RayDu0010 commited on
Commit
51ab1ab
·
verified ·
1 Parent(s): a0113dc

Upload folder using huggingface_hub

Browse files
47_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: 47_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
+ # 47_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
47_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
+ "gate_proj",
28
+ "down_proj",
29
+ "q_proj",
30
+ "o_proj",
31
+ "v_proj",
32
+ "up_proj",
33
+ "k_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
47_128_e3_3e-5/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbcb25ca41ba05f0eabc14b1d16ecce6bbaba195519b850cc3c4d87c7face419
3
+ size 791751704
47_128_e3_3e-5/all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.3183315431894548e+18,
4
+ "train_loss": 0.5906400148812522,
5
+ "train_runtime": 605.3446,
6
+ "train_samples": 9981,
7
+ "train_samples_per_second": 49.464,
8
+ "train_steps_per_second": 1.546
9
+ }
47_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
+ }
47_128_e3_3e-5/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
47_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
+ }
47_128_e3_3e-5/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
47_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
+ }
47_128_e3_3e-5/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.3183315431894548e+18,
4
+ "train_loss": 0.5906400148812522,
5
+ "train_runtime": 605.3446,
6
+ "train_samples": 9981,
7
+ "train_samples_per_second": 49.464,
8
+ "train_steps_per_second": 1.546
9
+ }
47_128_e3_3e-5/trainer_state.json ADDED
@@ -0,0 +1,1352 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 936,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.016025641025641024,
14
+ "grad_norm": 1.0152113437652588,
15
+ "learning_rate": 2.553191489361702e-06,
16
+ "loss": 1.3396,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.03205128205128205,
21
+ "grad_norm": 0.7789538502693176,
22
+ "learning_rate": 5.74468085106383e-06,
23
+ "loss": 1.3895,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.04807692307692308,
28
+ "grad_norm": 0.5663994550704956,
29
+ "learning_rate": 8.936170212765958e-06,
30
+ "loss": 1.3552,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.0641025641025641,
35
+ "grad_norm": 0.5530088543891907,
36
+ "learning_rate": 1.2127659574468084e-05,
37
+ "loss": 1.3031,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.08012820512820513,
42
+ "grad_norm": 0.5026463270187378,
43
+ "learning_rate": 1.531914893617021e-05,
44
+ "loss": 1.2908,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.09615384615384616,
49
+ "grad_norm": 0.5668408274650574,
50
+ "learning_rate": 1.8510638297872342e-05,
51
+ "loss": 1.2771,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.11217948717948718,
56
+ "grad_norm": 0.5910139679908752,
57
+ "learning_rate": 2.170212765957447e-05,
58
+ "loss": 1.2455,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.1282051282051282,
63
+ "grad_norm": 0.4434743821620941,
64
+ "learning_rate": 2.4893617021276595e-05,
65
+ "loss": 1.2561,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.14423076923076922,
70
+ "grad_norm": 0.4208380877971649,
71
+ "learning_rate": 2.8085106382978723e-05,
72
+ "loss": 1.2191,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.16025641025641027,
77
+ "grad_norm": 0.4137757420539856,
78
+ "learning_rate": 2.999962535868399e-05,
79
+ "loss": 1.215,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.1762820512820513,
84
+ "grad_norm": 0.4942193925380707,
85
+ "learning_rate": 2.9995410858796248e-05,
86
+ "loss": 1.2029,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.19230769230769232,
91
+ "grad_norm": 0.39837828278541565,
92
+ "learning_rate": 2.9986514877504622e-05,
93
+ "loss": 1.1738,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.20833333333333334,
98
+ "grad_norm": 0.5015051364898682,
99
+ "learning_rate": 2.997294019208353e-05,
100
+ "loss": 1.1747,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.22435897435897437,
105
+ "grad_norm": 0.4704567790031433,
106
+ "learning_rate": 2.995469104047204e-05,
107
+ "loss": 1.1484,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.2403846153846154,
112
+ "grad_norm": 0.8549149036407471,
113
+ "learning_rate": 2.9931773119950775e-05,
114
+ "loss": 1.1669,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.2564102564102564,
119
+ "grad_norm": 0.558935821056366,
120
+ "learning_rate": 2.99041935853633e-05,
121
+ "loss": 1.0948,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.2724358974358974,
126
+ "grad_norm": 0.6137709617614746,
127
+ "learning_rate": 2.9871961046882377e-05,
128
+ "loss": 1.1202,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.28846153846153844,
133
+ "grad_norm": 0.6656123399734497,
134
+ "learning_rate": 2.983508556732196e-05,
135
+ "loss": 1.1023,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.30448717948717946,
140
+ "grad_norm": 0.5648577213287354,
141
+ "learning_rate": 2.979357865899561e-05,
142
+ "loss": 1.0933,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.32051282051282054,
147
+ "grad_norm": 0.5777170062065125,
148
+ "learning_rate": 2.9747453280122436e-05,
149
+ "loss": 1.1068,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.33653846153846156,
154
+ "grad_norm": 0.5488264560699463,
155
+ "learning_rate": 2.969672383078159e-05,
156
+ "loss": 1.1017,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.3525641025641026,
161
+ "grad_norm": 0.5426512956619263,
162
+ "learning_rate": 2.964140614841668e-05,
163
+ "loss": 1.0567,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.3685897435897436,
168
+ "grad_norm": 0.6047531366348267,
169
+ "learning_rate": 2.9581517502891373e-05,
170
+ "loss": 1.0836,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.38461538461538464,
175
+ "grad_norm": 0.5907122492790222,
176
+ "learning_rate": 2.9517076591097877e-05,
177
+ "loss": 1.0331,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.40064102564102566,
182
+ "grad_norm": 0.6308097839355469,
183
+ "learning_rate": 2.9448103531119858e-05,
184
+ "loss": 0.9814,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.4166666666666667,
189
+ "grad_norm": 0.7864812612533569,
190
+ "learning_rate": 2.9374619855951676e-05,
191
+ "loss": 1.0021,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.4326923076923077,
196
+ "grad_norm": 0.6837188005447388,
197
+ "learning_rate": 2.929664850677595e-05,
198
+ "loss": 1.0085,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.44871794871794873,
203
+ "grad_norm": 0.7336333394050598,
204
+ "learning_rate": 2.921421382580142e-05,
205
+ "loss": 0.9884,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.46474358974358976,
210
+ "grad_norm": 0.6663369536399841,
211
+ "learning_rate": 2.9127341548663437e-05,
212
+ "loss": 1.0268,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.4807692307692308,
217
+ "grad_norm": 0.7226543426513672,
218
+ "learning_rate": 2.9036058796389484e-05,
219
+ "loss": 0.9887,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.4967948717948718,
224
+ "grad_norm": 0.7532234787940979,
225
+ "learning_rate": 2.8940394066932122e-05,
226
+ "loss": 0.9726,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.5128205128205128,
231
+ "grad_norm": 0.7370257377624512,
232
+ "learning_rate": 2.8840377226272102e-05,
233
+ "loss": 0.9482,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.5288461538461539,
238
+ "grad_norm": 0.6937476992607117,
239
+ "learning_rate": 2.873603949909435e-05,
240
+ "loss": 0.9048,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.5448717948717948,
245
+ "grad_norm": 0.79671311378479,
246
+ "learning_rate": 2.862741345903985e-05,
247
+ "loss": 0.902,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.5608974358974359,
252
+ "grad_norm": 0.894153892993927,
253
+ "learning_rate": 2.8514533018536286e-05,
254
+ "loss": 0.9479,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.5769230769230769,
259
+ "grad_norm": 0.7863439917564392,
260
+ "learning_rate": 2.839743341821082e-05,
261
+ "loss": 0.8866,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.592948717948718,
266
+ "grad_norm": 0.7851524353027344,
267
+ "learning_rate": 2.8276151215888127e-05,
268
+ "loss": 0.8897,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.6089743589743589,
273
+ "grad_norm": 0.8348742127418518,
274
+ "learning_rate": 2.8150724275177312e-05,
275
+ "loss": 0.8854,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.625,
280
+ "grad_norm": 0.9825112819671631,
281
+ "learning_rate": 2.8021191753651025e-05,
282
+ "loss": 0.8294,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.6410256410256411,
287
+ "grad_norm": 0.8231203556060791,
288
+ "learning_rate": 2.788759409062078e-05,
289
+ "loss": 0.8633,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.657051282051282,
294
+ "grad_norm": 0.8391622304916382,
295
+ "learning_rate": 2.774997299451196e-05,
296
+ "loss": 0.8104,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.6730769230769231,
301
+ "grad_norm": 1.005391001701355,
302
+ "learning_rate": 2.760837142984274e-05,
303
+ "loss": 0.823,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.6891025641025641,
308
+ "grad_norm": 0.8318763971328735,
309
+ "learning_rate": 2.7462833603810768e-05,
310
+ "loss": 0.8734,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.7051282051282052,
315
+ "grad_norm": 0.9581466913223267,
316
+ "learning_rate": 2.731340495249196e-05,
317
+ "loss": 0.813,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.7211538461538461,
322
+ "grad_norm": 0.8254058957099915,
323
+ "learning_rate": 2.7160132126655602e-05,
324
+ "loss": 0.8527,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 0.7371794871794872,
329
+ "grad_norm": 0.9684002995491028,
330
+ "learning_rate": 2.700306297720026e-05,
331
+ "loss": 0.8028,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 0.7532051282051282,
336
+ "grad_norm": 0.8673291206359863,
337
+ "learning_rate": 2.684224654021498e-05,
338
+ "loss": 0.8189,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 0.7692307692307693,
343
+ "grad_norm": 0.8910443782806396,
344
+ "learning_rate": 2.667773302167053e-05,
345
+ "loss": 0.769,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 0.7852564102564102,
350
+ "grad_norm": 0.986312985420227,
351
+ "learning_rate": 2.6509573781745376e-05,
352
+ "loss": 0.7687,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 0.8012820512820513,
357
+ "grad_norm": 1.141728162765503,
358
+ "learning_rate": 2.6337821318791303e-05,
359
+ "loss": 0.7597,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 0.8173076923076923,
364
+ "grad_norm": 0.9165905714035034,
365
+ "learning_rate": 2.6162529252943772e-05,
366
+ "loss": 0.7674,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 0.8333333333333334,
371
+ "grad_norm": 1.130582571029663,
372
+ "learning_rate": 2.598375230938198e-05,
373
+ "loss": 0.7397,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 0.8493589743589743,
378
+ "grad_norm": 0.9542099833488464,
379
+ "learning_rate": 2.5801546301244004e-05,
380
+ "loss": 0.8094,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 0.8653846153846154,
385
+ "grad_norm": 0.9411763548851013,
386
+ "learning_rate": 2.561596811220225e-05,
387
+ "loss": 0.7369,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 0.8814102564102564,
392
+ "grad_norm": 0.9600223898887634,
393
+ "learning_rate": 2.5427075678704676e-05,
394
+ "loss": 0.7312,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 0.8974358974358975,
399
+ "grad_norm": 0.937028169631958,
400
+ "learning_rate": 2.5234927971887388e-05,
401
+ "loss": 0.726,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 0.9134615384615384,
406
+ "grad_norm": 1.1456159353256226,
407
+ "learning_rate": 2.503958497916419e-05,
408
+ "loss": 0.6893,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 0.9294871794871795,
413
+ "grad_norm": 1.106656789779663,
414
+ "learning_rate": 2.484110768549885e-05,
415
+ "loss": 0.7073,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 0.9455128205128205,
420
+ "grad_norm": 1.0661927461624146,
421
+ "learning_rate": 2.4639558054365917e-05,
422
+ "loss": 0.6751,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 0.9615384615384616,
427
+ "grad_norm": 1.014714241027832,
428
+ "learning_rate": 2.443499900840614e-05,
429
+ "loss": 0.6495,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 0.9775641025641025,
434
+ "grad_norm": 1.0720497369766235,
435
+ "learning_rate": 2.422749440978232e-05,
436
+ "loss": 0.7033,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 0.9935897435897436,
441
+ "grad_norm": 0.9548969864845276,
442
+ "learning_rate": 2.4017109040241948e-05,
443
+ "loss": 0.7006,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 1.0096153846153846,
448
+ "grad_norm": 1.2945890426635742,
449
+ "learning_rate": 2.3803908580892694e-05,
450
+ "loss": 0.6513,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 1.0256410256410255,
455
+ "grad_norm": 1.0701019763946533,
456
+ "learning_rate": 2.358795959169713e-05,
457
+ "loss": 0.602,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 1.0416666666666667,
462
+ "grad_norm": 1.077828288078308,
463
+ "learning_rate": 2.336932949069314e-05,
464
+ "loss": 0.6166,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 1.0576923076923077,
469
+ "grad_norm": 1.114101529121399,
470
+ "learning_rate": 2.314808653294634e-05,
471
+ "loss": 0.6613,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 1.0737179487179487,
476
+ "grad_norm": 1.1929739713668823,
477
+ "learning_rate": 2.2924299789241255e-05,
478
+ "loss": 0.5797,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 1.0897435897435896,
483
+ "grad_norm": 1.1379876136779785,
484
+ "learning_rate": 2.2698039124517843e-05,
485
+ "loss": 0.5842,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 1.1057692307692308,
490
+ "grad_norm": 1.0790177583694458,
491
+ "learning_rate": 2.2469375176060017e-05,
492
+ "loss": 0.5579,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 1.1217948717948718,
497
+ "grad_norm": 1.275397539138794,
498
+ "learning_rate": 2.2238379331443118e-05,
499
+ "loss": 0.5848,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 1.1378205128205128,
504
+ "grad_norm": 1.1523648500442505,
505
+ "learning_rate": 2.2005123706247113e-05,
506
+ "loss": 0.5638,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 1.1538461538461537,
511
+ "grad_norm": 2.1769275665283203,
512
+ "learning_rate": 2.1769681121542527e-05,
513
+ "loss": 0.5847,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 1.169871794871795,
518
+ "grad_norm": 1.0980788469314575,
519
+ "learning_rate": 2.153212508115613e-05,
520
+ "loss": 0.5659,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 1.185897435897436,
525
+ "grad_norm": 1.1439530849456787,
526
+ "learning_rate": 2.1292529748723436e-05,
527
+ "loss": 0.5971,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 1.2019230769230769,
532
+ "grad_norm": 1.2120379209518433,
533
+ "learning_rate": 2.1050969924535267e-05,
534
+ "loss": 0.5255,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 1.217948717948718,
539
+ "grad_norm": 1.2199236154556274,
540
+ "learning_rate": 2.080752102218553e-05,
541
+ "loss": 0.5698,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 1.233974358974359,
546
+ "grad_norm": 1.3541291952133179,
547
+ "learning_rate": 2.05622590450275e-05,
548
+ "loss": 0.5301,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 1.25,
553
+ "grad_norm": 1.0394927263259888,
554
+ "learning_rate": 2.0315260562446048e-05,
555
+ "loss": 0.5702,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 1.266025641025641,
560
+ "grad_norm": 1.092409372329712,
561
+ "learning_rate": 2.0066602685953065e-05,
562
+ "loss": 0.5758,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 1.282051282051282,
567
+ "grad_norm": 1.0886386632919312,
568
+ "learning_rate": 1.9816363045113748e-05,
569
+ "loss": 0.4998,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 1.2980769230769231,
574
+ "grad_norm": 1.0895962715148926,
575
+ "learning_rate": 1.9564619763311043e-05,
576
+ "loss": 0.56,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 1.314102564102564,
581
+ "grad_norm": 1.1397515535354614,
582
+ "learning_rate": 1.931145143335601e-05,
583
+ "loss": 0.5455,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 1.330128205128205,
588
+ "grad_norm": 1.1242400407791138,
589
+ "learning_rate": 1.905693709295158e-05,
590
+ "loss": 0.519,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 1.3461538461538463,
595
+ "grad_norm": 1.0989638566970825,
596
+ "learning_rate": 1.880115620001743e-05,
597
+ "loss": 0.5472,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 1.3621794871794872,
602
+ "grad_norm": 1.214547038078308,
603
+ "learning_rate": 1.854418860788369e-05,
604
+ "loss": 0.4916,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 1.3782051282051282,
609
+ "grad_norm": 1.1969079971313477,
610
+ "learning_rate": 1.8286114540361192e-05,
611
+ "loss": 0.5111,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 1.3942307692307692,
616
+ "grad_norm": 1.1338014602661133,
617
+ "learning_rate": 1.802701456669603e-05,
618
+ "loss": 0.5169,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 1.4102564102564101,
623
+ "grad_norm": 1.1708518266677856,
624
+ "learning_rate": 1.776696957641634e-05,
625
+ "loss": 0.5234,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 1.4262820512820513,
630
+ "grad_norm": 1.1686491966247559,
631
+ "learning_rate": 1.7506060754079025e-05,
632
+ "loss": 0.5093,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 1.4423076923076923,
637
+ "grad_norm": 1.1275078058242798,
638
+ "learning_rate": 1.7244369553924408e-05,
639
+ "loss": 0.5143,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 1.4583333333333333,
644
+ "grad_norm": 1.2874627113342285,
645
+ "learning_rate": 1.6981977674446692e-05,
646
+ "loss": 0.497,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 1.4743589743589745,
651
+ "grad_norm": 1.0959718227386475,
652
+ "learning_rate": 1.671896703288815e-05,
653
+ "loss": 0.5022,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 1.4903846153846154,
658
+ "grad_norm": 1.1907219886779785,
659
+ "learning_rate": 1.6455419739665037e-05,
660
+ "loss": 0.4991,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 1.5064102564102564,
665
+ "grad_norm": 1.1953725814819336,
666
+ "learning_rate": 1.6191418072733176e-05,
667
+ "loss": 0.4638,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 1.5224358974358974,
672
+ "grad_norm": 1.1828627586364746,
673
+ "learning_rate": 1.5927044451901265e-05,
674
+ "loss": 0.4526,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 1.5384615384615383,
679
+ "grad_norm": 1.231021523475647,
680
+ "learning_rate": 1.5662381413099885e-05,
681
+ "loss": 0.4772,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 1.5544871794871795,
686
+ "grad_norm": 1.2150564193725586,
687
+ "learning_rate": 1.5397511582614238e-05,
688
+ "loss": 0.4707,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 1.5705128205128205,
693
+ "grad_norm": 1.2000958919525146,
694
+ "learning_rate": 1.5132517651288716e-05,
695
+ "loss": 0.4626,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 1.5865384615384617,
700
+ "grad_norm": 1.222455382347107,
701
+ "learning_rate": 1.4867482348711284e-05,
702
+ "loss": 0.5336,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 1.6025641025641026,
707
+ "grad_norm": 1.1986652612686157,
708
+ "learning_rate": 1.4602488417385766e-05,
709
+ "loss": 0.4666,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 1.6185897435897436,
714
+ "grad_norm": 1.194980263710022,
715
+ "learning_rate": 1.4337618586900119e-05,
716
+ "loss": 0.4718,
717
+ "step": 505
718
+ },
719
+ {
720
+ "epoch": 1.6346153846153846,
721
+ "grad_norm": 1.509094476699829,
722
+ "learning_rate": 1.4072955548098741e-05,
723
+ "loss": 0.4372,
724
+ "step": 510
725
+ },
726
+ {
727
+ "epoch": 1.6506410256410255,
728
+ "grad_norm": 1.3054978847503662,
729
+ "learning_rate": 1.3808581927266827e-05,
730
+ "loss": 0.474,
731
+ "step": 515
732
+ },
733
+ {
734
+ "epoch": 1.6666666666666665,
735
+ "grad_norm": 1.4275447130203247,
736
+ "learning_rate": 1.354458026033497e-05,
737
+ "loss": 0.4555,
738
+ "step": 520
739
+ },
740
+ {
741
+ "epoch": 1.6826923076923077,
742
+ "grad_norm": 1.1465692520141602,
743
+ "learning_rate": 1.3281032967111851e-05,
744
+ "loss": 0.3947,
745
+ "step": 525
746
+ },
747
+ {
748
+ "epoch": 1.6987179487179487,
749
+ "grad_norm": 1.2671295404434204,
750
+ "learning_rate": 1.3018022325553313e-05,
751
+ "loss": 0.4751,
752
+ "step": 530
753
+ },
754
+ {
755
+ "epoch": 1.7147435897435899,
756
+ "grad_norm": 1.2190231084823608,
757
+ "learning_rate": 1.2755630446075594e-05,
758
+ "loss": 0.4272,
759
+ "step": 535
760
+ },
761
+ {
762
+ "epoch": 1.7307692307692308,
763
+ "grad_norm": 1.2719204425811768,
764
+ "learning_rate": 1.2493939245920982e-05,
765
+ "loss": 0.4435,
766
+ "step": 540
767
+ },
768
+ {
769
+ "epoch": 1.7467948717948718,
770
+ "grad_norm": 1.1029138565063477,
771
+ "learning_rate": 1.2233030423583662e-05,
772
+ "loss": 0.45,
773
+ "step": 545
774
+ },
775
+ {
776
+ "epoch": 1.7628205128205128,
777
+ "grad_norm": 1.2707008123397827,
778
+ "learning_rate": 1.1972985433303976e-05,
779
+ "loss": 0.4111,
780
+ "step": 550
781
+ },
782
+ {
783
+ "epoch": 1.7788461538461537,
784
+ "grad_norm": 1.2311984300613403,
785
+ "learning_rate": 1.1713885459638814e-05,
786
+ "loss": 0.4413,
787
+ "step": 555
788
+ },
789
+ {
790
+ "epoch": 1.7948717948717947,
791
+ "grad_norm": 1.3677246570587158,
792
+ "learning_rate": 1.1455811392116308e-05,
793
+ "loss": 0.427,
794
+ "step": 560
795
+ },
796
+ {
797
+ "epoch": 1.810897435897436,
798
+ "grad_norm": 1.280250906944275,
799
+ "learning_rate": 1.1198843799982572e-05,
800
+ "loss": 0.4404,
801
+ "step": 565
802
+ },
803
+ {
804
+ "epoch": 1.8269230769230769,
805
+ "grad_norm": 1.304382085800171,
806
+ "learning_rate": 1.0943062907048421e-05,
807
+ "loss": 0.4069,
808
+ "step": 570
809
+ },
810
+ {
811
+ "epoch": 1.842948717948718,
812
+ "grad_norm": 1.230911374092102,
813
+ "learning_rate": 1.0688548566643992e-05,
814
+ "loss": 0.4145,
815
+ "step": 575
816
+ },
817
+ {
818
+ "epoch": 1.858974358974359,
819
+ "grad_norm": 1.1724607944488525,
820
+ "learning_rate": 1.0435380236688958e-05,
821
+ "loss": 0.3839,
822
+ "step": 580
823
+ },
824
+ {
825
+ "epoch": 1.875,
826
+ "grad_norm": 1.2222930192947388,
827
+ "learning_rate": 1.0183636954886256e-05,
828
+ "loss": 0.388,
829
+ "step": 585
830
+ },
831
+ {
832
+ "epoch": 1.891025641025641,
833
+ "grad_norm": 1.4366291761398315,
834
+ "learning_rate": 9.933397314046936e-06,
835
+ "loss": 0.3973,
836
+ "step": 590
837
+ },
838
+ {
839
+ "epoch": 1.907051282051282,
840
+ "grad_norm": 1.2406185865402222,
841
+ "learning_rate": 9.684739437553957e-06,
842
+ "loss": 0.4002,
843
+ "step": 595
844
+ },
845
+ {
846
+ "epoch": 1.9230769230769231,
847
+ "grad_norm": 1.3002291917800903,
848
+ "learning_rate": 9.437740954972494e-06,
849
+ "loss": 0.454,
850
+ "step": 600
851
+ },
852
+ {
853
+ "epoch": 1.939102564102564,
854
+ "grad_norm": 1.1818573474884033,
855
+ "learning_rate": 9.192478977814472e-06,
856
+ "loss": 0.3851,
857
+ "step": 605
858
+ },
859
+ {
860
+ "epoch": 1.9551282051282053,
861
+ "grad_norm": 1.3259531259536743,
862
+ "learning_rate": 8.949030075464729e-06,
863
+ "loss": 0.376,
864
+ "step": 610
865
+ },
866
+ {
867
+ "epoch": 1.9711538461538463,
868
+ "grad_norm": 1.1797511577606201,
869
+ "learning_rate": 8.707470251276568e-06,
870
+ "loss": 0.4092,
871
+ "step": 615
872
+ },
873
+ {
874
+ "epoch": 1.9871794871794872,
875
+ "grad_norm": 1.409891963005066,
876
+ "learning_rate": 8.467874918843875e-06,
877
+ "loss": 0.4336,
878
+ "step": 620
879
+ },
880
+ {
881
+ "epoch": 2.003205128205128,
882
+ "grad_norm": 1.2189013957977295,
883
+ "learning_rate": 8.230318878457474e-06,
884
+ "loss": 0.3807,
885
+ "step": 625
886
+ },
887
+ {
888
+ "epoch": 2.019230769230769,
889
+ "grad_norm": 1.479553461074829,
890
+ "learning_rate": 7.994876293752893e-06,
891
+ "loss": 0.3123,
892
+ "step": 630
893
+ },
894
+ {
895
+ "epoch": 2.03525641025641,
896
+ "grad_norm": 1.2196060419082642,
897
+ "learning_rate": 7.761620668556888e-06,
898
+ "loss": 0.341,
899
+ "step": 635
900
+ },
901
+ {
902
+ "epoch": 2.051282051282051,
903
+ "grad_norm": 1.1641342639923096,
904
+ "learning_rate": 7.530624823939984e-06,
905
+ "loss": 0.3192,
906
+ "step": 640
907
+ },
908
+ {
909
+ "epoch": 2.0673076923076925,
910
+ "grad_norm": 1.2591949701309204,
911
+ "learning_rate": 7.3019608754821635e-06,
912
+ "loss": 0.3522,
913
+ "step": 645
914
+ },
915
+ {
916
+ "epoch": 2.0833333333333335,
917
+ "grad_norm": 1.4112589359283447,
918
+ "learning_rate": 7.075700210758744e-06,
919
+ "loss": 0.3175,
920
+ "step": 650
921
+ },
922
+ {
923
+ "epoch": 2.0993589743589745,
924
+ "grad_norm": 1.2372866868972778,
925
+ "learning_rate": 6.851913467053668e-06,
926
+ "loss": 0.3578,
927
+ "step": 655
928
+ },
929
+ {
930
+ "epoch": 2.1153846153846154,
931
+ "grad_norm": 1.3091179132461548,
932
+ "learning_rate": 6.63067050930686e-06,
933
+ "loss": 0.3715,
934
+ "step": 660
935
+ },
936
+ {
937
+ "epoch": 2.1314102564102564,
938
+ "grad_norm": 1.362852931022644,
939
+ "learning_rate": 6.412040408302874e-06,
940
+ "loss": 0.342,
941
+ "step": 665
942
+ },
943
+ {
944
+ "epoch": 2.1474358974358974,
945
+ "grad_norm": 1.202670931816101,
946
+ "learning_rate": 6.19609141910731e-06,
947
+ "loss": 0.3297,
948
+ "step": 670
949
+ },
950
+ {
951
+ "epoch": 2.1634615384615383,
952
+ "grad_norm": 1.2479032278060913,
953
+ "learning_rate": 5.982890959758057e-06,
954
+ "loss": 0.369,
955
+ "step": 675
956
+ },
957
+ {
958
+ "epoch": 2.1794871794871793,
959
+ "grad_norm": 1.3502240180969238,
960
+ "learning_rate": 5.772505590217679e-06,
961
+ "loss": 0.3384,
962
+ "step": 680
963
+ },
964
+ {
965
+ "epoch": 2.1955128205128207,
966
+ "grad_norm": 1.2109317779541016,
967
+ "learning_rate": 5.5650009915938675e-06,
968
+ "loss": 0.3226,
969
+ "step": 685
970
+ },
971
+ {
972
+ "epoch": 2.2115384615384617,
973
+ "grad_norm": 1.1589144468307495,
974
+ "learning_rate": 5.360441945634085e-06,
975
+ "loss": 0.3115,
976
+ "step": 690
977
+ },
978
+ {
979
+ "epoch": 2.2275641025641026,
980
+ "grad_norm": 1.3105396032333374,
981
+ "learning_rate": 5.158892314501157e-06,
982
+ "loss": 0.293,
983
+ "step": 695
984
+ },
985
+ {
986
+ "epoch": 2.2435897435897436,
987
+ "grad_norm": 1.3465224504470825,
988
+ "learning_rate": 4.960415020835811e-06,
989
+ "loss": 0.3375,
990
+ "step": 700
991
+ },
992
+ {
993
+ "epoch": 2.2596153846153846,
994
+ "grad_norm": 1.3763256072998047,
995
+ "learning_rate": 4.765072028112614e-06,
996
+ "loss": 0.2767,
997
+ "step": 705
998
+ },
999
+ {
1000
+ "epoch": 2.2756410256410255,
1001
+ "grad_norm": 1.1780006885528564,
1002
+ "learning_rate": 4.5729243212953285e-06,
1003
+ "loss": 0.2764,
1004
+ "step": 710
1005
+ },
1006
+ {
1007
+ "epoch": 2.2916666666666665,
1008
+ "grad_norm": 1.26458740234375,
1009
+ "learning_rate": 4.384031887797753e-06,
1010
+ "loss": 0.3049,
1011
+ "step": 715
1012
+ },
1013
+ {
1014
+ "epoch": 2.3076923076923075,
1015
+ "grad_norm": 1.3050872087478638,
1016
+ "learning_rate": 4.198453698755995e-06,
1017
+ "loss": 0.3114,
1018
+ "step": 720
1019
+ },
1020
+ {
1021
+ "epoch": 2.323717948717949,
1022
+ "grad_norm": 1.2401924133300781,
1023
+ "learning_rate": 4.016247690618017e-06,
1024
+ "loss": 0.3242,
1025
+ "step": 725
1026
+ },
1027
+ {
1028
+ "epoch": 2.33974358974359,
1029
+ "grad_norm": 1.446115493774414,
1030
+ "learning_rate": 3.837470747056231e-06,
1031
+ "loss": 0.2663,
1032
+ "step": 730
1033
+ },
1034
+ {
1035
+ "epoch": 2.355769230769231,
1036
+ "grad_norm": 1.1924484968185425,
1037
+ "learning_rate": 3.6621786812086953e-06,
1038
+ "loss": 0.3284,
1039
+ "step": 735
1040
+ },
1041
+ {
1042
+ "epoch": 2.371794871794872,
1043
+ "grad_norm": 1.3654570579528809,
1044
+ "learning_rate": 3.490426218254629e-06,
1045
+ "loss": 0.2823,
1046
+ "step": 740
1047
+ },
1048
+ {
1049
+ "epoch": 2.3878205128205128,
1050
+ "grad_norm": 1.3856276273727417,
1051
+ "learning_rate": 3.322266978329468e-06,
1052
+ "loss": 0.3242,
1053
+ "step": 745
1054
+ },
1055
+ {
1056
+ "epoch": 2.4038461538461537,
1057
+ "grad_norm": 1.2586690187454224,
1058
+ "learning_rate": 3.1577534597850254e-06,
1059
+ "loss": 0.3232,
1060
+ "step": 750
1061
+ },
1062
+ {
1063
+ "epoch": 2.4198717948717947,
1064
+ "grad_norm": 1.24107027053833,
1065
+ "learning_rate": 2.9969370227997434e-06,
1066
+ "loss": 0.3233,
1067
+ "step": 755
1068
+ },
1069
+ {
1070
+ "epoch": 2.435897435897436,
1071
+ "grad_norm": 1.4022530317306519,
1072
+ "learning_rate": 2.8398678733444006e-06,
1073
+ "loss": 0.2746,
1074
+ "step": 760
1075
+ },
1076
+ {
1077
+ "epoch": 2.451923076923077,
1078
+ "grad_norm": 1.2960535287857056,
1079
+ "learning_rate": 2.68659504750804e-06,
1080
+ "loss": 0.2943,
1081
+ "step": 765
1082
+ },
1083
+ {
1084
+ "epoch": 2.467948717948718,
1085
+ "grad_norm": 1.2257177829742432,
1086
+ "learning_rate": 2.5371663961892345e-06,
1087
+ "loss": 0.3065,
1088
+ "step": 770
1089
+ },
1090
+ {
1091
+ "epoch": 2.483974358974359,
1092
+ "grad_norm": 1.4506504535675049,
1093
+ "learning_rate": 2.3916285701572586e-06,
1094
+ "loss": 0.3291,
1095
+ "step": 775
1096
+ },
1097
+ {
1098
+ "epoch": 2.5,
1099
+ "grad_norm": 1.1449183225631714,
1100
+ "learning_rate": 2.250027005488041e-06,
1101
+ "loss": 0.3104,
1102
+ "step": 780
1103
+ },
1104
+ {
1105
+ "epoch": 2.516025641025641,
1106
+ "grad_norm": 1.2913508415222168,
1107
+ "learning_rate": 2.112405909379221e-06,
1108
+ "loss": 0.3236,
1109
+ "step": 785
1110
+ },
1111
+ {
1112
+ "epoch": 2.532051282051282,
1113
+ "grad_norm": 1.3039257526397705,
1114
+ "learning_rate": 1.9788082463489743e-06,
1115
+ "loss": 0.2929,
1116
+ "step": 790
1117
+ },
1118
+ {
1119
+ "epoch": 2.5480769230769234,
1120
+ "grad_norm": 1.3046826124191284,
1121
+ "learning_rate": 1.8492757248226933e-06,
1122
+ "loss": 0.2808,
1123
+ "step": 795
1124
+ },
1125
+ {
1126
+ "epoch": 2.564102564102564,
1127
+ "grad_norm": 1.3544787168502808,
1128
+ "learning_rate": 1.7238487841118705e-06,
1129
+ "loss": 0.2895,
1130
+ "step": 800
1131
+ },
1132
+ {
1133
+ "epoch": 2.5801282051282053,
1134
+ "grad_norm": 1.2708160877227783,
1135
+ "learning_rate": 1.602566581789184e-06,
1136
+ "loss": 0.3007,
1137
+ "step": 805
1138
+ },
1139
+ {
1140
+ "epoch": 2.5961538461538463,
1141
+ "grad_norm": 1.2018102407455444,
1142
+ "learning_rate": 1.4854669814637145e-06,
1143
+ "loss": 0.2946,
1144
+ "step": 810
1145
+ },
1146
+ {
1147
+ "epoch": 2.6121794871794872,
1148
+ "grad_norm": 1.2204782962799072,
1149
+ "learning_rate": 1.3725865409601517e-06,
1150
+ "loss": 0.296,
1151
+ "step": 815
1152
+ },
1153
+ {
1154
+ "epoch": 2.628205128205128,
1155
+ "grad_norm": 1.4640064239501953,
1156
+ "learning_rate": 1.2639605009056486e-06,
1157
+ "loss": 0.2819,
1158
+ "step": 820
1159
+ },
1160
+ {
1161
+ "epoch": 2.644230769230769,
1162
+ "grad_norm": 1.2100766897201538,
1163
+ "learning_rate": 1.1596227737279014e-06,
1164
+ "loss": 0.2966,
1165
+ "step": 825
1166
+ },
1167
+ {
1168
+ "epoch": 2.66025641025641,
1169
+ "grad_norm": 1.2902816534042358,
1170
+ "learning_rate": 1.0596059330678742e-06,
1171
+ "loss": 0.3219,
1172
+ "step": 830
1173
+ },
1174
+ {
1175
+ "epoch": 2.676282051282051,
1176
+ "grad_norm": 1.4012353420257568,
1177
+ "learning_rate": 9.639412036105166e-07,
1178
+ "loss": 0.3503,
1179
+ "step": 835
1180
+ },
1181
+ {
1182
+ "epoch": 2.6923076923076925,
1183
+ "grad_norm": 1.2469552755355835,
1184
+ "learning_rate": 8.726584513365638e-07,
1185
+ "loss": 0.2992,
1186
+ "step": 840
1187
+ },
1188
+ {
1189
+ "epoch": 2.7083333333333335,
1190
+ "grad_norm": 1.3012679815292358,
1191
+ "learning_rate": 7.85786174198585e-07,
1192
+ "loss": 0.3078,
1193
+ "step": 845
1194
+ },
1195
+ {
1196
+ "epoch": 2.7243589743589745,
1197
+ "grad_norm": 1.2277898788452148,
1198
+ "learning_rate": 7.03351493224046e-07,
1199
+ "loss": 0.2744,
1200
+ "step": 850
1201
+ },
1202
+ {
1203
+ "epoch": 2.7403846153846154,
1204
+ "grad_norm": 1.2280902862548828,
1205
+ "learning_rate": 6.253801440483225e-07,
1206
+ "loss": 0.2796,
1207
+ "step": 855
1208
+ },
1209
+ {
1210
+ "epoch": 2.7564102564102564,
1211
+ "grad_norm": 1.3304959535598755,
1212
+ "learning_rate": 5.518964688801436e-07,
1213
+ "loss": 0.3008,
1214
+ "step": 860
1215
+ },
1216
+ {
1217
+ "epoch": 2.7724358974358974,
1218
+ "grad_norm": 1.3201477527618408,
1219
+ "learning_rate": 4.829234089021229e-07,
1220
+ "loss": 0.2651,
1221
+ "step": 865
1222
+ },
1223
+ {
1224
+ "epoch": 2.7884615384615383,
1225
+ "grad_norm": 1.2202049493789673,
1226
+ "learning_rate": 4.1848249710862597e-07,
1227
+ "loss": 0.2897,
1228
+ "step": 870
1229
+ },
1230
+ {
1231
+ "epoch": 2.8044871794871797,
1232
+ "grad_norm": 1.2734965085983276,
1233
+ "learning_rate": 3.585938515833237e-07,
1234
+ "loss": 0.3183,
1235
+ "step": 875
1236
+ },
1237
+ {
1238
+ "epoch": 2.8205128205128203,
1239
+ "grad_norm": 1.2806587219238281,
1240
+ "learning_rate": 3.032761692184105e-07,
1241
+ "loss": 0.315,
1242
+ "step": 880
1243
+ },
1244
+ {
1245
+ "epoch": 2.8365384615384617,
1246
+ "grad_norm": 1.185431718826294,
1247
+ "learning_rate": 2.525467198775655e-07,
1248
+ "loss": 0.2865,
1249
+ "step": 885
1250
+ },
1251
+ {
1252
+ "epoch": 2.8525641025641026,
1253
+ "grad_norm": 1.391359806060791,
1254
+ "learning_rate": 2.064213410043886e-07,
1255
+ "loss": 0.2592,
1256
+ "step": 890
1257
+ },
1258
+ {
1259
+ "epoch": 2.8685897435897436,
1260
+ "grad_norm": 1.2940336465835571,
1261
+ "learning_rate": 1.6491443267803886e-07,
1262
+ "loss": 0.2955,
1263
+ "step": 895
1264
+ },
1265
+ {
1266
+ "epoch": 2.8846153846153846,
1267
+ "grad_norm": 1.2029128074645996,
1268
+ "learning_rate": 1.2803895311762404e-07,
1269
+ "loss": 0.3024,
1270
+ "step": 900
1271
+ },
1272
+ {
1273
+ "epoch": 2.9006410256410255,
1274
+ "grad_norm": 1.2401751279830933,
1275
+ "learning_rate": 9.580641463670326e-08,
1276
+ "loss": 0.3436,
1277
+ "step": 905
1278
+ },
1279
+ {
1280
+ "epoch": 2.9166666666666665,
1281
+ "grad_norm": 1.3220281600952148,
1282
+ "learning_rate": 6.822688004922529e-08,
1283
+ "loss": 0.2829,
1284
+ "step": 910
1285
+ },
1286
+ {
1287
+ "epoch": 2.9326923076923075,
1288
+ "grad_norm": 1.2516306638717651,
1289
+ "learning_rate": 4.530895952796321e-08,
1290
+ "loss": 0.3066,
1291
+ "step": 915
1292
+ },
1293
+ {
1294
+ "epoch": 2.948717948717949,
1295
+ "grad_norm": 1.1940361261367798,
1296
+ "learning_rate": 2.7059807916468003e-08,
1297
+ "loss": 0.3064,
1298
+ "step": 920
1299
+ },
1300
+ {
1301
+ "epoch": 2.96474358974359,
1302
+ "grad_norm": 1.1401761770248413,
1303
+ "learning_rate": 1.3485122495380253e-08,
1304
+ "loss": 0.3047,
1305
+ "step": 925
1306
+ },
1307
+ {
1308
+ "epoch": 2.980769230769231,
1309
+ "grad_norm": 1.2352294921875,
1310
+ "learning_rate": 4.589141203752978e-09,
1311
+ "loss": 0.3024,
1312
+ "step": 930
1313
+ },
1314
+ {
1315
+ "epoch": 2.996794871794872,
1316
+ "grad_norm": 1.3165572881698608,
1317
+ "learning_rate": 3.74641316008284e-10,
1318
+ "loss": 0.2755,
1319
+ "step": 935
1320
+ },
1321
+ {
1322
+ "epoch": 3.0,
1323
+ "step": 936,
1324
+ "total_flos": 1.3183315431894548e+18,
1325
+ "train_loss": 0.5906400148812522,
1326
+ "train_runtime": 605.3446,
1327
+ "train_samples_per_second": 49.464,
1328
+ "train_steps_per_second": 1.546
1329
+ }
1330
+ ],
1331
+ "logging_steps": 5,
1332
+ "max_steps": 936,
1333
+ "num_input_tokens_seen": 0,
1334
+ "num_train_epochs": 3,
1335
+ "save_steps": 2000,
1336
+ "stateful_callbacks": {
1337
+ "TrainerControl": {
1338
+ "args": {
1339
+ "should_epoch_stop": false,
1340
+ "should_evaluate": false,
1341
+ "should_log": false,
1342
+ "should_save": false,
1343
+ "should_training_stop": false
1344
+ },
1345
+ "attributes": {}
1346
+ }
1347
+ },
1348
+ "total_flos": 1.3183315431894548e+18,
1349
+ "train_batch_size": 2,
1350
+ "trial_name": null,
1351
+ "trial_params": null
1352
+ }
47_128_e3_3e-5/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b10a6638891b4bd803c12aa22f2734567b4402aa188b05000b3d5a4cabf1502
3
+ size 8145
47_128_e3_3e-5/vocab.json ADDED
The diff for this file is too large to render. See raw diff