RayDu0010 commited on
Commit
6ebc5d5
·
verified ·
1 Parent(s): 3266553

Upload folder using huggingface_hub

Browse files
52_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: 52_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
+ # 52_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
52_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
+ "q_proj",
28
+ "o_proj",
29
+ "k_proj",
30
+ "gate_proj",
31
+ "v_proj",
32
+ "up_proj",
33
+ "down_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
52_128_e3_3e-5/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7575ff5faa11ffcf9036883bf5694b52b7176b7f709da3d7eebb8fd3da037af
3
+ size 791751704
52_128_e3_3e-5/all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.0148094862730199e+18,
4
+ "train_loss": 0.5318781840885785,
5
+ "train_runtime": 470.0601,
6
+ "train_samples": 7509,
7
+ "train_samples_per_second": 47.924,
8
+ "train_steps_per_second": 1.5
9
+ }
52_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
+ }
52_128_e3_3e-5/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
52_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
+ }
52_128_e3_3e-5/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
52_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
+ }
52_128_e3_3e-5/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.0148094862730199e+18,
4
+ "train_loss": 0.5318781840885785,
5
+ "train_runtime": 470.0601,
6
+ "train_samples": 7509,
7
+ "train_samples_per_second": 47.924,
8
+ "train_steps_per_second": 1.5
9
+ }
52_128_e3_3e-5/trainer_state.json ADDED
@@ -0,0 +1,1030 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 705,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02127659574468085,
14
+ "grad_norm": 1.1681504249572754,
15
+ "learning_rate": 3.3333333333333333e-06,
16
+ "loss": 1.2613,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.0425531914893617,
21
+ "grad_norm": 0.625912070274353,
22
+ "learning_rate": 7.5e-06,
23
+ "loss": 1.3084,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.06382978723404255,
28
+ "grad_norm": 0.6986785531044006,
29
+ "learning_rate": 1.1666666666666668e-05,
30
+ "loss": 1.2356,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.0851063829787234,
35
+ "grad_norm": 0.5111691355705261,
36
+ "learning_rate": 1.5833333333333333e-05,
37
+ "loss": 1.1754,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.10638297872340426,
42
+ "grad_norm": 0.5332735776901245,
43
+ "learning_rate": 1.9999999999999998e-05,
44
+ "loss": 1.2003,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.1276595744680851,
49
+ "grad_norm": 0.5613914132118225,
50
+ "learning_rate": 2.4166666666666667e-05,
51
+ "loss": 1.1905,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.14893617021276595,
56
+ "grad_norm": 0.4615066349506378,
57
+ "learning_rate": 2.8333333333333332e-05,
58
+ "loss": 1.1353,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.1702127659574468,
63
+ "grad_norm": 0.5815594792366028,
64
+ "learning_rate": 2.999851151624269e-05,
65
+ "loss": 1.1208,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.19148936170212766,
70
+ "grad_norm": 0.39489203691482544,
71
+ "learning_rate": 2.9989416296394506e-05,
72
+ "loss": 1.0922,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.2127659574468085,
77
+ "grad_norm": 0.4709049165248871,
78
+ "learning_rate": 2.9972057799999166e-05,
79
+ "loss": 1.1358,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.23404255319148937,
84
+ "grad_norm": 0.4302421510219574,
85
+ "learning_rate": 2.994644559634565e-05,
86
+ "loss": 1.0488,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.2553191489361702,
91
+ "grad_norm": 0.4911840260028839,
92
+ "learning_rate": 2.991259380477775e-05,
93
+ "loss": 1.1153,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.2765957446808511,
98
+ "grad_norm": 0.42401865124702454,
99
+ "learning_rate": 2.9870521086910417e-05,
100
+ "loss": 1.024,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.2978723404255319,
105
+ "grad_norm": 0.5002766847610474,
106
+ "learning_rate": 2.9820250636342107e-05,
107
+ "loss": 1.0948,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.3191489361702128,
112
+ "grad_norm": 0.526447057723999,
113
+ "learning_rate": 2.9761810165868784e-05,
114
+ "loss": 0.9974,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.3404255319148936,
119
+ "grad_norm": 0.5270617008209229,
120
+ "learning_rate": 2.9695231892206524e-05,
121
+ "loss": 0.9933,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.3617021276595745,
126
+ "grad_norm": 0.5693199634552002,
127
+ "learning_rate": 2.9620552518231302e-05,
128
+ "loss": 0.9656,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.3829787234042553,
133
+ "grad_norm": 0.6511000394821167,
134
+ "learning_rate": 2.9537813212745656e-05,
135
+ "loss": 0.9427,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.40425531914893614,
140
+ "grad_norm": 0.6241205930709839,
141
+ "learning_rate": 2.9447059587783354e-05,
142
+ "loss": 0.9992,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.425531914893617,
147
+ "grad_norm": 0.5776088237762451,
148
+ "learning_rate": 2.9348341673464726e-05,
149
+ "loss": 0.909,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.44680851063829785,
154
+ "grad_norm": 0.6403713226318359,
155
+ "learning_rate": 2.924171389041629e-05,
156
+ "loss": 0.9738,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.46808510638297873,
161
+ "grad_norm": 0.6323487758636475,
162
+ "learning_rate": 2.912723501977013e-05,
163
+ "loss": 0.9258,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.48936170212765956,
168
+ "grad_norm": 0.7640523314476013,
169
+ "learning_rate": 2.900496817075932e-05,
170
+ "loss": 0.8721,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.5106382978723404,
175
+ "grad_norm": 0.7880716919898987,
176
+ "learning_rate": 2.8874980745927502e-05,
177
+ "loss": 0.8938,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.5319148936170213,
182
+ "grad_norm": 0.7535836696624756,
183
+ "learning_rate": 2.873734440397156e-05,
184
+ "loss": 0.8434,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.5531914893617021,
189
+ "grad_norm": 0.7416653633117676,
190
+ "learning_rate": 2.8592135020238093e-05,
191
+ "loss": 0.832,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.574468085106383,
196
+ "grad_norm": 0.7539019584655762,
197
+ "learning_rate": 2.8439432644895238e-05,
198
+ "loss": 0.8387,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.5957446808510638,
203
+ "grad_norm": 0.6717402935028076,
204
+ "learning_rate": 2.8279321458803147e-05,
205
+ "loss": 0.8503,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.6170212765957447,
210
+ "grad_norm": 0.8196009993553162,
211
+ "learning_rate": 2.8111889727107218e-05,
212
+ "loss": 0.7981,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.6382978723404256,
217
+ "grad_norm": 0.8818630576133728,
218
+ "learning_rate": 2.7937229750579842e-05,
219
+ "loss": 0.83,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.6595744680851063,
224
+ "grad_norm": 0.8429226875305176,
225
+ "learning_rate": 2.775543781473736e-05,
226
+ "loss": 0.8117,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.6808510638297872,
231
+ "grad_norm": 0.7755163311958313,
232
+ "learning_rate": 2.7566614136760364e-05,
233
+ "loss": 0.8041,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.7021276595744681,
238
+ "grad_norm": 0.8224868178367615,
239
+ "learning_rate": 2.737086281024656e-05,
240
+ "loss": 0.7648,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.723404255319149,
245
+ "grad_norm": 0.802998423576355,
246
+ "learning_rate": 2.7168291747826657e-05,
247
+ "loss": 0.7309,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.7446808510638298,
252
+ "grad_norm": 0.934977114200592,
253
+ "learning_rate": 2.6959012621674953e-05,
254
+ "loss": 0.7275,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.7659574468085106,
259
+ "grad_norm": 0.9477068185806274,
260
+ "learning_rate": 2.6743140801947346e-05,
261
+ "loss": 0.7459,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.7872340425531915,
266
+ "grad_norm": 0.9177036881446838,
267
+ "learning_rate": 2.6520795293180768e-05,
268
+ "loss": 0.6988,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.8085106382978723,
273
+ "grad_norm": 0.9726608991622925,
274
+ "learning_rate": 2.629209866868905e-05,
275
+ "loss": 0.7519,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.8297872340425532,
280
+ "grad_norm": 0.9530746936798096,
281
+ "learning_rate": 2.605717700299146e-05,
282
+ "loss": 0.711,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.851063829787234,
287
+ "grad_norm": 0.9297530651092529,
288
+ "learning_rate": 2.5816159802311058e-05,
289
+ "loss": 0.7046,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.8723404255319149,
294
+ "grad_norm": 1.1215581893920898,
295
+ "learning_rate": 2.556917993318131e-05,
296
+ "loss": 0.7342,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.8936170212765957,
301
+ "grad_norm": 1.1242687702178955,
302
+ "learning_rate": 2.531637354920018e-05,
303
+ "loss": 0.6092,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.9148936170212766,
308
+ "grad_norm": 0.965260922908783,
309
+ "learning_rate": 2.5057880015972207e-05,
310
+ "loss": 0.623,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.9361702127659575,
315
+ "grad_norm": 0.9388829469680786,
316
+ "learning_rate": 2.4793841834279828e-05,
317
+ "loss": 0.6349,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.9574468085106383,
322
+ "grad_norm": 0.960932195186615,
323
+ "learning_rate": 2.4524404561526438e-05,
324
+ "loss": 0.6242,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 0.9787234042553191,
329
+ "grad_norm": 1.0344784259796143,
330
+ "learning_rate": 2.4249716731494322e-05,
331
+ "loss": 0.5868,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 1.0,
336
+ "grad_norm": 0.9949706792831421,
337
+ "learning_rate": 2.3969929772461866e-05,
338
+ "loss": 0.6448,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 1.0212765957446808,
343
+ "grad_norm": 0.9935529232025146,
344
+ "learning_rate": 2.3685197923725052e-05,
345
+ "loss": 0.5331,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 1.0425531914893618,
350
+ "grad_norm": 1.0526684522628784,
351
+ "learning_rate": 2.339567815056935e-05,
352
+ "loss": 0.5456,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 1.0638297872340425,
357
+ "grad_norm": 1.049608826637268,
358
+ "learning_rate": 2.3101530057738795e-05,
359
+ "loss": 0.5157,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 1.0851063829787233,
364
+ "grad_norm": 1.0828019380569458,
365
+ "learning_rate": 2.2802915801450085e-05,
366
+ "loss": 0.5237,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 1.1063829787234043,
371
+ "grad_norm": 1.1317226886749268,
372
+ "learning_rate": 2.25e-05,
373
+ "loss": 0.5404,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 1.127659574468085,
378
+ "grad_norm": 1.0299949645996094,
379
+ "learning_rate": 2.219294964301566e-05,
380
+ "loss": 0.5393,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 1.148936170212766,
385
+ "grad_norm": 1.0252625942230225,
386
+ "learning_rate": 2.188193399939742e-05,
387
+ "loss": 0.522,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 1.1702127659574468,
392
+ "grad_norm": 1.156378149986267,
393
+ "learning_rate": 2.1567124524005357e-05,
394
+ "loss": 0.4684,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 1.1914893617021276,
399
+ "grad_norm": 1.0907707214355469,
400
+ "learning_rate": 2.1248694763140645e-05,
401
+ "loss": 0.4646,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 1.2127659574468086,
406
+ "grad_norm": 1.1863120794296265,
407
+ "learning_rate": 2.0926820258873952e-05,
408
+ "loss": 0.5004,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 1.2340425531914894,
413
+ "grad_norm": 1.2463798522949219,
414
+ "learning_rate": 2.0601678452273665e-05,
415
+ "loss": 0.5017,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 1.2553191489361701,
420
+ "grad_norm": 1.1668238639831543,
421
+ "learning_rate": 2.027344858558725e-05,
422
+ "loss": 0.5118,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 1.2765957446808511,
427
+ "grad_norm": 1.1824675798416138,
428
+ "learning_rate": 1.9942311603429603e-05,
429
+ "loss": 0.4354,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 1.297872340425532,
434
+ "grad_norm": 1.4731124639511108,
435
+ "learning_rate": 1.9608450053033024e-05,
436
+ "loss": 0.4875,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 1.3191489361702127,
441
+ "grad_norm": 1.176293969154358,
442
+ "learning_rate": 1.927204798361363e-05,
443
+ "loss": 0.4943,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 1.3404255319148937,
448
+ "grad_norm": 1.3032501935958862,
449
+ "learning_rate": 1.8933290844909795e-05,
450
+ "loss": 0.4676,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 1.3617021276595744,
455
+ "grad_norm": 1.2204476594924927,
456
+ "learning_rate": 1.8592365384948532e-05,
457
+ "loss": 0.4536,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 1.3829787234042552,
462
+ "grad_norm": 1.265848159790039,
463
+ "learning_rate": 1.8249459547096148e-05,
464
+ "loss": 0.4422,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 1.4042553191489362,
469
+ "grad_norm": 1.128125548362732,
470
+ "learning_rate": 1.7904762366449924e-05,
471
+ "loss": 0.478,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 1.425531914893617,
476
+ "grad_norm": 1.0406056642532349,
477
+ "learning_rate": 1.7558463865627974e-05,
478
+ "loss": 0.4514,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 1.4468085106382977,
483
+ "grad_norm": 1.131724238395691,
484
+ "learning_rate": 1.7210754950014717e-05,
485
+ "loss": 0.4071,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 1.4680851063829787,
490
+ "grad_norm": 1.2132693529129028,
491
+ "learning_rate": 1.686182730251966e-05,
492
+ "loss": 0.4189,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 1.4893617021276595,
497
+ "grad_norm": 1.2118912935256958,
498
+ "learning_rate": 1.65118732779076e-05,
499
+ "loss": 0.3974,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 1.5106382978723403,
504
+ "grad_norm": 1.1566495895385742,
505
+ "learning_rate": 1.6161085796758444e-05,
506
+ "loss": 0.4291,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 1.5319148936170213,
511
+ "grad_norm": 1.2086267471313477,
512
+ "learning_rate": 1.5809658239115054e-05,
513
+ "loss": 0.4166,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 1.5531914893617023,
518
+ "grad_norm": 1.369402289390564,
519
+ "learning_rate": 1.5457784337877874e-05,
520
+ "loss": 0.4285,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 1.574468085106383,
525
+ "grad_norm": 1.2613654136657715,
526
+ "learning_rate": 1.5105658072005004e-05,
527
+ "loss": 0.4626,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 1.5957446808510638,
532
+ "grad_norm": 1.3263241052627563,
533
+ "learning_rate": 1.4753473559576626e-05,
534
+ "loss": 0.4422,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 1.6170212765957448,
539
+ "grad_norm": 1.14140784740448,
540
+ "learning_rate": 1.4401424950782726e-05,
541
+ "loss": 0.3906,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 1.6382978723404256,
546
+ "grad_norm": 1.1192632913589478,
547
+ "learning_rate": 1.404970632089315e-05,
548
+ "loss": 0.4207,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 1.6595744680851063,
553
+ "grad_norm": 1.184363603591919,
554
+ "learning_rate": 1.3698511563268918e-05,
555
+ "loss": 0.3859,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 1.6808510638297873,
560
+ "grad_norm": 1.1298928260803223,
561
+ "learning_rate": 1.3348034282473875e-05,
562
+ "loss": 0.3847,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 1.702127659574468,
567
+ "grad_norm": 1.1644887924194336,
568
+ "learning_rate": 1.2998467687545465e-05,
569
+ "loss": 0.3551,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 1.7234042553191489,
574
+ "grad_norm": 1.237197756767273,
575
+ "learning_rate": 1.2650004485483661e-05,
576
+ "loss": 0.3917,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 1.7446808510638299,
581
+ "grad_norm": 1.1724849939346313,
582
+ "learning_rate": 1.2302836775016517e-05,
583
+ "loss": 0.4013,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 1.7659574468085106,
588
+ "grad_norm": 1.3590863943099976,
589
+ "learning_rate": 1.1957155940701205e-05,
590
+ "loss": 0.4259,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 1.7872340425531914,
595
+ "grad_norm": 1.4391647577285767,
596
+ "learning_rate": 1.161315254741859e-05,
597
+ "loss": 0.3359,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 1.8085106382978724,
602
+ "grad_norm": 1.1264665126800537,
603
+ "learning_rate": 1.1271016235319815e-05,
604
+ "loss": 0.3526,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 1.8297872340425532,
609
+ "grad_norm": 1.2143665552139282,
610
+ "learning_rate": 1.0930935615282559e-05,
611
+ "loss": 0.3641,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 1.851063829787234,
616
+ "grad_norm": 1.3911160230636597,
617
+ "learning_rate": 1.0593098164934789e-05,
618
+ "loss": 0.3234,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 1.872340425531915,
623
+ "grad_norm": 1.2564088106155396,
624
+ "learning_rate": 1.0257690125303167e-05,
625
+ "loss": 0.3688,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 1.8936170212765957,
630
+ "grad_norm": 1.0881422758102417,
631
+ "learning_rate": 9.924896398143227e-06,
632
+ "loss": 0.3613,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 1.9148936170212765,
637
+ "grad_norm": 1.1326451301574707,
638
+ "learning_rate": 9.594900444007819e-06,
639
+ "loss": 0.34,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 1.9361702127659575,
644
+ "grad_norm": 1.2193176746368408,
645
+ "learning_rate": 9.26788418111008e-06,
646
+ "loss": 0.3783,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 1.9574468085106385,
651
+ "grad_norm": 1.2493762969970703,
652
+ "learning_rate": 8.944027885036605e-06,
653
+ "loss": 0.3514,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 1.978723404255319,
658
+ "grad_norm": 1.0819754600524902,
659
+ "learning_rate": 8.623510089366242e-06,
660
+ "loss": 0.3207,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 2.0,
665
+ "grad_norm": 1.2961006164550781,
666
+ "learning_rate": 8.306507487249094e-06,
667
+ "loss": 0.3724,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 2.021276595744681,
672
+ "grad_norm": 1.0820854902267456,
673
+ "learning_rate": 7.99319483400023e-06,
674
+ "loss": 0.2755,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 2.0425531914893615,
679
+ "grad_norm": 1.2421616315841675,
680
+ "learning_rate": 7.683744850761584e-06,
681
+ "loss": 0.2632,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 2.0638297872340425,
686
+ "grad_norm": 1.0670262575149536,
687
+ "learning_rate": 7.3783281292852485e-06,
688
+ "loss": 0.2752,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 2.0851063829787235,
693
+ "grad_norm": 1.1725709438323975,
694
+ "learning_rate": 7.077113037890703e-06,
695
+ "loss": 0.2739,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 2.106382978723404,
700
+ "grad_norm": 1.2927721738815308,
701
+ "learning_rate": 6.780265628647691e-06,
702
+ "loss": 0.2618,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 2.127659574468085,
707
+ "grad_norm": 1.2070021629333496,
708
+ "learning_rate": 6.487949545836048e-06,
709
+ "loss": 0.2768,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 2.148936170212766,
714
+ "grad_norm": 1.4090511798858643,
715
+ "learning_rate": 6.200325935732827e-06,
716
+ "loss": 0.2764,
717
+ "step": 505
718
+ },
719
+ {
720
+ "epoch": 2.1702127659574466,
721
+ "grad_norm": 1.3339381217956543,
722
+ "learning_rate": 5.91755335777656e-06,
723
+ "loss": 0.2589,
724
+ "step": 510
725
+ },
726
+ {
727
+ "epoch": 2.1914893617021276,
728
+ "grad_norm": 1.2423899173736572,
729
+ "learning_rate": 5.6397876971575205e-06,
730
+ "loss": 0.2686,
731
+ "step": 515
732
+ },
733
+ {
734
+ "epoch": 2.2127659574468086,
735
+ "grad_norm": 1.147936463356018,
736
+ "learning_rate": 5.3671820788823005e-06,
737
+ "loss": 0.2695,
738
+ "step": 520
739
+ },
740
+ {
741
+ "epoch": 2.2340425531914896,
742
+ "grad_norm": 1.3379814624786377,
743
+ "learning_rate": 5.0998867833599146e-06,
744
+ "loss": 0.2841,
745
+ "step": 525
746
+ },
747
+ {
748
+ "epoch": 2.25531914893617,
749
+ "grad_norm": 1.194452166557312,
750
+ "learning_rate": 4.83804916355616e-06,
751
+ "loss": 0.2772,
752
+ "step": 530
753
+ },
754
+ {
755
+ "epoch": 2.276595744680851,
756
+ "grad_norm": 1.0499582290649414,
757
+ "learning_rate": 4.5818135637616945e-06,
758
+ "loss": 0.2287,
759
+ "step": 535
760
+ },
761
+ {
762
+ "epoch": 2.297872340425532,
763
+ "grad_norm": 1.2598004341125488,
764
+ "learning_rate": 4.3313212400188265e-06,
765
+ "loss": 0.2708,
766
+ "step": 540
767
+ },
768
+ {
769
+ "epoch": 2.3191489361702127,
770
+ "grad_norm": 1.3534964323043823,
771
+ "learning_rate": 4.086710282250667e-06,
772
+ "loss": 0.2743,
773
+ "step": 545
774
+ },
775
+ {
776
+ "epoch": 2.3404255319148937,
777
+ "grad_norm": 1.27427077293396,
778
+ "learning_rate": 3.848115538135783e-06,
779
+ "loss": 0.2965,
780
+ "step": 550
781
+ },
782
+ {
783
+ "epoch": 2.3617021276595747,
784
+ "grad_norm": 1.1835789680480957,
785
+ "learning_rate": 3.61566853877013e-06,
786
+ "loss": 0.2484,
787
+ "step": 555
788
+ },
789
+ {
790
+ "epoch": 2.382978723404255,
791
+ "grad_norm": 1.3028374910354614,
792
+ "learning_rate": 3.3894974261574025e-06,
793
+ "loss": 0.2335,
794
+ "step": 560
795
+ },
796
+ {
797
+ "epoch": 2.404255319148936,
798
+ "grad_norm": 1.1831202507019043,
799
+ "learning_rate": 3.1697268825676423e-06,
800
+ "loss": 0.2757,
801
+ "step": 565
802
+ },
803
+ {
804
+ "epoch": 2.425531914893617,
805
+ "grad_norm": 1.0505186319351196,
806
+ "learning_rate": 2.956478061803147e-06,
807
+ "loss": 0.2622,
808
+ "step": 570
809
+ },
810
+ {
811
+ "epoch": 2.4468085106382977,
812
+ "grad_norm": 1.2381149530410767,
813
+ "learning_rate": 2.7498685224095337e-06,
814
+ "loss": 0.2607,
815
+ "step": 575
816
+ },
817
+ {
818
+ "epoch": 2.4680851063829787,
819
+ "grad_norm": 1.274715542793274,
820
+ "learning_rate": 2.550012162868731e-06,
821
+ "loss": 0.265,
822
+ "step": 580
823
+ },
824
+ {
825
+ "epoch": 2.4893617021276597,
826
+ "grad_norm": 1.3793457746505737,
827
+ "learning_rate": 2.3570191588097354e-06,
828
+ "loss": 0.2614,
829
+ "step": 585
830
+ },
831
+ {
832
+ "epoch": 2.5106382978723403,
833
+ "grad_norm": 1.1631361246109009,
834
+ "learning_rate": 2.1709959022716077e-06,
835
+ "loss": 0.2519,
836
+ "step": 590
837
+ },
838
+ {
839
+ "epoch": 2.5319148936170213,
840
+ "grad_norm": 1.412804365158081,
841
+ "learning_rate": 1.992044943052327e-06,
842
+ "loss": 0.2595,
843
+ "step": 595
844
+ },
845
+ {
846
+ "epoch": 2.5531914893617023,
847
+ "grad_norm": 1.2694616317749023,
848
+ "learning_rate": 1.8202649321757287e-06,
849
+ "loss": 0.2678,
850
+ "step": 600
851
+ },
852
+ {
853
+ "epoch": 2.574468085106383,
854
+ "grad_norm": 1.1237049102783203,
855
+ "learning_rate": 1.65575056750777e-06,
856
+ "loss": 0.2633,
857
+ "step": 605
858
+ },
859
+ {
860
+ "epoch": 2.595744680851064,
861
+ "grad_norm": 1.3573358058929443,
862
+ "learning_rate": 1.4985925415520396e-06,
863
+ "loss": 0.2446,
864
+ "step": 610
865
+ },
866
+ {
867
+ "epoch": 2.617021276595745,
868
+ "grad_norm": 1.3096789121627808,
869
+ "learning_rate": 1.3488774914533292e-06,
870
+ "loss": 0.2723,
871
+ "step": 615
872
+ },
873
+ {
874
+ "epoch": 2.6382978723404253,
875
+ "grad_norm": 1.2034170627593994,
876
+ "learning_rate": 1.2066879512368328e-06,
877
+ "loss": 0.2339,
878
+ "step": 620
879
+ },
880
+ {
881
+ "epoch": 2.6595744680851063,
882
+ "grad_norm": 1.1348567008972168,
883
+ "learning_rate": 1.072102306309276e-06,
884
+ "loss": 0.253,
885
+ "step": 625
886
+ },
887
+ {
888
+ "epoch": 2.6808510638297873,
889
+ "grad_norm": 1.0960131883621216,
890
+ "learning_rate": 9.451947502470632e-07,
891
+ "loss": 0.243,
892
+ "step": 630
893
+ },
894
+ {
895
+ "epoch": 2.702127659574468,
896
+ "grad_norm": 1.085120439529419,
897
+ "learning_rate": 8.260352438952995e-07,
898
+ "loss": 0.2853,
899
+ "step": 635
900
+ },
901
+ {
902
+ "epoch": 2.723404255319149,
903
+ "grad_norm": 1.2832350730895996,
904
+ "learning_rate": 7.146894768001744e-07,
905
+ "loss": 0.2366,
906
+ "step": 640
907
+ },
908
+ {
909
+ "epoch": 2.74468085106383,
910
+ "grad_norm": 1.1672836542129517,
911
+ "learning_rate": 6.112188309960315e-07,
912
+ "loss": 0.2457,
913
+ "step": 645
914
+ },
915
+ {
916
+ "epoch": 2.7659574468085104,
917
+ "grad_norm": 1.1914671659469604,
918
+ "learning_rate": 5.156803471670335e-07,
919
+ "loss": 0.2248,
920
+ "step": 650
921
+ },
922
+ {
923
+ "epoch": 2.7872340425531914,
924
+ "grad_norm": 1.2385162115097046,
925
+ "learning_rate": 4.2812669320212385e-07,
926
+ "loss": 0.271,
927
+ "step": 655
928
+ },
929
+ {
930
+ "epoch": 2.8085106382978724,
931
+ "grad_norm": 1.2312277555465698,
932
+ "learning_rate": 3.4860613516057347e-07,
933
+ "loss": 0.2213,
934
+ "step": 660
935
+ },
936
+ {
937
+ "epoch": 2.829787234042553,
938
+ "grad_norm": 1.427452802658081,
939
+ "learning_rate": 2.771625106641601e-07,
940
+ "loss": 0.2492,
941
+ "step": 665
942
+ },
943
+ {
944
+ "epoch": 2.851063829787234,
945
+ "grad_norm": 1.1704022884368896,
946
+ "learning_rate": 2.1383520473062747e-07,
947
+ "loss": 0.2665,
948
+ "step": 670
949
+ },
950
+ {
951
+ "epoch": 2.872340425531915,
952
+ "grad_norm": 1.1795364618301392,
953
+ "learning_rate": 1.5865912806173166e-07,
954
+ "loss": 0.2422,
955
+ "step": 675
956
+ },
957
+ {
958
+ "epoch": 2.8936170212765955,
959
+ "grad_norm": 1.3297723531723022,
960
+ "learning_rate": 1.1166469779789912e-07,
961
+ "loss": 0.2674,
962
+ "step": 680
963
+ },
964
+ {
965
+ "epoch": 2.9148936170212765,
966
+ "grad_norm": 1.30366051197052,
967
+ "learning_rate": 7.287782075002303e-08,
968
+ "loss": 0.2545,
969
+ "step": 685
970
+ },
971
+ {
972
+ "epoch": 2.9361702127659575,
973
+ "grad_norm": 1.1999595165252686,
974
+ "learning_rate": 4.231987911772428e-08,
975
+ "loss": 0.2611,
976
+ "step": 690
977
+ },
978
+ {
979
+ "epoch": 2.9574468085106385,
980
+ "grad_norm": 1.1886225938796997,
981
+ "learning_rate": 2.000771870189544e-08,
982
+ "loss": 0.2307,
983
+ "step": 695
984
+ },
985
+ {
986
+ "epoch": 2.978723404255319,
987
+ "grad_norm": 1.145747423171997,
988
+ "learning_rate": 5.9536396180492894e-09,
989
+ "loss": 0.2399,
990
+ "step": 700
991
+ },
992
+ {
993
+ "epoch": 3.0,
994
+ "grad_norm": 1.07390296459198,
995
+ "learning_rate": 1.6538951557620863e-10,
996
+ "loss": 0.2555,
997
+ "step": 705
998
+ },
999
+ {
1000
+ "epoch": 3.0,
1001
+ "step": 705,
1002
+ "total_flos": 1.0148094862730199e+18,
1003
+ "train_loss": 0.5318781840885785,
1004
+ "train_runtime": 470.0601,
1005
+ "train_samples_per_second": 47.924,
1006
+ "train_steps_per_second": 1.5
1007
+ }
1008
+ ],
1009
+ "logging_steps": 5,
1010
+ "max_steps": 705,
1011
+ "num_input_tokens_seen": 0,
1012
+ "num_train_epochs": 3,
1013
+ "save_steps": 2000,
1014
+ "stateful_callbacks": {
1015
+ "TrainerControl": {
1016
+ "args": {
1017
+ "should_epoch_stop": false,
1018
+ "should_evaluate": false,
1019
+ "should_log": false,
1020
+ "should_save": false,
1021
+ "should_training_stop": false
1022
+ },
1023
+ "attributes": {}
1024
+ }
1025
+ },
1026
+ "total_flos": 1.0148094862730199e+18,
1027
+ "train_batch_size": 2,
1028
+ "trial_name": null,
1029
+ "trial_params": null
1030
+ }
52_128_e3_3e-5/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63bd598fa0513a637605e1e491c206e278c57322a6f1e099eda5c4618b7584d1
3
+ size 8145
52_128_e3_3e-5/vocab.json ADDED
The diff for this file is too large to render. See raw diff