RayDu0010 commited on
Commit
8dd2df2
·
verified ·
1 Parent(s): a17149e

Upload folder using huggingface_hub

Browse files
19_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: 19_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
+ # 19_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
19_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
+ "k_proj",
28
+ "up_proj",
29
+ "q_proj",
30
+ "v_proj",
31
+ "down_proj",
32
+ "o_proj",
33
+ "gate_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
19_128_e3_3e-5/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:088d7e1a6c1e7d8ad3df8906213e359369a3d12550e46723aee6fcfca0909eb7
3
+ size 791751704
19_128_e3_3e-5/all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.3759050762074194e+18,
4
+ "train_loss": 0.5874219706771784,
5
+ "train_runtime": 632.2067,
6
+ "train_samples": 10278,
7
+ "train_samples_per_second": 48.772,
8
+ "train_steps_per_second": 1.528
9
+ }
19_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
+ }
19_128_e3_3e-5/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
19_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
+ }
19_128_e3_3e-5/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
19_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
+ }
19_128_e3_3e-5/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.3759050762074194e+18,
4
+ "train_loss": 0.5874219706771784,
5
+ "train_runtime": 632.2067,
6
+ "train_samples": 10278,
7
+ "train_samples_per_second": 48.772,
8
+ "train_steps_per_second": 1.528
9
+ }
19_128_e3_3e-5/trainer_state.json ADDED
@@ -0,0 +1,1394 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 966,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.015552099533437015,
14
+ "grad_norm": 1.1665724515914917,
15
+ "learning_rate": 2.4489795918367347e-06,
16
+ "loss": 1.3511,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.03110419906687403,
21
+ "grad_norm": 0.7245913743972778,
22
+ "learning_rate": 5.510204081632653e-06,
23
+ "loss": 1.4013,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.04665629860031104,
28
+ "grad_norm": 0.5644237399101257,
29
+ "learning_rate": 8.571428571428571e-06,
30
+ "loss": 1.2894,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.06220839813374806,
35
+ "grad_norm": 1.1369251012802124,
36
+ "learning_rate": 1.163265306122449e-05,
37
+ "loss": 1.3037,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.07776049766718507,
42
+ "grad_norm": 0.5249414443969727,
43
+ "learning_rate": 1.4693877551020408e-05,
44
+ "loss": 1.2825,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.09331259720062209,
49
+ "grad_norm": 0.5075188875198364,
50
+ "learning_rate": 1.7755102040816327e-05,
51
+ "loss": 1.2408,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.1088646967340591,
56
+ "grad_norm": 0.5279954671859741,
57
+ "learning_rate": 2.0816326530612247e-05,
58
+ "loss": 1.2877,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.12441679626749612,
63
+ "grad_norm": 0.48007676005363464,
64
+ "learning_rate": 2.3877551020408164e-05,
65
+ "loss": 1.2534,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.13996889580093314,
70
+ "grad_norm": 0.52071613073349,
71
+ "learning_rate": 2.6938775510204084e-05,
72
+ "loss": 1.2314,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.15552099533437014,
77
+ "grad_norm": 0.5492898225784302,
78
+ "learning_rate": 3e-05,
79
+ "loss": 1.2783,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.17107309486780714,
84
+ "grad_norm": 0.5895590782165527,
85
+ "learning_rate": 2.999779934619741e-05,
86
+ "loss": 1.1216,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.18662519440124417,
91
+ "grad_norm": 0.45102763175964355,
92
+ "learning_rate": 2.9991198030506576e-05,
93
+ "loss": 1.1467,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.20217729393468117,
98
+ "grad_norm": 0.46132299304008484,
99
+ "learning_rate": 2.9980197989888906e-05,
100
+ "loss": 1.1478,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.2177293934681182,
105
+ "grad_norm": 0.5213153958320618,
106
+ "learning_rate": 2.9964802451981894e-05,
107
+ "loss": 1.1288,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.2332814930015552,
112
+ "grad_norm": 0.7137885093688965,
113
+ "learning_rate": 2.9945015934152078e-05,
114
+ "loss": 1.1262,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.24883359253499224,
119
+ "grad_norm": 0.5476042032241821,
120
+ "learning_rate": 2.992084424216955e-05,
121
+ "loss": 1.1398,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.2643856920684292,
126
+ "grad_norm": 0.5478896498680115,
127
+ "learning_rate": 2.9892294468504425e-05,
128
+ "loss": 1.1329,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.27993779160186627,
133
+ "grad_norm": 0.5697451829910278,
134
+ "learning_rate": 2.9859374990245774e-05,
135
+ "loss": 1.0797,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.2954898911353033,
140
+ "grad_norm": 0.4974559247493744,
141
+ "learning_rate": 2.982209546664359e-05,
142
+ "loss": 1.1171,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.3110419906687403,
147
+ "grad_norm": 0.5971369743347168,
148
+ "learning_rate": 2.97804668362746e-05,
149
+ "loss": 1.1315,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.3265940902021773,
154
+ "grad_norm": 0.5410080552101135,
155
+ "learning_rate": 2.9734501313832623e-05,
156
+ "loss": 1.1018,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.3421461897356143,
161
+ "grad_norm": 0.5843712687492371,
162
+ "learning_rate": 2.9684212386544562e-05,
163
+ "loss": 1.0267,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.35769828926905134,
168
+ "grad_norm": 0.6015697121620178,
169
+ "learning_rate": 2.9629614810212954e-05,
170
+ "loss": 1.0076,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.37325038880248834,
175
+ "grad_norm": 0.602651834487915,
176
+ "learning_rate": 2.957072460488634e-05,
177
+ "loss": 1.0124,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.38880248833592534,
182
+ "grad_norm": 0.6042071580886841,
183
+ "learning_rate": 2.9507559050158618e-05,
184
+ "loss": 1.0516,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.40435458786936235,
189
+ "grad_norm": 0.6740609407424927,
190
+ "learning_rate": 2.9440136680098882e-05,
191
+ "loss": 0.999,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.4199066874027994,
196
+ "grad_norm": 0.6953685283660889,
197
+ "learning_rate": 2.9368477277813134e-05,
198
+ "loss": 0.9843,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.4354587869362364,
203
+ "grad_norm": 0.6302007436752319,
204
+ "learning_rate": 2.929260186963954e-05,
205
+ "loss": 1.0633,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.4510108864696734,
210
+ "grad_norm": 0.5916042327880859,
211
+ "learning_rate": 2.9212532718978817e-05,
212
+ "loss": 0.9495,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.4665629860031104,
217
+ "grad_norm": 0.7407164573669434,
218
+ "learning_rate": 2.9128293319761762e-05,
219
+ "loss": 0.9612,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.4821150855365474,
224
+ "grad_norm": 0.7023082971572876,
225
+ "learning_rate": 2.90399083895556e-05,
226
+ "loss": 0.9939,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.4976671850699845,
231
+ "grad_norm": 0.6539564728736877,
232
+ "learning_rate": 2.894740386231136e-05,
233
+ "loss": 0.9772,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.5132192846034215,
238
+ "grad_norm": 0.7266659736633301,
239
+ "learning_rate": 2.8850806880754333e-05,
240
+ "loss": 0.9117,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.5287713841368584,
245
+ "grad_norm": 0.6634218096733093,
246
+ "learning_rate": 2.8750145788419817e-05,
247
+ "loss": 0.9615,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.5443234836702955,
252
+ "grad_norm": 0.8376555442810059,
253
+ "learning_rate": 2.8645450121336567e-05,
254
+ "loss": 0.9009,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.5598755832037325,
259
+ "grad_norm": 0.8775768280029297,
260
+ "learning_rate": 2.85367505993603e-05,
261
+ "loss": 0.8598,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.5754276827371695,
266
+ "grad_norm": 0.7909477949142456,
267
+ "learning_rate": 2.8424079117159866e-05,
268
+ "loss": 0.8665,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.5909797822706065,
273
+ "grad_norm": 0.7720655202865601,
274
+ "learning_rate": 2.8307468734858692e-05,
275
+ "loss": 0.8442,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.6065318818040435,
280
+ "grad_norm": 0.7633533477783203,
281
+ "learning_rate": 2.8186953668334282e-05,
282
+ "loss": 0.844,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.6220839813374806,
287
+ "grad_norm": 0.8189910650253296,
288
+ "learning_rate": 2.806256927917856e-05,
289
+ "loss": 0.8068,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.6376360808709176,
294
+ "grad_norm": 0.8279641270637512,
295
+ "learning_rate": 2.793435206432205e-05,
296
+ "loss": 0.8302,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.6531881804043546,
301
+ "grad_norm": 0.8447226881980896,
302
+ "learning_rate": 2.780233964532495e-05,
303
+ "loss": 0.8415,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.6687402799377916,
308
+ "grad_norm": 0.8167079091072083,
309
+ "learning_rate": 2.7666570757338167e-05,
310
+ "loss": 0.8347,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.6842923794712286,
315
+ "grad_norm": 0.9327054023742676,
316
+ "learning_rate": 2.7527085237737654e-05,
317
+ "loss": 0.7996,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.6998444790046656,
322
+ "grad_norm": 0.811721682548523,
323
+ "learning_rate": 2.7383924014435294e-05,
324
+ "loss": 0.8218,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 0.7153965785381027,
329
+ "grad_norm": 0.8451733589172363,
330
+ "learning_rate": 2.7237129093869814e-05,
331
+ "loss": 0.8216,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 0.7309486780715396,
336
+ "grad_norm": 1.0027233362197876,
337
+ "learning_rate": 2.7086743548681228e-05,
338
+ "loss": 0.7764,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 0.7465007776049767,
343
+ "grad_norm": 1.0437304973602295,
344
+ "learning_rate": 2.693281150507246e-05,
345
+ "loss": 0.7948,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 0.7620528771384136,
350
+ "grad_norm": 0.9429616332054138,
351
+ "learning_rate": 2.6775378129861787e-05,
352
+ "loss": 0.8142,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 0.7776049766718507,
357
+ "grad_norm": 0.9813476800918579,
358
+ "learning_rate": 2.661448961722998e-05,
359
+ "loss": 0.8272,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 0.7931570762052877,
364
+ "grad_norm": 0.9027245044708252,
365
+ "learning_rate": 2.6450193175165994e-05,
366
+ "loss": 0.8074,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 0.8087091757387247,
371
+ "grad_norm": 0.9813098311424255,
372
+ "learning_rate": 2.628253701161516e-05,
373
+ "loss": 0.7499,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 0.8242612752721618,
378
+ "grad_norm": 0.9413791298866272,
379
+ "learning_rate": 2.6111570320333987e-05,
380
+ "loss": 0.7948,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 0.8398133748055988,
385
+ "grad_norm": 1.061509609222412,
386
+ "learning_rate": 2.5937343266455715e-05,
387
+ "loss": 0.7484,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 0.8553654743390358,
392
+ "grad_norm": 1.0488642454147339,
393
+ "learning_rate": 2.5759906971770828e-05,
394
+ "loss": 0.7763,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 0.8709175738724728,
399
+ "grad_norm": 0.9727094769477844,
400
+ "learning_rate": 2.5579313499726874e-05,
401
+ "loss": 0.7487,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 0.8864696734059098,
406
+ "grad_norm": 1.0250043869018555,
407
+ "learning_rate": 2.5395615840151986e-05,
408
+ "loss": 0.7112,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 0.9020217729393468,
413
+ "grad_norm": 1.0248920917510986,
414
+ "learning_rate": 2.5208867893706568e-05,
415
+ "loss": 0.7353,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 0.9175738724727839,
420
+ "grad_norm": 0.9377548098564148,
421
+ "learning_rate": 2.5019124456067755e-05,
422
+ "loss": 0.6972,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 0.9331259720062208,
427
+ "grad_norm": 1.1410298347473145,
428
+ "learning_rate": 2.4826441201851223e-05,
429
+ "loss": 0.6945,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 0.9486780715396579,
434
+ "grad_norm": 1.036268711090088,
435
+ "learning_rate": 2.463087466827511e-05,
436
+ "loss": 0.7185,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 0.9642301710730948,
441
+ "grad_norm": 0.9181062579154968,
442
+ "learning_rate": 2.4432482238570856e-05,
443
+ "loss": 0.7145,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 0.9797822706065319,
448
+ "grad_norm": 1.0887435674667358,
449
+ "learning_rate": 2.4231322125145777e-05,
450
+ "loss": 0.6757,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 0.995334370139969,
455
+ "grad_norm": 1.0177348852157593,
456
+ "learning_rate": 2.4027453352502337e-05,
457
+ "loss": 0.6528,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 1.009331259720062,
462
+ "grad_norm": 0.9978148937225342,
463
+ "learning_rate": 2.3820935739919173e-05,
464
+ "loss": 0.6153,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 1.0248833592534992,
469
+ "grad_norm": 1.1397278308868408,
470
+ "learning_rate": 2.361182988389888e-05,
471
+ "loss": 0.5659,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 1.0404354587869362,
476
+ "grad_norm": 0.9721418619155884,
477
+ "learning_rate": 2.3400197140387744e-05,
478
+ "loss": 0.6249,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 1.0559875583203733,
483
+ "grad_norm": 1.223249077796936,
484
+ "learning_rate": 2.3186099606772667e-05,
485
+ "loss": 0.5941,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 1.0715396578538103,
490
+ "grad_norm": 1.2995885610580444,
491
+ "learning_rate": 2.2969600103660517e-05,
492
+ "loss": 0.5937,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 1.0870917573872472,
497
+ "grad_norm": 1.1245447397232056,
498
+ "learning_rate": 2.275076215644526e-05,
499
+ "loss": 0.5536,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 1.1026438569206842,
504
+ "grad_norm": 0.9878132939338684,
505
+ "learning_rate": 2.2529649976668324e-05,
506
+ "loss": 0.5846,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 1.1181959564541213,
511
+ "grad_norm": 1.0392405986785889,
512
+ "learning_rate": 2.230632844317761e-05,
513
+ "loss": 0.5888,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 1.1337480559875583,
518
+ "grad_norm": 1.0900201797485352,
519
+ "learning_rate": 2.2080863083090696e-05,
520
+ "loss": 0.5771,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 1.1493001555209954,
525
+ "grad_norm": 1.2057057619094849,
526
+ "learning_rate": 2.185332005256785e-05,
527
+ "loss": 0.6013,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 1.1648522550544325,
532
+ "grad_norm": 1.0806993246078491,
533
+ "learning_rate": 2.162376611740047e-05,
534
+ "loss": 0.5444,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 1.1804043545878693,
539
+ "grad_norm": 1.0961475372314453,
540
+ "learning_rate": 2.1392268633420583e-05,
541
+ "loss": 0.5636,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 1.1959564541213064,
546
+ "grad_norm": 1.1113520860671997,
547
+ "learning_rate": 2.1158895526737313e-05,
548
+ "loss": 0.5751,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 1.2115085536547434,
553
+ "grad_norm": 1.0920902490615845,
554
+ "learning_rate": 2.0923715273805953e-05,
555
+ "loss": 0.5506,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 1.2270606531881805,
560
+ "grad_norm": 1.1759194135665894,
561
+ "learning_rate": 2.0686796881335555e-05,
562
+ "loss": 0.5751,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 1.2426127527216173,
567
+ "grad_norm": 1.2953706979751587,
568
+ "learning_rate": 2.0448209866040956e-05,
569
+ "loss": 0.5292,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 1.2581648522550544,
574
+ "grad_norm": 1.2400802373886108,
575
+ "learning_rate": 2.0208024234245155e-05,
576
+ "loss": 0.5356,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 1.2737169517884914,
581
+ "grad_norm": 1.1973105669021606,
582
+ "learning_rate": 1.9966310461338005e-05,
583
+ "loss": 0.5792,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 1.2892690513219285,
588
+ "grad_norm": 1.2088028192520142,
589
+ "learning_rate": 1.9723139471097307e-05,
590
+ "loss": 0.5398,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 1.3048211508553655,
595
+ "grad_norm": 1.1584738492965698,
596
+ "learning_rate": 1.9478582614878307e-05,
597
+ "loss": 0.5561,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 1.3203732503888026,
602
+ "grad_norm": 1.0781487226486206,
603
+ "learning_rate": 1.9232711650677754e-05,
604
+ "loss": 0.5403,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 1.3359253499222394,
609
+ "grad_norm": 1.3555227518081665,
610
+ "learning_rate": 1.8985598722078618e-05,
611
+ "loss": 0.5167,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 1.3514774494556765,
616
+ "grad_norm": 1.133573293685913,
617
+ "learning_rate": 1.8737316337081706e-05,
618
+ "loss": 0.5315,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 1.3670295489891136,
623
+ "grad_norm": 1.2002782821655273,
624
+ "learning_rate": 1.8487937346830292e-05,
625
+ "loss": 0.5322,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 1.3825816485225506,
630
+ "grad_norm": 1.1956273317337036,
631
+ "learning_rate": 1.823753492423415e-05,
632
+ "loss": 0.5454,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 1.3981337480559874,
637
+ "grad_norm": 1.0847748517990112,
638
+ "learning_rate": 1.7986182542499064e-05,
639
+ "loss": 0.5173,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 1.4136858475894245,
644
+ "grad_norm": 1.2930800914764404,
645
+ "learning_rate": 1.773395395356833e-05,
646
+ "loss": 0.4822,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 1.4292379471228616,
651
+ "grad_norm": 1.123884677886963,
652
+ "learning_rate": 1.7480923166482385e-05,
653
+ "loss": 0.436,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 1.4447900466562986,
658
+ "grad_norm": 1.1324944496154785,
659
+ "learning_rate": 1.7227164425663077e-05,
660
+ "loss": 0.5257,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 1.4603421461897357,
665
+ "grad_norm": 1.127148151397705,
666
+ "learning_rate": 1.6972752189128786e-05,
667
+ "loss": 0.4699,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 1.4758942457231727,
672
+ "grad_norm": 1.206831455230713,
673
+ "learning_rate": 1.671776110664695e-05,
674
+ "loss": 0.5033,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 1.4914463452566096,
679
+ "grad_norm": 1.3057889938354492,
680
+ "learning_rate": 1.6462265997830278e-05,
681
+ "loss": 0.5137,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 1.5069984447900466,
686
+ "grad_norm": 1.1263861656188965,
687
+ "learning_rate": 1.6206341830183137e-05,
688
+ "loss": 0.5449,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 1.5225505443234837,
693
+ "grad_norm": 1.5598522424697876,
694
+ "learning_rate": 1.595006369710455e-05,
695
+ "loss": 0.4338,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 1.5381026438569205,
700
+ "grad_norm": 1.1175037622451782,
701
+ "learning_rate": 1.5693506795854262e-05,
702
+ "loss": 0.4636,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 1.5536547433903576,
707
+ "grad_norm": 1.2600256204605103,
708
+ "learning_rate": 1.5436746405488323e-05,
709
+ "loss": 0.4665,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 1.5692068429237946,
714
+ "grad_norm": 1.0980114936828613,
715
+ "learning_rate": 1.5179857864770648e-05,
716
+ "loss": 0.4819,
717
+ "step": 505
718
+ },
719
+ {
720
+ "epoch": 1.5847589424572317,
721
+ "grad_norm": 1.2625893354415894,
722
+ "learning_rate": 1.4922916550067099e-05,
723
+ "loss": 0.4601,
724
+ "step": 510
725
+ },
726
+ {
727
+ "epoch": 1.6003110419906688,
728
+ "grad_norm": 1.1526122093200684,
729
+ "learning_rate": 1.4665997853228512e-05,
730
+ "loss": 0.4538,
731
+ "step": 515
732
+ },
733
+ {
734
+ "epoch": 1.6158631415241058,
735
+ "grad_norm": 1.2933363914489746,
736
+ "learning_rate": 1.440917715946918e-05,
737
+ "loss": 0.4669,
738
+ "step": 520
739
+ },
740
+ {
741
+ "epoch": 1.6314152410575429,
742
+ "grad_norm": 1.2250269651412964,
743
+ "learning_rate": 1.4152529825247266e-05,
744
+ "loss": 0.4563,
745
+ "step": 525
746
+ },
747
+ {
748
+ "epoch": 1.64696734059098,
749
+ "grad_norm": 1.214328408241272,
750
+ "learning_rate": 1.38961311561537e-05,
751
+ "loss": 0.4829,
752
+ "step": 530
753
+ },
754
+ {
755
+ "epoch": 1.6625194401244168,
756
+ "grad_norm": 1.1899065971374512,
757
+ "learning_rate": 1.3640056384815984e-05,
758
+ "loss": 0.4576,
759
+ "step": 535
760
+ },
761
+ {
762
+ "epoch": 1.6780715396578538,
763
+ "grad_norm": 1.2638428211212158,
764
+ "learning_rate": 1.3384380648823335e-05,
765
+ "loss": 0.4742,
766
+ "step": 540
767
+ },
768
+ {
769
+ "epoch": 1.6936236391912907,
770
+ "grad_norm": 1.4615281820297241,
771
+ "learning_rate": 1.312917896867985e-05,
772
+ "loss": 0.4565,
773
+ "step": 545
774
+ },
775
+ {
776
+ "epoch": 1.7091757387247277,
777
+ "grad_norm": 1.158037781715393,
778
+ "learning_rate": 1.2874526225791905e-05,
779
+ "loss": 0.4339,
780
+ "step": 550
781
+ },
782
+ {
783
+ "epoch": 1.7247278382581648,
784
+ "grad_norm": 1.2889515161514282,
785
+ "learning_rate": 1.2620497140496429e-05,
786
+ "loss": 0.4611,
787
+ "step": 555
788
+ },
789
+ {
790
+ "epoch": 1.7402799377916018,
791
+ "grad_norm": 1.189125418663025,
792
+ "learning_rate": 1.2367166250136427e-05,
793
+ "loss": 0.4112,
794
+ "step": 560
795
+ },
796
+ {
797
+ "epoch": 1.755832037325039,
798
+ "grad_norm": 1.255334496498108,
799
+ "learning_rate": 1.2114607887190197e-05,
800
+ "loss": 0.4427,
801
+ "step": 565
802
+ },
803
+ {
804
+ "epoch": 1.771384136858476,
805
+ "grad_norm": 1.326514482498169,
806
+ "learning_rate": 1.1862896157460625e-05,
807
+ "loss": 0.448,
808
+ "step": 570
809
+ },
810
+ {
811
+ "epoch": 1.786936236391913,
812
+ "grad_norm": 1.050620675086975,
813
+ "learning_rate": 1.1612104918331095e-05,
814
+ "loss": 0.4134,
815
+ "step": 575
816
+ },
817
+ {
818
+ "epoch": 1.80248833592535,
819
+ "grad_norm": 1.3778687715530396,
820
+ "learning_rate": 1.1362307757094127e-05,
821
+ "loss": 0.4037,
822
+ "step": 580
823
+ },
824
+ {
825
+ "epoch": 1.818040435458787,
826
+ "grad_norm": 1.1140987873077393,
827
+ "learning_rate": 1.1113577969359428e-05,
828
+ "loss": 0.4211,
829
+ "step": 585
830
+ },
831
+ {
832
+ "epoch": 1.833592534992224,
833
+ "grad_norm": 1.2997198104858398,
834
+ "learning_rate": 1.0865988537547428e-05,
835
+ "loss": 0.4474,
836
+ "step": 590
837
+ },
838
+ {
839
+ "epoch": 1.8491446345256608,
840
+ "grad_norm": 1.2311125993728638,
841
+ "learning_rate": 1.0619612109474733e-05,
842
+ "loss": 0.4117,
843
+ "step": 595
844
+ },
845
+ {
846
+ "epoch": 1.8646967340590979,
847
+ "grad_norm": 1.2353358268737793,
848
+ "learning_rate": 1.037452097703779e-05,
849
+ "loss": 0.4345,
850
+ "step": 600
851
+ },
852
+ {
853
+ "epoch": 1.880248833592535,
854
+ "grad_norm": 1.2450509071350098,
855
+ "learning_rate": 1.0130787055000947e-05,
856
+ "loss": 0.4215,
857
+ "step": 605
858
+ },
859
+ {
860
+ "epoch": 1.895800933125972,
861
+ "grad_norm": 1.1635645627975464,
862
+ "learning_rate": 9.888481859895166e-06,
863
+ "loss": 0.3964,
864
+ "step": 610
865
+ },
866
+ {
867
+ "epoch": 1.911353032659409,
868
+ "grad_norm": 1.2068110704421997,
869
+ "learning_rate": 9.647676489033671e-06,
870
+ "loss": 0.428,
871
+ "step": 615
872
+ },
873
+ {
874
+ "epoch": 1.926905132192846,
875
+ "grad_norm": 1.2517467737197876,
876
+ "learning_rate": 9.408441599650453e-06,
877
+ "loss": 0.3943,
878
+ "step": 620
879
+ },
880
+ {
881
+ "epoch": 1.9424572317262832,
882
+ "grad_norm": 1.3384915590286255,
883
+ "learning_rate": 9.170847388168056e-06,
884
+ "loss": 0.3926,
885
+ "step": 625
886
+ },
887
+ {
888
+ "epoch": 1.9580093312597202,
889
+ "grad_norm": 1.3269731998443604,
890
+ "learning_rate": 8.93496356960048e-06,
891
+ "loss": 0.3945,
892
+ "step": 630
893
+ },
894
+ {
895
+ "epoch": 1.973561430793157,
896
+ "grad_norm": 1.2442697286605835,
897
+ "learning_rate": 8.700859357097362e-06,
898
+ "loss": 0.365,
899
+ "step": 635
900
+ },
901
+ {
902
+ "epoch": 1.989113530326594,
903
+ "grad_norm": 1.3288805484771729,
904
+ "learning_rate": 8.468603441635425e-06,
905
+ "loss": 0.3966,
906
+ "step": 640
907
+ },
908
+ {
909
+ "epoch": 2.0031104199066876,
910
+ "grad_norm": 1.1929374933242798,
911
+ "learning_rate": 8.238263971863145e-06,
912
+ "loss": 0.393,
913
+ "step": 645
914
+ },
915
+ {
916
+ "epoch": 2.018662519440124,
917
+ "grad_norm": 1.252542495727539,
918
+ "learning_rate": 8.009908534104526e-06,
919
+ "loss": 0.3125,
920
+ "step": 650
921
+ },
922
+ {
923
+ "epoch": 2.0342146189735613,
924
+ "grad_norm": 1.299525260925293,
925
+ "learning_rate": 7.783604132527897e-06,
926
+ "loss": 0.3482,
927
+ "step": 655
928
+ },
929
+ {
930
+ "epoch": 2.0497667185069983,
931
+ "grad_norm": 1.264736294746399,
932
+ "learning_rate": 7.55941716948551e-06,
933
+ "loss": 0.3169,
934
+ "step": 660
935
+ },
936
+ {
937
+ "epoch": 2.0653188180404354,
938
+ "grad_norm": 1.3163446187973022,
939
+ "learning_rate": 7.337413426029715e-06,
940
+ "loss": 0.301,
941
+ "step": 665
942
+ },
943
+ {
944
+ "epoch": 2.0808709175738724,
945
+ "grad_norm": 1.332731008529663,
946
+ "learning_rate": 7.11765804261149e-06,
947
+ "loss": 0.3178,
948
+ "step": 670
949
+ },
950
+ {
951
+ "epoch": 2.0964230171073095,
952
+ "grad_norm": 1.308467984199524,
953
+ "learning_rate": 6.900215499966844e-06,
954
+ "loss": 0.3322,
955
+ "step": 675
956
+ },
957
+ {
958
+ "epoch": 2.1119751166407466,
959
+ "grad_norm": 1.137407898902893,
960
+ "learning_rate": 6.68514960019689e-06,
961
+ "loss": 0.3171,
962
+ "step": 680
963
+ },
964
+ {
965
+ "epoch": 2.1275272161741836,
966
+ "grad_norm": 1.1944776773452759,
967
+ "learning_rate": 6.4725234480469805e-06,
968
+ "loss": 0.3226,
969
+ "step": 685
970
+ },
971
+ {
972
+ "epoch": 2.1430793157076207,
973
+ "grad_norm": 1.4939020872116089,
974
+ "learning_rate": 6.262399432390485e-06,
975
+ "loss": 0.3048,
976
+ "step": 690
977
+ },
978
+ {
979
+ "epoch": 2.1586314152410577,
980
+ "grad_norm": 1.156252145767212,
981
+ "learning_rate": 6.05483920792261e-06,
982
+ "loss": 0.3564,
983
+ "step": 695
984
+ },
985
+ {
986
+ "epoch": 2.1741835147744943,
987
+ "grad_norm": 1.2493164539337158,
988
+ "learning_rate": 5.849903677069662e-06,
989
+ "loss": 0.3617,
990
+ "step": 700
991
+ },
992
+ {
993
+ "epoch": 2.1897356143079314,
994
+ "grad_norm": 1.427577018737793,
995
+ "learning_rate": 5.647652972118998e-06,
996
+ "loss": 0.3282,
997
+ "step": 705
998
+ },
999
+ {
1000
+ "epoch": 2.2052877138413685,
1001
+ "grad_norm": 1.2930374145507812,
1002
+ "learning_rate": 5.448146437575019e-06,
1003
+ "loss": 0.3015,
1004
+ "step": 710
1005
+ },
1006
+ {
1007
+ "epoch": 2.2208398133748055,
1008
+ "grad_norm": 1.4489259719848633,
1009
+ "learning_rate": 5.25144261274623e-06,
1010
+ "loss": 0.2967,
1011
+ "step": 715
1012
+ },
1013
+ {
1014
+ "epoch": 2.2363919129082426,
1015
+ "grad_norm": 1.0761257410049438,
1016
+ "learning_rate": 5.0575992145686534e-06,
1017
+ "loss": 0.3146,
1018
+ "step": 720
1019
+ },
1020
+ {
1021
+ "epoch": 2.2519440124416796,
1022
+ "grad_norm": 1.4483816623687744,
1023
+ "learning_rate": 4.86667312067046e-06,
1024
+ "loss": 0.3171,
1025
+ "step": 725
1026
+ },
1027
+ {
1028
+ "epoch": 2.2674961119751167,
1029
+ "grad_norm": 1.2705985307693481,
1030
+ "learning_rate": 4.6787203526829245e-06,
1031
+ "loss": 0.3637,
1032
+ "step": 730
1033
+ },
1034
+ {
1035
+ "epoch": 2.2830482115085537,
1036
+ "grad_norm": 1.365267038345337,
1037
+ "learning_rate": 4.493796059802525e-06,
1038
+ "loss": 0.3496,
1039
+ "step": 735
1040
+ },
1041
+ {
1042
+ "epoch": 2.298600311041991,
1043
+ "grad_norm": 1.1215273141860962,
1044
+ "learning_rate": 4.31195450260904e-06,
1045
+ "loss": 0.2845,
1046
+ "step": 740
1047
+ },
1048
+ {
1049
+ "epoch": 2.314152410575428,
1050
+ "grad_norm": 1.251165509223938,
1051
+ "learning_rate": 4.133249037144371e-06,
1052
+ "loss": 0.3173,
1053
+ "step": 745
1054
+ },
1055
+ {
1056
+ "epoch": 2.329704510108865,
1057
+ "grad_norm": 1.2096902132034302,
1058
+ "learning_rate": 3.957732099256801e-06,
1059
+ "loss": 0.2962,
1060
+ "step": 750
1061
+ },
1062
+ {
1063
+ "epoch": 2.3452566096423015,
1064
+ "grad_norm": 1.3482387065887451,
1065
+ "learning_rate": 3.7854551892152433e-06,
1066
+ "loss": 0.2963,
1067
+ "step": 755
1068
+ },
1069
+ {
1070
+ "epoch": 2.3608087091757386,
1071
+ "grad_norm": 1.2713910341262817,
1072
+ "learning_rate": 3.6164688565979774e-06,
1073
+ "loss": 0.2826,
1074
+ "step": 760
1075
+ },
1076
+ {
1077
+ "epoch": 2.3763608087091757,
1078
+ "grad_norm": 1.434398889541626,
1079
+ "learning_rate": 3.450822685460402e-06,
1080
+ "loss": 0.3071,
1081
+ "step": 765
1082
+ },
1083
+ {
1084
+ "epoch": 2.3919129082426127,
1085
+ "grad_norm": 1.4093025922775269,
1086
+ "learning_rate": 3.2885652797860395e-06,
1087
+ "loss": 0.29,
1088
+ "step": 770
1089
+ },
1090
+ {
1091
+ "epoch": 2.4074650077760498,
1092
+ "grad_norm": 1.1628525257110596,
1093
+ "learning_rate": 3.1297442492251254e-06,
1094
+ "loss": 0.2744,
1095
+ "step": 775
1096
+ },
1097
+ {
1098
+ "epoch": 2.423017107309487,
1099
+ "grad_norm": 1.2740814685821533,
1100
+ "learning_rate": 2.9744061951249797e-06,
1101
+ "loss": 0.2876,
1102
+ "step": 780
1103
+ },
1104
+ {
1105
+ "epoch": 2.438569206842924,
1106
+ "grad_norm": 1.0924385786056519,
1107
+ "learning_rate": 2.8225966968561845e-06,
1108
+ "loss": 0.3331,
1109
+ "step": 785
1110
+ },
1111
+ {
1112
+ "epoch": 2.454121306376361,
1113
+ "grad_norm": 1.4028589725494385,
1114
+ "learning_rate": 2.6743602984386944e-06,
1115
+ "loss": 0.2898,
1116
+ "step": 790
1117
+ },
1118
+ {
1119
+ "epoch": 2.469673405909798,
1120
+ "grad_norm": 1.3594895601272583,
1121
+ "learning_rate": 2.5297404954716967e-06,
1122
+ "loss": 0.2877,
1123
+ "step": 795
1124
+ },
1125
+ {
1126
+ "epoch": 2.4852255054432346,
1127
+ "grad_norm": 1.1996512413024902,
1128
+ "learning_rate": 2.3887797223710926e-06,
1129
+ "loss": 0.3164,
1130
+ "step": 800
1131
+ },
1132
+ {
1133
+ "epoch": 2.5007776049766717,
1134
+ "grad_norm": 1.3675403594970703,
1135
+ "learning_rate": 2.2515193399183954e-06,
1136
+ "loss": 0.3143,
1137
+ "step": 805
1138
+ },
1139
+ {
1140
+ "epoch": 2.5163297045101087,
1141
+ "grad_norm": 1.2102525234222412,
1142
+ "learning_rate": 2.117999623124629e-06,
1143
+ "loss": 0.3296,
1144
+ "step": 810
1145
+ },
1146
+ {
1147
+ "epoch": 2.531881804043546,
1148
+ "grad_norm": 1.39519464969635,
1149
+ "learning_rate": 1.988259749412778e-06,
1150
+ "loss": 0.3038,
1151
+ "step": 815
1152
+ },
1153
+ {
1154
+ "epoch": 2.547433903576983,
1155
+ "grad_norm": 1.2118239402770996,
1156
+ "learning_rate": 1.8623377871223746e-06,
1157
+ "loss": 0.3048,
1158
+ "step": 820
1159
+ },
1160
+ {
1161
+ "epoch": 2.56298600311042,
1162
+ "grad_norm": 1.0533260107040405,
1163
+ "learning_rate": 1.7402706843394311e-06,
1164
+ "loss": 0.2967,
1165
+ "step": 825
1166
+ },
1167
+ {
1168
+ "epoch": 2.578538102643857,
1169
+ "grad_norm": 1.3837428092956543,
1170
+ "learning_rate": 1.622094258055139e-06,
1171
+ "loss": 0.2996,
1172
+ "step": 830
1173
+ },
1174
+ {
1175
+ "epoch": 2.594090202177294,
1176
+ "grad_norm": 1.2500343322753906,
1177
+ "learning_rate": 1.5078431836564199e-06,
1178
+ "loss": 0.293,
1179
+ "step": 835
1180
+ },
1181
+ {
1182
+ "epoch": 2.609642301710731,
1183
+ "grad_norm": 1.4100749492645264,
1184
+ "learning_rate": 1.3975509847514434e-06,
1185
+ "loss": 0.3553,
1186
+ "step": 840
1187
+ },
1188
+ {
1189
+ "epoch": 2.625194401244168,
1190
+ "grad_norm": 1.1867926120758057,
1191
+ "learning_rate": 1.291250023333133e-06,
1192
+ "loss": 0.329,
1193
+ "step": 845
1194
+ },
1195
+ {
1196
+ "epoch": 2.640746500777605,
1197
+ "grad_norm": 1.2801156044006348,
1198
+ "learning_rate": 1.1889714902834897e-06,
1199
+ "loss": 0.3137,
1200
+ "step": 850
1201
+ },
1202
+ {
1203
+ "epoch": 2.6562986003110423,
1204
+ "grad_norm": 1.301249623298645,
1205
+ "learning_rate": 1.090745396221533e-06,
1206
+ "loss": 0.2994,
1207
+ "step": 855
1208
+ },
1209
+ {
1210
+ "epoch": 2.671850699844479,
1211
+ "grad_norm": 1.3433258533477783,
1212
+ "learning_rate": 9.96600562697586e-07,
1213
+ "loss": 0.267,
1214
+ "step": 860
1215
+ },
1216
+ {
1217
+ "epoch": 2.687402799377916,
1218
+ "grad_norm": 1.2630574703216553,
1219
+ "learning_rate": 9.065646137364314e-07,
1220
+ "loss": 0.3619,
1221
+ "step": 865
1222
+ },
1223
+ {
1224
+ "epoch": 2.702954898911353,
1225
+ "grad_norm": 1.2644740343093872,
1226
+ "learning_rate": 8.20663967731865e-07,
1227
+ "loss": 0.297,
1228
+ "step": 870
1229
+ },
1230
+ {
1231
+ "epoch": 2.71850699844479,
1232
+ "grad_norm": 1.3221532106399536,
1233
+ "learning_rate": 7.389238296949902e-07,
1234
+ "loss": 0.3194,
1235
+ "step": 875
1236
+ },
1237
+ {
1238
+ "epoch": 2.734059097978227,
1239
+ "grad_norm": 1.3244149684906006,
1240
+ "learning_rate": 6.613681838585517e-07,
1241
+ "loss": 0.3098,
1242
+ "step": 880
1243
+ },
1244
+ {
1245
+ "epoch": 2.749611197511664,
1246
+ "grad_norm": 1.1736044883728027,
1247
+ "learning_rate": 5.880197866394738e-07,
1248
+ "loss": 0.283,
1249
+ "step": 885
1250
+ },
1251
+ {
1252
+ "epoch": 2.765163297045101,
1253
+ "grad_norm": 1.3244141340255737,
1254
+ "learning_rate": 5.189001599616561e-07,
1255
+ "loss": 0.2777,
1256
+ "step": 890
1257
+ },
1258
+ {
1259
+ "epoch": 2.780715396578538,
1260
+ "grad_norm": 1.1822513341903687,
1261
+ "learning_rate": 4.54029584941002e-07,
1262
+ "loss": 0.3147,
1263
+ "step": 895
1264
+ },
1265
+ {
1266
+ "epoch": 2.796267496111975,
1267
+ "grad_norm": 1.1570910215377808,
1268
+ "learning_rate": 3.934270959345271e-07,
1269
+ "loss": 0.2742,
1270
+ "step": 900
1271
+ },
1272
+ {
1273
+ "epoch": 2.811819595645412,
1274
+ "grad_norm": 1.2180461883544922,
1275
+ "learning_rate": 3.371104749552817e-07,
1276
+ "loss": 0.2845,
1277
+ "step": 905
1278
+ },
1279
+ {
1280
+ "epoch": 2.827371695178849,
1281
+ "grad_norm": 1.2462286949157715,
1282
+ "learning_rate": 2.8509624645474464e-07,
1283
+ "loss": 0.3078,
1284
+ "step": 910
1285
+ },
1286
+ {
1287
+ "epoch": 2.842923794712286,
1288
+ "grad_norm": 1.2295945882797241,
1289
+ "learning_rate": 2.3739967247421502e-07,
1290
+ "loss": 0.2539,
1291
+ "step": 915
1292
+ },
1293
+ {
1294
+ "epoch": 2.858475894245723,
1295
+ "grad_norm": 1.2694175243377686,
1296
+ "learning_rate": 1.9403474816661272e-07,
1297
+ "loss": 0.2787,
1298
+ "step": 920
1299
+ },
1300
+ {
1301
+ "epoch": 2.87402799377916,
1302
+ "grad_norm": 1.1908364295959473,
1303
+ "learning_rate": 1.5501419769001656e-07,
1304
+ "loss": 0.2958,
1305
+ "step": 925
1306
+ },
1307
+ {
1308
+ "epoch": 2.8895800933125972,
1309
+ "grad_norm": 1.3138959407806396,
1310
+ "learning_rate": 1.203494704741276e-07,
1311
+ "loss": 0.3035,
1312
+ "step": 930
1313
+ },
1314
+ {
1315
+ "epoch": 2.9051321928460343,
1316
+ "grad_norm": 1.295821189880371,
1317
+ "learning_rate": 9.005073786078621e-08,
1318
+ "loss": 0.3641,
1319
+ "step": 935
1320
+ },
1321
+ {
1322
+ "epoch": 2.9206842923794714,
1323
+ "grad_norm": 1.3944648504257202,
1324
+ "learning_rate": 6.412689011947303e-08,
1325
+ "loss": 0.2998,
1326
+ "step": 940
1327
+ },
1328
+ {
1329
+ "epoch": 2.9362363919129084,
1330
+ "grad_norm": 1.3905586004257202,
1331
+ "learning_rate": 4.2585533838738756e-08,
1332
+ "loss": 0.3256,
1333
+ "step": 945
1334
+ },
1335
+ {
1336
+ "epoch": 2.9517884914463455,
1337
+ "grad_norm": 1.382743239402771,
1338
+ "learning_rate": 2.5432989694262886e-08,
1339
+ "loss": 0.2788,
1340
+ "step": 950
1341
+ },
1342
+ {
1343
+ "epoch": 2.9673405909797825,
1344
+ "grad_norm": 1.207732915878296,
1345
+ "learning_rate": 1.267429059424563e-08,
1346
+ "loss": 0.2751,
1347
+ "step": 955
1348
+ },
1349
+ {
1350
+ "epoch": 2.982892690513219,
1351
+ "grad_norm": 1.2087626457214355,
1352
+ "learning_rate": 4.313180202647482e-09,
1353
+ "loss": 0.3045,
1354
+ "step": 960
1355
+ },
1356
+ {
1357
+ "epoch": 2.998444790046656,
1358
+ "grad_norm": 1.259070873260498,
1359
+ "learning_rate": 3.521118407162627e-10,
1360
+ "loss": 0.3122,
1361
+ "step": 965
1362
+ },
1363
+ {
1364
+ "epoch": 3.0,
1365
+ "step": 966,
1366
+ "total_flos": 1.3759050762074194e+18,
1367
+ "train_loss": 0.5874219706771784,
1368
+ "train_runtime": 632.2067,
1369
+ "train_samples_per_second": 48.772,
1370
+ "train_steps_per_second": 1.528
1371
+ }
1372
+ ],
1373
+ "logging_steps": 5,
1374
+ "max_steps": 966,
1375
+ "num_input_tokens_seen": 0,
1376
+ "num_train_epochs": 3,
1377
+ "save_steps": 2000,
1378
+ "stateful_callbacks": {
1379
+ "TrainerControl": {
1380
+ "args": {
1381
+ "should_epoch_stop": false,
1382
+ "should_evaluate": false,
1383
+ "should_log": false,
1384
+ "should_save": false,
1385
+ "should_training_stop": false
1386
+ },
1387
+ "attributes": {}
1388
+ }
1389
+ },
1390
+ "total_flos": 1.3759050762074194e+18,
1391
+ "train_batch_size": 2,
1392
+ "trial_name": null,
1393
+ "trial_params": null
1394
+ }
19_128_e3_3e-5/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:933076bd603aa6d76a97b642ccb09f3049a06ee6df8d2d0308fb98e2f422d0aa
3
+ size 8145
19_128_e3_3e-5/vocab.json ADDED
The diff for this file is too large to render. See raw diff