RayDu0010 commited on
Commit
61dfecf
·
verified ·
1 Parent(s): 3e2cd99

Upload folder using huggingface_hub

Browse files
50_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: 50_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
+ # 50_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
50_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
+ "up_proj",
28
+ "v_proj",
29
+ "o_proj",
30
+ "down_proj",
31
+ "q_proj",
32
+ "gate_proj",
33
+ "k_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
50_128_e3_3e-5/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fa0fd3c08a91599400992f69242ddeb2423996f05062a2e0c641c5dbef1a509
3
+ size 791751704
50_128_e3_3e-5/all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.0028297439108137e+18,
4
+ "train_loss": 0.6319527648289999,
5
+ "train_runtime": 463.5299,
6
+ "train_samples": 7983,
7
+ "train_samples_per_second": 51.667,
8
+ "train_steps_per_second": 1.618
9
+ }
50_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
+ }
50_128_e3_3e-5/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
50_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
+ }
50_128_e3_3e-5/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
50_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
+ }
50_128_e3_3e-5/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.0028297439108137e+18,
4
+ "train_loss": 0.6319527648289999,
5
+ "train_runtime": 463.5299,
6
+ "train_samples": 7983,
7
+ "train_samples_per_second": 51.667,
8
+ "train_steps_per_second": 1.618
9
+ }
50_128_e3_3e-5/trainer_state.json ADDED
@@ -0,0 +1,1093 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 750,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02004008016032064,
14
+ "grad_norm": 0.9601594805717468,
15
+ "learning_rate": 3.157894736842105e-06,
16
+ "loss": 1.4299,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.04008016032064128,
21
+ "grad_norm": 0.7077376842498779,
22
+ "learning_rate": 7.105263157894737e-06,
23
+ "loss": 1.4563,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.06012024048096192,
28
+ "grad_norm": 1.0558604001998901,
29
+ "learning_rate": 1.1052631578947368e-05,
30
+ "loss": 1.4075,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.08016032064128256,
35
+ "grad_norm": 0.5508207678794861,
36
+ "learning_rate": 1.5e-05,
37
+ "loss": 1.412,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.10020040080160321,
42
+ "grad_norm": 0.6428379416465759,
43
+ "learning_rate": 1.894736842105263e-05,
44
+ "loss": 1.3401,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.12024048096192384,
49
+ "grad_norm": 0.4884888231754303,
50
+ "learning_rate": 2.2894736842105263e-05,
51
+ "loss": 1.3776,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.1402805611222445,
56
+ "grad_norm": 0.5136405229568481,
57
+ "learning_rate": 2.6842105263157896e-05,
58
+ "loss": 1.3186,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.16032064128256512,
63
+ "grad_norm": 0.4653320610523224,
64
+ "learning_rate": 2.999985398404377e-05,
65
+ "loss": 1.3112,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.18036072144288579,
70
+ "grad_norm": 0.5442164540290833,
71
+ "learning_rate": 2.999474372405878e-05,
72
+ "loss": 1.2911,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.20040080160320642,
77
+ "grad_norm": 0.5325270295143127,
78
+ "learning_rate": 2.9982335508768143e-05,
79
+ "loss": 1.2197,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.22044088176352705,
84
+ "grad_norm": 0.5432689785957336,
85
+ "learning_rate": 2.9962635377261457e-05,
86
+ "loss": 1.2172,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.24048096192384769,
91
+ "grad_norm": 0.6953958868980408,
92
+ "learning_rate": 2.99356529176105e-05,
93
+ "loss": 1.2559,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.2605210420841683,
98
+ "grad_norm": 0.4724169075489044,
99
+ "learning_rate": 2.9901401262202743e-05,
100
+ "loss": 1.1849,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.280561122244489,
105
+ "grad_norm": 0.5431613326072693,
106
+ "learning_rate": 2.9859897081349793e-05,
107
+ "loss": 1.179,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.30060120240480964,
112
+ "grad_norm": 0.5819985270500183,
113
+ "learning_rate": 2.981116057517393e-05,
114
+ "loss": 1.1285,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.32064128256513025,
119
+ "grad_norm": 0.49217310547828674,
120
+ "learning_rate": 2.9755215463776702e-05,
121
+ "loss": 1.2092,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.3406813627254509,
126
+ "grad_norm": 0.6440390944480896,
127
+ "learning_rate": 2.969208897569433e-05,
128
+ "loss": 1.1427,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.36072144288577157,
133
+ "grad_norm": 0.6890902519226074,
134
+ "learning_rate": 2.9621811834645543e-05,
135
+ "loss": 1.1399,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.3807615230460922,
140
+ "grad_norm": 0.690427303314209,
141
+ "learning_rate": 2.954441824457832e-05,
142
+ "loss": 1.112,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.40080160320641284,
147
+ "grad_norm": 0.6933308839797974,
148
+ "learning_rate": 2.945994587302282e-05,
149
+ "loss": 1.088,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.42084168336673344,
154
+ "grad_norm": 0.6218480467796326,
155
+ "learning_rate": 2.936843583275852e-05,
156
+ "loss": 1.0881,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.4408817635270541,
161
+ "grad_norm": 0.6375731229782104,
162
+ "learning_rate": 2.9269932661804623e-05,
163
+ "loss": 1.0777,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.46092184368737477,
168
+ "grad_norm": 0.7179180979728699,
169
+ "learning_rate": 2.9164484301743336e-05,
170
+ "loss": 1.0902,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.48096192384769537,
175
+ "grad_norm": 0.6413318514823914,
176
+ "learning_rate": 2.9052142074386702e-05,
177
+ "loss": 1.0459,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.501002004008016,
182
+ "grad_norm": 0.7498282194137573,
183
+ "learning_rate": 2.8932960656798166e-05,
184
+ "loss": 1.0084,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.5210420841683366,
189
+ "grad_norm": 0.7186252474784851,
190
+ "learning_rate": 2.880699805468126e-05,
191
+ "loss": 0.9392,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.5410821643286573,
196
+ "grad_norm": 0.780789315700531,
197
+ "learning_rate": 2.8674315574148126e-05,
198
+ "loss": 0.9971,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.561122244488978,
203
+ "grad_norm": 0.8073780536651611,
204
+ "learning_rate": 2.8534977791881816e-05,
205
+ "loss": 0.9529,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.5811623246492986,
210
+ "grad_norm": 0.8797677159309387,
211
+ "learning_rate": 2.8389052523706733e-05,
212
+ "loss": 0.9629,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.6012024048096193,
217
+ "grad_norm": 0.8914316296577454,
218
+ "learning_rate": 2.823661079158261e-05,
219
+ "loss": 0.9875,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.6212424849699398,
224
+ "grad_norm": 0.8675196766853333,
225
+ "learning_rate": 2.8077726789038077e-05,
226
+ "loss": 0.945,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.6412825651302605,
231
+ "grad_norm": 0.9290363192558289,
232
+ "learning_rate": 2.79124778450606e-05,
233
+ "loss": 0.9372,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.6613226452905812,
238
+ "grad_norm": 0.7931259274482727,
239
+ "learning_rate": 2.7740944386460365e-05,
240
+ "loss": 0.932,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.6813627254509018,
245
+ "grad_norm": 0.967017412185669,
246
+ "learning_rate": 2.7563209898726516e-05,
247
+ "loss": 0.9178,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.7014028056112225,
252
+ "grad_norm": 0.9028688669204712,
253
+ "learning_rate": 2.7379360885394664e-05,
254
+ "loss": 0.8881,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.7214428857715431,
259
+ "grad_norm": 0.9663246870040894,
260
+ "learning_rate": 2.7189486825945547e-05,
261
+ "loss": 0.8419,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.7414829659318637,
266
+ "grad_norm": 0.9064556956291199,
267
+ "learning_rate": 2.6993680132255295e-05,
268
+ "loss": 0.8883,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.7615230460921844,
273
+ "grad_norm": 0.9346010684967041,
274
+ "learning_rate": 2.6792036103618474e-05,
275
+ "loss": 0.8221,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.781563126252505,
280
+ "grad_norm": 0.9059447646141052,
281
+ "learning_rate": 2.6584652880365833e-05,
282
+ "loss": 0.8365,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.8016032064128257,
287
+ "grad_norm": 0.8932532668113708,
288
+ "learning_rate": 2.6371631396099333e-05,
289
+ "loss": 0.7956,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.8216432865731463,
294
+ "grad_norm": 1.0895155668258667,
295
+ "learning_rate": 2.615307532856764e-05,
296
+ "loss": 0.8126,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.8416833667334669,
301
+ "grad_norm": 1.0342001914978027,
302
+ "learning_rate": 2.5929091049206117e-05,
303
+ "loss": 0.8108,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.8617234468937875,
308
+ "grad_norm": 0.9378986954689026,
309
+ "learning_rate": 2.5699787571365704e-05,
310
+ "loss": 0.8219,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.8817635270541082,
315
+ "grad_norm": 1.00824773311615,
316
+ "learning_rate": 2.5465276497256048e-05,
317
+ "loss": 0.7829,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.9018036072144289,
322
+ "grad_norm": 1.0365967750549316,
323
+ "learning_rate": 2.52256719636286e-05,
324
+ "loss": 0.7554,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 0.9218436873747495,
329
+ "grad_norm": 1.0542258024215698,
330
+ "learning_rate": 2.4981090586226166e-05,
331
+ "loss": 0.8097,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 0.9418837675350702,
336
+ "grad_norm": 0.9865761399269104,
337
+ "learning_rate": 2.4731651403025895e-05,
338
+ "loss": 0.7749,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 0.9619238476953907,
343
+ "grad_norm": 0.9034010171890259,
344
+ "learning_rate": 2.4477475816303404e-05,
345
+ "loss": 0.7234,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 0.9819639278557114,
350
+ "grad_norm": 1.2438642978668213,
351
+ "learning_rate": 2.4218687533546193e-05,
352
+ "loss": 0.7378,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 1.0,
357
+ "grad_norm": 1.3256157636642456,
358
+ "learning_rate": 2.3955412507245078e-05,
359
+ "loss": 0.7626,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 1.0200400801603207,
364
+ "grad_norm": 1.66098153591156,
365
+ "learning_rate": 2.3687778873593e-05,
366
+ "loss": 0.6552,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 1.0400801603206413,
371
+ "grad_norm": 1.0742517709732056,
372
+ "learning_rate": 2.3415916890121047e-05,
373
+ "loss": 0.6472,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 1.060120240480962,
378
+ "grad_norm": 1.2974162101745605,
379
+ "learning_rate": 2.313995887230197e-05,
380
+ "loss": 0.6406,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 1.0801603206412826,
385
+ "grad_norm": 1.2350726127624512,
386
+ "learning_rate": 2.2860039129152136e-05,
387
+ "loss": 0.6404,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 1.1002004008016033,
392
+ "grad_norm": 1.0774811506271362,
393
+ "learning_rate": 2.257629389786321e-05,
394
+ "loss": 0.6216,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 1.1202404809619237,
399
+ "grad_norm": 1.3180279731750488,
400
+ "learning_rate": 2.2288861277495382e-05,
401
+ "loss": 0.6148,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 1.1402805611222444,
406
+ "grad_norm": 1.150285243988037,
407
+ "learning_rate": 2.1997881161764448e-05,
408
+ "loss": 0.6033,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 1.160320641282565,
413
+ "grad_norm": 1.1715692281723022,
414
+ "learning_rate": 2.1703495170955382e-05,
415
+ "loss": 0.5878,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 1.1803607214428857,
420
+ "grad_norm": 1.0309758186340332,
421
+ "learning_rate": 2.140584658299564e-05,
422
+ "loss": 0.6514,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 1.2004008016032064,
427
+ "grad_norm": 1.2580020427703857,
428
+ "learning_rate": 2.1105080263721663e-05,
429
+ "loss": 0.6189,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 1.220440881763527,
434
+ "grad_norm": 1.2592493295669556,
435
+ "learning_rate": 2.0801342596372522e-05,
436
+ "loss": 0.5979,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 1.2404809619238477,
441
+ "grad_norm": 1.6348594427108765,
442
+ "learning_rate": 2.0494781410345098e-05,
443
+ "loss": 0.5818,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 1.2605210420841684,
448
+ "grad_norm": 1.2832810878753662,
449
+ "learning_rate": 2.0185545909245344e-05,
450
+ "loss": 0.5807,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 1.280561122244489,
455
+ "grad_norm": 1.4134682416915894,
456
+ "learning_rate": 1.9873786598270786e-05,
457
+ "loss": 0.5971,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 1.3006012024048097,
462
+ "grad_norm": 1.2020596265792847,
463
+ "learning_rate": 1.955965521095948e-05,
464
+ "loss": 0.5732,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 1.3206412825651301,
469
+ "grad_norm": 1.3586162328720093,
470
+ "learning_rate": 1.9243304635341182e-05,
471
+ "loss": 0.5832,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 1.340681362725451,
476
+ "grad_norm": 1.333615779876709,
477
+ "learning_rate": 1.8924888839526612e-05,
478
+ "loss": 0.5508,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 1.3607214428857715,
483
+ "grad_norm": 1.3729833364486694,
484
+ "learning_rate": 1.8604562796771006e-05,
485
+ "loss": 0.5816,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 1.3807615230460921,
490
+ "grad_norm": 1.0932271480560303,
491
+ "learning_rate": 1.828248241004852e-05,
492
+ "loss": 0.5778,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 1.4008016032064128,
497
+ "grad_norm": 1.4792283773422241,
498
+ "learning_rate": 1.7958804436174103e-05,
499
+ "loss": 0.5543,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 1.4208416833667334,
504
+ "grad_norm": 1.3606455326080322,
505
+ "learning_rate": 1.763368640950981e-05,
506
+ "loss": 0.5459,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 1.440881763527054,
511
+ "grad_norm": 1.4115424156188965,
512
+ "learning_rate": 1.7307286565292687e-05,
513
+ "loss": 0.5598,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 1.4609218436873748,
518
+ "grad_norm": 1.1846997737884521,
519
+ "learning_rate": 1.6979763762621545e-05,
520
+ "loss": 0.5185,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 1.4809619238476954,
525
+ "grad_norm": 1.504781723022461,
526
+ "learning_rate": 1.6651277407140086e-05,
527
+ "loss": 0.5224,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 1.5010020040080159,
532
+ "grad_norm": 1.327328085899353,
533
+ "learning_rate": 1.632198737345403e-05,
534
+ "loss": 0.4929,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 1.5210420841683367,
539
+ "grad_norm": 1.3167201280593872,
540
+ "learning_rate": 1.5992053927320006e-05,
541
+ "loss": 0.5017,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 1.5410821643286572,
546
+ "grad_norm": 1.3048160076141357,
547
+ "learning_rate": 1.5661637647644072e-05,
548
+ "loss": 0.5119,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 1.561122244488978,
553
+ "grad_norm": 1.3039623498916626,
554
+ "learning_rate": 1.5330899348327798e-05,
555
+ "loss": 0.5018,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 1.5811623246492985,
560
+ "grad_norm": 1.2859169244766235,
561
+ "learning_rate": 1.5e-05,
562
+ "loss": 0.5242,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 1.6012024048096194,
567
+ "grad_norm": 1.2298582792282104,
568
+ "learning_rate": 1.4669100651672204e-05,
569
+ "loss": 0.491,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 1.6212424849699398,
574
+ "grad_norm": 1.371962308883667,
575
+ "learning_rate": 1.4338362352355932e-05,
576
+ "loss": 0.4422,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 1.6412825651302605,
581
+ "grad_norm": 1.4055190086364746,
582
+ "learning_rate": 1.4007946072679995e-05,
583
+ "loss": 0.5177,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 1.6613226452905812,
588
+ "grad_norm": 1.2292001247406006,
589
+ "learning_rate": 1.3678012626545978e-05,
590
+ "loss": 0.4764,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 1.6813627254509018,
595
+ "grad_norm": 1.3181291818618774,
596
+ "learning_rate": 1.3348722592859918e-05,
597
+ "loss": 0.4641,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 1.7014028056112225,
602
+ "grad_norm": 1.2101354598999023,
603
+ "learning_rate": 1.3020236237378454e-05,
604
+ "loss": 0.485,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 1.7214428857715431,
609
+ "grad_norm": 1.5303170680999756,
610
+ "learning_rate": 1.2692713434707316e-05,
611
+ "loss": 0.4541,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 1.7414829659318638,
616
+ "grad_norm": 1.2315529584884644,
617
+ "learning_rate": 1.236631359049019e-05,
618
+ "loss": 0.4644,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 1.7615230460921842,
623
+ "grad_norm": 1.313323736190796,
624
+ "learning_rate": 1.2041195563825898e-05,
625
+ "loss": 0.4577,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 1.7815631262525051,
630
+ "grad_norm": 1.313490867614746,
631
+ "learning_rate": 1.1717517589951479e-05,
632
+ "loss": 0.5103,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 1.8016032064128256,
637
+ "grad_norm": 1.4138275384902954,
638
+ "learning_rate": 1.1395437203228997e-05,
639
+ "loss": 0.4468,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 1.8216432865731464,
644
+ "grad_norm": 1.2883437871932983,
645
+ "learning_rate": 1.1075111160473392e-05,
646
+ "loss": 0.4768,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 1.8416833667334669,
651
+ "grad_norm": 1.1784231662750244,
652
+ "learning_rate": 1.0756695364658818e-05,
653
+ "loss": 0.4507,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 1.8617234468937875,
658
+ "grad_norm": 1.329169511795044,
659
+ "learning_rate": 1.0440344789040528e-05,
660
+ "loss": 0.4645,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 1.8817635270541082,
665
+ "grad_norm": 1.1398073434829712,
666
+ "learning_rate": 1.0126213401729218e-05,
667
+ "loss": 0.4253,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 1.9018036072144289,
672
+ "grad_norm": 1.2670029401779175,
673
+ "learning_rate": 9.814454090754654e-06,
674
+ "loss": 0.4486,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 1.9218436873747495,
679
+ "grad_norm": 1.262534260749817,
680
+ "learning_rate": 9.505218589654904e-06,
681
+ "loss": 0.4731,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 1.9418837675350702,
686
+ "grad_norm": 1.5234050750732422,
687
+ "learning_rate": 9.198657403627477e-06,
688
+ "loss": 0.3779,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 1.9619238476953909,
693
+ "grad_norm": 1.2874265909194946,
694
+ "learning_rate": 8.894919736278343e-06,
695
+ "loss": 0.4278,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 1.9819639278557113,
700
+ "grad_norm": 1.4344435930252075,
701
+ "learning_rate": 8.594153417004359e-06,
702
+ "loss": 0.4079,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 2.0,
707
+ "grad_norm": 1.8803514242172241,
708
+ "learning_rate": 8.296504829044619e-06,
709
+ "loss": 0.4317,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 2.0200400801603204,
714
+ "grad_norm": 1.4884893894195557,
715
+ "learning_rate": 8.002118838235551e-06,
716
+ "loss": 0.3601,
717
+ "step": 505
718
+ },
719
+ {
720
+ "epoch": 2.0400801603206413,
721
+ "grad_norm": 1.4421247243881226,
722
+ "learning_rate": 7.711138722504615e-06,
723
+ "loss": 0.3866,
724
+ "step": 510
725
+ },
726
+ {
727
+ "epoch": 2.0601202404809618,
728
+ "grad_norm": 1.256477952003479,
729
+ "learning_rate": 7.423706102136791e-06,
730
+ "loss": 0.3651,
731
+ "step": 515
732
+ },
733
+ {
734
+ "epoch": 2.0801603206412826,
735
+ "grad_norm": 1.4792113304138184,
736
+ "learning_rate": 7.139960870847866e-06,
737
+ "loss": 0.3381,
738
+ "step": 520
739
+ },
740
+ {
741
+ "epoch": 2.100200400801603,
742
+ "grad_norm": 1.4830726385116577,
743
+ "learning_rate": 6.860041127698033e-06,
744
+ "loss": 0.3347,
745
+ "step": 525
746
+ },
747
+ {
748
+ "epoch": 2.120240480961924,
749
+ "grad_norm": 1.2962840795516968,
750
+ "learning_rate": 6.584083109878955e-06,
751
+ "loss": 0.3176,
752
+ "step": 530
753
+ },
754
+ {
755
+ "epoch": 2.1402805611222444,
756
+ "grad_norm": 1.4664140939712524,
757
+ "learning_rate": 6.312221126406996e-06,
758
+ "loss": 0.3177,
759
+ "step": 535
760
+ },
761
+ {
762
+ "epoch": 2.1603206412825653,
763
+ "grad_norm": 1.4860647916793823,
764
+ "learning_rate": 6.044587492754926e-06,
765
+ "loss": 0.3529,
766
+ "step": 540
767
+ },
768
+ {
769
+ "epoch": 2.1803607214428857,
770
+ "grad_norm": 1.3849903345108032,
771
+ "learning_rate": 5.781312466453806e-06,
772
+ "loss": 0.4032,
773
+ "step": 545
774
+ },
775
+ {
776
+ "epoch": 2.2004008016032066,
777
+ "grad_norm": 1.2633053064346313,
778
+ "learning_rate": 5.522524183696602e-06,
779
+ "loss": 0.3442,
780
+ "step": 550
781
+ },
782
+ {
783
+ "epoch": 2.220440881763527,
784
+ "grad_norm": 1.4522321224212646,
785
+ "learning_rate": 5.26834859697411e-06,
786
+ "loss": 0.3393,
787
+ "step": 555
788
+ },
789
+ {
790
+ "epoch": 2.2404809619238475,
791
+ "grad_norm": 1.42525053024292,
792
+ "learning_rate": 5.018909413773837e-06,
793
+ "loss": 0.2937,
794
+ "step": 560
795
+ },
796
+ {
797
+ "epoch": 2.2605210420841684,
798
+ "grad_norm": 1.418398380279541,
799
+ "learning_rate": 4.7743280363714e-06,
800
+ "loss": 0.3211,
801
+ "step": 565
802
+ },
803
+ {
804
+ "epoch": 2.280561122244489,
805
+ "grad_norm": 1.4734710454940796,
806
+ "learning_rate": 4.534723502743956e-06,
807
+ "loss": 0.3164,
808
+ "step": 570
809
+ },
810
+ {
811
+ "epoch": 2.3006012024048097,
812
+ "grad_norm": 1.3787811994552612,
813
+ "learning_rate": 4.300212428634301e-06,
814
+ "loss": 0.3408,
815
+ "step": 575
816
+ },
817
+ {
818
+ "epoch": 2.32064128256513,
819
+ "grad_norm": 1.2773798704147339,
820
+ "learning_rate": 4.0709089507938815e-06,
821
+ "loss": 0.3547,
822
+ "step": 580
823
+ },
824
+ {
825
+ "epoch": 2.340681362725451,
826
+ "grad_norm": 1.4758018255233765,
827
+ "learning_rate": 3.846924671432358e-06,
828
+ "loss": 0.3217,
829
+ "step": 585
830
+ },
831
+ {
832
+ "epoch": 2.3607214428857715,
833
+ "grad_norm": 1.4780973196029663,
834
+ "learning_rate": 3.628368603900671e-06,
835
+ "loss": 0.332,
836
+ "step": 590
837
+ },
838
+ {
839
+ "epoch": 2.3807615230460923,
840
+ "grad_norm": 1.3057918548583984,
841
+ "learning_rate": 3.4153471196341686e-06,
842
+ "loss": 0.3754,
843
+ "step": 595
844
+ },
845
+ {
846
+ "epoch": 2.400801603206413,
847
+ "grad_norm": 1.3187614679336548,
848
+ "learning_rate": 3.207963896381528e-06,
849
+ "loss": 0.3226,
850
+ "step": 600
851
+ },
852
+ {
853
+ "epoch": 2.420841683366733,
854
+ "grad_norm": 1.334956169128418,
855
+ "learning_rate": 3.006319867744707e-06,
856
+ "loss": 0.3531,
857
+ "step": 605
858
+ },
859
+ {
860
+ "epoch": 2.440881763527054,
861
+ "grad_norm": 1.3731131553649902,
862
+ "learning_rate": 2.8105131740544525e-06,
863
+ "loss": 0.3235,
864
+ "step": 610
865
+ },
866
+ {
867
+ "epoch": 2.460921843687375,
868
+ "grad_norm": 1.4084428548812866,
869
+ "learning_rate": 2.6206391146053416e-06,
870
+ "loss": 0.3184,
871
+ "step": 615
872
+ },
873
+ {
874
+ "epoch": 2.4809619238476954,
875
+ "grad_norm": 1.4517178535461426,
876
+ "learning_rate": 2.436790101273485e-06,
877
+ "loss": 0.3392,
878
+ "step": 620
879
+ },
880
+ {
881
+ "epoch": 2.501002004008016,
882
+ "grad_norm": 1.5006723403930664,
883
+ "learning_rate": 2.259055613539638e-06,
884
+ "loss": 0.3315,
885
+ "step": 625
886
+ },
887
+ {
888
+ "epoch": 2.5210420841683367,
889
+ "grad_norm": 1.3534520864486694,
890
+ "learning_rate": 2.0875221549394015e-06,
891
+ "loss": 0.3424,
892
+ "step": 630
893
+ },
894
+ {
895
+ "epoch": 2.541082164328657,
896
+ "grad_norm": 1.399511694908142,
897
+ "learning_rate": 1.9222732109619205e-06,
898
+ "loss": 0.3097,
899
+ "step": 635
900
+ },
901
+ {
902
+ "epoch": 2.561122244488978,
903
+ "grad_norm": 1.4096386432647705,
904
+ "learning_rate": 1.7633892084173926e-06,
905
+ "loss": 0.3333,
906
+ "step": 640
907
+ },
908
+ {
909
+ "epoch": 2.5811623246492985,
910
+ "grad_norm": 1.376615047454834,
911
+ "learning_rate": 1.6109474762932703e-06,
912
+ "loss": 0.3306,
913
+ "step": 645
914
+ },
915
+ {
916
+ "epoch": 2.6012024048096194,
917
+ "grad_norm": 1.313376784324646,
918
+ "learning_rate": 1.465022208118183e-06,
919
+ "loss": 0.3357,
920
+ "step": 650
921
+ },
922
+ {
923
+ "epoch": 2.62124248496994,
924
+ "grad_norm": 1.2844678163528442,
925
+ "learning_rate": 1.3256844258518742e-06,
926
+ "loss": 0.3357,
927
+ "step": 655
928
+ },
929
+ {
930
+ "epoch": 2.6412825651302603,
931
+ "grad_norm": 1.2250995635986328,
932
+ "learning_rate": 1.1930019453187413e-06,
933
+ "loss": 0.3009,
934
+ "step": 660
935
+ },
936
+ {
937
+ "epoch": 2.661322645290581,
938
+ "grad_norm": 1.3458664417266846,
939
+ "learning_rate": 1.0670393432018355e-06,
940
+ "loss": 0.2964,
941
+ "step": 665
942
+ },
943
+ {
944
+ "epoch": 2.681362725450902,
945
+ "grad_norm": 1.33137845993042,
946
+ "learning_rate": 9.478579256133018e-07,
947
+ "loss": 0.342,
948
+ "step": 670
949
+ },
950
+ {
951
+ "epoch": 2.7014028056112225,
952
+ "grad_norm": 1.37694251537323,
953
+ "learning_rate": 8.355156982566642e-07,
954
+ "loss": 0.2957,
955
+ "step": 675
956
+ },
957
+ {
958
+ "epoch": 2.721442885771543,
959
+ "grad_norm": 1.3889362812042236,
960
+ "learning_rate": 7.300673381953827e-07,
961
+ "loss": 0.3074,
962
+ "step": 680
963
+ },
964
+ {
965
+ "epoch": 2.741482965931864,
966
+ "grad_norm": 1.4869498014450073,
967
+ "learning_rate": 6.31564167241479e-07,
968
+ "loss": 0.3207,
969
+ "step": 685
970
+ },
971
+ {
972
+ "epoch": 2.7615230460921842,
973
+ "grad_norm": 1.3570873737335205,
974
+ "learning_rate": 5.400541269771808e-07,
975
+ "loss": 0.289,
976
+ "step": 690
977
+ },
978
+ {
979
+ "epoch": 2.781563126252505,
980
+ "grad_norm": 1.3235721588134766,
981
+ "learning_rate": 4.555817554216774e-07,
982
+ "loss": 0.3235,
983
+ "step": 695
984
+ },
985
+ {
986
+ "epoch": 2.8016032064128256,
987
+ "grad_norm": 1.5211927890777588,
988
+ "learning_rate": 3.781881653544611e-07,
989
+ "loss": 0.3074,
990
+ "step": 700
991
+ },
992
+ {
993
+ "epoch": 2.8216432865731464,
994
+ "grad_norm": 1.2272603511810303,
995
+ "learning_rate": 3.079110243056721e-07,
996
+ "loss": 0.3113,
997
+ "step": 705
998
+ },
999
+ {
1000
+ "epoch": 2.841683366733467,
1001
+ "grad_norm": 1.310747742652893,
1002
+ "learning_rate": 2.447845362232992e-07,
1003
+ "loss": 0.3325,
1004
+ "step": 710
1005
+ },
1006
+ {
1007
+ "epoch": 2.8617234468937873,
1008
+ "grad_norm": 1.551400065422058,
1009
+ "learning_rate": 1.888394248260733e-07,
1010
+ "loss": 0.3107,
1011
+ "step": 715
1012
+ },
1013
+ {
1014
+ "epoch": 2.881763527054108,
1015
+ "grad_norm": 1.3516111373901367,
1016
+ "learning_rate": 1.4010291865020842e-07,
1017
+ "loss": 0.2965,
1018
+ "step": 720
1019
+ },
1020
+ {
1021
+ "epoch": 2.901803607214429,
1022
+ "grad_norm": 1.4808698892593384,
1023
+ "learning_rate": 9.85987377972558e-08,
1024
+ "loss": 0.319,
1025
+ "step": 725
1026
+ },
1027
+ {
1028
+ "epoch": 2.9218436873747495,
1029
+ "grad_norm": 1.1399931907653809,
1030
+ "learning_rate": 6.434708238949871e-08,
1031
+ "loss": 0.3275,
1032
+ "step": 730
1033
+ },
1034
+ {
1035
+ "epoch": 2.94188376753507,
1036
+ "grad_norm": 1.4613176584243774,
1037
+ "learning_rate": 3.736462273854324e-08,
1038
+ "loss": 0.3318,
1039
+ "step": 735
1040
+ },
1041
+ {
1042
+ "epoch": 2.961923847695391,
1043
+ "grad_norm": 1.3203116655349731,
1044
+ "learning_rate": 1.7664491231855208e-08,
1045
+ "loss": 0.3238,
1046
+ "step": 740
1047
+ },
1048
+ {
1049
+ "epoch": 2.9819639278557113,
1050
+ "grad_norm": 1.420268177986145,
1051
+ "learning_rate": 5.256275941222799e-09,
1052
+ "loss": 0.286,
1053
+ "step": 745
1054
+ },
1055
+ {
1056
+ "epoch": 3.0,
1057
+ "grad_norm": 1.8541890382766724,
1058
+ "learning_rate": 1.460159562294283e-10,
1059
+ "loss": 0.3792,
1060
+ "step": 750
1061
+ },
1062
+ {
1063
+ "epoch": 3.0,
1064
+ "step": 750,
1065
+ "total_flos": 1.0028297439108137e+18,
1066
+ "train_loss": 0.6319527648289999,
1067
+ "train_runtime": 463.5299,
1068
+ "train_samples_per_second": 51.667,
1069
+ "train_steps_per_second": 1.618
1070
+ }
1071
+ ],
1072
+ "logging_steps": 5,
1073
+ "max_steps": 750,
1074
+ "num_input_tokens_seen": 0,
1075
+ "num_train_epochs": 3,
1076
+ "save_steps": 2000,
1077
+ "stateful_callbacks": {
1078
+ "TrainerControl": {
1079
+ "args": {
1080
+ "should_epoch_stop": false,
1081
+ "should_evaluate": false,
1082
+ "should_log": false,
1083
+ "should_save": false,
1084
+ "should_training_stop": false
1085
+ },
1086
+ "attributes": {}
1087
+ }
1088
+ },
1089
+ "total_flos": 1.0028297439108137e+18,
1090
+ "train_batch_size": 2,
1091
+ "trial_name": null,
1092
+ "trial_params": null
1093
+ }
50_128_e3_3e-5/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a9301a8d692213ae33ae04d44a2e36945253772867bceaffbed2ffffbd98a9e
3
+ size 8145
50_128_e3_3e-5/vocab.json ADDED
The diff for this file is too large to render. See raw diff