655282523e-06,
150
+ "loss": 2.3199,
151
+ "step": 1000
152
+ },
153
+ {
154
+ "epoch": 0.0034708764541526143,
155
+ "eval_loss": 2.2719526290893555,
156
+ "eval_runtime": 26.9345,
157
+ "eval_samples_per_second": 17.71,
158
+ "eval_steps_per_second": 0.371,
159
+ "step": 1000
160
+ },
161
+ {
162
+ "epoch": 0.0038179640995678757,
163
+ "grad_norm": 3.5708882808685303,
164
+ "learning_rate": 3.817853672081077e-06,
165
+ "loss": 2.2467,
166
+ "step": 1100
167
+ },
168
+ {
169
+ "epoch": 0.0038179640995678757,
170
+ "eval_loss": 2.206721067428589,
171
+ "eval_runtime": 27.0387,
172
+ "eval_samples_per_second": 17.641,
173
+ "eval_steps_per_second": 0.37,
174
+ "step": 1100
175
+ },
176
+ {
177
+ "epoch": 0.004165051744983137,
178
+ "grad_norm": 3.284808397293091,
179
+ "learning_rate": 4.164931278633902e-06,
180
+ "loss": 2.2017,
181
+ "step": 1200
182
+ },
183
+ {
184
+ "epoch": 0.004165051744983137,
185
+ "eval_loss": 2.1687662601470947,
186
+ "eval_runtime": 26.9942,
187
+ "eval_samples_per_second": 17.67,
188
+ "eval_steps_per_second": 0.37,
189
+ "step": 1200
190
+ },
191
+ {
192
+ "epoch": 0.004512139390398399,
193
+ "grad_norm": 3.306734323501587,
194
+ "learning_rate": 4.5120088851867285e-06,
195
+ "loss": 2.1612,
196
+ "step": 1300
197
+ },
198
+ {
199
+ "epoch": 0.004512139390398399,
200
+ "eval_loss": 2.129286766052246,
201
+ "eval_runtime": 27.1243,
202
+ "eval_samples_per_second": 17.586,
203
+ "eval_steps_per_second": 0.369,
204
+ "step": 1300
205
+ },
206
+ {
207
+ "epoch": 0.00485922703581366,
208
+ "grad_norm": 4.48453950881958,
209
+ "learning_rate": 4.859086491739554e-06,
210
+ "loss": 2.1302,
211
+ "step": 1400
212
+ },
213
+ {
214
+ "epoch": 0.00485922703581366,
215
+ "eval_loss": 2.1066970825195312,
216
+ "eval_runtime": 26.7667,
217
+ "eval_samples_per_second": 17.821,
218
+ "eval_steps_per_second": 0.374,
219
+ "step": 1400
220
+ },
221
+ {
222
+ "epoch": 0.0052063146812289214,
223
+ "grad_norm": 3.936067819595337,
224
+ "learning_rate": 5.206164098292378e-06,
225
+ "loss": 2.1019,
226
+ "step": 1500
227
+ },
228
+ {
229
+ "epoch": 0.0052063146812289214,
230
+ "eval_loss": 2.079268217086792,
231
+ "eval_runtime": 26.9038,
232
+ "eval_samples_per_second": 17.73,
233
+ "eval_steps_per_second": 0.372,
234
+ "step": 1500
235
+ },
236
+ {
237
+ "epoch": 0.005553402326644183,
238
+ "grad_norm": 3.049617290496826,
239
+ "learning_rate": 5.5532417048452035e-06,
240
+ "loss": 2.0839,
241
+ "step": 1600
242
+ },
243
+ {
244
+ "epoch": 0.005553402326644183,
245
+ "eval_loss": 2.063786268234253,
246
+ "eval_runtime": 26.8676,
247
+ "eval_samples_per_second": 17.754,
248
+ "eval_steps_per_second": 0.372,
249
+ "step": 1600
250
+ },
251
+ {
252
+ "epoch": 0.005900489972059444,
253
+ "grad_norm": 2.732224464416504,
254
+ "learning_rate": 5.900319311398029e-06,
255
+ "loss": 2.0707,
256
+ "step": 1700
257
+ },
258
+ {
259
+ "epoch": 0.005900489972059444,
260
+ "eval_loss": 2.046088695526123,
261
+ "eval_runtime": 26.9915,
262
+ "eval_samples_per_second": 17.672,
263
+ "eval_steps_per_second": 0.37,
264
+ "step": 1700
265
+ },
266
+ {
267
+ "epoch": 0.006247577617474706,
268
+ "grad_norm": 2.1865687370300293,
269
+ "learning_rate": 6.247396917950854e-06,
270
+ "loss": 2.0527,
271
+ "step": 1800
272
+ },
273
+ {
274
+ "epoch": 0.006247577617474706,
275
+ "eval_loss": 2.031470537185669,
276
+ "eval_runtime": 26.9114,
277
+ "eval_samples_per_second": 17.725,
278
+ "eval_steps_per_second": 0.372,
279
+ "step": 1800
280
+ },
281
+ {
282
+ "epoch": 0.006594665262889967,
283
+ "grad_norm": 2.854724407196045,
284
+ "learning_rate": 6.59447452450368e-06,
285
+ "loss": 2.0407,
286
+ "step": 1900
287
+ },
288
+ {
289
+ "epoch": 0.006594665262889967,
290
+ "eval_loss": 2.0221400260925293,
291
+ "eval_runtime": 26.7594,
292
+ "eval_samples_per_second": 17.825,
293
+ "eval_steps_per_second": 0.374,
294
+ "step": 1900
295
+ },
296
+ {
297
+ "epoch": 0.006941752908305229,
298
+ "grad_norm": 2.716592788696289,
299
+ "learning_rate": 6.9415521310565046e-06,
300
+ "loss": 2.0369,
301
+ "step": 2000
302
+ },
303
+ {
304
+ "epoch": 0.006941752908305229,
305
+ "eval_loss": 2.0095324516296387,
306
+ "eval_runtime": 26.7666,
307
+ "eval_samples_per_second": 17.821,
308
+ "eval_steps_per_second": 0.374,
309
+ "step": 2000
310
+ },
311
+ {
312
+ "epoch": 0.00728884055372049,
313
+ "grad_norm": 3.099235773086548,
314
+ "learning_rate": 7.28862973760933e-06,
315
+ "loss": 2.0172,
316
+ "step": 2100
317
+ },
318
+ {
319
+ "epoch": 0.00728884055372049,
320
+ "eval_loss": 1.9926340579986572,
321
+ "eval_runtime": 26.7511,
322
+ "eval_samples_per_second": 17.831,
323
+ "eval_steps_per_second": 0.374,
324
+ "step": 2100
325
+ },
326
+ {
327
+ "epoch": 0.0076359281991357515,
328
+ "grad_norm": 2.7901623249053955,
329
+ "learning_rate": 7.635707344162154e-06,
330
+ "loss": 2.0011,
331
+ "step": 2200
332
+ },
333
+ {
334
+ "epoch": 0.0076359281991357515,
335
+ "eval_loss": 1.9787664413452148,
336
+ "eval_runtime": 26.8686,
337
+ "eval_samples_per_second": 17.753,
338
+ "eval_steps_per_second": 0.372,
339
+ "step": 2200
340
+ },
341
+ {
342
+ "epoch": 0.007983015844551014,
343
+ "grad_norm": 1.9205849170684814,
344
+ "learning_rate": 7.982784950714981e-06,
345
+ "loss": 1.9848,
346
+ "step": 2300
347
+ },
348
+ {
349
+ "epoch": 0.007983015844551014,
350
+ "eval_loss": 1.9650758504867554,
351
+ "eval_runtime": 26.6567,
352
+ "eval_samples_per_second": 17.894,
353
+ "eval_steps_per_second": 0.375,
354
+ "step": 2300
355
+ },
356
+ {
357
+ "epoch": 0.008330103489966274,
358
+ "grad_norm": 2.2833688259124756,
359
+ "learning_rate": 8.329862557267805e-06,
360
+ "loss": 1.9804,
361
+ "step": 2400
362
+ },
363
+ {
364
+ "epoch": 0.008330103489966274,
365
+ "eval_loss": 1.95713472366333,
366
+ "eval_runtime": 26.6415,
367
+ "eval_samples_per_second": 17.904,
368
+ "eval_steps_per_second": 0.375,
369
+ "step": 2400
370
+ },
371
+ {
372
+ "epoch": 0.008677191135381537,
373
+ "grad_norm": 2.6494622230529785,
374
+ "learning_rate": 8.67694016382063e-06,
375
+ "loss": 1.9622,
376
+ "step": 2500
377
+ },
378
+ {
379
+ "epoch": 0.008677191135381537,
380
+ "eval_loss": 1.949569821357727,
381
+ "eval_runtime": 26.7134,
382
+ "eval_samples_per_second": 17.856,
383
+ "eval_steps_per_second": 0.374,
384
+ "step": 2500
385
+ },
386
+ {
387
+ "epoch": 0.009024278780796797,
388
+ "grad_norm": 1.9379554986953735,
389
+ "learning_rate": 9.024017770373457e-06,
390
+ "loss": 1.9624,
391
+ "step": 2600
392
+ },
393
+ {
394
+ "epoch": 0.009024278780796797,
395
+ "eval_loss": 1.9367306232452393,
396
+ "eval_runtime": 26.6328,
397
+ "eval_samples_per_second": 17.91,
398
+ "eval_steps_per_second": 0.375,
399
+ "step": 2600
400
+ },
401
+ {
402
+ "epoch": 0.00937136642621206,
403
+ "grad_norm": 1.797877311706543,
404
+ "learning_rate": 9.37109537692628e-06,
405
+ "loss": 1.9466,
406
+ "step": 2700
407
+ },
408
+ {
409
+ "epoch": 0.00937136642621206,
410
+ "eval_loss": 1.9342317581176758,
411
+ "eval_runtime": 26.6027,
412
+ "eval_samples_per_second": 17.931,
413
+ "eval_steps_per_second": 0.376,
414
+ "step": 2700
415
+ },
416
+ {
417
+ "epoch": 0.00971845407162732,
418
+ "grad_norm": 2.123497724533081,
419
+ "learning_rate": 9.718172983479108e-06,
420
+ "loss": 1.9421,
421
+ "step": 2800
422
+ },
423
+ {
424
+ "epoch": 0.00971845407162732,
425
+ "eval_loss": 1.9269955158233643,
426
+ "eval_runtime": 26.3282,
427
+ "eval_samples_per_second": 18.117,
428
+ "eval_steps_per_second": 0.38,
429
+ "step": 2800
430
+ },
431
+ {
432
+ "epoch": 0.010065541717042582,
433
+ "grad_norm": 2.386960029602051,
434
+ "learning_rate": 1.0065250590031931e-05,
435
+ "loss": 1.9395,
436
+ "step": 2900
437
+ },
438
+ {
439
+ "epoch": 0.010065541717042582,
440
+ "eval_loss": 1.9186092615127563,
441
+ "eval_runtime": 26.5488,
442
+ "eval_samples_per_second": 17.967,
443
+ "eval_steps_per_second": 0.377,
444
+ "step": 2900
445
+ },
446
+ {
447
+ "epoch": 0.010412629362457843,
448
+ "grad_norm": 1.994126558303833,
449
+ "learning_rate": 1.0412328196584756e-05,
450
+ "loss": 1.9242,
451
+ "step": 3000
452
+ },
453
+ {
454
+ "epoch": 0.010412629362457843,
455
+ "eval_loss": 1.9123972654342651,
456
+ "eval_runtime": 26.4618,
457
+ "eval_samples_per_second": 18.026,
458
+ "eval_steps_per_second": 0.378,
459
+ "step": 3000
460
+ },
461
+ {
462
+ "epoch": 0.010759717007873105,
463
+ "grad_norm": 1.7175105810165405,
464
+ "learning_rate": 1.0759405803137582e-05,
465
+ "loss": 1.9232,
466
+ "step": 3100
467
+ },
468
+ {
469
+ "epoch": 0.010759717007873105,
470
+ "eval_loss": 1.903687834739685,
471
+ "eval_runtime": 26.5449,
472
+ "eval_samples_per_second": 17.97,
473
+ "eval_steps_per_second": 0.377,
474
+ "step": 3100
475
+ },
476
+ {
477
+ "epoch": 0.011106804653288366,
478
+ "grad_norm": 1.8057008981704712,
479
+ "learning_rate": 1.1106483409690407e-05,
480
+ "loss": 1.923,
481
+ "step": 3200
482
+ },
483
+ {
484
+ "epoch": 0.011106804653288366,
485
+ "eval_loss": 1.9004727602005005,
486
+ "eval_runtime": 26.3249,
487
+ "eval_samples_per_second": 18.12,
488
+ "eval_steps_per_second": 0.38,
489
+ "step": 3200
490
+ },
491
+ {
492
+ "epoch": 0.011453892298703628,
493
+ "grad_norm": 1.6960588693618774,
494
+ "learning_rate": 1.1453561016243232e-05,
495
+ "loss": 1.9102,
496
+ "step": 3300
497
+ },
498
+ {
499
+ "epoch": 0.011453892298703628,
500
+ "eval_loss": 1.8942128419876099,
501
+ "eval_runtime": 26.351,
502
+ "eval_samples_per_second": 18.102,
503
+ "eval_steps_per_second": 0.379,
504
+ "step": 3300
505
+ },
506
+ {
507
+ "epoch": 0.011800979944118889,
508
+ "grad_norm": 1.8168739080429077,
509
+ "learning_rate": 1.1800638622796058e-05,
510
+ "loss": 1.9074,
511
+ "step": 3400
512
+ },
513
+ {
514
+ "epoch": 0.011800979944118889,
515
+ "eval_loss": 1.889912486076355,
516
+ "eval_runtime": 26.273,
517
+ "eval_samples_per_second": 18.155,
518
+ "eval_steps_per_second": 0.381,
519
+ "step": 3400
520
+ },
521
+ {
522
+ "epoch": 0.012148067589534151,
523
+ "grad_norm": 1.8745700120925903,
524
+ "learning_rate": 1.2147716229348883e-05,
525
+ "loss": 1.9053,
526
+ "step": 3500
527
+ },
528
+ {
529
+ "epoch": 0.012148067589534151,
530
+ "eval_loss": 1.8899447917938232,
531
+ "eval_runtime": 26.3575,
532
+ "eval_samples_per_second": 18.097,
533
+ "eval_steps_per_second": 0.379,
534
+ "step": 3500
535
+ },
536
+ {
537
+ "epoch": 0.012495155234949411,
538
+ "grad_norm": 1.77675199508667,
539
+ "learning_rate": 1.2494793835901708e-05,
540
+ "loss": 1.8983,
541
+ "step": 3600
542
+ },
543
+ {
544
+ "epoch": 0.012495155234949411,
545
+ "eval_loss": 1.8839936256408691,
546
+ "eval_runtime": 26.4506,
547
+ "eval_samples_per_second": 18.034,
548
+ "eval_steps_per_second": 0.378,
549
+ "step": 3600
550
+ },
551
+ {
552
+ "epoch": 0.012842242880364674,
553
+ "grad_norm": 1.473862648010254,
554
+ "learning_rate": 1.2841871442454533e-05,
555
+ "loss": 1.8998,
556
+ "step": 3700
557
+ },
558
+ {
559
+ "epoch": 0.012842242880364674,
560
+ "eval_loss": 1.8791130781173706,
561
+ "eval_runtime": 26.7984,
562
+ "eval_samples_per_second": 17.8,
563
+ "eval_steps_per_second": 0.373,
564
+ "step": 3700
565
+ },
566
+ {
567
+ "epoch": 0.013189330525779934,
568
+ "grad_norm": 1.486438512802124,
569
+ "learning_rate": 1.318894904900736e-05,
570
+ "loss": 1.8951,
571
+ "step": 3800
572
+ },
573
+ {
574
+ "epoch": 0.013189330525779934,
575
+ "eval_loss": 1.8784898519515991,
576
+ "eval_runtime": 26.3412,
577
+ "eval_samples_per_second": 18.109,
578
+ "eval_steps_per_second": 0.38,
579
+ "step": 3800
580
+ },
581
+ {
582
+ "epoch": 0.013536418171195197,
583
+ "grad_norm": 1.2373360395431519,
584
+ "learning_rate": 1.3536026655560182e-05,
585
+ "loss": 1.887,
586
+ "step": 3900
587
+ },
588
+ {
589
+ "epoch": 0.013536418171195197,
590
+ "eval_loss": 1.870314121246338,
591
+ "eval_runtime": 26.436,
592
+ "eval_samples_per_second": 18.044,
593
+ "eval_steps_per_second": 0.378,
594
+ "step": 3900
595
+ },
596
+ {
597
+ "epoch": 0.013883505816610457,
598
+ "grad_norm": 1.5347727537155151,
599
+ "learning_rate": 1.3883104262113009e-05,
600
+ "loss": 1.8951,
601
+ "step": 4000
602
+ },
603
+ {
604
+ "epoch": 0.013883505816610457,
605
+ "eval_loss": 1.8662590980529785,
606
+ "eval_runtime": 26.4553,
607
+ "eval_samples_per_second": 18.03,
608
+ "eval_steps_per_second": 0.378,
609
+ "step": 4000
610
+ },
611
+ {
612
+ "epoch": 0.01423059346202572,
613
+ "grad_norm": 1.771752953529358,
614
+ "learning_rate": 1.4230181868665834e-05,
615
+ "loss": 1.8854,
616
+ "step": 4100
617
+ },
618
+ {
619
+ "epoch": 0.01423059346202572,
620
+ "eval_loss": 1.8646233081817627,
621
+ "eval_runtime": 26.398,
622
+ "eval_samples_per_second": 18.07,
623
+ "eval_steps_per_second": 0.379,
624
+ "step": 4100
625
+ },
626
+ {
627
+ "epoch": 0.01457768110744098,
628
+ "grad_norm": 2.278961420059204,
629
+ "learning_rate": 1.457725947521866e-05,
630
+ "loss": 1.8829,
631
+ "step": 4200
632
+ },
633
+ {
634
+ "epoch": 0.01457768110744098,
635
+ "eval_loss": 1.8655200004577637,
636
+ "eval_runtime": 26.4296,
637
+ "eval_samples_per_second": 18.048,
638
+ "eval_steps_per_second": 0.378,
639
+ "step": 4200
640
+ },
641
+ {
642
+ "epoch": 0.014924768752856242,
643
+ "grad_norm": 1.965826392173767,
644
+ "learning_rate": 1.4924337081771487e-05,
645
+ "loss": 1.8768,
646
+ "step": 4300
647
+ },
648
+ {
649
+ "epoch": 0.014924768752856242,
650
+ "eval_loss": 1.861385464668274,
651
+ "eval_runtime": 26.4002,
652
+ "eval_samples_per_second": 18.068,
653
+ "eval_steps_per_second": 0.379,
654
+ "step": 4300
655
+ },
656
+ {
657
+ "epoch": 0.015271856398271503,
658
+ "grad_norm": 1.2046449184417725,
659
+ "learning_rate": 1.527141468832431e-05,
660
+ "loss": 1.8789,
661
+ "step": 4400
662
+ },
663
+ {
664
+ "epoch": 0.015271856398271503,
665
+ "eval_loss": 1.8564562797546387,
666
+ "eval_runtime": 26.5199,
667
+ "eval_samples_per_second": 17.986,
668
+ "eval_steps_per_second": 0.377,
669
+ "step": 4400
670
+ },
671
+ {
672
+ "epoch": 0.015618944043686765,
673
+ "grad_norm": 1.2664066553115845,
674
+ "learning_rate": 1.5618492294877134e-05,
675
+ "loss": 1.8676,
676
+ "step": 4500
677
+ },
678
+ {
679
+ "epoch": 0.015618944043686765,
680
+ "eval_loss": 1.8561848402023315,
681
+ "eval_runtime": 26.3757,
682
+ "eval_samples_per_second": 18.085,
683
+ "eval_steps_per_second": 0.379,
684
+ "step": 4500
685
+ },
686
+ {
687
+ "epoch": 0.015966031689102027,
688
+ "grad_norm": 1.242021918296814,
689
+ "learning_rate": 1.5965569901429962e-05,
690
+ "loss": 1.8747,
691
+ "step": 4600
692
+ },
693
+ {
694
+ "epoch": 0.015966031689102027,
695
+ "eval_loss": 1.8486684560775757,
696
+ "eval_runtime": 26.3838,
697
+ "eval_samples_per_second": 18.079,
698
+ "eval_steps_per_second": 0.379,
699
+ "step": 4600
700
+ },
701
+ {
702
+ "epoch": 0.016313119334517286,
703
+ "grad_norm": 1.7827301025390625,
704
+ "learning_rate": 1.6312647507982788e-05,
705
+ "loss": 1.8675,
706
+ "step": 4700
707
+ },
708
+ {
709
+ "epoch": 0.016313119334517286,
710
+ "eval_loss": 1.848850131034851,
711
+ "eval_runtime": 26.3928,
712
+ "eval_samples_per_second": 18.073,
713
+ "eval_steps_per_second": 0.379,
714
+ "step": 4700
715
+ },
716
+ {
717
+ "epoch": 0.01666020697993255,
718
+ "grad_norm": 1.4154130220413208,
719
+ "learning_rate": 1.665972511453561e-05,
720
+ "loss": 1.8646,
721
+ "step": 4800
722
+ },
723
+ {
724
+ "epoch": 0.01666020697993255,
725
+ "eval_loss": 1.8437469005584717,
726
+ "eval_runtime": 26.3717,
727
+ "eval_samples_per_second": 18.088,
728
+ "eval_steps_per_second": 0.379,
729
+ "step": 4800
730
+ },
731
+ {
732
+ "epoch": 0.01700729462534781,
733
+ "grad_norm": 1.556569218635559,
734
+ "learning_rate": 1.7006802721088435e-05,
735
+ "loss": 1.8633,
736
+ "step": 4900
737
+ },
738
+ {
739
+ "epoch": 0.01700729462534781,
740
+ "eval_loss": 1.8424543142318726,
741
+ "eval_runtime": 26.5267,
742
+ "eval_samples_per_second": 17.982,
743
+ "eval_steps_per_second": 0.377,
744
+ "step": 4900
745
+ },
746
+ {
747
+ "epoch": 0.017354382270763073,
748
+ "grad_norm": 1.2393227815628052,
749
+ "learning_rate": 1.735388032764126e-05,
750
+ "loss": 1.8581,
751
+ "step": 5000
752
+ },
753
+ {
754
+ "epoch": 0.017354382270763073,
755
+ "eval_loss": 1.8405553102493286,
756
+ "eval_runtime": 26.3219,
757
+ "eval_samples_per_second": 18.122,
758
+ "eval_steps_per_second": 0.38,
759
+ "step": 5000
760
+ },
761
+ {
762
+ "epoch": 0.017701469916178332,
763
+ "grad_norm": 1.141632318496704,
764
+ "learning_rate": 1.770095793419409e-05,
765
+ "loss": 1.8589,
766
+ "step": 5100
767
+ },
768
+ {
769
+ "epoch": 0.017701469916178332,
770
+ "eval_loss": 1.8358362913131714,
771
+ "eval_runtime": 26.3268,
772
+ "eval_samples_per_second": 18.118,
773
+ "eval_steps_per_second": 0.38,
774
+ "step": 5100
775
+ },
776
+ {
777
+ "epoch": 0.018048557561593594,
778
+ "grad_norm": 1.1542439460754395,
779
+ "learning_rate": 1.8048035540746914e-05,
780
+ "loss": 1.8583,
781
+ "step": 5200
782
+ },
783
+ {
784
+ "epoch": 0.018048557561593594,
785
+ "eval_loss": 1.8365525007247925,
786
+ "eval_runtime": 26.4883,
787
+ "eval_samples_per_second": 18.008,
788
+ "eval_steps_per_second": 0.378,
789
+ "step": 5200
790
+ },
791
+ {
792
+ "epoch": 0.018395645207008857,
793
+ "grad_norm": 1.0082952976226807,
794
+ "learning_rate": 1.8395113147299736e-05,
795
+ "loss": 1.8523,
796
+ "step": 5300
797
+ },
798
+ {
799
+ "epoch": 0.018395645207008857,
800
+ "eval_loss": 1.83348548412323,
801
+ "eval_runtime": 26.7213,
802
+ "eval_samples_per_second": 17.851,
803
+ "eval_steps_per_second": 0.374,
804
+ "step": 5300
805
+ },
806
+ {
807
+ "epoch": 0.01874273285242412,
808
+ "grad_norm": 1.3992128372192383,
809
+ "learning_rate": 1.874219075385256e-05,
810
+ "loss": 1.8557,
811
+ "step": 5400
812
+ },
813
+ {
814
+ "epoch": 0.01874273285242412,
815
+ "eval_loss": 1.830024003982544,
816
+ "eval_runtime": 26.3985,
817
+ "eval_samples_per_second": 18.069,
818
+ "eval_steps_per_second": 0.379,
819
+ "step": 5400
820
+ },
821
+ {
822
+ "epoch": 0.019089820497839378,
823
+ "grad_norm": 1.0521454811096191,
824
+ "learning_rate": 1.9089268360405386e-05,
825
+ "loss": 1.8541,
826
+ "step": 5500
827
+ },
828
+ {
829
+ "epoch": 0.019089820497839378,
830
+ "eval_loss": 1.8300797939300537,
831
+ "eval_runtime": 26.4761,
832
+ "eval_samples_per_second": 18.016,
833
+ "eval_steps_per_second": 0.378,
834
+ "step": 5500
835
+ },
836
+ {
837
+ "epoch": 0.01943690814325464,
838
+ "grad_norm": 1.2668583393096924,
839
+ "learning_rate": 1.9436345966958215e-05,
840
+ "loss": 1.8453,
841
+ "step": 5600
842
+ },
843
+ {
844
+ "epoch": 0.01943690814325464,
845
+ "eval_loss": 1.8309643268585205,
846
+ "eval_runtime": 26.3911,
847
+ "eval_samples_per_second": 18.074,
848
+ "eval_steps_per_second": 0.379,
849
+ "step": 5600
850
+ },
851
+ {
852
+ "epoch": 0.019783995788669902,
853
+ "grad_norm": 1.09402334690094,
854
+ "learning_rate": 1.9783423573511037e-05,
855
+ "loss": 1.8536,
856
+ "step": 5700
857
+ },
858
+ {
859
+ "epoch": 0.019783995788669902,
860
+ "eval_loss": 1.8289095163345337,
861
+ "eval_runtime": 26.4192,
862
+ "eval_samples_per_second": 18.055,
863
+ "eval_steps_per_second": 0.379,
864
+ "step": 5700
865
+ },
866
+ {
867
+ "epoch": 0.020131083434085165,
868
+ "grad_norm": 0.960943341255188,
869
+ "learning_rate": 2.0130501180063862e-05,
870
+ "loss": 1.8509,
871
+ "step": 5800
872
+ },
873
+ {
874
+ "epoch": 0.020131083434085165,
875
+ "eval_loss": 1.824504017829895,
876
+ "eval_runtime": 26.471,
877
+ "eval_samples_per_second": 18.02,
878
+ "eval_steps_per_second": 0.378,
879
+ "step": 5800
880
+ },
881
+ {
882
+ "epoch": 0.020478171079500423,
883
+ "grad_norm": 1.0958678722381592,
884
+ "learning_rate": 2.0477578786616688e-05,
885
+ "loss": 1.8452,
886
+ "step": 5900
887
+ },
888
+ {
889
+ "epoch": 0.020478171079500423,
890
+ "eval_loss": 1.8239096403121948,
891
+ "eval_runtime": 26.3508,
892
+ "eval_samples_per_second": 18.102,
893
+ "eval_steps_per_second": 0.379,
894
+ "step": 5900
895
+ },
896
+ {
897
+ "epoch": 0.020825258724915686,
898
+ "grad_norm": 1.1169177293777466,
899
+ "learning_rate": 2.0824656393169513e-05,
900
+ "loss": 1.8431,
901
+ "step": 6000
902
+ },
903
+ {
904
+ "epoch": 0.020825258724915686,
905
+ "eval_loss": 1.8211857080459595,
906
+ "eval_runtime": 26.3842,
907
+ "eval_samples_per_second": 18.079,
908
+ "eval_steps_per_second": 0.379,
909
+ "step": 6000
910
+ },
911
+ {
912
+ "epoch": 0.021172346370330948,
913
+ "grad_norm": 1.2566906213760376,
914
+ "learning_rate": 2.117173399972234e-05,
915
+ "loss": 1.8399,
916
+ "step": 6100
917
+ },
918
+ {
919
+ "epoch": 0.021172346370330948,
920
+ "eval_loss": 1.8177697658538818,
921
+ "eval_runtime": 26.4481,
922
+ "eval_samples_per_second": 18.035,
923
+ "eval_steps_per_second": 0.378,
924
+ "step": 6100
925
+ },
926
+ {
927
+ "epoch": 0.02151943401574621,
928
+ "grad_norm": 1.0141446590423584,
929
+ "learning_rate": 2.1518811606275163e-05,
930
+ "loss": 1.8412,
931
+ "step": 6200
932
+ },
933
+ {
934
+ "epoch": 0.02151943401574621,
935
+ "eval_loss": 1.8186702728271484,
936
+ "eval_runtime": 26.5203,
937
+ "eval_samples_per_second": 17.986,
938
+ "eval_steps_per_second": 0.377,
939
+ "step": 6200
940
+ },
941
+ {
942
+ "epoch": 0.021866521661161473,
943
+ "grad_norm": 1.1088286638259888,
944
+ "learning_rate": 2.186588921282799e-05,
945
+ "loss": 1.8433,
946
+ "step": 6300
947
+ },
948
+ {
949
+ "epoch": 0.021866521661161473,
950
+ "eval_loss": 1.8170266151428223,
951
+ "eval_runtime": 26.8479,
952
+ "eval_samples_per_second": 17.767,
953
+ "eval_steps_per_second": 0.372,
954
+ "step": 6300
955
+ },
956
+ {
957
+ "epoch": 0.02221360930657673,
958
+ "grad_norm": 1.0931763648986816,
959
+ "learning_rate": 2.2212966819380814e-05,
960
+ "loss": 1.8363,
961
+ "step": 6400
962
+ },
963
+ {
964
+ "epoch": 0.02221360930657673,
965
+ "eval_loss": 1.81370210647583,
966
+ "eval_runtime": 26.4259,
967
+ "eval_samples_per_second": 18.05,
968
+ "eval_steps_per_second": 0.378,
969
+ "step": 6400
970
+ },
971
+ {
972
+ "epoch": 0.022560696951991994,
973
+ "grad_norm": 1.040462851524353,
974
+ "learning_rate": 2.256004442593364e-05,
975
+ "loss": 1.8339,
976
+ "step": 6500
977
+ },
978
+ {
979
+ "epoch": 0.022560696951991994,
980
+ "eval_loss": 1.8151589632034302,
981
+ "eval_runtime": 26.44,
982
+ "eval_samples_per_second": 18.041,
983
+ "eval_steps_per_second": 0.378,
984
+ "step": 6500
985
+ },
986
+ {
987
+ "epoch": 0.022907784597407256,
988
+ "grad_norm": 1.0170607566833496,
989
+ "learning_rate": 2.2907122032486464e-05,
990
+ "loss": 1.833,
991
+ "step": 6600
992
+ },
993
+ {
994
+ "epoch": 0.022907784597407256,
995
+ "eval_loss": 1.8107798099517822,
996
+ "eval_runtime": 26.3941,
997
+ "eval_samples_per_second": 18.072,
998
+ "eval_steps_per_second": 0.379,
999
+ "step": 6600
1000
+ },
1001
+ {
1002
+ "epoch": 0.02325487224282252,
1003
+ "grad_norm": 0.813853919506073,
1004
+ "learning_rate": 2.325419963903929e-05,
1005
+ "loss": 1.8338,
1006
+ "step": 6700
1007
+ },
1008
+ {
1009
+ "epoch": 0.02325487224282252,
1010
+ "eval_loss": 1.8114594221115112,
1011
+ "eval_runtime": 26.3741,
1012
+ "eval_samples_per_second": 18.086,
1013
+ "eval_steps_per_second": 0.379,
1014
+ "step": 6700
1015
+ },
1016
+ {
1017
+ "epoch": 0.023601959888237777,
1018
+ "grad_norm": 1.4288556575775146,
1019
+ "learning_rate": 2.3601277245592115e-05,
1020
+ "loss": 1.8301,
1021
+ "step": 6800
1022
+ },
1023
+ {
1024
+ "epoch": 0.023601959888237777,
1025
+ "eval_loss": 1.8073900938034058,
1026
+ "eval_runtime": 26.3565,
1027
+ "eval_samples_per_second": 18.098,
1028
+ "eval_steps_per_second": 0.379,
1029
+ "step": 6800
1030
+ },
1031
+ {
1032
+ "epoch": 0.02394904753365304,
1033
+ "grad_norm": 0.8318554162979126,
1034
+ "learning_rate": 2.394835485214494e-05,
1035
+ "loss": 1.8293,
1036
+ "step": 6900
1037
+ },
1038
+ {
1039
+ "epoch": 0.02394904753365304,
1040
+ "eval_loss": 1.80862295627594,
1041
+ "eval_runtime": 26.4221,
1042
+ "eval_samples_per_second": 18.053,
1043
+ "eval_steps_per_second": 0.378,
1044
+ "step": 6900
1045
+ },
1046
+ {
1047
+ "epoch": 0.024296135179068302,
1048
+ "grad_norm": 0.9045419096946716,
1049
+ "learning_rate": 2.4295432458697766e-05,
1050
+ "loss": 1.8324,
1051
+ "step": 7000
1052
+ },
1053
+ {
1054
+ "epoch": 0.024296135179068302,
1055
+ "eval_loss": 1.805204153060913,
1056
+ "eval_runtime": 26.4185,
1057
+ "eval_samples_per_second": 18.056,
1058
+ "eval_steps_per_second": 0.379,
1059
+ "step": 7000
1060
+ }
1061
+ ],
1062
+ "logging_steps": 100,
1063
+ "max_steps": 288111,
1064
+ "num_input_tokens_seen": 0,
1065
+ "num_train_epochs": 1,
1066
+ "save_steps": 200,
1067
+ "stateful_callbacks": {
1068
+ "TrainerControl": {
1069
+ "args": {
1070
+ "should_epoch_stop": false,
1071
+ "should_evaluate": false,
1072
+ "should_log": false,
1073
+ "should_save": true,
1074
+ "should_training_stop": false
1075
+ },
1076
+ "attributes": {}
1077
+ }
1078
+ },
1079
+ "total_flos": 1.46085192400896e+18,
1080
+ "train_batch_size": 48,
1081
+ "trial_name": null,
1082
+ "trial_params": null
1083
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aaabad18018a1e9d309cf888aa604baa9f9a0b564776b67697d9675fde47834
3
+ size 5368