RayDu0010 commited on
Commit
1d00f28
·
verified ·
1 Parent(s): c0854f2

Upload folder using huggingface_hub

Browse files
34_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: 34_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
+ # 34_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
34_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
+ "gate_proj",
29
+ "v_proj",
30
+ "q_proj",
31
+ "down_proj",
32
+ "o_proj",
33
+ "up_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
34_128_e3_3e-5/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1487227c11bd5ad22e62b31c3289b7f6741a480fbdde79286587ed5d3afce407
3
+ size 791751704
34_128_e3_3e-5/all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.3276046288371057e+18,
4
+ "train_loss": 0.5875154959830599,
5
+ "train_runtime": 622.6891,
6
+ "train_samples": 10176,
7
+ "train_samples_per_second": 49.026,
8
+ "train_steps_per_second": 1.532
9
+ }
34_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
+ }
34_128_e3_3e-5/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
34_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
+ }
34_128_e3_3e-5/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
34_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
+ }
34_128_e3_3e-5/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.3276046288371057e+18,
4
+ "train_loss": 0.5875154959830599,
5
+ "train_runtime": 622.6891,
6
+ "train_samples": 10176,
7
+ "train_samples_per_second": 49.026,
8
+ "train_steps_per_second": 1.532
9
+ }
34_128_e3_3e-5/trainer_state.json ADDED
@@ -0,0 +1,1373 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 954,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.015723270440251572,
14
+ "grad_norm": 1.7447788715362549,
15
+ "learning_rate": 2.4999999999999998e-06,
16
+ "loss": 1.3493,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.031446540880503145,
21
+ "grad_norm": 0.8561593890190125,
22
+ "learning_rate": 5.625e-06,
23
+ "loss": 1.3409,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.04716981132075472,
28
+ "grad_norm": 0.6100626587867737,
29
+ "learning_rate": 8.750000000000001e-06,
30
+ "loss": 1.2695,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.06289308176100629,
35
+ "grad_norm": 0.5857648253440857,
36
+ "learning_rate": 1.1874999999999999e-05,
37
+ "loss": 1.3176,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.07861635220125786,
42
+ "grad_norm": 0.5983219742774963,
43
+ "learning_rate": 1.5e-05,
44
+ "loss": 1.245,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.09433962264150944,
49
+ "grad_norm": 0.599701464176178,
50
+ "learning_rate": 1.8125e-05,
51
+ "loss": 1.2775,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.11006289308176101,
56
+ "grad_norm": 0.5667367577552795,
57
+ "learning_rate": 2.125e-05,
58
+ "loss": 1.2042,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.12578616352201258,
63
+ "grad_norm": 0.4971155822277069,
64
+ "learning_rate": 2.4375e-05,
65
+ "loss": 1.228,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.14150943396226415,
70
+ "grad_norm": 0.48500925302505493,
71
+ "learning_rate": 2.75e-05,
72
+ "loss": 1.163,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.15723270440251572,
77
+ "grad_norm": 0.5088741779327393,
78
+ "learning_rate": 2.999990982125682e-05,
79
+ "loss": 1.2266,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.17295597484276728,
84
+ "grad_norm": 0.5195717215538025,
85
+ "learning_rate": 2.9996753679094844e-05,
86
+ "loss": 1.2064,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.18867924528301888,
91
+ "grad_norm": 0.6063700914382935,
92
+ "learning_rate": 2.9989089684009233e-05,
93
+ "loss": 1.189,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.20440251572327045,
98
+ "grad_norm": 0.5188394784927368,
99
+ "learning_rate": 2.99769201397094e-05,
100
+ "loss": 1.1333,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.22012578616352202,
105
+ "grad_norm": 0.5473522543907166,
106
+ "learning_rate": 2.996024870422141e-05,
107
+ "loss": 1.1476,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.2358490566037736,
112
+ "grad_norm": 0.44609779119491577,
113
+ "learning_rate": 2.9939080388788412e-05,
114
+ "loss": 1.1574,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.25157232704402516,
119
+ "grad_norm": 0.5138863325119019,
120
+ "learning_rate": 2.9913421556364333e-05,
121
+ "loss": 1.1009,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.2672955974842767,
126
+ "grad_norm": 0.540778636932373,
127
+ "learning_rate": 2.9883279919701227e-05,
128
+ "loss": 1.1434,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.2830188679245283,
133
+ "grad_norm": 0.49269890785217285,
134
+ "learning_rate": 2.9848664539030916e-05,
135
+ "loss": 1.1088,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.29874213836477986,
140
+ "grad_norm": 0.5773661136627197,
141
+ "learning_rate": 2.98095858193416e-05,
142
+ "loss": 1.0482,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.31446540880503143,
147
+ "grad_norm": 0.5998203158378601,
148
+ "learning_rate": 2.9766055507250207e-05,
149
+ "loss": 1.117,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.330188679245283,
154
+ "grad_norm": 0.6300597190856934,
155
+ "learning_rate": 2.971808668747153e-05,
156
+ "loss": 1.0527,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.34591194968553457,
161
+ "grad_norm": 0.624108612537384,
162
+ "learning_rate": 2.966569377888509e-05,
163
+ "loss": 0.9928,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.36163522012578614,
168
+ "grad_norm": 0.6175949573516846,
169
+ "learning_rate": 2.960889253020099e-05,
170
+ "loss": 1.0801,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.37735849056603776,
175
+ "grad_norm": 0.6203843355178833,
176
+ "learning_rate": 2.9547700015226022e-05,
177
+ "loss": 1.0173,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.39308176100628933,
182
+ "grad_norm": 0.6166127324104309,
183
+ "learning_rate": 2.94821346277315e-05,
184
+ "loss": 1.0389,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.4088050314465409,
189
+ "grad_norm": 0.5912259221076965,
190
+ "learning_rate": 2.9412216075924286e-05,
191
+ "loss": 0.9747,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.42452830188679247,
196
+ "grad_norm": 0.6402767300605774,
197
+ "learning_rate": 2.9337965376522717e-05,
198
+ "loss": 1.0173,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.44025157232704404,
203
+ "grad_norm": 0.6088610291481018,
204
+ "learning_rate": 2.925940484843925e-05,
205
+ "loss": 0.9824,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.4559748427672956,
210
+ "grad_norm": 0.7480473518371582,
211
+ "learning_rate": 2.9176558106071615e-05,
212
+ "loss": 0.9779,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.4716981132075472,
217
+ "grad_norm": 0.658454179763794,
218
+ "learning_rate": 2.908945005220464e-05,
219
+ "loss": 0.9751,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.48742138364779874,
224
+ "grad_norm": 0.7153352499008179,
225
+ "learning_rate": 2.8998106870524714e-05,
226
+ "loss": 0.9567,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.5031446540880503,
231
+ "grad_norm": 0.6384544372558594,
232
+ "learning_rate": 2.8902556017749297e-05,
233
+ "loss": 0.9462,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.5188679245283019,
238
+ "grad_norm": 0.7507193088531494,
239
+ "learning_rate": 2.8802826215373742e-05,
240
+ "loss": 0.9397,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.5345911949685535,
245
+ "grad_norm": 0.7118956446647644,
246
+ "learning_rate": 2.869894744103793e-05,
247
+ "loss": 0.9601,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.550314465408805,
252
+ "grad_norm": 0.8133665919303894,
253
+ "learning_rate": 2.859095091951534e-05,
254
+ "loss": 0.9094,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.5660377358490566,
259
+ "grad_norm": 0.7545745968818665,
260
+ "learning_rate": 2.847886911332725e-05,
261
+ "loss": 0.9014,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.5817610062893082,
266
+ "grad_norm": 0.7839163541793823,
267
+ "learning_rate": 2.8362735712984848e-05,
268
+ "loss": 0.9141,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.5974842767295597,
273
+ "grad_norm": 0.7458662986755371,
274
+ "learning_rate": 2.8242585626862273e-05,
275
+ "loss": 0.8988,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.6132075471698113,
280
+ "grad_norm": 0.7991396188735962,
281
+ "learning_rate": 2.811845497070354e-05,
282
+ "loss": 0.836,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.6289308176100629,
287
+ "grad_norm": 0.8973209857940674,
288
+ "learning_rate": 2.7990381056766583e-05,
289
+ "loss": 0.8891,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.6446540880503144,
294
+ "grad_norm": 1.0156831741333008,
295
+ "learning_rate": 2.7858402382607577e-05,
296
+ "loss": 0.8029,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.660377358490566,
301
+ "grad_norm": 0.8685197234153748,
302
+ "learning_rate": 2.7722558619509055e-05,
303
+ "loss": 0.8356,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.6761006289308176,
308
+ "grad_norm": 0.8903525471687317,
309
+ "learning_rate": 2.758289060055514e-05,
310
+ "loss": 0.8306,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.6918238993710691,
315
+ "grad_norm": 0.9233618974685669,
316
+ "learning_rate": 2.743944030835761e-05,
317
+ "loss": 0.7877,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.7075471698113207,
322
+ "grad_norm": 0.9873324632644653,
323
+ "learning_rate": 2.7292250862436397e-05,
324
+ "loss": 0.8691,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 0.7232704402515723,
329
+ "grad_norm": 1.0208094120025635,
330
+ "learning_rate": 2.7141366506258326e-05,
331
+ "loss": 0.7905,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 0.7389937106918238,
336
+ "grad_norm": 0.9661519527435303,
337
+ "learning_rate": 2.6986832593938088e-05,
338
+ "loss": 0.8416,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 0.7547169811320755,
343
+ "grad_norm": 0.9928529858589172,
344
+ "learning_rate": 2.6828695576605254e-05,
345
+ "loss": 0.8853,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 0.7704402515723271,
350
+ "grad_norm": 0.9525806307792664,
351
+ "learning_rate": 2.6667002988441638e-05,
352
+ "loss": 0.7426,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 0.7861635220125787,
357
+ "grad_norm": 0.8340609669685364,
358
+ "learning_rate": 2.6501803432393043e-05,
359
+ "loss": 0.8517,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 0.8018867924528302,
364
+ "grad_norm": 0.9258195161819458,
365
+ "learning_rate": 2.6333146565559775e-05,
366
+ "loss": 0.844,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 0.8176100628930818,
371
+ "grad_norm": 1.0497370958328247,
372
+ "learning_rate": 2.6161083084270284e-05,
373
+ "loss": 0.7655,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 0.8333333333333334,
378
+ "grad_norm": 0.9773187041282654,
379
+ "learning_rate": 2.5985664708842438e-05,
380
+ "loss": 0.7352,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 0.8490566037735849,
385
+ "grad_norm": 0.9626678824424744,
386
+ "learning_rate": 2.5806944168036967e-05,
387
+ "loss": 0.8074,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 0.8647798742138365,
392
+ "grad_norm": 1.1205562353134155,
393
+ "learning_rate": 2.5624975183207813e-05,
394
+ "loss": 0.7203,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 0.8805031446540881,
399
+ "grad_norm": 0.8669278621673584,
400
+ "learning_rate": 2.5439812452154105e-05,
401
+ "loss": 0.7817,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 0.8962264150943396,
406
+ "grad_norm": 0.9948189854621887,
407
+ "learning_rate": 2.5251511632678613e-05,
408
+ "loss": 0.7195,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 0.9119496855345912,
413
+ "grad_norm": 0.9700251221656799,
414
+ "learning_rate": 2.506012932585766e-05,
415
+ "loss": 0.7597,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 0.9276729559748428,
420
+ "grad_norm": 1.2674739360809326,
421
+ "learning_rate": 2.486572305902749e-05,
422
+ "loss": 0.711,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 0.9433962264150944,
427
+ "grad_norm": 1.1886234283447266,
428
+ "learning_rate": 2.4668351268492184e-05,
429
+ "loss": 0.6785,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 0.9591194968553459,
434
+ "grad_norm": 1.0957750082015991,
435
+ "learning_rate": 2.4468073281958393e-05,
436
+ "loss": 0.6817,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 0.9748427672955975,
441
+ "grad_norm": 0.9777420163154602,
442
+ "learning_rate": 2.4264949300702107e-05,
443
+ "loss": 0.6538,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 0.9905660377358491,
448
+ "grad_norm": 0.9823374152183533,
449
+ "learning_rate": 2.405904038147282e-05,
450
+ "loss": 0.6623,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 1.0062893081761006,
455
+ "grad_norm": 1.097525954246521,
456
+ "learning_rate": 2.385040841814061e-05,
457
+ "loss": 0.6485,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 1.0220125786163523,
462
+ "grad_norm": 1.1357083320617676,
463
+ "learning_rate": 2.363911612309149e-05,
464
+ "loss": 0.6541,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 1.0377358490566038,
469
+ "grad_norm": 1.1014593839645386,
470
+ "learning_rate": 2.3425227008376832e-05,
471
+ "loss": 0.5885,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 1.0534591194968554,
476
+ "grad_norm": 1.0642061233520508,
477
+ "learning_rate": 2.3208805366622342e-05,
478
+ "loss": 0.5911,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 1.069182389937107,
483
+ "grad_norm": 1.109059453010559,
484
+ "learning_rate": 2.2989916251702436e-05,
485
+ "loss": 0.6251,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 1.0849056603773586,
490
+ "grad_norm": 1.2384252548217773,
491
+ "learning_rate": 2.276862545918579e-05,
492
+ "loss": 0.5804,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 1.10062893081761,
497
+ "grad_norm": 1.16849684715271,
498
+ "learning_rate": 2.2544999506557953e-05,
499
+ "loss": 0.6055,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 1.1163522012578617,
504
+ "grad_norm": 1.1576168537139893,
505
+ "learning_rate": 2.2319105613226925e-05,
506
+ "loss": 0.5576,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 1.1320754716981132,
511
+ "grad_norm": 1.182163119316101,
512
+ "learning_rate": 2.20910116803178e-05,
513
+ "loss": 0.569,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 1.1477987421383649,
518
+ "grad_norm": 1.1394355297088623,
519
+ "learning_rate": 2.1860786270262444e-05,
520
+ "loss": 0.5445,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 1.1635220125786163,
525
+ "grad_norm": 1.251783847808838,
526
+ "learning_rate": 2.1628498586190414e-05,
527
+ "loss": 0.6085,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 1.179245283018868,
532
+ "grad_norm": 1.0371774435043335,
533
+ "learning_rate": 2.139421845112729e-05,
534
+ "loss": 0.5608,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 1.1949685534591195,
539
+ "grad_norm": 1.0839347839355469,
540
+ "learning_rate": 2.1158016287006672e-05,
541
+ "loss": 0.5547,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 1.2106918238993711,
546
+ "grad_norm": 1.2301808595657349,
547
+ "learning_rate": 2.0919963093502146e-05,
548
+ "loss": 0.5562,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 1.2264150943396226,
553
+ "grad_norm": 1.058773398399353,
554
+ "learning_rate": 2.0680130426685608e-05,
555
+ "loss": 0.5378,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 1.2421383647798743,
560
+ "grad_norm": 1.324985384941101,
561
+ "learning_rate": 2.0438590377518292e-05,
562
+ "loss": 0.5034,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 1.2578616352201257,
567
+ "grad_norm": 1.3010754585266113,
568
+ "learning_rate": 2.0195415550181087e-05,
569
+ "loss": 0.5132,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 1.2735849056603774,
574
+ "grad_norm": 1.3227932453155518,
575
+ "learning_rate": 1.9950679040250536e-05,
576
+ "loss": 0.5407,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 1.2893081761006289,
581
+ "grad_norm": 1.068479061126709,
582
+ "learning_rate": 1.9704454412727125e-05,
583
+ "loss": 0.5414,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 1.3050314465408805,
588
+ "grad_norm": 1.2793065309524536,
589
+ "learning_rate": 1.9456815679922512e-05,
590
+ "loss": 0.5205,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 1.320754716981132,
595
+ "grad_norm": 1.0442254543304443,
596
+ "learning_rate": 1.9207837279212245e-05,
597
+ "loss": 0.4947,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 1.3364779874213837,
602
+ "grad_norm": 1.1317323446273804,
603
+ "learning_rate": 1.8957594050660752e-05,
604
+ "loss": 0.5805,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 1.3522012578616351,
609
+ "grad_norm": 1.2340036630630493,
610
+ "learning_rate": 1.870616121452528e-05,
611
+ "loss": 0.5455,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 1.3679245283018868,
616
+ "grad_norm": 1.1451706886291504,
617
+ "learning_rate": 1.8453614348645504e-05,
618
+ "loss": 0.5305,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 1.3836477987421385,
623
+ "grad_norm": 1.1318262815475464,
624
+ "learning_rate": 1.8200029365725755e-05,
625
+ "loss": 0.5094,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 1.39937106918239,
630
+ "grad_norm": 1.190490961074829,
631
+ "learning_rate": 1.7945482490516465e-05,
632
+ "loss": 0.5018,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 1.4150943396226414,
637
+ "grad_norm": 1.2844213247299194,
638
+ "learning_rate": 1.769005023690192e-05,
639
+ "loss": 0.4979,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 1.430817610062893,
644
+ "grad_norm": 1.0878610610961914,
645
+ "learning_rate": 1.743380938490104e-05,
646
+ "loss": 0.4798,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 1.4465408805031448,
651
+ "grad_norm": 1.2521717548370361,
652
+ "learning_rate": 1.7176836957588192e-05,
653
+ "loss": 0.5035,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 1.4622641509433962,
658
+ "grad_norm": 1.2694942951202393,
659
+ "learning_rate": 1.691921019794093e-05,
660
+ "loss": 0.5186,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 1.4779874213836477,
665
+ "grad_norm": 1.3717033863067627,
666
+ "learning_rate": 1.6661006545621618e-05,
667
+ "loss": 0.5246,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 1.4937106918238994,
672
+ "grad_norm": 1.0457336902618408,
673
+ "learning_rate": 1.64023036137e-05,
674
+ "loss": 0.4775,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 1.509433962264151,
679
+ "grad_norm": 1.2197635173797607,
680
+ "learning_rate": 1.6143179165323553e-05,
681
+ "loss": 0.5123,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 1.5251572327044025,
686
+ "grad_norm": 1.2237622737884521,
687
+ "learning_rate": 1.5883711090342767e-05,
688
+ "loss": 0.4423,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 1.540880503144654,
693
+ "grad_norm": 1.1911721229553223,
694
+ "learning_rate": 1.5623977381898413e-05,
695
+ "loss": 0.4464,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 1.5566037735849056,
700
+ "grad_norm": 1.0949735641479492,
701
+ "learning_rate": 1.53640561129776e-05,
702
+ "loss": 0.4796,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 1.5723270440251573,
707
+ "grad_norm": 1.3594024181365967,
708
+ "learning_rate": 1.5104025412946007e-05,
709
+ "loss": 0.4519,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 1.5880503144654088,
714
+ "grad_norm": 1.1604455709457397,
715
+ "learning_rate": 1.484396344406304e-05,
716
+ "loss": 0.4773,
717
+ "step": 505
718
+ },
719
+ {
720
+ "epoch": 1.6037735849056602,
721
+ "grad_norm": 1.16139554977417,
722
+ "learning_rate": 1.4583948377987166e-05,
723
+ "loss": 0.4818,
724
+ "step": 510
725
+ },
726
+ {
727
+ "epoch": 1.619496855345912,
728
+ "grad_norm": 1.2463083267211914,
729
+ "learning_rate": 1.4324058372278415e-05,
730
+ "loss": 0.482,
731
+ "step": 515
732
+ },
733
+ {
734
+ "epoch": 1.6352201257861636,
735
+ "grad_norm": 1.1182204484939575,
736
+ "learning_rate": 1.4064371546905077e-05,
737
+ "loss": 0.4702,
738
+ "step": 520
739
+ },
740
+ {
741
+ "epoch": 1.650943396226415,
742
+ "grad_norm": 1.0829519033432007,
743
+ "learning_rate": 1.3804965960761774e-05,
744
+ "loss": 0.4604,
745
+ "step": 525
746
+ },
747
+ {
748
+ "epoch": 1.6666666666666665,
749
+ "grad_norm": 1.501689076423645,
750
+ "learning_rate": 1.354591958820582e-05,
751
+ "loss": 0.4417,
752
+ "step": 530
753
+ },
754
+ {
755
+ "epoch": 1.6823899371069182,
756
+ "grad_norm": 1.2083019018173218,
757
+ "learning_rate": 1.3287310295619027e-05,
758
+ "loss": 0.4275,
759
+ "step": 535
760
+ },
761
+ {
762
+ "epoch": 1.6981132075471699,
763
+ "grad_norm": 1.2580461502075195,
764
+ "learning_rate": 1.3029215818001947e-05,
765
+ "loss": 0.4609,
766
+ "step": 540
767
+ },
768
+ {
769
+ "epoch": 1.7138364779874213,
770
+ "grad_norm": 1.192415475845337,
771
+ "learning_rate": 1.2771713735607647e-05,
772
+ "loss": 0.4173,
773
+ "step": 545
774
+ },
775
+ {
776
+ "epoch": 1.7295597484276728,
777
+ "grad_norm": 1.2384852170944214,
778
+ "learning_rate": 1.2514881450621942e-05,
779
+ "loss": 0.4362,
780
+ "step": 550
781
+ },
782
+ {
783
+ "epoch": 1.7452830188679245,
784
+ "grad_norm": 1.144734501838684,
785
+ "learning_rate": 1.2258796163897212e-05,
786
+ "loss": 0.4068,
787
+ "step": 555
788
+ },
789
+ {
790
+ "epoch": 1.7610062893081762,
791
+ "grad_norm": 1.0873130559921265,
792
+ "learning_rate": 1.2003534851746654e-05,
793
+ "loss": 0.4054,
794
+ "step": 560
795
+ },
796
+ {
797
+ "epoch": 1.7767295597484276,
798
+ "grad_norm": 1.2902498245239258,
799
+ "learning_rate": 1.1749174242806153e-05,
800
+ "loss": 0.4138,
801
+ "step": 565
802
+ },
803
+ {
804
+ "epoch": 1.7924528301886793,
805
+ "grad_norm": 1.1792351007461548,
806
+ "learning_rate": 1.1495790794970476e-05,
807
+ "loss": 0.4667,
808
+ "step": 570
809
+ },
810
+ {
811
+ "epoch": 1.808176100628931,
812
+ "grad_norm": 1.159265398979187,
813
+ "learning_rate": 1.1243460672410919e-05,
814
+ "loss": 0.4478,
815
+ "step": 575
816
+ },
817
+ {
818
+ "epoch": 1.8238993710691824,
819
+ "grad_norm": 1.0803265571594238,
820
+ "learning_rate": 1.0992259722681225e-05,
821
+ "loss": 0.417,
822
+ "step": 580
823
+ },
824
+ {
825
+ "epoch": 1.8396226415094339,
826
+ "grad_norm": 1.1645803451538086,
827
+ "learning_rate": 1.0742263453918684e-05,
828
+ "loss": 0.4323,
829
+ "step": 585
830
+ },
831
+ {
832
+ "epoch": 1.8553459119496856,
833
+ "grad_norm": 1.342177391052246,
834
+ "learning_rate": 1.0493547012147241e-05,
835
+ "loss": 0.4311,
836
+ "step": 590
837
+ },
838
+ {
839
+ "epoch": 1.8710691823899372,
840
+ "grad_norm": 1.1767390966415405,
841
+ "learning_rate": 1.024618515868946e-05,
842
+ "loss": 0.4223,
843
+ "step": 595
844
+ },
845
+ {
846
+ "epoch": 1.8867924528301887,
847
+ "grad_norm": 1.1813294887542725,
848
+ "learning_rate": 1.000025224769412e-05,
849
+ "loss": 0.3996,
850
+ "step": 600
851
+ },
852
+ {
853
+ "epoch": 1.9025157232704402,
854
+ "grad_norm": 1.250900149345398,
855
+ "learning_rate": 9.755822203786213e-06,
856
+ "loss": 0.4019,
857
+ "step": 605
858
+ },
859
+ {
860
+ "epoch": 1.9182389937106918,
861
+ "grad_norm": 1.2568508386611938,
862
+ "learning_rate": 9.512968499846047e-06,
863
+ "loss": 0.421,
864
+ "step": 610
865
+ },
866
+ {
867
+ "epoch": 1.9339622641509435,
868
+ "grad_norm": 1.3641937971115112,
869
+ "learning_rate": 9.27176413492414e-06,
870
+ "loss": 0.42,
871
+ "step": 615
872
+ },
873
+ {
874
+ "epoch": 1.949685534591195,
875
+ "grad_norm": 1.4102277755737305,
876
+ "learning_rate": 9.032281612298516e-06,
877
+ "loss": 0.418,
878
+ "step": 620
879
+ },
880
+ {
881
+ "epoch": 1.9654088050314464,
882
+ "grad_norm": 1.3464930057525635,
883
+ "learning_rate": 8.794592917681079e-06,
884
+ "loss": 0.4212,
885
+ "step": 625
886
+ },
887
+ {
888
+ "epoch": 1.9811320754716981,
889
+ "grad_norm": 1.280279517173767,
890
+ "learning_rate": 8.558769497579514e-06,
891
+ "loss": 0.4267,
892
+ "step": 630
893
+ },
894
+ {
895
+ "epoch": 1.9968553459119498,
896
+ "grad_norm": 1.1603142023086548,
897
+ "learning_rate": 8.324882237821284e-06,
898
+ "loss": 0.4016,
899
+ "step": 635
900
+ },
901
+ {
902
+ "epoch": 2.0125786163522013,
903
+ "grad_norm": 1.2689299583435059,
904
+ "learning_rate": 8.093001442246147e-06,
905
+ "loss": 0.3318,
906
+ "step": 640
907
+ },
908
+ {
909
+ "epoch": 2.0283018867924527,
910
+ "grad_norm": 1.3831123113632202,
911
+ "learning_rate": 7.863196811573651e-06,
912
+ "loss": 0.3319,
913
+ "step": 645
914
+ },
915
+ {
916
+ "epoch": 2.0440251572327046,
917
+ "grad_norm": 1.2091630697250366,
918
+ "learning_rate": 7.635537422451892e-06,
919
+ "loss": 0.3565,
920
+ "step": 650
921
+ },
922
+ {
923
+ "epoch": 2.059748427672956,
924
+ "grad_norm": 1.3288401365280151,
925
+ "learning_rate": 7.410091706693814e-06,
926
+ "loss": 0.3468,
927
+ "step": 655
928
+ },
929
+ {
930
+ "epoch": 2.0754716981132075,
931
+ "grad_norm": 1.2414021492004395,
932
+ "learning_rate": 7.1869274307074524e-06,
933
+ "loss": 0.3328,
934
+ "step": 660
935
+ },
936
+ {
937
+ "epoch": 2.091194968553459,
938
+ "grad_norm": 1.1965888738632202,
939
+ "learning_rate": 6.96611167512609e-06,
940
+ "loss": 0.3567,
941
+ "step": 665
942
+ },
943
+ {
944
+ "epoch": 2.106918238993711,
945
+ "grad_norm": 1.2389326095581055,
946
+ "learning_rate": 6.747710814644589e-06,
947
+ "loss": 0.3096,
948
+ "step": 670
949
+ },
950
+ {
951
+ "epoch": 2.1226415094339623,
952
+ "grad_norm": 1.2089444398880005,
953
+ "learning_rate": 6.5317904980679176e-06,
954
+ "loss": 0.326,
955
+ "step": 675
956
+ },
957
+ {
958
+ "epoch": 2.138364779874214,
959
+ "grad_norm": 1.1517267227172852,
960
+ "learning_rate": 6.31841562857787e-06,
961
+ "loss": 0.3166,
962
+ "step": 680
963
+ },
964
+ {
965
+ "epoch": 2.1540880503144653,
966
+ "grad_norm": 1.284354329109192,
967
+ "learning_rate": 6.107650344223909e-06,
968
+ "loss": 0.3335,
969
+ "step": 685
970
+ },
971
+ {
972
+ "epoch": 2.169811320754717,
973
+ "grad_norm": 1.4233475923538208,
974
+ "learning_rate": 5.899557998644004e-06,
975
+ "loss": 0.3249,
976
+ "step": 690
977
+ },
978
+ {
979
+ "epoch": 2.1855345911949686,
980
+ "grad_norm": 1.155491828918457,
981
+ "learning_rate": 5.694201142021245e-06,
982
+ "loss": 0.3229,
983
+ "step": 695
984
+ },
985
+ {
986
+ "epoch": 2.20125786163522,
987
+ "grad_norm": 1.4067448377609253,
988
+ "learning_rate": 5.491641502281978e-06,
989
+ "loss": 0.3064,
990
+ "step": 700
991
+ },
992
+ {
993
+ "epoch": 2.2169811320754715,
994
+ "grad_norm": 1.2239614725112915,
995
+ "learning_rate": 5.291939966541091e-06,
996
+ "loss": 0.2757,
997
+ "step": 705
998
+ },
999
+ {
1000
+ "epoch": 2.2327044025157234,
1001
+ "grad_norm": 1.1853607892990112,
1002
+ "learning_rate": 5.095156562800048e-06,
1003
+ "loss": 0.3092,
1004
+ "step": 710
1005
+ },
1006
+ {
1007
+ "epoch": 2.248427672955975,
1008
+ "grad_norm": 1.4731969833374023,
1009
+ "learning_rate": 4.901350441903135e-06,
1010
+ "loss": 0.2832,
1011
+ "step": 715
1012
+ },
1013
+ {
1014
+ "epoch": 2.2641509433962264,
1015
+ "grad_norm": 1.2331801652908325,
1016
+ "learning_rate": 4.71057985975744e-06,
1017
+ "loss": 0.3704,
1018
+ "step": 720
1019
+ },
1020
+ {
1021
+ "epoch": 2.279874213836478,
1022
+ "grad_norm": 1.2259901762008667,
1023
+ "learning_rate": 4.522902159821737e-06,
1024
+ "loss": 0.3205,
1025
+ "step": 725
1026
+ },
1027
+ {
1028
+ "epoch": 2.2955974842767297,
1029
+ "grad_norm": 1.2311729192733765,
1030
+ "learning_rate": 4.338373755869739e-06,
1031
+ "loss": 0.2924,
1032
+ "step": 730
1033
+ },
1034
+ {
1035
+ "epoch": 2.311320754716981,
1036
+ "grad_norm": 1.125938892364502,
1037
+ "learning_rate": 4.157050115032724e-06,
1038
+ "loss": 0.299,
1039
+ "step": 735
1040
+ },
1041
+ {
1042
+ "epoch": 2.3270440251572326,
1043
+ "grad_norm": 1.2641942501068115,
1044
+ "learning_rate": 3.978985741126789e-06,
1045
+ "loss": 0.3381,
1046
+ "step": 740
1047
+ },
1048
+ {
1049
+ "epoch": 2.342767295597484,
1050
+ "grad_norm": 1.1418442726135254,
1051
+ "learning_rate": 3.804234158269593e-06,
1052
+ "loss": 0.3328,
1053
+ "step": 745
1054
+ },
1055
+ {
1056
+ "epoch": 2.358490566037736,
1057
+ "grad_norm": 1.2997685670852661,
1058
+ "learning_rate": 3.632847894791651e-06,
1059
+ "loss": 0.2858,
1060
+ "step": 750
1061
+ },
1062
+ {
1063
+ "epoch": 2.3742138364779874,
1064
+ "grad_norm": 1.3442941904067993,
1065
+ "learning_rate": 3.4648784674468687e-06,
1066
+ "loss": 0.3103,
1067
+ "step": 755
1068
+ },
1069
+ {
1070
+ "epoch": 2.389937106918239,
1071
+ "grad_norm": 1.1932765245437622,
1072
+ "learning_rate": 3.3003763659272435e-06,
1073
+ "loss": 0.3195,
1074
+ "step": 760
1075
+ },
1076
+ {
1077
+ "epoch": 2.4056603773584904,
1078
+ "grad_norm": 1.1639267206192017,
1079
+ "learning_rate": 3.139391037686214e-06,
1080
+ "loss": 0.2776,
1081
+ "step": 765
1082
+ },
1083
+ {
1084
+ "epoch": 2.4213836477987423,
1085
+ "grad_norm": 1.2642326354980469,
1086
+ "learning_rate": 2.981970873075326e-06,
1087
+ "loss": 0.3148,
1088
+ "step": 770
1089
+ },
1090
+ {
1091
+ "epoch": 2.4371069182389937,
1092
+ "grad_norm": 1.1740034818649292,
1093
+ "learning_rate": 2.8281631907986445e-06,
1094
+ "loss": 0.2856,
1095
+ "step": 775
1096
+ },
1097
+ {
1098
+ "epoch": 2.452830188679245,
1099
+ "grad_norm": 1.3195215463638306,
1100
+ "learning_rate": 2.678014223689293e-06,
1101
+ "loss": 0.3195,
1102
+ "step": 780
1103
+ },
1104
+ {
1105
+ "epoch": 2.468553459119497,
1106
+ "grad_norm": 1.420884609222412,
1107
+ "learning_rate": 2.5315691048123886e-06,
1108
+ "loss": 0.328,
1109
+ "step": 785
1110
+ },
1111
+ {
1112
+ "epoch": 2.4842767295597485,
1113
+ "grad_norm": 1.2376039028167725,
1114
+ "learning_rate": 2.3888718538985617e-06,
1115
+ "loss": 0.3171,
1116
+ "step": 790
1117
+ },
1118
+ {
1119
+ "epoch": 2.5,
1120
+ "grad_norm": 1.2642303705215454,
1121
+ "learning_rate": 2.2499653641121275e-06,
1122
+ "loss": 0.2694,
1123
+ "step": 795
1124
+ },
1125
+ {
1126
+ "epoch": 2.5157232704402515,
1127
+ "grad_norm": 1.2741889953613281,
1128
+ "learning_rate": 2.114891389157885e-06,
1129
+ "loss": 0.3256,
1130
+ "step": 800
1131
+ },
1132
+ {
1133
+ "epoch": 2.531446540880503,
1134
+ "grad_norm": 1.377629280090332,
1135
+ "learning_rate": 1.983690530730439e-06,
1136
+ "loss": 0.3216,
1137
+ "step": 805
1138
+ },
1139
+ {
1140
+ "epoch": 2.547169811320755,
1141
+ "grad_norm": 1.2991048097610474,
1142
+ "learning_rate": 1.8564022263097895e-06,
1143
+ "loss": 0.2806,
1144
+ "step": 810
1145
+ },
1146
+ {
1147
+ "epoch": 2.5628930817610063,
1148
+ "grad_norm": 1.3558663129806519,
1149
+ "learning_rate": 1.7330647373068642e-06,
1150
+ "loss": 0.29,
1151
+ "step": 815
1152
+ },
1153
+ {
1154
+ "epoch": 2.5786163522012577,
1155
+ "grad_norm": 1.4122823476791382,
1156
+ "learning_rate": 1.6137151375625985e-06,
1157
+ "loss": 0.3092,
1158
+ "step": 820
1159
+ },
1160
+ {
1161
+ "epoch": 2.5943396226415096,
1162
+ "grad_norm": 1.2300971746444702,
1163
+ "learning_rate": 1.4983893022039518e-06,
1164
+ "loss": 0.3006,
1165
+ "step": 825
1166
+ },
1167
+ {
1168
+ "epoch": 2.610062893081761,
1169
+ "grad_norm": 1.313216209411621,
1170
+ "learning_rate": 1.387121896860246e-06,
1171
+ "loss": 0.3206,
1172
+ "step": 830
1173
+ },
1174
+ {
1175
+ "epoch": 2.6257861635220126,
1176
+ "grad_norm": 1.4024757146835327,
1177
+ "learning_rate": 1.2799463672430766e-06,
1178
+ "loss": 0.2887,
1179
+ "step": 835
1180
+ },
1181
+ {
1182
+ "epoch": 2.641509433962264,
1183
+ "grad_norm": 1.3736701011657715,
1184
+ "learning_rate": 1.1768949290929238e-06,
1185
+ "loss": 0.2834,
1186
+ "step": 840
1187
+ },
1188
+ {
1189
+ "epoch": 2.6572327044025155,
1190
+ "grad_norm": 1.0894758701324463,
1191
+ "learning_rate": 1.0779985584954556e-06,
1192
+ "loss": 0.298,
1193
+ "step": 845
1194
+ },
1195
+ {
1196
+ "epoch": 2.6729559748427674,
1197
+ "grad_norm": 1.193097710609436,
1198
+ "learning_rate": 9.83286982570486e-07,
1199
+ "loss": 0.3191,
1200
+ "step": 850
1201
+ },
1202
+ {
1203
+ "epoch": 2.688679245283019,
1204
+ "grad_norm": 1.2591214179992676,
1205
+ "learning_rate": 8.927886705363181e-07,
1206
+ "loss": 0.2779,
1207
+ "step": 855
1208
+ },
1209
+ {
1210
+ "epoch": 2.7044025157232703,
1211
+ "grad_norm": 1.1771700382232666,
1212
+ "learning_rate": 8.065308251522452e-07,
1213
+ "loss": 0.2617,
1214
+ "step": 860
1215
+ },
1216
+ {
1217
+ "epoch": 2.720125786163522,
1218
+ "grad_norm": 1.1566683053970337,
1219
+ "learning_rate": 7.245393745417039e-07,
1220
+ "loss": 0.2726,
1221
+ "step": 865
1222
+ },
1223
+ {
1224
+ "epoch": 2.7358490566037736,
1225
+ "grad_norm": 1.2059237957000732,
1226
+ "learning_rate": 6.468389643985717e-07,
1227
+ "loss": 0.31,
1228
+ "step": 870
1229
+ },
1230
+ {
1231
+ "epoch": 2.751572327044025,
1232
+ "grad_norm": 1.3186904191970825,
1233
+ "learning_rate": 5.73452950578956e-07,
1234
+ "loss": 0.2745,
1235
+ "step": 875
1236
+ },
1237
+ {
1238
+ "epoch": 2.767295597484277,
1239
+ "grad_norm": 1.2649286985397339,
1240
+ "learning_rate": 5.044033920806935e-07,
1241
+ "loss": 0.2983,
1242
+ "step": 880
1243
+ },
1244
+ {
1245
+ "epoch": 2.7830188679245285,
1246
+ "grad_norm": 1.293013095855713,
1247
+ "learning_rate": 4.3971104441266565e-07,
1248
+ "loss": 0.3052,
1249
+ "step": 885
1250
+ },
1251
+ {
1252
+ "epoch": 2.79874213836478,
1253
+ "grad_norm": 1.215193510055542,
1254
+ "learning_rate": 3.793953533559247e-07,
1255
+ "loss": 0.3229,
1256
+ "step": 890
1257
+ },
1258
+ {
1259
+ "epoch": 2.8144654088050314,
1260
+ "grad_norm": 1.3370041847229004,
1261
+ "learning_rate": 3.234744491185204e-07,
1262
+ "loss": 0.3034,
1263
+ "step": 895
1264
+ },
1265
+ {
1266
+ "epoch": 2.830188679245283,
1267
+ "grad_norm": 1.1949117183685303,
1268
+ "learning_rate": 2.7196514088576487e-07,
1269
+ "loss": 0.3166,
1270
+ "step": 900
1271
+ },
1272
+ {
1273
+ "epoch": 2.8459119496855347,
1274
+ "grad_norm": 1.142907738685608,
1275
+ "learning_rate": 2.2488291176758047e-07,
1276
+ "loss": 0.3125,
1277
+ "step": 905
1278
+ },
1279
+ {
1280
+ "epoch": 2.861635220125786,
1281
+ "grad_norm": 1.2134130001068115,
1282
+ "learning_rate": 1.8224191414446145e-07,
1283
+ "loss": 0.2773,
1284
+ "step": 910
1285
+ },
1286
+ {
1287
+ "epoch": 2.8773584905660377,
1288
+ "grad_norm": 1.1938163042068481,
1289
+ "learning_rate": 1.440549654134149e-07,
1290
+ "loss": 0.2876,
1291
+ "step": 915
1292
+ },
1293
+ {
1294
+ "epoch": 2.8930817610062896,
1295
+ "grad_norm": 1.2450705766677856,
1296
+ "learning_rate": 1.1033354413521435e-07,
1297
+ "loss": 0.2588,
1298
+ "step": 920
1299
+ },
1300
+ {
1301
+ "epoch": 2.908805031446541,
1302
+ "grad_norm": 1.3103667497634888,
1303
+ "learning_rate": 8.108778658406646e-08,
1304
+ "loss": 0.2777,
1305
+ "step": 925
1306
+ },
1307
+ {
1308
+ "epoch": 2.9245283018867925,
1309
+ "grad_norm": 1.1999613046646118,
1310
+ "learning_rate": 5.632648370076487e-08,
1311
+ "loss": 0.291,
1312
+ "step": 930
1313
+ },
1314
+ {
1315
+ "epoch": 2.940251572327044,
1316
+ "grad_norm": 1.1664392948150635,
1317
+ "learning_rate": 3.605707845023232e-08,
1318
+ "loss": 0.2792,
1319
+ "step": 935
1320
+ },
1321
+ {
1322
+ "epoch": 2.9559748427672954,
1323
+ "grad_norm": 1.1370396614074707,
1324
+ "learning_rate": 2.028566358425188e-08,
1325
+ "loss": 0.2857,
1326
+ "step": 940
1327
+ },
1328
+ {
1329
+ "epoch": 2.9716981132075473,
1330
+ "grad_norm": 1.2326672077178955,
1331
+ "learning_rate": 9.016979810055337e-09,
1332
+ "loss": 0.3044,
1333
+ "step": 945
1334
+ },
1335
+ {
1336
+ "epoch": 2.9874213836477987,
1337
+ "grad_norm": 1.256286859512329,
1338
+ "learning_rate": 2.254414365318036e-09,
1339
+ "loss": 0.2743,
1340
+ "step": 950
1341
+ },
1342
+ {
1343
+ "epoch": 3.0,
1344
+ "step": 954,
1345
+ "total_flos": 1.3276046288371057e+18,
1346
+ "train_loss": 0.5875154959830599,
1347
+ "train_runtime": 622.6891,
1348
+ "train_samples_per_second": 49.026,
1349
+ "train_steps_per_second": 1.532
1350
+ }
1351
+ ],
1352
+ "logging_steps": 5,
1353
+ "max_steps": 954,
1354
+ "num_input_tokens_seen": 0,
1355
+ "num_train_epochs": 3,
1356
+ "save_steps": 2000,
1357
+ "stateful_callbacks": {
1358
+ "TrainerControl": {
1359
+ "args": {
1360
+ "should_epoch_stop": false,
1361
+ "should_evaluate": false,
1362
+ "should_log": false,
1363
+ "should_save": false,
1364
+ "should_training_stop": false
1365
+ },
1366
+ "attributes": {}
1367
+ }
1368
+ },
1369
+ "total_flos": 1.3276046288371057e+18,
1370
+ "train_batch_size": 2,
1371
+ "trial_name": null,
1372
+ "trial_params": null
1373
+ }
34_128_e3_3e-5/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2679d07df82053bba70c68a59e6d67c647f40ef7411d8eadb4eb51fd52d2812b
3
+ size 8145
34_128_e3_3e-5/vocab.json ADDED
The diff for this file is too large to render. See raw diff