RayDu0010 commited on
Commit
8c8ffa4
·
verified ·
1 Parent(s): 54ba118

Upload folder using huggingface_hub

Browse files
2_128_e3_3e-5/README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: ibm-granite/granite-3.3-8b-base
5
+ tags:
6
+ - alignment-handbook
7
+ - generated_from_trainer
8
+ datasets:
9
+ - data/knowledge_lora_training_data_2000
10
+ model-index:
11
+ - name: 2_128_e3_3e-5
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # 2_128_e3_3e-5
19
+
20
+ This model is a fine-tuned version of [ibm-granite/granite-3.3-8b-base](https://huggingface.co/ibm-granite/granite-3.3-8b-base) on the data/knowledge_lora_training_data_2000 dataset.
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 3e-05
40
+ - train_batch_size: 2
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - distributed_type: multi-GPU
44
+ - num_devices: 8
45
+ - gradient_accumulation_steps: 2
46
+ - total_train_batch_size: 32
47
+ - total_eval_batch_size: 64
48
+ - optimizer: Use adamw_torch with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
+ - lr_scheduler_type: cosine
50
+ - lr_scheduler_warmup_ratio: 0.05
51
+ - num_epochs: 3.0
52
+
53
+ ### Training results
54
+
55
+
56
+
57
+ ### Framework versions
58
+
59
+ - PEFT 0.15.2
60
+ - Transformers 4.52.4
61
+ - Pytorch 2.7.0+cu126
62
+ - Datasets 3.6.0
63
+ - Tokenizers 0.21.2
2_128_e3_3e-5/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "ibm-granite/granite-3.3-8b-base",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 256,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 128,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "down_proj",
28
+ "q_proj",
29
+ "k_proj",
30
+ "up_proj",
31
+ "o_proj",
32
+ "gate_proj",
33
+ "v_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
2_128_e3_3e-5/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36a9be3fc167d2d75e862a646171219a7e3a3263aba99eb4510d8ff9b4079a4c
3
+ size 791751704
2_128_e3_3e-5/all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.482127184633004e+18,
4
+ "train_loss": 0.5478373010360187,
5
+ "train_runtime": 672.1067,
6
+ "train_samples": 10710,
7
+ "train_samples_per_second": 47.805,
8
+ "train_steps_per_second": 1.495
9
+ }
2_128_e3_3e-5/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GraniteForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0,
7
+ "attention_multiplier": 0.0078125,
8
+ "bos_token_id": 0,
9
+ "embedding_multiplier": 12.0,
10
+ "eos_token_id": 0,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 12800,
15
+ "logits_scaling": 16.0,
16
+ "max_position_embeddings": 131072,
17
+ "mlp_bias": false,
18
+ "model_type": "granite",
19
+ "num_attention_heads": 32,
20
+ "num_hidden_layers": 40,
21
+ "num_key_value_heads": 8,
22
+ "pad_token_id": 0,
23
+ "residual_multiplier": 0.22,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": null,
26
+ "rope_theta": 10000000.0,
27
+ "tie_word_embeddings": true,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.52.4",
30
+ "use_cache": true,
31
+ "vocab_size": 49152
32
+ }
2_128_e3_3e-5/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
2_128_e3_3e-5/special_tokens_map.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<fim_prefix>",
5
+ "<fim_middle>",
6
+ "<fim_suffix>",
7
+ "<fim_pad>",
8
+ "<filename>",
9
+ "<gh_stars>",
10
+ "<issue_start>",
11
+ "<issue_comment>",
12
+ "<issue_closed>",
13
+ "<jupyter_start>",
14
+ "<jupyter_text>",
15
+ "<jupyter_code>",
16
+ "<jupyter_output>",
17
+ "<empty_output>",
18
+ "<commit_before>",
19
+ "<commit_msg>",
20
+ "<commit_after>",
21
+ "<reponame>"
22
+ ],
23
+ "bos_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "eos_token": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "pad_token": "<reponame>",
38
+ "unk_token": {
39
+ "content": "<|endoftext|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ }
45
+ }
2_128_e3_3e-5/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
2_128_e3_3e-5/tokenizer_config.json ADDED
@@ -0,0 +1,188 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<fim_prefix>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<fim_middle>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<fim_suffix>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<fim_pad>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<filename>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<gh_stars>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<issue_start>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_comment>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_closed>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<jupyter_start>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_text>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_code>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_output>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<empty_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<commit_before>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<commit_msg>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "17": {
141
+ "content": "<commit_after>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "18": {
149
+ "content": "<reponame>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ }
156
+ },
157
+ "additional_special_tokens": [
158
+ "<|endoftext|>",
159
+ "<fim_prefix>",
160
+ "<fim_middle>",
161
+ "<fim_suffix>",
162
+ "<fim_pad>",
163
+ "<filename>",
164
+ "<gh_stars>",
165
+ "<issue_start>",
166
+ "<issue_comment>",
167
+ "<issue_closed>",
168
+ "<jupyter_start>",
169
+ "<jupyter_text>",
170
+ "<jupyter_code>",
171
+ "<jupyter_output>",
172
+ "<empty_output>",
173
+ "<commit_before>",
174
+ "<commit_msg>",
175
+ "<commit_after>",
176
+ "<reponame>"
177
+ ],
178
+ "bos_token": "<|endoftext|>",
179
+ "clean_up_tokenization_spaces": true,
180
+ "eos_token": "<|endoftext|>",
181
+ "extra_special_tokens": {},
182
+ "model_max_length": 8192,
183
+ "pad_token": "<reponame>",
184
+ "padding_side": "left",
185
+ "tokenizer_class": "GPT2Tokenizer",
186
+ "unk_token": "<|endoftext|>",
187
+ "vocab_size": 49152
188
+ }
2_128_e3_3e-5/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.482127184633004e+18,
4
+ "train_loss": 0.5478373010360187,
5
+ "train_runtime": 672.1067,
6
+ "train_samples": 10710,
7
+ "train_samples_per_second": 47.805,
8
+ "train_steps_per_second": 1.495
9
+ }
2_128_e3_3e-5/trainer_state.json ADDED
@@ -0,0 +1,1450 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1005,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.014925373134328358,
14
+ "grad_norm": 1.1936415433883667,
15
+ "learning_rate": 2.3529411764705885e-06,
16
+ "loss": 1.3178,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.029850746268656716,
21
+ "grad_norm": 0.8011311292648315,
22
+ "learning_rate": 5.294117647058824e-06,
23
+ "loss": 1.299,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.04477611940298507,
28
+ "grad_norm": 0.5648296475410461,
29
+ "learning_rate": 8.23529411764706e-06,
30
+ "loss": 1.2979,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.05970149253731343,
35
+ "grad_norm": 1.0879466533660889,
36
+ "learning_rate": 1.1176470588235295e-05,
37
+ "loss": 1.2498,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.07462686567164178,
42
+ "grad_norm": 0.5851609110832214,
43
+ "learning_rate": 1.411764705882353e-05,
44
+ "loss": 1.2138,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.08955223880597014,
49
+ "grad_norm": 0.5263943076133728,
50
+ "learning_rate": 1.7058823529411763e-05,
51
+ "loss": 1.1806,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.1044776119402985,
56
+ "grad_norm": 0.37341439723968506,
57
+ "learning_rate": 1.9999999999999998e-05,
58
+ "loss": 1.2425,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.11940298507462686,
63
+ "grad_norm": 0.4495214521884918,
64
+ "learning_rate": 2.2941176470588233e-05,
65
+ "loss": 1.2472,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.13432835820895522,
70
+ "grad_norm": 0.5549694299697876,
71
+ "learning_rate": 2.5882352941176472e-05,
72
+ "loss": 1.1519,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.14925373134328357,
77
+ "grad_norm": 0.4199811816215515,
78
+ "learning_rate": 2.8823529411764707e-05,
79
+ "loss": 1.185,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.16417910447761194,
84
+ "grad_norm": 0.42709535360336304,
85
+ "learning_rate": 2.9999268013221688e-05,
86
+ "loss": 1.1315,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.1791044776119403,
91
+ "grad_norm": 0.5405896306037903,
92
+ "learning_rate": 2.9994795019399927e-05,
93
+ "loss": 1.1239,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.19402985074626866,
98
+ "grad_norm": 0.43888697028160095,
99
+ "learning_rate": 2.9986256902246587e-05,
100
+ "loss": 1.0712,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.208955223880597,
105
+ "grad_norm": 0.48112964630126953,
106
+ "learning_rate": 2.9973655976464824e-05,
107
+ "loss": 1.0667,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.22388059701492538,
112
+ "grad_norm": 0.5392914414405823,
113
+ "learning_rate": 2.995699565819452e-05,
114
+ "loss": 1.1046,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.23880597014925373,
119
+ "grad_norm": 0.51181560754776,
120
+ "learning_rate": 2.993628046408618e-05,
121
+ "loss": 1.1095,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.2537313432835821,
126
+ "grad_norm": 0.448114275932312,
127
+ "learning_rate": 2.991151601007646e-05,
128
+ "loss": 1.1248,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.26865671641791045,
133
+ "grad_norm": 0.5458486676216125,
134
+ "learning_rate": 2.9882709009865653e-05,
135
+ "loss": 1.0544,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.2835820895522388,
140
+ "grad_norm": 0.5127103328704834,
141
+ "learning_rate": 2.98498672730976e-05,
142
+ "loss": 1.0849,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.29850746268656714,
147
+ "grad_norm": 0.5187199711799622,
148
+ "learning_rate": 2.9812999703242502e-05,
149
+ "loss": 1.0488,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.31343283582089554,
154
+ "grad_norm": 0.5600414276123047,
155
+ "learning_rate": 2.977211629518312e-05,
156
+ "loss": 1.0317,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.3283582089552239,
161
+ "grad_norm": 0.5698317885398865,
162
+ "learning_rate": 2.9727228132505178e-05,
163
+ "loss": 0.9852,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.34328358208955223,
168
+ "grad_norm": 0.5142781138420105,
169
+ "learning_rate": 2.967834738449256e-05,
170
+ "loss": 1.0272,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.3582089552238806,
175
+ "grad_norm": 0.5430530905723572,
176
+ "learning_rate": 2.9625487302828198e-05,
177
+ "loss": 0.994,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.373134328358209,
182
+ "grad_norm": 0.668404221534729,
183
+ "learning_rate": 2.956866221800151e-05,
184
+ "loss": 1.0267,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.3880597014925373,
189
+ "grad_norm": 0.6017296314239502,
190
+ "learning_rate": 2.9507887535423357e-05,
191
+ "loss": 0.9794,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.40298507462686567,
196
+ "grad_norm": 0.8586568832397461,
197
+ "learning_rate": 2.944317973124962e-05,
198
+ "loss": 0.9733,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.417910447761194,
203
+ "grad_norm": 0.6064942479133606,
204
+ "learning_rate": 2.937455634791447e-05,
205
+ "loss": 0.9092,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.43283582089552236,
210
+ "grad_norm": 0.6258195638656616,
211
+ "learning_rate": 2.9302035989374565e-05,
212
+ "loss": 0.9095,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.44776119402985076,
217
+ "grad_norm": 0.6791467070579529,
218
+ "learning_rate": 2.9225638316065483e-05,
219
+ "loss": 0.9329,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.4626865671641791,
224
+ "grad_norm": 0.7371143698692322,
225
+ "learning_rate": 2.9145384039571743e-05,
226
+ "loss": 0.9231,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.47761194029850745,
231
+ "grad_norm": 0.7199986577033997,
232
+ "learning_rate": 2.9061294917011817e-05,
233
+ "loss": 0.8616,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.4925373134328358,
238
+ "grad_norm": 0.7791478037834167,
239
+ "learning_rate": 2.897339374513975e-05,
240
+ "loss": 0.884,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.5074626865671642,
245
+ "grad_norm": 0.8169253468513489,
246
+ "learning_rate": 2.888170435416491e-05,
247
+ "loss": 0.9079,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.5223880597014925,
252
+ "grad_norm": 0.6654359698295593,
253
+ "learning_rate": 2.878625160129155e-05,
254
+ "loss": 0.8549,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.5373134328358209,
259
+ "grad_norm": 0.8726022839546204,
260
+ "learning_rate": 2.8687061363979963e-05,
261
+ "loss": 0.8601,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.5522388059701493,
266
+ "grad_norm": 0.77958744764328,
267
+ "learning_rate": 2.858416053293105e-05,
268
+ "loss": 0.8176,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.5671641791044776,
273
+ "grad_norm": 0.7674434781074524,
274
+ "learning_rate": 2.84775770047962e-05,
275
+ "loss": 0.8029,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.582089552238806,
280
+ "grad_norm": 0.7162519693374634,
281
+ "learning_rate": 2.8367339674614402e-05,
282
+ "loss": 0.8761,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.5970149253731343,
287
+ "grad_norm": 0.8640219569206238,
288
+ "learning_rate": 2.825347842797879e-05,
289
+ "loss": 0.8374,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.6119402985074627,
294
+ "grad_norm": 0.7389693260192871,
295
+ "learning_rate": 2.8136024132934552e-05,
296
+ "loss": 0.804,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.6268656716417911,
301
+ "grad_norm": 0.974527895450592,
302
+ "learning_rate": 2.8015008631610545e-05,
303
+ "loss": 0.8253,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.6417910447761194,
308
+ "grad_norm": 0.7666051983833313,
309
+ "learning_rate": 2.789046473158682e-05,
310
+ "loss": 0.8327,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.6567164179104478,
315
+ "grad_norm": 0.8711564540863037,
316
+ "learning_rate": 2.7762426197000404e-05,
317
+ "loss": 0.7511,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.6716417910447762,
322
+ "grad_norm": 0.8236544728279114,
323
+ "learning_rate": 2.763092773939177e-05,
324
+ "loss": 0.8551,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 0.6865671641791045,
329
+ "grad_norm": 0.8237460851669312,
330
+ "learning_rate": 2.749600500829448e-05,
331
+ "loss": 0.7853,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 0.7014925373134329,
336
+ "grad_norm": 0.9001902937889099,
337
+ "learning_rate": 2.7357694581570475e-05,
338
+ "loss": 0.7611,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 0.7164179104477612,
343
+ "grad_norm": 0.8697739839553833,
344
+ "learning_rate": 2.7216033955493756e-05,
345
+ "loss": 0.7656,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 0.7313432835820896,
350
+ "grad_norm": 0.7716524600982666,
351
+ "learning_rate": 2.7071061534585064e-05,
352
+ "loss": 0.7567,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 0.746268656716418,
357
+ "grad_norm": 0.8154096007347107,
358
+ "learning_rate": 2.6922816621200302e-05,
359
+ "loss": 0.7274,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 0.7611940298507462,
364
+ "grad_norm": 0.8069023489952087,
365
+ "learning_rate": 2.6771339404875602e-05,
366
+ "loss": 0.7115,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 0.7761194029850746,
371
+ "grad_norm": 1.0328160524368286,
372
+ "learning_rate": 2.6616670951431842e-05,
373
+ "loss": 0.7695,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 0.7910447761194029,
378
+ "grad_norm": 0.8895705938339233,
379
+ "learning_rate": 2.645885319184159e-05,
380
+ "loss": 0.717,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 0.8059701492537313,
385
+ "grad_norm": 0.7964750528335571,
386
+ "learning_rate": 2.6297928910861546e-05,
387
+ "loss": 0.7042,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 0.8208955223880597,
392
+ "grad_norm": 0.8405295014381409,
393
+ "learning_rate": 2.6133941735433496e-05,
394
+ "loss": 0.6939,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 0.835820895522388,
399
+ "grad_norm": 1.0508198738098145,
400
+ "learning_rate": 2.596693612285691e-05,
401
+ "loss": 0.7287,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 0.8507462686567164,
406
+ "grad_norm": 0.9012879133224487,
407
+ "learning_rate": 2.5796957348736522e-05,
408
+ "loss": 0.6646,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 0.8656716417910447,
413
+ "grad_norm": 0.990813672542572,
414
+ "learning_rate": 2.5624051494707967e-05,
415
+ "loss": 0.6691,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 0.8805970149253731,
420
+ "grad_norm": 0.8366561532020569,
421
+ "learning_rate": 2.5448265435944957e-05,
422
+ "loss": 0.6826,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 0.8955223880597015,
427
+ "grad_norm": 0.8978521823883057,
428
+ "learning_rate": 2.5269646828451323e-05,
429
+ "loss": 0.6714,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 0.9104477611940298,
434
+ "grad_norm": 0.9813509583473206,
435
+ "learning_rate": 2.5088244096141355e-05,
436
+ "loss": 0.6563,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 0.9253731343283582,
441
+ "grad_norm": 0.9724867939949036,
442
+ "learning_rate": 2.490410641771196e-05,
443
+ "loss": 0.7257,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 0.9402985074626866,
448
+ "grad_norm": 1.1510107517242432,
449
+ "learning_rate": 2.4717283713310224e-05,
450
+ "loss": 0.6253,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 0.9552238805970149,
455
+ "grad_norm": 1.104021668434143,
456
+ "learning_rate": 2.4527826630999922e-05,
457
+ "loss": 0.6789,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 0.9701492537313433,
462
+ "grad_norm": 1.060115098953247,
463
+ "learning_rate": 2.4335786533030736e-05,
464
+ "loss": 0.6366,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 0.9850746268656716,
469
+ "grad_norm": 1.024133563041687,
470
+ "learning_rate": 2.414121548191381e-05,
471
+ "loss": 0.6211,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 1.0,
476
+ "grad_norm": 0.941692054271698,
477
+ "learning_rate": 2.39441662263075e-05,
478
+ "loss": 0.6087,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 1.0149253731343284,
483
+ "grad_norm": 1.182281494140625,
484
+ "learning_rate": 2.374469218671708e-05,
485
+ "loss": 0.6062,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 1.0298507462686568,
490
+ "grad_norm": 1.2160669565200806,
491
+ "learning_rate": 2.3542847441012325e-05,
492
+ "loss": 0.5772,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 1.044776119402985,
497
+ "grad_norm": 1.051630973815918,
498
+ "learning_rate": 2.333868670976688e-05,
499
+ "loss": 0.558,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 1.0597014925373134,
504
+ "grad_norm": 1.1331043243408203,
505
+ "learning_rate": 2.3132265341423382e-05,
506
+ "loss": 0.5661,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 1.0746268656716418,
511
+ "grad_norm": 1.0946743488311768,
512
+ "learning_rate": 2.292363929728836e-05,
513
+ "loss": 0.546,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 1.0895522388059702,
518
+ "grad_norm": 1.2076295614242554,
519
+ "learning_rate": 2.2712865136361037e-05,
520
+ "loss": 0.5187,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 1.1044776119402986,
525
+ "grad_norm": 1.2114005088806152,
526
+ "learning_rate": 2.25e-05,
527
+ "loss": 0.5682,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 1.1194029850746268,
532
+ "grad_norm": 0.9777150750160217,
533
+ "learning_rate": 2.2285101596432084e-05,
534
+ "loss": 0.5737,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 1.1343283582089552,
539
+ "grad_norm": 1.0940109491348267,
540
+ "learning_rate": 2.2068228185107524e-05,
541
+ "loss": 0.5084,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 1.1492537313432836,
546
+ "grad_norm": 1.0106772184371948,
547
+ "learning_rate": 2.1849438560905697e-05,
548
+ "loss": 0.5529,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 1.164179104477612,
553
+ "grad_norm": 0.9576737880706787,
554
+ "learning_rate": 2.162879203819568e-05,
555
+ "loss": 0.4859,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 1.1791044776119404,
560
+ "grad_norm": 1.06365168094635,
561
+ "learning_rate": 2.1406348434755994e-05,
562
+ "loss": 0.5127,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 1.1940298507462686,
567
+ "grad_norm": 1.0055838823318481,
568
+ "learning_rate": 2.118216805555788e-05,
569
+ "loss": 0.4942,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 1.208955223880597,
574
+ "grad_norm": 1.1863685846328735,
575
+ "learning_rate": 2.0956311676416464e-05,
576
+ "loss": 0.5223,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 1.2238805970149254,
581
+ "grad_norm": 1.1252774000167847,
582
+ "learning_rate": 2.0728840527514294e-05,
583
+ "loss": 0.4785,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 1.2388059701492538,
588
+ "grad_norm": 1.134757399559021,
589
+ "learning_rate": 2.0499816276801724e-05,
590
+ "loss": 0.5052,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 1.2537313432835822,
595
+ "grad_norm": 1.0209614038467407,
596
+ "learning_rate": 2.0269301013278555e-05,
597
+ "loss": 0.5208,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 1.2686567164179103,
602
+ "grad_norm": 1.060960292816162,
603
+ "learning_rate": 2.0037357230161587e-05,
604
+ "loss": 0.4837,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 1.2835820895522387,
609
+ "grad_norm": 1.0340241193771362,
610
+ "learning_rate": 1.9804047807942564e-05,
611
+ "loss": 0.4973,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 1.2985074626865671,
616
+ "grad_norm": 1.2472810745239258,
617
+ "learning_rate": 1.956943599734112e-05,
618
+ "loss": 0.4962,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 1.3134328358208955,
623
+ "grad_norm": 1.099755883216858,
624
+ "learning_rate": 1.9333585402157365e-05,
625
+ "loss": 0.5169,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 1.328358208955224,
630
+ "grad_norm": 1.2505892515182495,
631
+ "learning_rate": 1.9096559962028746e-05,
632
+ "loss": 0.4608,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 1.3432835820895521,
637
+ "grad_norm": 1.0441431999206543,
638
+ "learning_rate": 1.88584239350959e-05,
639
+ "loss": 0.4526,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 1.3582089552238805,
644
+ "grad_norm": 1.1357834339141846,
645
+ "learning_rate": 1.861924188058205e-05,
646
+ "loss": 0.4598,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 1.373134328358209,
651
+ "grad_norm": 1.0953128337860107,
652
+ "learning_rate": 1.8379078641290923e-05,
653
+ "loss": 0.4761,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 1.3880597014925373,
658
+ "grad_norm": 1.1454157829284668,
659
+ "learning_rate": 1.8137999326027696e-05,
660
+ "loss": 0.4476,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 1.4029850746268657,
665
+ "grad_norm": 1.136718988418579,
666
+ "learning_rate": 1.7896069291947827e-05,
667
+ "loss": 0.4767,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 1.417910447761194,
672
+ "grad_norm": 1.2287747859954834,
673
+ "learning_rate": 1.7653354126838593e-05,
674
+ "loss": 0.4895,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 1.4328358208955223,
679
+ "grad_norm": 1.2421404123306274,
680
+ "learning_rate": 1.7409919631338124e-05,
681
+ "loss": 0.4497,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 1.4477611940298507,
686
+ "grad_norm": 1.2321255207061768,
687
+ "learning_rate": 1.7165831801096635e-05,
688
+ "loss": 0.4562,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 1.462686567164179,
693
+ "grad_norm": 1.145817518234253,
694
+ "learning_rate": 1.6921156808884904e-05,
695
+ "loss": 0.4579,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 1.4776119402985075,
700
+ "grad_norm": 1.1590453386306763,
701
+ "learning_rate": 1.6675960986654675e-05,
702
+ "loss": 0.4286,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 1.4925373134328357,
707
+ "grad_norm": 1.1244103908538818,
708
+ "learning_rate": 1.6430310807555884e-05,
709
+ "loss": 0.4615,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 1.5074626865671643,
714
+ "grad_norm": 1.3445566892623901,
715
+ "learning_rate": 1.618427286791568e-05,
716
+ "loss": 0.4497,
717
+ "step": 505
718
+ },
719
+ {
720
+ "epoch": 1.5223880597014925,
721
+ "grad_norm": 1.043714165687561,
722
+ "learning_rate": 1.593791386918396e-05,
723
+ "loss": 0.4193,
724
+ "step": 510
725
+ },
726
+ {
727
+ "epoch": 1.537313432835821,
728
+ "grad_norm": 1.227029800415039,
729
+ "learning_rate": 1.5691300599850495e-05,
730
+ "loss": 0.4536,
731
+ "step": 515
732
+ },
733
+ {
734
+ "epoch": 1.5522388059701493,
735
+ "grad_norm": 1.1881043910980225,
736
+ "learning_rate": 1.5444499917338398e-05,
737
+ "loss": 0.4398,
738
+ "step": 520
739
+ },
740
+ {
741
+ "epoch": 1.5671641791044775,
742
+ "grad_norm": 1.1590487957000732,
743
+ "learning_rate": 1.5197578729878915e-05,
744
+ "loss": 0.4193,
745
+ "step": 525
746
+ },
747
+ {
748
+ "epoch": 1.582089552238806,
749
+ "grad_norm": 1.143646240234375,
750
+ "learning_rate": 1.4950603978372467e-05,
751
+ "loss": 0.4248,
752
+ "step": 530
753
+ },
754
+ {
755
+ "epoch": 1.5970149253731343,
756
+ "grad_norm": 1.2340905666351318,
757
+ "learning_rate": 1.4703642618240806e-05,
758
+ "loss": 0.4214,
759
+ "step": 535
760
+ },
761
+ {
762
+ "epoch": 1.6119402985074627,
763
+ "grad_norm": 1.1602320671081543,
764
+ "learning_rate": 1.4456761601275254e-05,
765
+ "loss": 0.4379,
766
+ "step": 540
767
+ },
768
+ {
769
+ "epoch": 1.626865671641791,
770
+ "grad_norm": 1.1080914735794067,
771
+ "learning_rate": 1.4210027857485932e-05,
772
+ "loss": 0.411,
773
+ "step": 545
774
+ },
775
+ {
776
+ "epoch": 1.6417910447761193,
777
+ "grad_norm": 1.2245306968688965,
778
+ "learning_rate": 1.3963508276956832e-05,
779
+ "loss": 0.3917,
780
+ "step": 550
781
+ },
782
+ {
783
+ "epoch": 1.6567164179104479,
784
+ "grad_norm": 1.128736138343811,
785
+ "learning_rate": 1.371726969171182e-05,
786
+ "loss": 0.4208,
787
+ "step": 555
788
+ },
789
+ {
790
+ "epoch": 1.671641791044776,
791
+ "grad_norm": 1.1787062883377075,
792
+ "learning_rate": 1.34713788575963e-05,
793
+ "loss": 0.4566,
794
+ "step": 560
795
+ },
796
+ {
797
+ "epoch": 1.6865671641791045,
798
+ "grad_norm": 1.0624361038208008,
799
+ "learning_rate": 1.3225902436179515e-05,
800
+ "loss": 0.3836,
801
+ "step": 565
802
+ },
803
+ {
804
+ "epoch": 1.7014925373134329,
805
+ "grad_norm": 1.165006399154663,
806
+ "learning_rate": 1.2980906976682508e-05,
807
+ "loss": 0.4087,
808
+ "step": 570
809
+ },
810
+ {
811
+ "epoch": 1.716417910447761,
812
+ "grad_norm": 1.2284427881240845,
813
+ "learning_rate": 1.2736458897936432e-05,
814
+ "loss": 0.4,
815
+ "step": 575
816
+ },
817
+ {
818
+ "epoch": 1.7313432835820897,
819
+ "grad_norm": 1.223211646080017,
820
+ "learning_rate": 1.2492624470376253e-05,
821
+ "loss": 0.4149,
822
+ "step": 580
823
+ },
824
+ {
825
+ "epoch": 1.7462686567164178,
826
+ "grad_norm": 1.2130999565124512,
827
+ "learning_rate": 1.22494697980747e-05,
828
+ "loss": 0.3921,
829
+ "step": 585
830
+ },
831
+ {
832
+ "epoch": 1.7611940298507462,
833
+ "grad_norm": 1.1766337156295776,
834
+ "learning_rate": 1.20070608008213e-05,
835
+ "loss": 0.4109,
836
+ "step": 590
837
+ },
838
+ {
839
+ "epoch": 1.7761194029850746,
840
+ "grad_norm": 1.3741768598556519,
841
+ "learning_rate": 1.1765463196251349e-05,
842
+ "loss": 0.4134,
843
+ "step": 595
844
+ },
845
+ {
846
+ "epoch": 1.7910447761194028,
847
+ "grad_norm": 1.1917859315872192,
848
+ "learning_rate": 1.1524742482029728e-05,
849
+ "loss": 0.4252,
850
+ "step": 600
851
+ },
852
+ {
853
+ "epoch": 1.8059701492537314,
854
+ "grad_norm": 1.2797183990478516,
855
+ "learning_rate": 1.1284963918094346e-05,
856
+ "loss": 0.3733,
857
+ "step": 605
858
+ },
859
+ {
860
+ "epoch": 1.8208955223880596,
861
+ "grad_norm": 1.1159847974777222,
862
+ "learning_rate": 1.104619250896399e-05,
863
+ "loss": 0.3997,
864
+ "step": 610
865
+ },
866
+ {
867
+ "epoch": 1.835820895522388,
868
+ "grad_norm": 1.3664534091949463,
869
+ "learning_rate": 1.0808492986115476e-05,
870
+ "loss": 0.3821,
871
+ "step": 615
872
+ },
873
+ {
874
+ "epoch": 1.8507462686567164,
875
+ "grad_norm": 1.210760235786438,
876
+ "learning_rate": 1.0571929790434792e-05,
877
+ "loss": 0.4107,
878
+ "step": 620
879
+ },
880
+ {
881
+ "epoch": 1.8656716417910446,
882
+ "grad_norm": 1.217391848564148,
883
+ "learning_rate": 1.0336567054747033e-05,
884
+ "loss": 0.4017,
885
+ "step": 625
886
+ },
887
+ {
888
+ "epoch": 1.8805970149253732,
889
+ "grad_norm": 1.246115803718567,
890
+ "learning_rate": 1.0102468586429808e-05,
891
+ "loss": 0.3738,
892
+ "step": 630
893
+ },
894
+ {
895
+ "epoch": 1.8955223880597014,
896
+ "grad_norm": 1.0801810026168823,
897
+ "learning_rate": 9.86969785011497e-06,
898
+ "loss": 0.3889,
899
+ "step": 635
900
+ },
901
+ {
902
+ "epoch": 1.9104477611940298,
903
+ "grad_norm": 1.1230485439300537,
904
+ "learning_rate": 9.638317950483167e-06,
905
+ "loss": 0.4431,
906
+ "step": 640
907
+ },
908
+ {
909
+ "epoch": 1.9253731343283582,
910
+ "grad_norm": 1.2072858810424805,
911
+ "learning_rate": 9.408391615156023e-06,
912
+ "loss": 0.3637,
913
+ "step": 645
914
+ },
915
+ {
916
+ "epoch": 1.9402985074626866,
917
+ "grad_norm": 1.1373963356018066,
918
+ "learning_rate": 9.179981177690566e-06,
919
+ "loss": 0.3738,
920
+ "step": 650
921
+ },
922
+ {
923
+ "epoch": 1.955223880597015,
924
+ "grad_norm": 1.2958288192749023,
925
+ "learning_rate": 8.953148560680419e-06,
926
+ "loss": 0.3544,
927
+ "step": 655
928
+ },
929
+ {
930
+ "epoch": 1.9701492537313432,
931
+ "grad_norm": 1.0563827753067017,
932
+ "learning_rate": 8.727955258968462e-06,
933
+ "loss": 0.3481,
934
+ "step": 660
935
+ },
936
+ {
937
+ "epoch": 1.9850746268656716,
938
+ "grad_norm": 1.2998480796813965,
939
+ "learning_rate": 8.504462322975442e-06,
940
+ "loss": 0.3665,
941
+ "step": 665
942
+ },
943
+ {
944
+ "epoch": 2.0,
945
+ "grad_norm": 1.3147248029708862,
946
+ "learning_rate": 8.282730342149059e-06,
947
+ "loss": 0.3383,
948
+ "step": 670
949
+ },
950
+ {
951
+ "epoch": 2.014925373134328,
952
+ "grad_norm": 1.1079124212265015,
953
+ "learning_rate": 8.062819428538009e-06,
954
+ "loss": 0.2936,
955
+ "step": 675
956
+ },
957
+ {
958
+ "epoch": 2.029850746268657,
959
+ "grad_norm": 1.253826379776001,
960
+ "learning_rate": 7.844789200495517e-06,
961
+ "loss": 0.297,
962
+ "step": 680
963
+ },
964
+ {
965
+ "epoch": 2.044776119402985,
966
+ "grad_norm": 1.0365105867385864,
967
+ "learning_rate": 7.628698766516625e-06,
968
+ "loss": 0.3391,
969
+ "step": 685
970
+ },
971
+ {
972
+ "epoch": 2.0597014925373136,
973
+ "grad_norm": 1.523829698562622,
974
+ "learning_rate": 7.414606709213735e-06,
975
+ "loss": 0.2841,
976
+ "step": 690
977
+ },
978
+ {
979
+ "epoch": 2.074626865671642,
980
+ "grad_norm": 1.3061442375183105,
981
+ "learning_rate": 7.202571069434772e-06,
982
+ "loss": 0.2874,
983
+ "step": 695
984
+ },
985
+ {
986
+ "epoch": 2.08955223880597,
987
+ "grad_norm": 1.1913034915924072,
988
+ "learning_rate": 6.992649330528146e-06,
989
+ "loss": 0.3118,
990
+ "step": 700
991
+ },
992
+ {
993
+ "epoch": 2.1044776119402986,
994
+ "grad_norm": 1.2372983694076538,
995
+ "learning_rate": 6.78489840275887e-06,
996
+ "loss": 0.3048,
997
+ "step": 705
998
+ },
999
+ {
1000
+ "epoch": 2.1194029850746268,
1001
+ "grad_norm": 1.207451581954956,
1002
+ "learning_rate": 6.579374607880116e-06,
1003
+ "loss": 0.3184,
1004
+ "step": 710
1005
+ },
1006
+ {
1007
+ "epoch": 2.1343283582089554,
1008
+ "grad_norm": 1.1948586702346802,
1009
+ "learning_rate": 6.376133663864196e-06,
1010
+ "loss": 0.2921,
1011
+ "step": 715
1012
+ },
1013
+ {
1014
+ "epoch": 2.1492537313432836,
1015
+ "grad_norm": 1.109611988067627,
1016
+ "learning_rate": 6.175230669797306e-06,
1017
+ "loss": 0.2919,
1018
+ "step": 720
1019
+ },
1020
+ {
1021
+ "epoch": 2.1641791044776117,
1022
+ "grad_norm": 1.3636291027069092,
1023
+ "learning_rate": 5.976720090942066e-06,
1024
+ "loss": 0.2716,
1025
+ "step": 725
1026
+ },
1027
+ {
1028
+ "epoch": 2.1791044776119404,
1029
+ "grad_norm": 1.219353199005127,
1030
+ "learning_rate": 5.780655743971844e-06,
1031
+ "loss": 0.3033,
1032
+ "step": 730
1033
+ },
1034
+ {
1035
+ "epoch": 2.1940298507462686,
1036
+ "grad_norm": 1.2699675559997559,
1037
+ "learning_rate": 5.587090782380912e-06,
1038
+ "loss": 0.3124,
1039
+ "step": 735
1040
+ },
1041
+ {
1042
+ "epoch": 2.208955223880597,
1043
+ "grad_norm": 1.3106281757354736,
1044
+ "learning_rate": 5.3960776820744415e-06,
1045
+ "loss": 0.254,
1046
+ "step": 740
1047
+ },
1048
+ {
1049
+ "epoch": 2.2238805970149254,
1050
+ "grad_norm": 1.1213213205337524,
1051
+ "learning_rate": 5.207668227142178e-06,
1052
+ "loss": 0.2919,
1053
+ "step": 745
1054
+ },
1055
+ {
1056
+ "epoch": 2.2388059701492535,
1057
+ "grad_norm": 1.3240259885787964,
1058
+ "learning_rate": 5.021913495819593e-06,
1059
+ "loss": 0.2833,
1060
+ "step": 750
1061
+ },
1062
+ {
1063
+ "epoch": 2.253731343283582,
1064
+ "grad_norm": 1.1573519706726074,
1065
+ "learning_rate": 4.838863846640524e-06,
1066
+ "loss": 0.3073,
1067
+ "step": 755
1068
+ },
1069
+ {
1070
+ "epoch": 2.2686567164179103,
1071
+ "grad_norm": 1.3405065536499023,
1072
+ "learning_rate": 4.6585689047848264e-06,
1073
+ "loss": 0.2861,
1074
+ "step": 760
1075
+ },
1076
+ {
1077
+ "epoch": 2.283582089552239,
1078
+ "grad_norm": 1.0261584520339966,
1079
+ "learning_rate": 4.481077548624871e-06,
1080
+ "loss": 0.2648,
1081
+ "step": 765
1082
+ },
1083
+ {
1084
+ "epoch": 2.298507462686567,
1085
+ "grad_norm": 1.32846999168396,
1086
+ "learning_rate": 4.306437896474523e-06,
1087
+ "loss": 0.2879,
1088
+ "step": 770
1089
+ },
1090
+ {
1091
+ "epoch": 2.3134328358208958,
1092
+ "grad_norm": 1.1488946676254272,
1093
+ "learning_rate": 4.134697293544158e-06,
1094
+ "loss": 0.2564,
1095
+ "step": 775
1096
+ },
1097
+ {
1098
+ "epoch": 2.328358208955224,
1099
+ "grad_norm": 1.0947158336639404,
1100
+ "learning_rate": 3.965902299105245e-06,
1101
+ "loss": 0.2802,
1102
+ "step": 780
1103
+ },
1104
+ {
1105
+ "epoch": 2.343283582089552,
1106
+ "grad_norm": 1.0991296768188477,
1107
+ "learning_rate": 3.8000986738680245e-06,
1108
+ "loss": 0.2903,
1109
+ "step": 785
1110
+ },
1111
+ {
1112
+ "epoch": 2.3582089552238807,
1113
+ "grad_norm": 1.1161385774612427,
1114
+ "learning_rate": 3.637331367575698e-06,
1115
+ "loss": 0.2712,
1116
+ "step": 790
1117
+ },
1118
+ {
1119
+ "epoch": 2.373134328358209,
1120
+ "grad_norm": 1.5450501441955566,
1121
+ "learning_rate": 3.4776445068184365e-06,
1122
+ "loss": 0.2758,
1123
+ "step": 795
1124
+ },
1125
+ {
1126
+ "epoch": 2.388059701492537,
1127
+ "grad_norm": 1.128070592880249,
1128
+ "learning_rate": 3.32108138307054e-06,
1129
+ "loss": 0.2778,
1130
+ "step": 800
1131
+ },
1132
+ {
1133
+ "epoch": 2.4029850746268657,
1134
+ "grad_norm": 1.107636570930481,
1135
+ "learning_rate": 3.1676844409540607e-06,
1136
+ "loss": 0.2878,
1137
+ "step": 805
1138
+ },
1139
+ {
1140
+ "epoch": 2.417910447761194,
1141
+ "grad_norm": 1.1108747720718384,
1142
+ "learning_rate": 3.017495266731942e-06,
1143
+ "loss": 0.2509,
1144
+ "step": 810
1145
+ },
1146
+ {
1147
+ "epoch": 2.4328358208955225,
1148
+ "grad_norm": 1.2078962326049805,
1149
+ "learning_rate": 2.8705545770338758e-06,
1150
+ "loss": 0.295,
1151
+ "step": 815
1152
+ },
1153
+ {
1154
+ "epoch": 2.4477611940298507,
1155
+ "grad_norm": 1.092396855354309,
1156
+ "learning_rate": 2.7269022078179638e-06,
1157
+ "loss": 0.2683,
1158
+ "step": 820
1159
+ },
1160
+ {
1161
+ "epoch": 2.4626865671641793,
1162
+ "grad_norm": 1.1813055276870728,
1163
+ "learning_rate": 2.5865771035710777e-06,
1164
+ "loss": 0.2995,
1165
+ "step": 825
1166
+ },
1167
+ {
1168
+ "epoch": 2.4776119402985075,
1169
+ "grad_norm": 1.1523305177688599,
1170
+ "learning_rate": 2.449617306750913e-06,
1171
+ "loss": 0.3208,
1172
+ "step": 830
1173
+ },
1174
+ {
1175
+ "epoch": 2.4925373134328357,
1176
+ "grad_norm": 1.1093213558197021,
1177
+ "learning_rate": 2.3160599474726073e-06,
1178
+ "loss": 0.2873,
1179
+ "step": 835
1180
+ },
1181
+ {
1182
+ "epoch": 2.5074626865671643,
1183
+ "grad_norm": 1.1179418563842773,
1184
+ "learning_rate": 2.1859412334426853e-06,
1185
+ "loss": 0.2613,
1186
+ "step": 840
1187
+ },
1188
+ {
1189
+ "epoch": 2.5223880597014925,
1190
+ "grad_norm": 1.1804648637771606,
1191
+ "learning_rate": 2.0592964401430377e-06,
1192
+ "loss": 0.2934,
1193
+ "step": 845
1194
+ },
1195
+ {
1196
+ "epoch": 2.5373134328358207,
1197
+ "grad_norm": 1.260128378868103,
1198
+ "learning_rate": 1.936159901267682e-06,
1199
+ "loss": 0.2912,
1200
+ "step": 850
1201
+ },
1202
+ {
1203
+ "epoch": 2.5522388059701493,
1204
+ "grad_norm": 1.1166480779647827,
1205
+ "learning_rate": 1.8165649994148203e-06,
1206
+ "loss": 0.2507,
1207
+ "step": 855
1208
+ },
1209
+ {
1210
+ "epoch": 2.5671641791044775,
1211
+ "grad_norm": 1.1106736660003662,
1212
+ "learning_rate": 1.7005441570367164e-06,
1213
+ "loss": 0.2609,
1214
+ "step": 860
1215
+ },
1216
+ {
1217
+ "epoch": 2.582089552238806,
1218
+ "grad_norm": 1.2218323945999146,
1219
+ "learning_rate": 1.5881288276499211e-06,
1220
+ "loss": 0.2887,
1221
+ "step": 865
1222
+ },
1223
+ {
1224
+ "epoch": 2.5970149253731343,
1225
+ "grad_norm": 1.1319966316223145,
1226
+ "learning_rate": 1.4793494873081504e-06,
1227
+ "loss": 0.2547,
1228
+ "step": 870
1229
+ },
1230
+ {
1231
+ "epoch": 2.611940298507463,
1232
+ "grad_norm": 1.1479063034057617,
1233
+ "learning_rate": 1.374235626340128e-06,
1234
+ "loss": 0.2594,
1235
+ "step": 875
1236
+ },
1237
+ {
1238
+ "epoch": 2.626865671641791,
1239
+ "grad_norm": 1.2150938510894775,
1240
+ "learning_rate": 1.2728157413547232e-06,
1241
+ "loss": 0.2899,
1242
+ "step": 880
1243
+ },
1244
+ {
1245
+ "epoch": 2.6417910447761193,
1246
+ "grad_norm": 1.1205209493637085,
1247
+ "learning_rate": 1.1751173275154403e-06,
1248
+ "loss": 0.2238,
1249
+ "step": 885
1250
+ },
1251
+ {
1252
+ "epoch": 2.656716417910448,
1253
+ "grad_norm": 1.1784629821777344,
1254
+ "learning_rate": 1.0811668710864098e-06,
1255
+ "loss": 0.2659,
1256
+ "step": 890
1257
+ },
1258
+ {
1259
+ "epoch": 2.671641791044776,
1260
+ "grad_norm": 1.2707682847976685,
1261
+ "learning_rate": 9.909898422519198e-07,
1262
+ "loss": 0.262,
1263
+ "step": 895
1264
+ },
1265
+ {
1266
+ "epoch": 2.6865671641791042,
1267
+ "grad_norm": 1.0494028329849243,
1268
+ "learning_rate": 9.046106882113753e-07,
1269
+ "loss": 0.2817,
1270
+ "step": 900
1271
+ },
1272
+ {
1273
+ "epoch": 2.701492537313433,
1274
+ "grad_norm": 1.4347975254058838,
1275
+ "learning_rate": 8.220528265516125e-07,
1276
+ "loss": 0.2685,
1277
+ "step": 905
1278
+ },
1279
+ {
1280
+ "epoch": 2.716417910447761,
1281
+ "grad_norm": 1.1479558944702148,
1282
+ "learning_rate": 7.433386388983343e-07,
1283
+ "loss": 0.2736,
1284
+ "step": 910
1285
+ },
1286
+ {
1287
+ "epoch": 2.7313432835820897,
1288
+ "grad_norm": 1.0413694381713867,
1289
+ "learning_rate": 6.684894648484069e-07,
1290
+ "loss": 0.2911,
1291
+ "step": 915
1292
+ },
1293
+ {
1294
+ "epoch": 2.746268656716418,
1295
+ "grad_norm": 1.1672275066375732,
1296
+ "learning_rate": 5.975255961846343e-07,
1297
+ "loss": 0.2262,
1298
+ "step": 920
1299
+ },
1300
+ {
1301
+ "epoch": 2.7611940298507465,
1302
+ "grad_norm": 1.1373767852783203,
1303
+ "learning_rate": 5.304662713746205e-07,
1304
+ "loss": 0.2714,
1305
+ "step": 925
1306
+ },
1307
+ {
1308
+ "epoch": 2.7761194029850746,
1309
+ "grad_norm": 1.1416226625442505,
1310
+ "learning_rate": 4.6732967035517326e-07,
1311
+ "loss": 0.2465,
1312
+ "step": 930
1313
+ },
1314
+ {
1315
+ "epoch": 2.791044776119403,
1316
+ "grad_norm": 1.2618836164474487,
1317
+ "learning_rate": 4.081329096036829e-07,
1318
+ "loss": 0.2971,
1319
+ "step": 935
1320
+ },
1321
+ {
1322
+ "epoch": 2.8059701492537314,
1323
+ "grad_norm": 1.1520038843154907,
1324
+ "learning_rate": 3.528920374977979e-07,
1325
+ "loss": 0.2506,
1326
+ "step": 940
1327
+ },
1328
+ {
1329
+ "epoch": 2.8208955223880596,
1330
+ "grad_norm": 1.231122612953186,
1331
+ "learning_rate": 3.0162202996468156e-07,
1332
+ "loss": 0.2525,
1333
+ "step": 945
1334
+ },
1335
+ {
1336
+ "epoch": 2.835820895522388,
1337
+ "grad_norm": 1.2169133424758911,
1338
+ "learning_rate": 2.5433678642100664e-07,
1339
+ "loss": 0.2834,
1340
+ "step": 950
1341
+ },
1342
+ {
1343
+ "epoch": 2.8507462686567164,
1344
+ "grad_norm": 1.2695796489715576,
1345
+ "learning_rate": 2.110491260047792e-07,
1346
+ "loss": 0.2772,
1347
+ "step": 955
1348
+ },
1349
+ {
1350
+ "epoch": 2.8656716417910446,
1351
+ "grad_norm": 1.1452456712722778,
1352
+ "learning_rate": 1.7177078410005041e-07,
1353
+ "loss": 0.2584,
1354
+ "step": 960
1355
+ },
1356
+ {
1357
+ "epoch": 2.8805970149253732,
1358
+ "grad_norm": 1.173682689666748,
1359
+ "learning_rate": 1.3651240915542652e-07,
1360
+ "loss": 0.2962,
1361
+ "step": 965
1362
+ },
1363
+ {
1364
+ "epoch": 2.8955223880597014,
1365
+ "grad_norm": 1.1223686933517456,
1366
+ "learning_rate": 1.0528355979724624e-07,
1367
+ "loss": 0.31,
1368
+ "step": 970
1369
+ },
1370
+ {
1371
+ "epoch": 2.91044776119403,
1372
+ "grad_norm": 1.1745933294296265,
1373
+ "learning_rate": 7.809270223821552e-08,
1374
+ "loss": 0.2515,
1375
+ "step": 975
1376
+ },
1377
+ {
1378
+ "epoch": 2.925373134328358,
1379
+ "grad_norm": 1.2465354204177856,
1380
+ "learning_rate": 5.4947207982204985e-08,
1381
+ "loss": 0.2521,
1382
+ "step": 980
1383
+ },
1384
+ {
1385
+ "epoch": 2.9402985074626864,
1386
+ "grad_norm": 1.225307822227478,
1387
+ "learning_rate": 3.585335182580529e-08,
1388
+ "loss": 0.2909,
1389
+ "step": 985
1390
+ },
1391
+ {
1392
+ "epoch": 2.955223880597015,
1393
+ "grad_norm": 1.2866557836532593,
1394
+ "learning_rate": 2.0816310157227846e-08,
1395
+ "loss": 0.2654,
1396
+ "step": 990
1397
+ },
1398
+ {
1399
+ "epoch": 2.970149253731343,
1400
+ "grad_norm": 1.1425098180770874,
1401
+ "learning_rate": 9.840159552969019e-09,
1402
+ "loss": 0.2893,
1403
+ "step": 995
1404
+ },
1405
+ {
1406
+ "epoch": 2.9850746268656714,
1407
+ "grad_norm": 1.2532261610031128,
1408
+ "learning_rate": 2.9278756726375257e-09,
1409
+ "loss": 0.2369,
1410
+ "step": 1000
1411
+ },
1412
+ {
1413
+ "epoch": 3.0,
1414
+ "grad_norm": 1.1680136919021606,
1415
+ "learning_rate": 8.133245225305785e-11,
1416
+ "loss": 0.2499,
1417
+ "step": 1005
1418
+ },
1419
+ {
1420
+ "epoch": 3.0,
1421
+ "step": 1005,
1422
+ "total_flos": 1.482127184633004e+18,
1423
+ "train_loss": 0.5478373010360187,
1424
+ "train_runtime": 672.1067,
1425
+ "train_samples_per_second": 47.805,
1426
+ "train_steps_per_second": 1.495
1427
+ }
1428
+ ],
1429
+ "logging_steps": 5,
1430
+ "max_steps": 1005,
1431
+ "num_input_tokens_seen": 0,
1432
+ "num_train_epochs": 3,
1433
+ "save_steps": 2000,
1434
+ "stateful_callbacks": {
1435
+ "TrainerControl": {
1436
+ "args": {
1437
+ "should_epoch_stop": false,
1438
+ "should_evaluate": false,
1439
+ "should_log": false,
1440
+ "should_save": false,
1441
+ "should_training_stop": false
1442
+ },
1443
+ "attributes": {}
1444
+ }
1445
+ },
1446
+ "total_flos": 1.482127184633004e+18,
1447
+ "train_batch_size": 2,
1448
+ "trial_name": null,
1449
+ "trial_params": null
1450
+ }
2_128_e3_3e-5/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:029e470f5991d42ad81e00ee01edf16b3c021d8308a6a72505c8365c9183f4b9
3
+ size 8145
2_128_e3_3e-5/vocab.json ADDED
The diff for this file is too large to render. See raw diff