RayDu0010 commited on
Commit
1486bbd
·
verified ·
1 Parent(s): 3326b87

Upload folder using huggingface_hub

Browse files
40_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: 40_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
+ # 40_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
40_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
+ "o_proj",
29
+ "down_proj",
30
+ "up_proj",
31
+ "gate_proj",
32
+ "q_proj",
33
+ "v_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
40_128_e3_3e-5/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f2e3c119c8aba91d6d9a7cd013cadaf6adbaabcefc2d011a4c9fe8f334e3872
3
+ size 791751704
40_128_e3_3e-5/all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.4714141706656154e+18,
4
+ "train_loss": 0.5800944429501301,
5
+ "train_runtime": 704.6914,
6
+ "train_samples": 11301,
7
+ "train_samples_per_second": 48.11,
8
+ "train_steps_per_second": 1.507
9
+ }
40_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
+ }
40_128_e3_3e-5/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
40_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
+ }
40_128_e3_3e-5/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
40_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
+ }
40_128_e3_3e-5/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.4714141706656154e+18,
4
+ "train_loss": 0.5800944429501301,
5
+ "train_runtime": 704.6914,
6
+ "train_samples": 11301,
7
+ "train_samples_per_second": 48.11,
8
+ "train_steps_per_second": 1.507
9
+ }
40_128_e3_3e-5/trainer_state.json ADDED
@@ -0,0 +1,1527 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1062,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.014144271570014143,
14
+ "grad_norm": 1.0747876167297363,
15
+ "learning_rate": 2.222222222222222e-06,
16
+ "loss": 1.37,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.028288543140028287,
21
+ "grad_norm": 0.9176684617996216,
22
+ "learning_rate": 4.9999999999999996e-06,
23
+ "loss": 1.3437,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.042432814710042434,
28
+ "grad_norm": 0.6062710881233215,
29
+ "learning_rate": 7.777777777777777e-06,
30
+ "loss": 1.3197,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.056577086280056574,
35
+ "grad_norm": 0.6705710291862488,
36
+ "learning_rate": 1.0555555555555555e-05,
37
+ "loss": 1.3693,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.07072135785007072,
42
+ "grad_norm": 0.5237507224082947,
43
+ "learning_rate": 1.3333333333333333e-05,
44
+ "loss": 1.2591,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.08486562942008487,
49
+ "grad_norm": 0.5683798789978027,
50
+ "learning_rate": 1.6111111111111115e-05,
51
+ "loss": 1.3247,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.09900990099009901,
56
+ "grad_norm": 0.4752490520477295,
57
+ "learning_rate": 1.888888888888889e-05,
58
+ "loss": 1.1759,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.11315417256011315,
63
+ "grad_norm": 0.5820473432540894,
64
+ "learning_rate": 2.1666666666666667e-05,
65
+ "loss": 1.2121,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.1272984441301273,
70
+ "grad_norm": 0.5026617050170898,
71
+ "learning_rate": 2.4444444444444445e-05,
72
+ "loss": 1.2535,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.14144271570014144,
77
+ "grad_norm": 0.5747225880622864,
78
+ "learning_rate": 2.7222222222222223e-05,
79
+ "loss": 1.2304,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.15558698727015557,
84
+ "grad_norm": 0.6030910611152649,
85
+ "learning_rate": 3e-05,
86
+ "loss": 1.2436,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.16973125884016974,
91
+ "grad_norm": 1.212446928024292,
92
+ "learning_rate": 2.9998178743291113e-05,
93
+ "loss": 1.1933,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.18387553041018387,
98
+ "grad_norm": 0.7449299097061157,
99
+ "learning_rate": 2.9992715415427915e-05,
100
+ "loss": 1.153,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.19801980198019803,
105
+ "grad_norm": 0.51857990026474,
106
+ "learning_rate": 2.998361134309341e-05,
107
+ "loss": 1.1067,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.21216407355021216,
112
+ "grad_norm": 0.6298156976699829,
113
+ "learning_rate": 2.997086873706798e-05,
114
+ "loss": 1.1413,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.2263083451202263,
119
+ "grad_norm": 0.5145334601402283,
120
+ "learning_rate": 2.995449069169251e-05,
121
+ "loss": 1.1386,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.24045261669024046,
126
+ "grad_norm": 0.6031376123428345,
127
+ "learning_rate": 2.9934481184117005e-05,
128
+ "loss": 1.1274,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.2545968882602546,
133
+ "grad_norm": 0.6600082516670227,
134
+ "learning_rate": 2.9910845073334793e-05,
135
+ "loss": 1.1306,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.26874115983026875,
140
+ "grad_norm": 0.6091558933258057,
141
+ "learning_rate": 2.9883588099002583e-05,
142
+ "loss": 1.0814,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.2828854314002829,
147
+ "grad_norm": 0.6019696593284607,
148
+ "learning_rate": 2.9852716880046687e-05,
149
+ "loss": 1.0414,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.297029702970297,
154
+ "grad_norm": 0.6119039058685303,
155
+ "learning_rate": 2.981823891305572e-05,
156
+ "loss": 1.0931,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.31117397454031115,
161
+ "grad_norm": 0.7030906677246094,
162
+ "learning_rate": 2.9780162570460182e-05,
163
+ "loss": 1.1144,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.32531824611032534,
168
+ "grad_norm": 0.668877899646759,
169
+ "learning_rate": 2.9738497098499325e-05,
170
+ "loss": 0.9888,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.33946251768033947,
175
+ "grad_norm": 0.6111065745353699,
176
+ "learning_rate": 2.969325261497586e-05,
177
+ "loss": 1.0458,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.3536067892503536,
182
+ "grad_norm": 0.6681651473045349,
183
+ "learning_rate": 2.9644440106799003e-05,
184
+ "loss": 0.9838,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.36775106082036774,
189
+ "grad_norm": 0.7722393870353699,
190
+ "learning_rate": 2.9592071427316492e-05,
191
+ "loss": 1.0157,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.38189533239038187,
196
+ "grad_norm": 0.7012617588043213,
197
+ "learning_rate": 2.9536159293436172e-05,
198
+ "loss": 0.9982,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.39603960396039606,
203
+ "grad_norm": 0.6404555439949036,
204
+ "learning_rate": 2.9476717282537897e-05,
205
+ "loss": 0.9726,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.4101838755304102,
210
+ "grad_norm": 0.6939463019371033,
211
+ "learning_rate": 2.9413759829176497e-05,
212
+ "loss": 0.9465,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.4243281471004243,
217
+ "grad_norm": 0.7188811898231506,
218
+ "learning_rate": 2.934730222157653e-05,
219
+ "loss": 0.9744,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.43847241867043846,
224
+ "grad_norm": 0.7883697152137756,
225
+ "learning_rate": 2.927736059791984e-05,
226
+ "loss": 0.9622,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.4526166902404526,
231
+ "grad_norm": 0.6849822402000427,
232
+ "learning_rate": 2.9203951942426587e-05,
233
+ "loss": 0.954,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.4667609618104668,
238
+ "grad_norm": 0.7410770058631897,
239
+ "learning_rate": 2.9127094081230952e-05,
240
+ "loss": 0.9627,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.4809052333804809,
245
+ "grad_norm": 0.8676487803459167,
246
+ "learning_rate": 2.9046805678052312e-05,
247
+ "loss": 0.8986,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.49504950495049505,
252
+ "grad_norm": 0.7439620494842529,
253
+ "learning_rate": 2.8963106229663064e-05,
254
+ "loss": 0.9137,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.5091937765205092,
259
+ "grad_norm": 0.7417446374893188,
260
+ "learning_rate": 2.8876016061154125e-05,
261
+ "loss": 0.8868,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.5233380480905233,
266
+ "grad_norm": 0.9714059233665466,
267
+ "learning_rate": 2.8785556320999308e-05,
268
+ "loss": 0.9291,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.5374823196605375,
273
+ "grad_norm": 0.9033262729644775,
274
+ "learning_rate": 2.8691748975919784e-05,
275
+ "loss": 0.8629,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.5516265912305516,
280
+ "grad_norm": 0.8753783702850342,
281
+ "learning_rate": 2.8594616805549752e-05,
282
+ "loss": 0.9318,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.5657708628005658,
287
+ "grad_norm": 0.8650000691413879,
288
+ "learning_rate": 2.84941833969048e-05,
289
+ "loss": 0.8456,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.57991513437058,
294
+ "grad_norm": 0.803869903087616,
295
+ "learning_rate": 2.8390473138654175e-05,
296
+ "loss": 0.8589,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.594059405940594,
301
+ "grad_norm": 0.9435705542564392,
302
+ "learning_rate": 2.828351121519835e-05,
303
+ "loss": 0.8684,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.6082036775106082,
308
+ "grad_norm": 0.8487920761108398,
309
+ "learning_rate": 2.817332360055343e-05,
310
+ "loss": 0.859,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.6223479490806223,
315
+ "grad_norm": 1.0288132429122925,
316
+ "learning_rate": 2.8059937052043724e-05,
317
+ "loss": 0.8331,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.6364922206506365,
322
+ "grad_norm": 0.8828144073486328,
323
+ "learning_rate": 2.7943379103804196e-05,
324
+ "loss": 0.8601,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 0.6506364922206507,
329
+ "grad_norm": 0.9337291717529297,
330
+ "learning_rate": 2.7823678060094198e-05,
331
+ "loss": 0.812,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 0.6647807637906648,
336
+ "grad_norm": 0.9571611881256104,
337
+ "learning_rate": 2.770086298842426e-05,
338
+ "loss": 0.8843,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 0.6789250353606789,
343
+ "grad_norm": 0.9417634606361389,
344
+ "learning_rate": 2.7574963712497486e-05,
345
+ "loss": 0.8524,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 0.693069306930693,
350
+ "grad_norm": 0.9588803052902222,
351
+ "learning_rate": 2.7446010804967314e-05,
352
+ "loss": 0.786,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 0.7072135785007072,
357
+ "grad_norm": 1.0345133543014526,
358
+ "learning_rate": 2.7314035580013487e-05,
359
+ "loss": 0.7833,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 0.7213578500707214,
364
+ "grad_norm": 0.9964139461517334,
365
+ "learning_rate": 2.717907008573785e-05,
366
+ "loss": 0.8229,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 0.7355021216407355,
371
+ "grad_norm": 0.9235431551933289,
372
+ "learning_rate": 2.7041147096381988e-05,
373
+ "loss": 0.802,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 0.7496463932107497,
378
+ "grad_norm": 0.9187133312225342,
379
+ "learning_rate": 2.6900300104368527e-05,
380
+ "loss": 0.7653,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 0.7637906647807637,
385
+ "grad_norm": 1.0263481140136719,
386
+ "learning_rate": 2.6756563312168022e-05,
387
+ "loss": 0.7958,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 0.7779349363507779,
392
+ "grad_norm": 1.0640482902526855,
393
+ "learning_rate": 2.6609971623993412e-05,
394
+ "loss": 0.7892,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 0.7920792079207921,
399
+ "grad_norm": 1.0356693267822266,
400
+ "learning_rate": 2.6460560637324113e-05,
401
+ "loss": 0.7171,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 0.8062234794908062,
406
+ "grad_norm": 1.0989431142807007,
407
+ "learning_rate": 2.6308366634261697e-05,
408
+ "loss": 0.7517,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 0.8203677510608204,
413
+ "grad_norm": 1.0880135297775269,
414
+ "learning_rate": 2.6153426572719393e-05,
415
+ "loss": 0.7939,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 0.8345120226308345,
420
+ "grad_norm": 1.1122990846633911,
421
+ "learning_rate": 2.5995778077447393e-05,
422
+ "loss": 0.7389,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 0.8486562942008486,
427
+ "grad_norm": 1.0430350303649902,
428
+ "learning_rate": 2.5835459430896334e-05,
429
+ "loss": 0.7213,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 0.8628005657708628,
434
+ "grad_norm": 0.967939555644989,
435
+ "learning_rate": 2.5672509563920953e-05,
436
+ "loss": 0.7432,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 0.8769448373408769,
441
+ "grad_norm": 1.1871763467788696,
442
+ "learning_rate": 2.5506968046326374e-05,
443
+ "loss": 0.7079,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 0.8910891089108911,
448
+ "grad_norm": 1.0143920183181763,
449
+ "learning_rate": 2.5338875077259207e-05,
450
+ "loss": 0.7313,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 0.9052333804809052,
455
+ "grad_norm": 1.0292450189590454,
456
+ "learning_rate": 2.5168271475445795e-05,
457
+ "loss": 0.7361,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 0.9193776520509194,
462
+ "grad_norm": 1.0853692293167114,
463
+ "learning_rate": 2.499519866928006e-05,
464
+ "loss": 0.6833,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 0.9335219236209336,
469
+ "grad_norm": 1.0352710485458374,
470
+ "learning_rate": 2.4819698686763245e-05,
471
+ "loss": 0.6425,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 0.9476661951909476,
476
+ "grad_norm": 1.0205281972885132,
477
+ "learning_rate": 2.464181414529809e-05,
478
+ "loss": 0.7286,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 0.9618104667609618,
483
+ "grad_norm": 0.9438811540603638,
484
+ "learning_rate": 2.4461588241339877e-05,
485
+ "loss": 0.6974,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 0.9759547383309759,
490
+ "grad_norm": 1.1373602151870728,
491
+ "learning_rate": 2.4279064739906824e-05,
492
+ "loss": 0.7025,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 0.9900990099009901,
497
+ "grad_norm": 1.1266069412231445,
498
+ "learning_rate": 2.4094287963952468e-05,
499
+ "loss": 0.6841,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 1.002828854314003,
504
+ "grad_norm": 1.1110751628875732,
505
+ "learning_rate": 2.3907302783602522e-05,
506
+ "loss": 0.6328,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 1.016973125884017,
511
+ "grad_norm": 1.2206801176071167,
512
+ "learning_rate": 2.3718154605258885e-05,
513
+ "loss": 0.6137,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 1.031117397454031,
518
+ "grad_norm": 1.1173489093780518,
519
+ "learning_rate": 2.3526889360573387e-05,
520
+ "loss": 0.6244,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 1.0452616690240453,
525
+ "grad_norm": 1.0903688669204712,
526
+ "learning_rate": 2.3333553495294033e-05,
527
+ "loss": 0.6073,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 1.0594059405940595,
532
+ "grad_norm": 1.176391839981079,
533
+ "learning_rate": 2.3138193957986392e-05,
534
+ "loss": 0.5768,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 1.0735502121640736,
539
+ "grad_norm": 1.2393953800201416,
540
+ "learning_rate": 2.2940858188632853e-05,
541
+ "loss": 0.6164,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 1.0876944837340876,
546
+ "grad_norm": 1.1328738927841187,
547
+ "learning_rate": 2.27415941071126e-05,
548
+ "loss": 0.6001,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 1.1018387553041018,
553
+ "grad_norm": 1.177234411239624,
554
+ "learning_rate": 2.2540450101565002e-05,
555
+ "loss": 0.5825,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 1.115983026874116,
560
+ "grad_norm": 1.1380234956741333,
561
+ "learning_rate": 2.233747501663934e-05,
562
+ "loss": 0.5835,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 1.1301272984441302,
567
+ "grad_norm": 1.1904233694076538,
568
+ "learning_rate": 2.213271814163363e-05,
569
+ "loss": 0.583,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 1.1442715700141444,
574
+ "grad_norm": 1.1253855228424072,
575
+ "learning_rate": 2.192622919852551e-05,
576
+ "loss": 0.5717,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 1.1584158415841583,
581
+ "grad_norm": 1.1348365545272827,
582
+ "learning_rate": 2.171805832989804e-05,
583
+ "loss": 0.515,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 1.1725601131541725,
588
+ "grad_norm": 3.9128365516662598,
589
+ "learning_rate": 2.1508256086763372e-05,
590
+ "loss": 0.5338,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 1.1867043847241867,
595
+ "grad_norm": 1.2760491371154785,
596
+ "learning_rate": 2.1296873416287216e-05,
597
+ "loss": 0.602,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 1.200848656294201,
602
+ "grad_norm": 1.1506465673446655,
603
+ "learning_rate": 2.108396164941713e-05,
604
+ "loss": 0.542,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 1.214992927864215,
609
+ "grad_norm": 1.3541408777236938,
610
+ "learning_rate": 2.0869572488417626e-05,
611
+ "loss": 0.5526,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 1.229137199434229,
616
+ "grad_norm": 1.2495580911636353,
617
+ "learning_rate": 2.0653757994315078e-05,
618
+ "loss": 0.5571,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 1.2432814710042432,
623
+ "grad_norm": 1.0765597820281982,
624
+ "learning_rate": 2.0436570574255526e-05,
625
+ "loss": 0.5613,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 1.2574257425742574,
630
+ "grad_norm": 1.1566628217697144,
631
+ "learning_rate": 2.0218062968778407e-05,
632
+ "loss": 0.5351,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 1.2715700141442716,
637
+ "grad_norm": 1.2175307273864746,
638
+ "learning_rate": 1.999828823900939e-05,
639
+ "loss": 0.5652,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 1.2857142857142856,
644
+ "grad_norm": 1.3737910985946655,
645
+ "learning_rate": 1.977729975377527e-05,
646
+ "loss": 0.5215,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 1.2998585572842998,
651
+ "grad_norm": 1.1195306777954102,
652
+ "learning_rate": 1.9555151176644223e-05,
653
+ "loss": 0.5084,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 1.314002828854314,
658
+ "grad_norm": 1.362184762954712,
659
+ "learning_rate": 1.933189645289445e-05,
660
+ "loss": 0.559,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 1.3281471004243282,
665
+ "grad_norm": 1.1672699451446533,
666
+ "learning_rate": 1.91075897964144e-05,
667
+ "loss": 0.566,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 1.3422913719943423,
672
+ "grad_norm": 1.208543062210083,
673
+ "learning_rate": 1.888228567653781e-05,
674
+ "loss": 0.5355,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 1.3564356435643563,
679
+ "grad_norm": 1.0605934858322144,
680
+ "learning_rate": 1.8656038804816662e-05,
681
+ "loss": 0.5459,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 1.3705799151343705,
686
+ "grad_norm": 1.148271918296814,
687
+ "learning_rate": 1.8428904121735345e-05,
688
+ "loss": 0.4845,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 1.3847241867043847,
693
+ "grad_norm": 1.2314975261688232,
694
+ "learning_rate": 1.8200936783369252e-05,
695
+ "loss": 0.4972,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 1.3988684582743989,
700
+ "grad_norm": 1.2481882572174072,
701
+ "learning_rate": 1.7972192147990966e-05,
702
+ "loss": 0.4997,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 1.413012729844413,
707
+ "grad_norm": 1.225356101989746,
708
+ "learning_rate": 1.7742725762627395e-05,
709
+ "loss": 0.5161,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 1.427157001414427,
714
+ "grad_norm": 1.1728451251983643,
715
+ "learning_rate": 1.7512593349571046e-05,
716
+ "loss": 0.4983,
717
+ "step": 505
718
+ },
719
+ {
720
+ "epoch": 1.4413012729844414,
721
+ "grad_norm": 1.2952357530593872,
722
+ "learning_rate": 1.7281850792848752e-05,
723
+ "loss": 0.5022,
724
+ "step": 510
725
+ },
726
+ {
727
+ "epoch": 1.4554455445544554,
728
+ "grad_norm": 1.2876229286193848,
729
+ "learning_rate": 1.7050554124651103e-05,
730
+ "loss": 0.4516,
731
+ "step": 515
732
+ },
733
+ {
734
+ "epoch": 1.4695898161244696,
735
+ "grad_norm": 1.1211971044540405,
736
+ "learning_rate": 1.6818759511725922e-05,
737
+ "loss": 0.4811,
738
+ "step": 520
739
+ },
740
+ {
741
+ "epoch": 1.4837340876944838,
742
+ "grad_norm": 1.3078140020370483,
743
+ "learning_rate": 1.658652324173907e-05,
744
+ "loss": 0.4739,
745
+ "step": 525
746
+ },
747
+ {
748
+ "epoch": 1.4978783592644977,
749
+ "grad_norm": 1.2832328081130981,
750
+ "learning_rate": 1.6353901709605838e-05,
751
+ "loss": 0.4684,
752
+ "step": 530
753
+ },
754
+ {
755
+ "epoch": 1.5120226308345122,
756
+ "grad_norm": 1.3249483108520508,
757
+ "learning_rate": 1.6120951403796367e-05,
758
+ "loss": 0.4753,
759
+ "step": 535
760
+ },
761
+ {
762
+ "epoch": 1.5261669024045261,
763
+ "grad_norm": 1.29241943359375,
764
+ "learning_rate": 1.5887728892618292e-05,
765
+ "loss": 0.4788,
766
+ "step": 540
767
+ },
768
+ {
769
+ "epoch": 1.5403111739745403,
770
+ "grad_norm": 1.4164788722991943,
771
+ "learning_rate": 1.5654290810480043e-05,
772
+ "loss": 0.4903,
773
+ "step": 545
774
+ },
775
+ {
776
+ "epoch": 1.5544554455445545,
777
+ "grad_norm": 1.2816201448440552,
778
+ "learning_rate": 1.5420693844138036e-05,
779
+ "loss": 0.4881,
780
+ "step": 550
781
+ },
782
+ {
783
+ "epoch": 1.5685997171145685,
784
+ "grad_norm": 1.2834993600845337,
785
+ "learning_rate": 1.5186994718931227e-05,
786
+ "loss": 0.4516,
787
+ "step": 555
788
+ },
789
+ {
790
+ "epoch": 1.5827439886845829,
791
+ "grad_norm": 1.1459758281707764,
792
+ "learning_rate": 1.4953250185006236e-05,
793
+ "loss": 0.4445,
794
+ "step": 560
795
+ },
796
+ {
797
+ "epoch": 1.5968882602545968,
798
+ "grad_norm": 1.440295696258545,
799
+ "learning_rate": 1.471951700353647e-05,
800
+ "loss": 0.4532,
801
+ "step": 565
802
+ },
803
+ {
804
+ "epoch": 1.611032531824611,
805
+ "grad_norm": 1.3762218952178955,
806
+ "learning_rate": 1.4485851932938575e-05,
807
+ "loss": 0.4815,
808
+ "step": 570
809
+ },
810
+ {
811
+ "epoch": 1.6251768033946252,
812
+ "grad_norm": 1.3329559564590454,
813
+ "learning_rate": 1.4252311715089542e-05,
814
+ "loss": 0.4569,
815
+ "step": 575
816
+ },
817
+ {
818
+ "epoch": 1.6393210749646392,
819
+ "grad_norm": 1.402673602104187,
820
+ "learning_rate": 1.4018953061547854e-05,
821
+ "loss": 0.4652,
822
+ "step": 580
823
+ },
824
+ {
825
+ "epoch": 1.6534653465346536,
826
+ "grad_norm": 1.4348127841949463,
827
+ "learning_rate": 1.3785832639781951e-05,
828
+ "loss": 0.4202,
829
+ "step": 585
830
+ },
831
+ {
832
+ "epoch": 1.6676096181046676,
833
+ "grad_norm": 1.2199482917785645,
834
+ "learning_rate": 1.355300705940945e-05,
835
+ "loss": 0.4324,
836
+ "step": 590
837
+ },
838
+ {
839
+ "epoch": 1.6817538896746818,
840
+ "grad_norm": 1.3008084297180176,
841
+ "learning_rate": 1.3320532858450382e-05,
842
+ "loss": 0.4605,
843
+ "step": 595
844
+ },
845
+ {
846
+ "epoch": 1.695898161244696,
847
+ "grad_norm": 1.2740421295166016,
848
+ "learning_rate": 1.3088466489597838e-05,
849
+ "loss": 0.4299,
850
+ "step": 600
851
+ },
852
+ {
853
+ "epoch": 1.71004243281471,
854
+ "grad_norm": 1.1773841381072998,
855
+ "learning_rate": 1.2856864306509303e-05,
856
+ "loss": 0.4496,
857
+ "step": 605
858
+ },
859
+ {
860
+ "epoch": 1.7241867043847243,
861
+ "grad_norm": 1.207871913909912,
862
+ "learning_rate": 1.2625782550122076e-05,
863
+ "loss": 0.4233,
864
+ "step": 610
865
+ },
866
+ {
867
+ "epoch": 1.7383309759547383,
868
+ "grad_norm": 1.3398220539093018,
869
+ "learning_rate": 1.2395277334996045e-05,
870
+ "loss": 0.408,
871
+ "step": 615
872
+ },
873
+ {
874
+ "epoch": 1.7524752475247525,
875
+ "grad_norm": 1.2410794496536255,
876
+ "learning_rate": 1.2165404635687139e-05,
877
+ "loss": 0.4705,
878
+ "step": 620
879
+ },
880
+ {
881
+ "epoch": 1.7666195190947667,
882
+ "grad_norm": 1.2651870250701904,
883
+ "learning_rate": 1.1936220273154797e-05,
884
+ "loss": 0.3864,
885
+ "step": 625
886
+ },
887
+ {
888
+ "epoch": 1.7807637906647806,
889
+ "grad_norm": 1.211180329322815,
890
+ "learning_rate": 1.1707779901206733e-05,
891
+ "loss": 0.4949,
892
+ "step": 630
893
+ },
894
+ {
895
+ "epoch": 1.794908062234795,
896
+ "grad_norm": 1.4778695106506348,
897
+ "learning_rate": 1.1480138992984276e-05,
898
+ "loss": 0.3812,
899
+ "step": 635
900
+ },
901
+ {
902
+ "epoch": 1.809052333804809,
903
+ "grad_norm": 1.4688681364059448,
904
+ "learning_rate": 1.1253352827491594e-05,
905
+ "loss": 0.3877,
906
+ "step": 640
907
+ },
908
+ {
909
+ "epoch": 1.8231966053748232,
910
+ "grad_norm": 1.1402958631515503,
911
+ "learning_rate": 1.102747647617209e-05,
912
+ "loss": 0.4121,
913
+ "step": 645
914
+ },
915
+ {
916
+ "epoch": 1.8373408769448374,
917
+ "grad_norm": 1.1975047588348389,
918
+ "learning_rate": 1.080256478953512e-05,
919
+ "loss": 0.3955,
920
+ "step": 650
921
+ },
922
+ {
923
+ "epoch": 1.8514851485148514,
924
+ "grad_norm": 1.1926662921905518,
925
+ "learning_rate": 1.0578672383836437e-05,
926
+ "loss": 0.4215,
927
+ "step": 655
928
+ },
929
+ {
930
+ "epoch": 1.8656294200848658,
931
+ "grad_norm": 1.2760437726974487,
932
+ "learning_rate": 1.0355853627815506e-05,
933
+ "loss": 0.4006,
934
+ "step": 660
935
+ },
936
+ {
937
+ "epoch": 1.8797736916548797,
938
+ "grad_norm": 1.4059710502624512,
939
+ "learning_rate": 1.0134162629492895e-05,
940
+ "loss": 0.3827,
941
+ "step": 665
942
+ },
943
+ {
944
+ "epoch": 1.893917963224894,
945
+ "grad_norm": 1.2398746013641357,
946
+ "learning_rate": 9.913653223031e-06,
947
+ "loss": 0.4394,
948
+ "step": 670
949
+ },
950
+ {
951
+ "epoch": 1.908062234794908,
952
+ "grad_norm": 1.2536640167236328,
953
+ "learning_rate": 9.69437895566128e-06,
954
+ "loss": 0.434,
955
+ "step": 675
956
+ },
957
+ {
958
+ "epoch": 1.922206506364922,
959
+ "grad_norm": 1.2083989381790161,
960
+ "learning_rate": 9.476393074681134e-06,
961
+ "loss": 0.373,
962
+ "step": 680
963
+ },
964
+ {
965
+ "epoch": 1.9363507779349365,
966
+ "grad_norm": 1.4742071628570557,
967
+ "learning_rate": 9.259748514523654e-06,
968
+ "loss": 0.4302,
969
+ "step": 685
970
+ },
971
+ {
972
+ "epoch": 1.9504950495049505,
973
+ "grad_norm": 1.3321889638900757,
974
+ "learning_rate": 9.044497883903326e-06,
975
+ "loss": 0.4123,
976
+ "step": 690
977
+ },
978
+ {
979
+ "epoch": 1.9646393210749646,
980
+ "grad_norm": 1.318691372871399,
981
+ "learning_rate": 8.83069345304083e-06,
982
+ "loss": 0.4065,
983
+ "step": 695
984
+ },
985
+ {
986
+ "epoch": 1.9787835926449788,
987
+ "grad_norm": 1.1592934131622314,
988
+ "learning_rate": 8.618387140970047e-06,
989
+ "loss": 0.4068,
990
+ "step": 700
991
+ },
992
+ {
993
+ "epoch": 1.9929278642149928,
994
+ "grad_norm": 1.3373466730117798,
995
+ "learning_rate": 8.407630502930325e-06,
996
+ "loss": 0.3732,
997
+ "step": 705
998
+ },
999
+ {
1000
+ "epoch": 2.005657708628006,
1001
+ "grad_norm": 1.3178142309188843,
1002
+ "learning_rate": 8.198474717847146e-06,
1003
+ "loss": 0.3324,
1004
+ "step": 710
1005
+ },
1006
+ {
1007
+ "epoch": 2.01980198019802,
1008
+ "grad_norm": 1.3491764068603516,
1009
+ "learning_rate": 7.99097057590407e-06,
1010
+ "loss": 0.3049,
1011
+ "step": 715
1012
+ },
1013
+ {
1014
+ "epoch": 2.033946251768034,
1015
+ "grad_norm": 1.3911669254302979,
1016
+ "learning_rate": 7.785168466209188e-06,
1017
+ "loss": 0.3717,
1018
+ "step": 720
1019
+ },
1020
+ {
1021
+ "epoch": 2.048090523338048,
1022
+ "grad_norm": 1.2549090385437012,
1023
+ "learning_rate": 7.581118364558889e-06,
1024
+ "loss": 0.3314,
1025
+ "step": 725
1026
+ },
1027
+ {
1028
+ "epoch": 2.062234794908062,
1029
+ "grad_norm": 1.4089620113372803,
1030
+ "learning_rate": 7.378869821302062e-06,
1031
+ "loss": 0.2837,
1032
+ "step": 730
1033
+ },
1034
+ {
1035
+ "epoch": 2.0763790664780766,
1036
+ "grad_norm": 1.3678315877914429,
1037
+ "learning_rate": 7.17847194930753e-06,
1038
+ "loss": 0.3274,
1039
+ "step": 735
1040
+ },
1041
+ {
1042
+ "epoch": 2.0905233380480905,
1043
+ "grad_norm": 1.3062889575958252,
1044
+ "learning_rate": 6.9799734120378105e-06,
1045
+ "loss": 0.304,
1046
+ "step": 740
1047
+ },
1048
+ {
1049
+ "epoch": 2.1046676096181045,
1050
+ "grad_norm": 1.329067349433899,
1051
+ "learning_rate": 6.783422411731932e-06,
1052
+ "loss": 0.3303,
1053
+ "step": 745
1054
+ },
1055
+ {
1056
+ "epoch": 2.118811881188119,
1057
+ "grad_norm": 1.3522324562072754,
1058
+ "learning_rate": 6.58886667770028e-06,
1059
+ "loss": 0.3137,
1060
+ "step": 750
1061
+ },
1062
+ {
1063
+ "epoch": 2.132956152758133,
1064
+ "grad_norm": 1.4457988739013672,
1065
+ "learning_rate": 6.3963534547343126e-06,
1066
+ "loss": 0.362,
1067
+ "step": 755
1068
+ },
1069
+ {
1070
+ "epoch": 2.1471004243281473,
1071
+ "grad_norm": 1.3124420642852783,
1072
+ "learning_rate": 6.205929491633869e-06,
1073
+ "loss": 0.3058,
1074
+ "step": 760
1075
+ },
1076
+ {
1077
+ "epoch": 2.1612446958981613,
1078
+ "grad_norm": 1.2871772050857544,
1079
+ "learning_rate": 6.017641029854996e-06,
1080
+ "loss": 0.3073,
1081
+ "step": 765
1082
+ },
1083
+ {
1084
+ "epoch": 2.1753889674681752,
1085
+ "grad_norm": 1.3655152320861816,
1086
+ "learning_rate": 5.831533792280926e-06,
1087
+ "loss": 0.3076,
1088
+ "step": 770
1089
+ },
1090
+ {
1091
+ "epoch": 2.1895332390381896,
1092
+ "grad_norm": 1.3126295804977417,
1093
+ "learning_rate": 5.647652972118998e-06,
1094
+ "loss": 0.3274,
1095
+ "step": 775
1096
+ },
1097
+ {
1098
+ "epoch": 2.2036775106082036,
1099
+ "grad_norm": 1.5045477151870728,
1100
+ "learning_rate": 5.46604322192618e-06,
1101
+ "loss": 0.3136,
1102
+ "step": 780
1103
+ },
1104
+ {
1105
+ "epoch": 2.217821782178218,
1106
+ "grad_norm": 1.4632354974746704,
1107
+ "learning_rate": 5.286748642765945e-06,
1108
+ "loss": 0.3171,
1109
+ "step": 785
1110
+ },
1111
+ {
1112
+ "epoch": 2.231966053748232,
1113
+ "grad_norm": 1.320110559463501,
1114
+ "learning_rate": 5.109812773498968e-06,
1115
+ "loss": 0.3346,
1116
+ "step": 790
1117
+ },
1118
+ {
1119
+ "epoch": 2.246110325318246,
1120
+ "grad_norm": 1.2929133176803589,
1121
+ "learning_rate": 4.935278580210451e-06,
1122
+ "loss": 0.3189,
1123
+ "step": 795
1124
+ },
1125
+ {
1126
+ "epoch": 2.2602545968882604,
1127
+ "grad_norm": 1.3376307487487793,
1128
+ "learning_rate": 4.763188445776447e-06,
1129
+ "loss": 0.292,
1130
+ "step": 800
1131
+ },
1132
+ {
1133
+ "epoch": 2.2743988684582743,
1134
+ "grad_norm": 1.1776471138000488,
1135
+ "learning_rate": 4.593584159571875e-06,
1136
+ "loss": 0.3154,
1137
+ "step": 805
1138
+ },
1139
+ {
1140
+ "epoch": 2.2885431400282887,
1141
+ "grad_norm": 1.370813250541687,
1142
+ "learning_rate": 4.426506907322624e-06,
1143
+ "loss": 0.2917,
1144
+ "step": 810
1145
+ },
1146
+ {
1147
+ "epoch": 2.3026874115983027,
1148
+ "grad_norm": 1.5107824802398682,
1149
+ "learning_rate": 4.261997261104223e-06,
1150
+ "loss": 0.306,
1151
+ "step": 815
1152
+ },
1153
+ {
1154
+ "epoch": 2.3168316831683167,
1155
+ "grad_norm": 1.4351601600646973,
1156
+ "learning_rate": 4.100095169489597e-06,
1157
+ "loss": 0.314,
1158
+ "step": 820
1159
+ },
1160
+ {
1161
+ "epoch": 2.330975954738331,
1162
+ "grad_norm": 1.2377662658691406,
1163
+ "learning_rate": 3.940839947848141e-06,
1164
+ "loss": 0.29,
1165
+ "step": 825
1166
+ },
1167
+ {
1168
+ "epoch": 2.345120226308345,
1169
+ "grad_norm": 1.245755672454834,
1170
+ "learning_rate": 3.7842702687986374e-06,
1171
+ "loss": 0.3079,
1172
+ "step": 830
1173
+ },
1174
+ {
1175
+ "epoch": 2.3592644978783595,
1176
+ "grad_norm": 1.3531545400619507,
1177
+ "learning_rate": 3.630424152818203e-06,
1178
+ "loss": 0.296,
1179
+ "step": 835
1180
+ },
1181
+ {
1182
+ "epoch": 2.3734087694483734,
1183
+ "grad_norm": 1.3729636669158936,
1184
+ "learning_rate": 3.479338959009625e-06,
1185
+ "loss": 0.2965,
1186
+ "step": 840
1187
+ },
1188
+ {
1189
+ "epoch": 2.3875530410183874,
1190
+ "grad_norm": 1.1836105585098267,
1191
+ "learning_rate": 3.331051376029279e-06,
1192
+ "loss": 0.305,
1193
+ "step": 845
1194
+ },
1195
+ {
1196
+ "epoch": 2.401697312588402,
1197
+ "grad_norm": 1.2209349870681763,
1198
+ "learning_rate": 3.1855974131778696e-06,
1199
+ "loss": 0.3104,
1200
+ "step": 850
1201
+ },
1202
+ {
1203
+ "epoch": 2.4158415841584158,
1204
+ "grad_norm": 1.2353330850601196,
1205
+ "learning_rate": 3.0430123916561677e-06,
1206
+ "loss": 0.3022,
1207
+ "step": 855
1208
+ },
1209
+ {
1210
+ "epoch": 2.42998585572843,
1211
+ "grad_norm": 1.3358441591262817,
1212
+ "learning_rate": 2.90333093598776e-06,
1213
+ "loss": 0.2998,
1214
+ "step": 860
1215
+ },
1216
+ {
1217
+ "epoch": 2.444130127298444,
1218
+ "grad_norm": 1.2911655902862549,
1219
+ "learning_rate": 2.7665869656110974e-06,
1220
+ "loss": 0.3072,
1221
+ "step": 865
1222
+ },
1223
+ {
1224
+ "epoch": 2.458274398868458,
1225
+ "grad_norm": 1.2605494260787964,
1226
+ "learning_rate": 2.6328136866426294e-06,
1227
+ "loss": 0.3059,
1228
+ "step": 870
1229
+ },
1230
+ {
1231
+ "epoch": 2.4724186704384725,
1232
+ "grad_norm": 1.2094409465789795,
1233
+ "learning_rate": 2.502043583813268e-06,
1234
+ "loss": 0.3329,
1235
+ "step": 875
1236
+ },
1237
+ {
1238
+ "epoch": 2.4865629420084865,
1239
+ "grad_norm": 1.2831439971923828,
1240
+ "learning_rate": 2.3743084125799515e-06,
1241
+ "loss": 0.2914,
1242
+ "step": 880
1243
+ },
1244
+ {
1245
+ "epoch": 2.500707213578501,
1246
+ "grad_norm": 1.215518832206726,
1247
+ "learning_rate": 2.2496391914143634e-06,
1248
+ "loss": 0.2867,
1249
+ "step": 885
1250
+ },
1251
+ {
1252
+ "epoch": 2.514851485148515,
1253
+ "grad_norm": 1.2915934324264526,
1254
+ "learning_rate": 2.1280661942705554e-06,
1255
+ "loss": 0.2983,
1256
+ "step": 890
1257
+ },
1258
+ {
1259
+ "epoch": 2.528995756718529,
1260
+ "grad_norm": 1.3412643671035767,
1261
+ "learning_rate": 2.0096189432334194e-06,
1262
+ "loss": 0.3044,
1263
+ "step": 895
1264
+ },
1265
+ {
1266
+ "epoch": 2.5431400282885432,
1267
+ "grad_norm": 1.569348931312561,
1268
+ "learning_rate": 1.8943262013497082e-06,
1269
+ "loss": 0.3047,
1270
+ "step": 900
1271
+ },
1272
+ {
1273
+ "epoch": 2.557284299858557,
1274
+ "grad_norm": 1.1776511669158936,
1275
+ "learning_rate": 1.782215965643364e-06,
1276
+ "loss": 0.302,
1277
+ "step": 905
1278
+ },
1279
+ {
1280
+ "epoch": 2.571428571428571,
1281
+ "grad_norm": 1.4418659210205078,
1282
+ "learning_rate": 1.6733154603169177e-06,
1283
+ "loss": 0.2784,
1284
+ "step": 910
1285
+ },
1286
+ {
1287
+ "epoch": 2.5855728429985856,
1288
+ "grad_norm": 1.2630493640899658,
1289
+ "learning_rate": 1.5676511301404861e-06,
1290
+ "loss": 0.3066,
1291
+ "step": 915
1292
+ },
1293
+ {
1294
+ "epoch": 2.5997171145685996,
1295
+ "grad_norm": 1.289921522140503,
1296
+ "learning_rate": 1.465248634030103e-06,
1297
+ "loss": 0.2822,
1298
+ "step": 920
1299
+ },
1300
+ {
1301
+ "epoch": 2.613861386138614,
1302
+ "grad_norm": 1.3747721910476685,
1303
+ "learning_rate": 1.3661328388168358e-06,
1304
+ "loss": 0.324,
1305
+ "step": 925
1306
+ },
1307
+ {
1308
+ "epoch": 2.628005657708628,
1309
+ "grad_norm": 1.282092571258545,
1310
+ "learning_rate": 1.2703278132082936e-06,
1311
+ "loss": 0.2958,
1312
+ "step": 930
1313
+ },
1314
+ {
1315
+ "epoch": 2.6421499292786423,
1316
+ "grad_norm": 1.5044610500335693,
1317
+ "learning_rate": 1.177856821943884e-06,
1318
+ "loss": 0.3087,
1319
+ "step": 935
1320
+ },
1321
+ {
1322
+ "epoch": 2.6562942008486563,
1323
+ "grad_norm": 1.4018510580062866,
1324
+ "learning_rate": 1.0887423201453778e-06,
1325
+ "loss": 0.3106,
1326
+ "step": 940
1327
+ },
1328
+ {
1329
+ "epoch": 2.6704384724186703,
1330
+ "grad_norm": 1.3021882772445679,
1331
+ "learning_rate": 1.0030059478640025e-06,
1332
+ "loss": 0.2947,
1333
+ "step": 945
1334
+ },
1335
+ {
1336
+ "epoch": 2.6845827439886847,
1337
+ "grad_norm": 1.2126119136810303,
1338
+ "learning_rate": 9.206685248255248e-07,
1339
+ "loss": 0.3121,
1340
+ "step": 950
1341
+ },
1342
+ {
1343
+ "epoch": 2.6987270155586986,
1344
+ "grad_norm": 1.6471376419067383,
1345
+ "learning_rate": 8.417500453744864e-07,
1346
+ "loss": 0.295,
1347
+ "step": 955
1348
+ },
1349
+ {
1350
+ "epoch": 2.7128712871287126,
1351
+ "grad_norm": 1.3624587059020996,
1352
+ "learning_rate": 7.662696736189129e-07,
1353
+ "loss": 0.2726,
1354
+ "step": 960
1355
+ },
1356
+ {
1357
+ "epoch": 2.727015558698727,
1358
+ "grad_norm": 1.3491227626800537,
1359
+ "learning_rate": 6.942457387765977e-07,
1360
+ "loss": 0.3072,
1361
+ "step": 965
1362
+ },
1363
+ {
1364
+ "epoch": 2.741159830268741,
1365
+ "grad_norm": 1.3611608743667603,
1366
+ "learning_rate": 6.256957307241396e-07,
1367
+ "loss": 0.2974,
1368
+ "step": 970
1369
+ },
1370
+ {
1371
+ "epoch": 2.7553041018387554,
1372
+ "grad_norm": 1.4269694089889526,
1373
+ "learning_rate": 5.606362957498195e-07,
1374
+ "loss": 0.2974,
1375
+ "step": 975
1376
+ },
1377
+ {
1378
+ "epoch": 2.7694483734087694,
1379
+ "grad_norm": 1.268566370010376,
1380
+ "learning_rate": 4.990832325112898e-07,
1381
+ "loss": 0.3229,
1382
+ "step": 980
1383
+ },
1384
+ {
1385
+ "epoch": 2.783592644978784,
1386
+ "grad_norm": 1.2628452777862549,
1387
+ "learning_rate": 4.4105148819913564e-07,
1388
+ "loss": 0.2755,
1389
+ "step": 985
1390
+ },
1391
+ {
1392
+ "epoch": 2.7977369165487977,
1393
+ "grad_norm": 1.3664195537567139,
1394
+ "learning_rate": 3.865551549071772e-07,
1395
+ "loss": 0.3018,
1396
+ "step": 990
1397
+ },
1398
+ {
1399
+ "epoch": 2.8118811881188117,
1400
+ "grad_norm": 1.238341212272644,
1401
+ "learning_rate": 3.3560746621043193e-07,
1402
+ "loss": 0.2972,
1403
+ "step": 995
1404
+ },
1405
+ {
1406
+ "epoch": 2.826025459688826,
1407
+ "grad_norm": 1.3370441198349,
1408
+ "learning_rate": 2.8822079395154357e-07,
1409
+ "loss": 0.279,
1410
+ "step": 1000
1411
+ },
1412
+ {
1413
+ "epoch": 2.84016973125884,
1414
+ "grad_norm": 1.3175510168075562,
1415
+ "learning_rate": 2.4440664523648017e-07,
1416
+ "loss": 0.2728,
1417
+ "step": 1005
1418
+ },
1419
+ {
1420
+ "epoch": 2.854314002828854,
1421
+ "grad_norm": 1.2302629947662354,
1422
+ "learning_rate": 2.041756596402161e-07,
1423
+ "loss": 0.3307,
1424
+ "step": 1010
1425
+ },
1426
+ {
1427
+ "epoch": 2.8684582743988685,
1428
+ "grad_norm": 1.3024208545684814,
1429
+ "learning_rate": 1.6753760662307217e-07,
1430
+ "loss": 0.2853,
1431
+ "step": 1015
1432
+ },
1433
+ {
1434
+ "epoch": 2.882602545968883,
1435
+ "grad_norm": 1.253223180770874,
1436
+ "learning_rate": 1.3450138315836303e-07,
1437
+ "loss": 0.3198,
1438
+ "step": 1020
1439
+ },
1440
+ {
1441
+ "epoch": 2.896746817538897,
1442
+ "grad_norm": 1.291290521621704,
1443
+ "learning_rate": 1.050750115719057e-07,
1444
+ "loss": 0.2894,
1445
+ "step": 1025
1446
+ },
1447
+ {
1448
+ "epoch": 2.910891089108911,
1449
+ "grad_norm": 1.2627896070480347,
1450
+ "learning_rate": 7.926563759392436e-08,
1451
+ "loss": 0.3246,
1452
+ "step": 1030
1453
+ },
1454
+ {
1455
+ "epoch": 2.9250353606789252,
1456
+ "grad_norm": 1.2756233215332031,
1457
+ "learning_rate": 5.7079528623816824e-08,
1458
+ "loss": 0.307,
1459
+ "step": 1035
1460
+ },
1461
+ {
1462
+ "epoch": 2.939179632248939,
1463
+ "grad_norm": 1.2428276538848877,
1464
+ "learning_rate": 3.85220722082269e-08,
1465
+ "loss": 0.2967,
1466
+ "step": 1040
1467
+ },
1468
+ {
1469
+ "epoch": 2.953323903818953,
1470
+ "grad_norm": 1.1538597345352173,
1471
+ "learning_rate": 2.3597774732750932e-08,
1472
+ "loss": 0.3116,
1473
+ "step": 1045
1474
+ },
1475
+ {
1476
+ "epoch": 2.9674681753889676,
1477
+ "grad_norm": 1.210798740386963,
1478
+ "learning_rate": 1.2310260327646483e-08,
1479
+ "loss": 0.2935,
1480
+ "step": 1050
1481
+ },
1482
+ {
1483
+ "epoch": 2.9816124469589815,
1484
+ "grad_norm": 1.3450415134429932,
1485
+ "learning_rate": 4.662269987756318e-09,
1486
+ "loss": 0.2806,
1487
+ "step": 1055
1488
+ },
1489
+ {
1490
+ "epoch": 2.9957567185289955,
1491
+ "grad_norm": 1.2402905225753784,
1492
+ "learning_rate": 6.556609069091613e-10,
1493
+ "loss": 0.2728,
1494
+ "step": 1060
1495
+ },
1496
+ {
1497
+ "epoch": 3.0,
1498
+ "step": 1062,
1499
+ "total_flos": 1.4714141706656154e+18,
1500
+ "train_loss": 0.5800944429501301,
1501
+ "train_runtime": 704.6914,
1502
+ "train_samples_per_second": 48.11,
1503
+ "train_steps_per_second": 1.507
1504
+ }
1505
+ ],
1506
+ "logging_steps": 5,
1507
+ "max_steps": 1062,
1508
+ "num_input_tokens_seen": 0,
1509
+ "num_train_epochs": 3,
1510
+ "save_steps": 2000,
1511
+ "stateful_callbacks": {
1512
+ "TrainerControl": {
1513
+ "args": {
1514
+ "should_epoch_stop": false,
1515
+ "should_evaluate": false,
1516
+ "should_log": false,
1517
+ "should_save": false,
1518
+ "should_training_stop": false
1519
+ },
1520
+ "attributes": {}
1521
+ }
1522
+ },
1523
+ "total_flos": 1.4714141706656154e+18,
1524
+ "train_batch_size": 2,
1525
+ "trial_name": null,
1526
+ "trial_params": null
1527
+ }
40_128_e3_3e-5/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63f34301e7f2a4deb71bd93c03a1d0745e59a29e1033e9adce024f48f3cfee36
3
+ size 8145
40_128_e3_3e-5/vocab.json ADDED
The diff for this file is too large to render. See raw diff