Ba2han commited on
Commit
4429c11
·
1 Parent(s): b5cacc7

Training in progress, step 300, checkpoint

Browse files
last-checkpoint/config.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3CanonForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoModelForCausalLM": "patch.Qwen3CanonForCausalLM"
9
+ },
10
+ "bos_token_id": 50030,
11
+ "dtype": "bfloat16",
12
+ "eos_token_id": 50031,
13
+ "head_dim": 64,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 1024,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 4096,
18
+ "layer_types": [
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention"
61
+ ],
62
+ "max_position_embeddings": 8192,
63
+ "max_window_layers": 42,
64
+ "model_name": "test_checkpoint",
65
+ "model_type": "qwen3",
66
+ "num_attention_heads": 12,
67
+ "num_hidden_layers": 42,
68
+ "num_key_value_heads": 4,
69
+ "pad_token_id": 50034,
70
+ "qk_norm_freeze_affine": true,
71
+ "resid_lambda_init": 1.0,
72
+ "rms_norm_eps": 1e-06,
73
+ "rope_parameters": {
74
+ "rope_theta": 50000,
75
+ "rope_type": "default"
76
+ },
77
+ "sliding_window": null,
78
+ "softcap_divisor": 7.5,
79
+ "softcap_logits": true,
80
+ "softcap_scale": 23.0,
81
+ "softcap_shift": 5.0,
82
+ "tie_word_embeddings": true,
83
+ "transformers_version": "5.6.2",
84
+ "unsloth_version": "2026.4.8",
85
+ "use_cache": false,
86
+ "use_qk_norm_patch": true,
87
+ "use_sliding_window": false,
88
+ "vocab_size": 50048,
89
+ "x0_lambda_init": 0.1
90
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50030,
4
+ "eos_token_id": [
5
+ 50031
6
+ ],
7
+ "max_length": 8192,
8
+ "output_attentions": false,
9
+ "output_hidden_states": false,
10
+ "pad_token_id": 50034,
11
+ "transformers_version": "5.6.2",
12
+ "use_cache": false
13
+ }
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|begin_of_text|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|end_of_text|>",
6
+ "is_local": true,
7
+ "local_files_only": false,
8
+ "model_input_names": [
9
+ "input_ids",
10
+ "attention_mask"
11
+ ],
12
+ "model_max_length": 8192,
13
+ "pad_token": "<|finetune_right_pad_id|>",
14
+ "padding_side": "right",
15
+ "tokenizer_class": "TokenizersBackend",
16
+ "unk_token": null,
17
+ "added_tokens_decoder": {
18
+ "50030": {
19
+ "content": "<|begin_of_text|>",
20
+ "single_word": false,
21
+ "lstrip": false,
22
+ "rstrip": false,
23
+ "normalized": false,
24
+ "special": true
25
+ },
26
+ "50031": {
27
+ "content": "<|end_of_text|>",
28
+ "single_word": false,
29
+ "lstrip": false,
30
+ "rstrip": false,
31
+ "normalized": false,
32
+ "special": true
33
+ },
34
+ "50032": {
35
+ "content": "<|reserved_special_token_0|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ "50033": {
43
+ "content": "<|reserved_special_token_1|>",
44
+ "single_word": false,
45
+ "lstrip": false,
46
+ "rstrip": false,
47
+ "normalized": false,
48
+ "special": true
49
+ },
50
+ "50034": {
51
+ "content": "<|finetune_right_pad_id|>",
52
+ "single_word": false,
53
+ "lstrip": false,
54
+ "rstrip": false,
55
+ "normalized": false,
56
+ "special": true
57
+ },
58
+ "50035": {
59
+ "content": "<|reserved_special_token_2|>",
60
+ "single_word": false,
61
+ "lstrip": false,
62
+ "rstrip": false,
63
+ "normalized": false,
64
+ "special": true
65
+ },
66
+ "50036": {
67
+ "content": "<|start_header_id|>",
68
+ "single_word": false,
69
+ "lstrip": false,
70
+ "rstrip": false,
71
+ "normalized": false,
72
+ "special": true
73
+ },
74
+ "50037": {
75
+ "content": "<|end_header_id|>",
76
+ "single_word": false,
77
+ "lstrip": false,
78
+ "rstrip": false,
79
+ "normalized": false,
80
+ "special": true
81
+ },
82
+ "50038": {
83
+ "content": "<|eom_id|>",
84
+ "single_word": false,
85
+ "lstrip": false,
86
+ "rstrip": false,
87
+ "normalized": false,
88
+ "special": true
89
+ },
90
+ "50039": {
91
+ "content": "<|eot_id|>",
92
+ "single_word": false,
93
+ "lstrip": false,
94
+ "rstrip": false,
95
+ "normalized": false,
96
+ "special": true
97
+ },
98
+ "50040": {
99
+ "content": "<|python_tag|>",
100
+ "single_word": false,
101
+ "lstrip": false,
102
+ "rstrip": false,
103
+ "normalized": false,
104
+ "special": true
105
+ },
106
+ "50041": {
107
+ "content": "<|reserved_special_token_3|>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ "50042": {
115
+ "content": "<|reserved_special_token_4|>",
116
+ "single_word": false,
117
+ "lstrip": false,
118
+ "rstrip": false,
119
+ "normalized": false,
120
+ "special": true
121
+ },
122
+ "50043": {
123
+ "content": "<|reserved_special_token_5|>",
124
+ "single_word": false,
125
+ "lstrip": false,
126
+ "rstrip": false,
127
+ "normalized": false,
128
+ "special": true
129
+ },
130
+ "50044": {
131
+ "content": "<|reserved_special_token_6|>",
132
+ "single_word": false,
133
+ "lstrip": false,
134
+ "rstrip": false,
135
+ "normalized": false,
136
+ "special": true
137
+ },
138
+ "50045": {
139
+ "content": "<|reserved_special_token_7|>",
140
+ "single_word": false,
141
+ "lstrip": false,
142
+ "rstrip": false,
143
+ "normalized": false,
144
+ "special": true
145
+ },
146
+ "50046": {
147
+ "content": "<|reserved_special_token_8|>",
148
+ "single_word": false,
149
+ "lstrip": false,
150
+ "rstrip": false,
151
+ "normalized": false,
152
+ "special": true
153
+ },
154
+ "50047": {
155
+ "content": "<|reserved_special_token_9|>",
156
+ "single_word": false,
157
+ "lstrip": false,
158
+ "rstrip": false,
159
+ "normalized": false,
160
+ "special": true
161
+ }
162
+ }
163
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,1084 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.02633678020516626,
6
+ "eval_steps": 957,
7
+ "global_step": 300,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.00017557853470110841,
14
+ "grad_norm": 0.30078125,
15
+ "learning_rate": 2.090126243625115e-05,
16
+ "loss": 10.960652351379395,
17
+ "step": 2
18
+ },
19
+ {
20
+ "epoch": 0.00035115706940221683,
21
+ "grad_norm": 0.314453125,
22
+ "learning_rate": 6.270378730875344e-05,
23
+ "loss": 10.96611499786377,
24
+ "step": 4
25
+ },
26
+ {
27
+ "epoch": 0.0005267356041033253,
28
+ "grad_norm": 0.337890625,
29
+ "learning_rate": 0.00010450631218125576,
30
+ "loss": 10.96183967590332,
31
+ "step": 6
32
+ },
33
+ {
34
+ "epoch": 0.0007023141388044337,
35
+ "grad_norm": 0.380859375,
36
+ "learning_rate": 0.00014630883705375804,
37
+ "loss": 10.948229789733887,
38
+ "step": 8
39
+ },
40
+ {
41
+ "epoch": 0.000877892673505542,
42
+ "grad_norm": 0.400390625,
43
+ "learning_rate": 0.00018811136192626034,
44
+ "loss": 10.914310455322266,
45
+ "step": 10
46
+ },
47
+ {
48
+ "epoch": 0.0010534712082066505,
49
+ "grad_norm": 0.498046875,
50
+ "learning_rate": 0.00022991388679876267,
51
+ "loss": 10.865043640136719,
52
+ "step": 12
53
+ },
54
+ {
55
+ "epoch": 0.0012290497429077588,
56
+ "grad_norm": 0.6171875,
57
+ "learning_rate": 0.0002717164116712649,
58
+ "loss": 10.783700942993164,
59
+ "step": 14
60
+ },
61
+ {
62
+ "epoch": 0.0014046282776088673,
63
+ "grad_norm": 0.8359375,
64
+ "learning_rate": 0.0003135189365437672,
65
+ "loss": 10.673444747924805,
66
+ "step": 16
67
+ },
68
+ {
69
+ "epoch": 0.0015802068123099756,
70
+ "grad_norm": 0.81640625,
71
+ "learning_rate": 0.0003553214614162695,
72
+ "loss": 10.533811569213867,
73
+ "step": 18
74
+ },
75
+ {
76
+ "epoch": 0.001755785347011084,
77
+ "grad_norm": 0.890625,
78
+ "learning_rate": 0.00039712398628877183,
79
+ "loss": 10.36827564239502,
80
+ "step": 20
81
+ },
82
+ {
83
+ "epoch": 0.0019313638817121926,
84
+ "grad_norm": 1.0,
85
+ "learning_rate": 0.0004389265111612742,
86
+ "loss": 10.181196212768555,
87
+ "step": 22
88
+ },
89
+ {
90
+ "epoch": 0.002106942416413301,
91
+ "grad_norm": 0.90625,
92
+ "learning_rate": 0.0004807290360337765,
93
+ "loss": 9.960575103759766,
94
+ "step": 24
95
+ },
96
+ {
97
+ "epoch": 0.002282520951114409,
98
+ "grad_norm": 0.97265625,
99
+ "learning_rate": 0.0005225315609062787,
100
+ "loss": 9.699069023132324,
101
+ "step": 26
102
+ },
103
+ {
104
+ "epoch": 0.0024580994858155176,
105
+ "grad_norm": 1.1328125,
106
+ "learning_rate": 0.000564334085778781,
107
+ "loss": 9.424476623535156,
108
+ "step": 28
109
+ },
110
+ {
111
+ "epoch": 0.002633678020516626,
112
+ "grad_norm": 1.03125,
113
+ "learning_rate": 0.0006061366106512833,
114
+ "loss": 9.146112442016602,
115
+ "step": 30
116
+ },
117
+ {
118
+ "epoch": 0.0028092565552177346,
119
+ "grad_norm": 0.93359375,
120
+ "learning_rate": 0.0006479391355237856,
121
+ "loss": 8.853119850158691,
122
+ "step": 32
123
+ },
124
+ {
125
+ "epoch": 0.002984835089918843,
126
+ "grad_norm": 0.828125,
127
+ "learning_rate": 0.0006897416603962879,
128
+ "loss": 8.57155704498291,
129
+ "step": 34
130
+ },
131
+ {
132
+ "epoch": 0.003160413624619951,
133
+ "grad_norm": 0.625,
134
+ "learning_rate": 0.0007315441852687902,
135
+ "loss": 8.293695449829102,
136
+ "step": 36
137
+ },
138
+ {
139
+ "epoch": 0.0033359921593210597,
140
+ "grad_norm": 0.5078125,
141
+ "learning_rate": 0.0007733467101412925,
142
+ "loss": 8.079232215881348,
143
+ "step": 38
144
+ },
145
+ {
146
+ "epoch": 0.003511570694022168,
147
+ "grad_norm": 0.52734375,
148
+ "learning_rate": 0.0008151492350137948,
149
+ "loss": 7.869166851043701,
150
+ "step": 40
151
+ },
152
+ {
153
+ "epoch": 0.0036871492287232767,
154
+ "grad_norm": 0.486328125,
155
+ "learning_rate": 0.0008569517598862971,
156
+ "loss": 7.719941139221191,
157
+ "step": 42
158
+ },
159
+ {
160
+ "epoch": 0.003862727763424385,
161
+ "grad_norm": 0.33984375,
162
+ "learning_rate": 0.0008987542847587994,
163
+ "loss": 7.580569744110107,
164
+ "step": 44
165
+ },
166
+ {
167
+ "epoch": 0.004038306298125493,
168
+ "grad_norm": 0.29296875,
169
+ "learning_rate": 0.0009405568096313017,
170
+ "loss": 7.442490100860596,
171
+ "step": 46
172
+ },
173
+ {
174
+ "epoch": 0.004213884832826602,
175
+ "grad_norm": 0.33203125,
176
+ "learning_rate": 0.0009823593345038041,
177
+ "loss": 7.3093085289001465,
178
+ "step": 48
179
+ },
180
+ {
181
+ "epoch": 0.00438946336752771,
182
+ "grad_norm": 0.2353515625,
183
+ "learning_rate": 0.0010241618593763062,
184
+ "loss": 7.1847639083862305,
185
+ "step": 50
186
+ },
187
+ {
188
+ "epoch": 0.004565041902228818,
189
+ "grad_norm": 0.2275390625,
190
+ "learning_rate": 0.0010659643842488085,
191
+ "loss": 7.069242000579834,
192
+ "step": 52
193
+ },
194
+ {
195
+ "epoch": 0.004740620436929927,
196
+ "grad_norm": 0.30859375,
197
+ "learning_rate": 0.0011077669091213108,
198
+ "loss": 6.970668792724609,
199
+ "step": 54
200
+ },
201
+ {
202
+ "epoch": 0.004916198971631035,
203
+ "grad_norm": 0.291015625,
204
+ "learning_rate": 0.0011495694339938131,
205
+ "loss": 6.86820125579834,
206
+ "step": 56
207
+ },
208
+ {
209
+ "epoch": 0.005091777506332144,
210
+ "grad_norm": 0.34375,
211
+ "learning_rate": 0.0011913719588663154,
212
+ "loss": 6.78927755355835,
213
+ "step": 58
214
+ },
215
+ {
216
+ "epoch": 0.005267356041033252,
217
+ "grad_norm": 0.318359375,
218
+ "learning_rate": 0.0012331744837388177,
219
+ "loss": 6.671013832092285,
220
+ "step": 60
221
+ },
222
+ {
223
+ "epoch": 0.00544293457573436,
224
+ "grad_norm": 0.328125,
225
+ "learning_rate": 0.00127497700861132,
226
+ "loss": 6.608604431152344,
227
+ "step": 62
228
+ },
229
+ {
230
+ "epoch": 0.005618513110435469,
231
+ "grad_norm": 0.359375,
232
+ "learning_rate": 0.0013167795334838223,
233
+ "loss": 6.491241455078125,
234
+ "step": 64
235
+ },
236
+ {
237
+ "epoch": 0.005794091645136577,
238
+ "grad_norm": 0.38671875,
239
+ "learning_rate": 0.0013585820583563247,
240
+ "loss": 6.4354963302612305,
241
+ "step": 66
242
+ },
243
+ {
244
+ "epoch": 0.005969670179837686,
245
+ "grad_norm": 0.34375,
246
+ "learning_rate": 0.001400384583228827,
247
+ "loss": 6.354619979858398,
248
+ "step": 68
249
+ },
250
+ {
251
+ "epoch": 0.006145248714538794,
252
+ "grad_norm": 0.373046875,
253
+ "learning_rate": 0.0014421871081013293,
254
+ "loss": 6.282101631164551,
255
+ "step": 70
256
+ },
257
+ {
258
+ "epoch": 0.006320827249239902,
259
+ "grad_norm": 0.37109375,
260
+ "learning_rate": 0.0014839896329738316,
261
+ "loss": 6.176161766052246,
262
+ "step": 72
263
+ },
264
+ {
265
+ "epoch": 0.006496405783941011,
266
+ "grad_norm": 0.408203125,
267
+ "learning_rate": 0.0015257921578463339,
268
+ "loss": 6.122098922729492,
269
+ "step": 74
270
+ },
271
+ {
272
+ "epoch": 0.006671984318642119,
273
+ "grad_norm": 0.37109375,
274
+ "learning_rate": 0.001567594682718836,
275
+ "loss": 6.045535564422607,
276
+ "step": 76
277
+ },
278
+ {
279
+ "epoch": 0.006847562853343228,
280
+ "grad_norm": 0.4765625,
281
+ "learning_rate": 0.0016093972075913385,
282
+ "loss": 5.991270542144775,
283
+ "step": 78
284
+ },
285
+ {
286
+ "epoch": 0.007023141388044336,
287
+ "grad_norm": 0.57421875,
288
+ "learning_rate": 0.0016511997324638406,
289
+ "loss": 5.9186930656433105,
290
+ "step": 80
291
+ },
292
+ {
293
+ "epoch": 0.007198719922745444,
294
+ "grad_norm": 0.40234375,
295
+ "learning_rate": 0.001693002257336343,
296
+ "loss": 5.854170322418213,
297
+ "step": 82
298
+ },
299
+ {
300
+ "epoch": 0.007374298457446553,
301
+ "grad_norm": 0.333984375,
302
+ "learning_rate": 0.0017348047822088452,
303
+ "loss": 5.790707111358643,
304
+ "step": 84
305
+ },
306
+ {
307
+ "epoch": 0.007549876992147661,
308
+ "grad_norm": 0.54296875,
309
+ "learning_rate": 0.0017766073070813477,
310
+ "loss": 5.740701675415039,
311
+ "step": 86
312
+ },
313
+ {
314
+ "epoch": 0.00772545552684877,
315
+ "grad_norm": 0.66796875,
316
+ "learning_rate": 0.0018184098319538498,
317
+ "loss": 5.699957370758057,
318
+ "step": 88
319
+ },
320
+ {
321
+ "epoch": 0.007901034061549878,
322
+ "grad_norm": 0.404296875,
323
+ "learning_rate": 0.0018602123568263523,
324
+ "loss": 5.671308994293213,
325
+ "step": 90
326
+ },
327
+ {
328
+ "epoch": 0.008076612596250986,
329
+ "grad_norm": 0.40625,
330
+ "learning_rate": 0.0019020148816988546,
331
+ "loss": 5.610586166381836,
332
+ "step": 92
333
+ },
334
+ {
335
+ "epoch": 0.008252191130952095,
336
+ "grad_norm": 0.39453125,
337
+ "learning_rate": 0.001943817406571357,
338
+ "loss": 5.554894924163818,
339
+ "step": 94
340
+ },
341
+ {
342
+ "epoch": 0.008427769665653204,
343
+ "grad_norm": 0.3359375,
344
+ "learning_rate": 0.001985619931443859,
345
+ "loss": 5.456742763519287,
346
+ "step": 96
347
+ },
348
+ {
349
+ "epoch": 0.008603348200354312,
350
+ "grad_norm": 0.404296875,
351
+ "learning_rate": 0.0020274224563163615,
352
+ "loss": 5.479247093200684,
353
+ "step": 98
354
+ },
355
+ {
356
+ "epoch": 0.00877892673505542,
357
+ "grad_norm": 0.3828125,
358
+ "learning_rate": 0.002069224981188864,
359
+ "loss": 5.427374839782715,
360
+ "step": 100
361
+ },
362
+ {
363
+ "epoch": 0.00895450526975653,
364
+ "grad_norm": 0.59375,
365
+ "learning_rate": 0.002111027506061366,
366
+ "loss": 5.365617752075195,
367
+ "step": 102
368
+ },
369
+ {
370
+ "epoch": 0.009130083804457637,
371
+ "grad_norm": 0.71875,
372
+ "learning_rate": 0.0021528300309338684,
373
+ "loss": 5.361892223358154,
374
+ "step": 104
375
+ },
376
+ {
377
+ "epoch": 0.009305662339158745,
378
+ "grad_norm": 0.431640625,
379
+ "learning_rate": 0.0021946325558063707,
380
+ "loss": 5.33181095123291,
381
+ "step": 106
382
+ },
383
+ {
384
+ "epoch": 0.009481240873859854,
385
+ "grad_norm": 0.35546875,
386
+ "learning_rate": 0.002236435080678873,
387
+ "loss": 5.2017741203308105,
388
+ "step": 108
389
+ },
390
+ {
391
+ "epoch": 0.009656819408560962,
392
+ "grad_norm": 0.4375,
393
+ "learning_rate": 0.0022782376055513753,
394
+ "loss": 5.1847686767578125,
395
+ "step": 110
396
+ },
397
+ {
398
+ "epoch": 0.00983239794326207,
399
+ "grad_norm": 0.51953125,
400
+ "learning_rate": 0.0023200401304238776,
401
+ "loss": 5.185354232788086,
402
+ "step": 112
403
+ },
404
+ {
405
+ "epoch": 0.01000797647796318,
406
+ "grad_norm": 0.51171875,
407
+ "learning_rate": 0.00236184265529638,
408
+ "loss": 5.12120246887207,
409
+ "step": 114
410
+ },
411
+ {
412
+ "epoch": 0.010183555012664288,
413
+ "grad_norm": 0.5078125,
414
+ "learning_rate": 0.0024036451801688822,
415
+ "loss": 5.126992225646973,
416
+ "step": 116
417
+ },
418
+ {
419
+ "epoch": 0.010359133547365396,
420
+ "grad_norm": 0.361328125,
421
+ "learning_rate": 0.0024454477050413845,
422
+ "loss": 5.073342800140381,
423
+ "step": 118
424
+ },
425
+ {
426
+ "epoch": 0.010534712082066505,
427
+ "grad_norm": 0.431640625,
428
+ "learning_rate": 0.002487250229913887,
429
+ "loss": 4.999391555786133,
430
+ "step": 120
431
+ },
432
+ {
433
+ "epoch": 0.010710290616767613,
434
+ "grad_norm": 0.546875,
435
+ "learning_rate": 0.002529052754786389,
436
+ "loss": 5.031741619110107,
437
+ "step": 122
438
+ },
439
+ {
440
+ "epoch": 0.01088586915146872,
441
+ "grad_norm": 0.4453125,
442
+ "learning_rate": 0.0025708552796588915,
443
+ "loss": 4.9870171546936035,
444
+ "step": 124
445
+ },
446
+ {
447
+ "epoch": 0.01106144768616983,
448
+ "grad_norm": 0.470703125,
449
+ "learning_rate": 0.0026126578045313938,
450
+ "loss": 4.929328441619873,
451
+ "step": 126
452
+ },
453
+ {
454
+ "epoch": 0.011237026220870939,
455
+ "grad_norm": 0.447265625,
456
+ "learning_rate": 0.002654460329403896,
457
+ "loss": 4.910821914672852,
458
+ "step": 128
459
+ },
460
+ {
461
+ "epoch": 0.011412604755572046,
462
+ "grad_norm": 0.515625,
463
+ "learning_rate": 0.0026962628542763984,
464
+ "loss": 4.8920087814331055,
465
+ "step": 130
466
+ },
467
+ {
468
+ "epoch": 0.011588183290273155,
469
+ "grad_norm": 0.9140625,
470
+ "learning_rate": 0.0027380653791489007,
471
+ "loss": 4.849368095397949,
472
+ "step": 132
473
+ },
474
+ {
475
+ "epoch": 0.011763761824974264,
476
+ "grad_norm": 0.6015625,
477
+ "learning_rate": 0.002779867904021403,
478
+ "loss": 4.815767765045166,
479
+ "step": 134
480
+ },
481
+ {
482
+ "epoch": 0.011939340359675372,
483
+ "grad_norm": 0.62890625,
484
+ "learning_rate": 0.0028216704288939053,
485
+ "loss": 4.809019565582275,
486
+ "step": 136
487
+ },
488
+ {
489
+ "epoch": 0.01211491889437648,
490
+ "grad_norm": 0.5234375,
491
+ "learning_rate": 0.0028634729537664076,
492
+ "loss": 4.747541427612305,
493
+ "step": 138
494
+ },
495
+ {
496
+ "epoch": 0.012290497429077589,
497
+ "grad_norm": 0.4765625,
498
+ "learning_rate": 0.00290527547863891,
499
+ "loss": 4.7378010749816895,
500
+ "step": 140
501
+ },
502
+ {
503
+ "epoch": 0.012466075963778698,
504
+ "grad_norm": 0.44921875,
505
+ "learning_rate": 0.002947078003511412,
506
+ "loss": 4.686991214752197,
507
+ "step": 142
508
+ },
509
+ {
510
+ "epoch": 0.012641654498479805,
511
+ "grad_norm": 0.52734375,
512
+ "learning_rate": 0.0029888805283839145,
513
+ "loss": 4.707539081573486,
514
+ "step": 144
515
+ },
516
+ {
517
+ "epoch": 0.012817233033180914,
518
+ "grad_norm": 0.49609375,
519
+ "learning_rate": 0.003030683053256417,
520
+ "loss": 4.634755611419678,
521
+ "step": 146
522
+ },
523
+ {
524
+ "epoch": 0.012992811567882023,
525
+ "grad_norm": 0.56640625,
526
+ "learning_rate": 0.0030724855781289187,
527
+ "loss": 4.611801624298096,
528
+ "step": 148
529
+ },
530
+ {
531
+ "epoch": 0.01316839010258313,
532
+ "grad_norm": 0.5703125,
533
+ "learning_rate": 0.003114288103001422,
534
+ "loss": 4.616387844085693,
535
+ "step": 150
536
+ },
537
+ {
538
+ "epoch": 0.013343968637284239,
539
+ "grad_norm": 0.474609375,
540
+ "learning_rate": 0.0031560906278739237,
541
+ "loss": 4.566751956939697,
542
+ "step": 152
543
+ },
544
+ {
545
+ "epoch": 0.013519547171985348,
546
+ "grad_norm": 0.859375,
547
+ "learning_rate": 0.003197893152746426,
548
+ "loss": 4.5823516845703125,
549
+ "step": 154
550
+ },
551
+ {
552
+ "epoch": 0.013695125706686457,
553
+ "grad_norm": 0.66015625,
554
+ "learning_rate": 0.003239695677618928,
555
+ "loss": 4.515060901641846,
556
+ "step": 156
557
+ },
558
+ {
559
+ "epoch": 0.013870704241387564,
560
+ "grad_norm": 0.58203125,
561
+ "learning_rate": 0.003281498202491431,
562
+ "loss": 4.500759124755859,
563
+ "step": 158
564
+ },
565
+ {
566
+ "epoch": 0.014046282776088673,
567
+ "grad_norm": 0.494140625,
568
+ "learning_rate": 0.003323300727363933,
569
+ "loss": 4.467392444610596,
570
+ "step": 160
571
+ },
572
+ {
573
+ "epoch": 0.014221861310789782,
574
+ "grad_norm": 0.431640625,
575
+ "learning_rate": 0.0033651032522364352,
576
+ "loss": 4.431788921356201,
577
+ "step": 162
578
+ },
579
+ {
580
+ "epoch": 0.014397439845490889,
581
+ "grad_norm": 0.4921875,
582
+ "learning_rate": 0.003406905777108937,
583
+ "loss": 4.449859142303467,
584
+ "step": 164
585
+ },
586
+ {
587
+ "epoch": 0.014573018380191998,
588
+ "grad_norm": 0.494140625,
589
+ "learning_rate": 0.0034487083019814403,
590
+ "loss": 4.380939960479736,
591
+ "step": 166
592
+ },
593
+ {
594
+ "epoch": 0.014748596914893107,
595
+ "grad_norm": 0.5234375,
596
+ "learning_rate": 0.003490510826853942,
597
+ "loss": 4.370035171508789,
598
+ "step": 168
599
+ },
600
+ {
601
+ "epoch": 0.014924175449594214,
602
+ "grad_norm": 0.51171875,
603
+ "learning_rate": 0.0035323133517264444,
604
+ "loss": 4.3310227394104,
605
+ "step": 170
606
+ },
607
+ {
608
+ "epoch": 0.015099753984295323,
609
+ "grad_norm": 0.51171875,
610
+ "learning_rate": 0.0035741158765989467,
611
+ "loss": 4.363381862640381,
612
+ "step": 172
613
+ },
614
+ {
615
+ "epoch": 0.015275332518996432,
616
+ "grad_norm": 0.404296875,
617
+ "learning_rate": 0.0036159184014714495,
618
+ "loss": 4.319387912750244,
619
+ "step": 174
620
+ },
621
+ {
622
+ "epoch": 0.01545091105369754,
623
+ "grad_norm": 0.46875,
624
+ "learning_rate": 0.0036577209263439514,
625
+ "loss": 4.258921146392822,
626
+ "step": 176
627
+ },
628
+ {
629
+ "epoch": 0.01562648958839865,
630
+ "grad_norm": 0.48828125,
631
+ "learning_rate": 0.0036995234512164537,
632
+ "loss": 4.2898406982421875,
633
+ "step": 178
634
+ },
635
+ {
636
+ "epoch": 0.015802068123099755,
637
+ "grad_norm": 0.671875,
638
+ "learning_rate": 0.003741325976088956,
639
+ "loss": 4.256139278411865,
640
+ "step": 180
641
+ },
642
+ {
643
+ "epoch": 0.015977646657800864,
644
+ "grad_norm": 0.388671875,
645
+ "learning_rate": 0.0037831285009614587,
646
+ "loss": 4.20559024810791,
647
+ "step": 182
648
+ },
649
+ {
650
+ "epoch": 0.016153225192501973,
651
+ "grad_norm": 0.392578125,
652
+ "learning_rate": 0.0038249310258339606,
653
+ "loss": 4.260622024536133,
654
+ "step": 184
655
+ },
656
+ {
657
+ "epoch": 0.016328803727203082,
658
+ "grad_norm": 0.474609375,
659
+ "learning_rate": 0.003866733550706463,
660
+ "loss": 4.154942989349365,
661
+ "step": 186
662
+ },
663
+ {
664
+ "epoch": 0.01650438226190419,
665
+ "grad_norm": 0.4453125,
666
+ "learning_rate": 0.003908536075578965,
667
+ "loss": 4.221053123474121,
668
+ "step": 188
669
+ },
670
+ {
671
+ "epoch": 0.0166799607966053,
672
+ "grad_norm": 0.39453125,
673
+ "learning_rate": 0.0039503386004514675,
674
+ "loss": 4.153572082519531,
675
+ "step": 190
676
+ },
677
+ {
678
+ "epoch": 0.01685553933130641,
679
+ "grad_norm": 0.3359375,
680
+ "learning_rate": 0.003992141125323969,
681
+ "loss": 4.154505729675293,
682
+ "step": 192
683
+ },
684
+ {
685
+ "epoch": 0.017031117866007514,
686
+ "grad_norm": 0.369140625,
687
+ "learning_rate": 0.004033943650196472,
688
+ "loss": 4.094570636749268,
689
+ "step": 194
690
+ },
691
+ {
692
+ "epoch": 0.017206696400708623,
693
+ "grad_norm": 0.3515625,
694
+ "learning_rate": 0.004075746175068974,
695
+ "loss": 4.124532222747803,
696
+ "step": 196
697
+ },
698
+ {
699
+ "epoch": 0.017382274935409732,
700
+ "grad_norm": 0.431640625,
701
+ "learning_rate": 0.004117548699941477,
702
+ "loss": 4.099862575531006,
703
+ "step": 198
704
+ },
705
+ {
706
+ "epoch": 0.01755785347011084,
707
+ "grad_norm": 0.40625,
708
+ "learning_rate": 0.0041593512248139786,
709
+ "loss": 4.086720943450928,
710
+ "step": 200
711
+ },
712
+ {
713
+ "epoch": 0.01773343200481195,
714
+ "grad_norm": 0.38671875,
715
+ "learning_rate": 0.004201153749686481,
716
+ "loss": 4.042497158050537,
717
+ "step": 202
718
+ },
719
+ {
720
+ "epoch": 0.01790901053951306,
721
+ "grad_norm": 0.36328125,
722
+ "learning_rate": 0.004242956274558983,
723
+ "loss": 4.051867961883545,
724
+ "step": 204
725
+ },
726
+ {
727
+ "epoch": 0.018084589074214168,
728
+ "grad_norm": 0.365234375,
729
+ "learning_rate": 0.004284758799431486,
730
+ "loss": 4.011574745178223,
731
+ "step": 206
732
+ },
733
+ {
734
+ "epoch": 0.018260167608915273,
735
+ "grad_norm": 0.37890625,
736
+ "learning_rate": 0.004326561324303988,
737
+ "loss": 4.033310890197754,
738
+ "step": 208
739
+ },
740
+ {
741
+ "epoch": 0.018435746143616382,
742
+ "grad_norm": 0.384765625,
743
+ "learning_rate": 0.0043683638491764905,
744
+ "loss": 4.015084743499756,
745
+ "step": 210
746
+ },
747
+ {
748
+ "epoch": 0.01861132467831749,
749
+ "grad_norm": 0.3125,
750
+ "learning_rate": 0.004410166374048992,
751
+ "loss": 3.971015691757202,
752
+ "step": 212
753
+ },
754
+ {
755
+ "epoch": 0.0187869032130186,
756
+ "grad_norm": 0.298828125,
757
+ "learning_rate": 0.004451968898921495,
758
+ "loss": 4.00208044052124,
759
+ "step": 214
760
+ },
761
+ {
762
+ "epoch": 0.01896248174771971,
763
+ "grad_norm": 0.375,
764
+ "learning_rate": 0.004493771423793997,
765
+ "loss": 3.9292211532592773,
766
+ "step": 216
767
+ },
768
+ {
769
+ "epoch": 0.019138060282420818,
770
+ "grad_norm": 0.349609375,
771
+ "learning_rate": 0.0045355739486665,
772
+ "loss": 3.9596006870269775,
773
+ "step": 218
774
+ },
775
+ {
776
+ "epoch": 0.019313638817121923,
777
+ "grad_norm": 0.291015625,
778
+ "learning_rate": 0.004577376473539002,
779
+ "loss": 3.935854911804199,
780
+ "step": 220
781
+ },
782
+ {
783
+ "epoch": 0.019489217351823032,
784
+ "grad_norm": 0.349609375,
785
+ "learning_rate": 0.004619178998411504,
786
+ "loss": 3.8975400924682617,
787
+ "step": 222
788
+ },
789
+ {
790
+ "epoch": 0.01966479588652414,
791
+ "grad_norm": 0.31640625,
792
+ "learning_rate": 0.004660981523284006,
793
+ "loss": 3.903998613357544,
794
+ "step": 224
795
+ },
796
+ {
797
+ "epoch": 0.01984037442122525,
798
+ "grad_norm": 0.39453125,
799
+ "learning_rate": 0.004702784048156509,
800
+ "loss": 3.9066410064697266,
801
+ "step": 226
802
+ },
803
+ {
804
+ "epoch": 0.02001595295592636,
805
+ "grad_norm": 0.36328125,
806
+ "learning_rate": 0.004744586573029011,
807
+ "loss": 3.874302864074707,
808
+ "step": 228
809
+ },
810
+ {
811
+ "epoch": 0.020191531490627468,
812
+ "grad_norm": 0.2734375,
813
+ "learning_rate": 0.0047863890979015136,
814
+ "loss": 3.894779920578003,
815
+ "step": 230
816
+ },
817
+ {
818
+ "epoch": 0.020367110025328577,
819
+ "grad_norm": 0.33203125,
820
+ "learning_rate": 0.004828191622774015,
821
+ "loss": 3.8634965419769287,
822
+ "step": 232
823
+ },
824
+ {
825
+ "epoch": 0.020542688560029682,
826
+ "grad_norm": 0.3125,
827
+ "learning_rate": 0.004869994147646518,
828
+ "loss": 3.846660852432251,
829
+ "step": 234
830
+ },
831
+ {
832
+ "epoch": 0.02071826709473079,
833
+ "grad_norm": 0.267578125,
834
+ "learning_rate": 0.00491179667251902,
835
+ "loss": 3.856271505355835,
836
+ "step": 236
837
+ },
838
+ {
839
+ "epoch": 0.0208938456294319,
840
+ "grad_norm": 0.30078125,
841
+ "learning_rate": 0.004953599197391523,
842
+ "loss": 3.823467969894409,
843
+ "step": 238
844
+ },
845
+ {
846
+ "epoch": 0.02106942416413301,
847
+ "grad_norm": 0.330078125,
848
+ "learning_rate": 0.004995401722264025,
849
+ "loss": 3.782071590423584,
850
+ "step": 240
851
+ },
852
+ {
853
+ "epoch": 0.021245002698834118,
854
+ "grad_norm": 0.302734375,
855
+ "learning_rate": 0.005,
856
+ "loss": 3.7924273014068604,
857
+ "step": 242
858
+ },
859
+ {
860
+ "epoch": 0.021420581233535227,
861
+ "grad_norm": 0.296875,
862
+ "learning_rate": 0.005,
863
+ "loss": 3.7755682468414307,
864
+ "step": 244
865
+ },
866
+ {
867
+ "epoch": 0.021596159768236336,
868
+ "grad_norm": 0.294921875,
869
+ "learning_rate": 0.005,
870
+ "loss": 3.7866594791412354,
871
+ "step": 246
872
+ },
873
+ {
874
+ "epoch": 0.02177173830293744,
875
+ "grad_norm": 0.28515625,
876
+ "learning_rate": 0.005,
877
+ "loss": 3.7925446033477783,
878
+ "step": 248
879
+ },
880
+ {
881
+ "epoch": 0.02194731683763855,
882
+ "grad_norm": 0.306640625,
883
+ "learning_rate": 0.005,
884
+ "loss": 3.7477009296417236,
885
+ "step": 250
886
+ },
887
+ {
888
+ "epoch": 0.02212289537233966,
889
+ "grad_norm": 0.271484375,
890
+ "learning_rate": 0.005,
891
+ "loss": 3.7392055988311768,
892
+ "step": 252
893
+ },
894
+ {
895
+ "epoch": 0.022298473907040768,
896
+ "grad_norm": 0.25,
897
+ "learning_rate": 0.005,
898
+ "loss": 3.7321717739105225,
899
+ "step": 254
900
+ },
901
+ {
902
+ "epoch": 0.022474052441741877,
903
+ "grad_norm": 0.28515625,
904
+ "learning_rate": 0.005,
905
+ "loss": 3.714862823486328,
906
+ "step": 256
907
+ },
908
+ {
909
+ "epoch": 0.022649630976442986,
910
+ "grad_norm": 0.2265625,
911
+ "learning_rate": 0.005,
912
+ "loss": 3.6854515075683594,
913
+ "step": 258
914
+ },
915
+ {
916
+ "epoch": 0.02282520951114409,
917
+ "grad_norm": 0.23828125,
918
+ "learning_rate": 0.005,
919
+ "loss": 3.6973862648010254,
920
+ "step": 260
921
+ },
922
+ {
923
+ "epoch": 0.0230007880458452,
924
+ "grad_norm": 0.255859375,
925
+ "learning_rate": 0.005,
926
+ "loss": 3.674755096435547,
927
+ "step": 262
928
+ },
929
+ {
930
+ "epoch": 0.02317636658054631,
931
+ "grad_norm": 0.232421875,
932
+ "learning_rate": 0.005,
933
+ "loss": 3.6436076164245605,
934
+ "step": 264
935
+ },
936
+ {
937
+ "epoch": 0.023351945115247418,
938
+ "grad_norm": 0.2275390625,
939
+ "learning_rate": 0.005,
940
+ "loss": 3.640627384185791,
941
+ "step": 266
942
+ },
943
+ {
944
+ "epoch": 0.023527523649948527,
945
+ "grad_norm": 0.2421875,
946
+ "learning_rate": 0.005,
947
+ "loss": 3.653189182281494,
948
+ "step": 268
949
+ },
950
+ {
951
+ "epoch": 0.023703102184649636,
952
+ "grad_norm": 0.2412109375,
953
+ "learning_rate": 0.005,
954
+ "loss": 3.6322195529937744,
955
+ "step": 270
956
+ },
957
+ {
958
+ "epoch": 0.023878680719350745,
959
+ "grad_norm": 0.201171875,
960
+ "learning_rate": 0.005,
961
+ "loss": 3.608694553375244,
962
+ "step": 272
963
+ },
964
+ {
965
+ "epoch": 0.02405425925405185,
966
+ "grad_norm": 0.224609375,
967
+ "learning_rate": 0.005,
968
+ "loss": 3.6067698001861572,
969
+ "step": 274
970
+ },
971
+ {
972
+ "epoch": 0.02422983778875296,
973
+ "grad_norm": 0.208984375,
974
+ "learning_rate": 0.005,
975
+ "loss": 3.6058900356292725,
976
+ "step": 276
977
+ },
978
+ {
979
+ "epoch": 0.02440541632345407,
980
+ "grad_norm": 0.2197265625,
981
+ "learning_rate": 0.005,
982
+ "loss": 3.6085643768310547,
983
+ "step": 278
984
+ },
985
+ {
986
+ "epoch": 0.024580994858155177,
987
+ "grad_norm": 0.1806640625,
988
+ "learning_rate": 0.005,
989
+ "loss": 3.5690369606018066,
990
+ "step": 280
991
+ },
992
+ {
993
+ "epoch": 0.024756573392856286,
994
+ "grad_norm": 0.21875,
995
+ "learning_rate": 0.005,
996
+ "loss": 3.5159733295440674,
997
+ "step": 282
998
+ },
999
+ {
1000
+ "epoch": 0.024932151927557395,
1001
+ "grad_norm": 0.2041015625,
1002
+ "learning_rate": 0.005,
1003
+ "loss": 3.557368755340576,
1004
+ "step": 284
1005
+ },
1006
+ {
1007
+ "epoch": 0.025107730462258504,
1008
+ "grad_norm": 0.2197265625,
1009
+ "learning_rate": 0.005,
1010
+ "loss": 3.53389310836792,
1011
+ "step": 286
1012
+ },
1013
+ {
1014
+ "epoch": 0.02528330899695961,
1015
+ "grad_norm": 0.23046875,
1016
+ "learning_rate": 0.005,
1017
+ "loss": 3.520721912384033,
1018
+ "step": 288
1019
+ },
1020
+ {
1021
+ "epoch": 0.02545888753166072,
1022
+ "grad_norm": 0.2119140625,
1023
+ "learning_rate": 0.005,
1024
+ "loss": 3.5246963500976562,
1025
+ "step": 290
1026
+ },
1027
+ {
1028
+ "epoch": 0.025634466066361827,
1029
+ "grad_norm": 0.193359375,
1030
+ "learning_rate": 0.005,
1031
+ "loss": 3.473104238510132,
1032
+ "step": 292
1033
+ },
1034
+ {
1035
+ "epoch": 0.025810044601062936,
1036
+ "grad_norm": 0.1875,
1037
+ "learning_rate": 0.005,
1038
+ "loss": 3.4929323196411133,
1039
+ "step": 294
1040
+ },
1041
+ {
1042
+ "epoch": 0.025985623135764045,
1043
+ "grad_norm": 0.2060546875,
1044
+ "learning_rate": 0.005,
1045
+ "loss": 3.433466911315918,
1046
+ "step": 296
1047
+ },
1048
+ {
1049
+ "epoch": 0.026161201670465154,
1050
+ "grad_norm": 0.2373046875,
1051
+ "learning_rate": 0.005,
1052
+ "loss": 3.480882406234741,
1053
+ "step": 298
1054
+ },
1055
+ {
1056
+ "epoch": 0.02633678020516626,
1057
+ "grad_norm": 0.2333984375,
1058
+ "learning_rate": 0.005,
1059
+ "loss": 3.4181106090545654,
1060
+ "step": 300
1061
+ }
1062
+ ],
1063
+ "logging_steps": 2,
1064
+ "max_steps": 11961,
1065
+ "num_input_tokens_seen": 0,
1066
+ "num_train_epochs": 2,
1067
+ "save_steps": 300,
1068
+ "stateful_callbacks": {
1069
+ "TrainerControl": {
1070
+ "args": {
1071
+ "should_epoch_stop": false,
1072
+ "should_evaluate": false,
1073
+ "should_log": false,
1074
+ "should_save": true,
1075
+ "should_training_stop": false
1076
+ },
1077
+ "attributes": {}
1078
+ }
1079
+ },
1080
+ "total_flos": 5.071178624049867e+17,
1081
+ "train_batch_size": 2,
1082
+ "trial_name": null,
1083
+ "trial_params": null
1084
+ }