RayDu0010 commited on
Commit
c435fe8
·
verified ·
1 Parent(s): b9f2046

Upload folder using huggingface_hub

Browse files
25_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: 25_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
+ # 25_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
25_128_e3_3e-5/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "ibm-granite/granite-3.3-8b-base",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 256,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 128,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "up_proj",
28
+ "gate_proj",
29
+ "q_proj",
30
+ "k_proj",
31
+ "v_proj",
32
+ "o_proj",
33
+ "down_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
25_128_e3_3e-5/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:646c9ad9b4d4ade658ce1b8b0436581e9d47e65130b1f23a7356577c712418f9
3
+ size 791751704
25_128_e3_3e-5/all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.2069706775889183e+18,
4
+ "train_loss": 0.5579275732626588,
5
+ "train_runtime": 555.4859,
6
+ "train_samples": 8994,
7
+ "train_samples_per_second": 48.574,
8
+ "train_steps_per_second": 1.523
9
+ }
25_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
+ }
25_128_e3_3e-5/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
25_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
+ }
25_128_e3_3e-5/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
25_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
+ }
25_128_e3_3e-5/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.2069706775889183e+18,
4
+ "train_loss": 0.5579275732626588,
5
+ "train_runtime": 555.4859,
6
+ "train_samples": 8994,
7
+ "train_samples_per_second": 48.574,
8
+ "train_steps_per_second": 1.523
9
+ }
25_128_e3_3e-5/trainer_state.json ADDED
@@ -0,0 +1,1226 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 846,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.017761989342806393,
14
+ "grad_norm": 1.3231275081634521,
15
+ "learning_rate": 2.7906976744186046e-06,
16
+ "loss": 1.315,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.035523978685612786,
21
+ "grad_norm": 0.701774537563324,
22
+ "learning_rate": 6.279069767441861e-06,
23
+ "loss": 1.3216,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.05328596802841918,
28
+ "grad_norm": 0.6771687269210815,
29
+ "learning_rate": 9.767441860465117e-06,
30
+ "loss": 1.2848,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.07104795737122557,
35
+ "grad_norm": 0.5326308012008667,
36
+ "learning_rate": 1.3255813953488373e-05,
37
+ "loss": 1.3087,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.08880994671403197,
42
+ "grad_norm": 0.5053356885910034,
43
+ "learning_rate": 1.674418604651163e-05,
44
+ "loss": 1.2309,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.10657193605683836,
49
+ "grad_norm": 0.5353951454162598,
50
+ "learning_rate": 2.0232558139534883e-05,
51
+ "loss": 1.2124,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.12433392539964476,
56
+ "grad_norm": 0.4567808210849762,
57
+ "learning_rate": 2.3720930232558138e-05,
58
+ "loss": 1.2386,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.14209591474245115,
63
+ "grad_norm": 0.5020460486412048,
64
+ "learning_rate": 2.7209302325581395e-05,
65
+ "loss": 1.1801,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.15985790408525755,
70
+ "grad_norm": 0.44761934876441956,
71
+ "learning_rate": 2.999988520331045e-05,
72
+ "loss": 1.1471,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.17761989342806395,
77
+ "grad_norm": 0.4367366135120392,
78
+ "learning_rate": 2.9995867503669133e-05,
79
+ "loss": 1.1527,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.19538188277087035,
84
+ "grad_norm": 0.5834628343582153,
85
+ "learning_rate": 2.998611172653345e-05,
86
+ "loss": 1.1714,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.21314387211367672,
91
+ "grad_norm": 0.48230427503585815,
92
+ "learning_rate": 2.997062160489219e-05,
93
+ "loss": 1.1064,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.23090586145648312,
98
+ "grad_norm": 0.46752408146858215,
99
+ "learning_rate": 2.9949403065946194e-05,
100
+ "loss": 1.1452,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.24866785079928952,
105
+ "grad_norm": 0.6091781258583069,
106
+ "learning_rate": 2.992246422884032e-05,
107
+ "loss": 1.1293,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.2664298401420959,
112
+ "grad_norm": 0.48189669847488403,
113
+ "learning_rate": 2.9889815401556762e-05,
114
+ "loss": 1.0857,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.2841918294849023,
119
+ "grad_norm": 0.5191056132316589,
120
+ "learning_rate": 2.985146907697069e-05,
121
+ "loss": 1.0908,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.3019538188277087,
126
+ "grad_norm": 0.5504825115203857,
127
+ "learning_rate": 2.9807439928069994e-05,
128
+ "loss": 1.0999,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.3197158081705151,
133
+ "grad_norm": 0.5600771903991699,
134
+ "learning_rate": 2.975774480234071e-05,
135
+ "loss": 1.0105,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.33747779751332146,
140
+ "grad_norm": 0.5626690983772278,
141
+ "learning_rate": 2.970240271532045e-05,
142
+ "loss": 1.0566,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.3552397868561279,
147
+ "grad_norm": 0.5404466390609741,
148
+ "learning_rate": 2.964143484332221e-05,
149
+ "loss": 1.0193,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.37300177619893427,
154
+ "grad_norm": 0.5624865889549255,
155
+ "learning_rate": 2.957486451533141e-05,
156
+ "loss": 1.0111,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.3907637655417407,
161
+ "grad_norm": 0.5766105651855469,
162
+ "learning_rate": 2.9502717204079163e-05,
163
+ "loss": 0.9937,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.40852575488454707,
168
+ "grad_norm": 0.5540288090705872,
169
+ "learning_rate": 2.942502051629532e-05,
170
+ "loss": 0.9447,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.42628774422735344,
175
+ "grad_norm": 0.6186960935592651,
176
+ "learning_rate": 2.9341804182144896e-05,
177
+ "loss": 0.9791,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.44404973357015987,
182
+ "grad_norm": 0.5866276025772095,
183
+ "learning_rate": 2.9253100043852037e-05,
184
+ "loss": 0.9629,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.46181172291296624,
189
+ "grad_norm": 0.6540477275848389,
190
+ "learning_rate": 2.915894204351575e-05,
191
+ "loss": 0.9535,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.47957371225577267,
196
+ "grad_norm": 0.6920923590660095,
197
+ "learning_rate": 2.9059366210122185e-05,
198
+ "loss": 0.9492,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.49733570159857904,
203
+ "grad_norm": 0.7717536687850952,
204
+ "learning_rate": 2.895441064575837e-05,
205
+ "loss": 0.8635,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.5150976909413855,
210
+ "grad_norm": 0.8334298133850098,
211
+ "learning_rate": 2.884411551103266e-05,
212
+ "loss": 0.8679,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.5328596802841918,
217
+ "grad_norm": 0.6875845789909363,
218
+ "learning_rate": 2.872852300970753e-05,
219
+ "loss": 0.9134,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.5506216696269982,
224
+ "grad_norm": 0.7502499222755432,
225
+ "learning_rate": 2.8607677372550573e-05,
226
+ "loss": 0.8622,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.5683836589698046,
231
+ "grad_norm": 0.8312597870826721,
232
+ "learning_rate": 2.8481624840409862e-05,
233
+ "loss": 0.8886,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.5861456483126111,
238
+ "grad_norm": 0.8703055381774902,
239
+ "learning_rate": 2.835041364652015e-05,
240
+ "loss": 0.921,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.6039076376554174,
245
+ "grad_norm": 1.0531996488571167,
246
+ "learning_rate": 2.821409399804675e-05,
247
+ "loss": 0.8508,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.6216696269982238,
252
+ "grad_norm": 0.7947110533714294,
253
+ "learning_rate": 2.807271805687404e-05,
254
+ "loss": 0.849,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.6394316163410302,
259
+ "grad_norm": 0.8096781969070435,
260
+ "learning_rate": 2.792633991964606e-05,
261
+ "loss": 0.8264,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.6571936056838366,
266
+ "grad_norm": 0.8436487913131714,
267
+ "learning_rate": 2.7775015597066726e-05,
268
+ "loss": 0.811,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.6749555950266429,
273
+ "grad_norm": 0.9463394284248352,
274
+ "learning_rate": 2.7618802992467718e-05,
275
+ "loss": 0.7928,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.6927175843694494,
280
+ "grad_norm": 0.8976422548294067,
281
+ "learning_rate": 2.7457761879652084e-05,
282
+ "loss": 0.7814,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.7104795737122558,
287
+ "grad_norm": 0.9050946831703186,
288
+ "learning_rate": 2.7291953880022184e-05,
289
+ "loss": 0.8017,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.7282415630550622,
294
+ "grad_norm": 0.8991579413414001,
295
+ "learning_rate": 2.7121442439000614e-05,
296
+ "loss": 0.7883,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.7460035523978685,
301
+ "grad_norm": 0.9045212864875793,
302
+ "learning_rate": 2.6946292801753227e-05,
303
+ "loss": 0.709,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.7637655417406749,
308
+ "grad_norm": 0.9687134027481079,
309
+ "learning_rate": 2.6766571988223436e-05,
310
+ "loss": 0.7271,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.7815275310834814,
315
+ "grad_norm": 0.8315659165382385,
316
+ "learning_rate": 2.6582348767487466e-05,
317
+ "loss": 0.7252,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.7992895204262878,
322
+ "grad_norm": 0.9432047009468079,
323
+ "learning_rate": 2.639369363144027e-05,
324
+ "loss": 0.732,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 0.8170515097690941,
329
+ "grad_norm": 0.9895256161689758,
330
+ "learning_rate": 2.6200678767822256e-05,
331
+ "loss": 0.7338,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 0.8348134991119005,
336
+ "grad_norm": 1.087295651435852,
337
+ "learning_rate": 2.600337803259704e-05,
338
+ "loss": 0.6926,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 0.8525754884547069,
343
+ "grad_norm": 0.8864995241165161,
344
+ "learning_rate": 2.5801866921690965e-05,
345
+ "loss": 0.6809,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 0.8703374777975134,
350
+ "grad_norm": 0.9925051927566528,
351
+ "learning_rate": 2.559622254210502e-05,
352
+ "loss": 0.7017,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 0.8880994671403197,
357
+ "grad_norm": 1.123909592628479,
358
+ "learning_rate": 2.5386523582410305e-05,
359
+ "loss": 0.669,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 0.9058614564831261,
364
+ "grad_norm": 1.0412914752960205,
365
+ "learning_rate": 2.5172850282638344e-05,
366
+ "loss": 0.6782,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 0.9236234458259325,
371
+ "grad_norm": 0.9874035716056824,
372
+ "learning_rate": 2.495528440357772e-05,
373
+ "loss": 0.664,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 0.9413854351687388,
378
+ "grad_norm": 1.0234025716781616,
379
+ "learning_rate": 2.4733909195488806e-05,
380
+ "loss": 0.6844,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 0.9591474245115453,
385
+ "grad_norm": 0.9540771245956421,
386
+ "learning_rate": 2.4508809366248555e-05,
387
+ "loss": 0.6767,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 0.9769094138543517,
392
+ "grad_norm": 0.9452133774757385,
393
+ "learning_rate": 2.428007104893755e-05,
394
+ "loss": 0.6391,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 0.9946714031971581,
399
+ "grad_norm": 0.9797477126121521,
400
+ "learning_rate": 2.4047781768881715e-05,
401
+ "loss": 0.6235,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 1.0106571936056838,
406
+ "grad_norm": 1.0686089992523193,
407
+ "learning_rate": 2.3812030410161258e-05,
408
+ "loss": 0.5832,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 1.0284191829484903,
413
+ "grad_norm": 0.9488253593444824,
414
+ "learning_rate": 2.3572907181599742e-05,
415
+ "loss": 0.5822,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 1.0461811722912966,
420
+ "grad_norm": 1.0656824111938477,
421
+ "learning_rate": 2.3330503582246204e-05,
422
+ "loss": 0.5604,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 1.063943161634103,
427
+ "grad_norm": 1.0964164733886719,
428
+ "learning_rate": 2.308491236636363e-05,
429
+ "loss": 0.5829,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 1.0817051509769093,
434
+ "grad_norm": 1.0837876796722412,
435
+ "learning_rate": 2.2836227507937067e-05,
436
+ "loss": 0.5631,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 1.0994671403197158,
441
+ "grad_norm": 1.1674449443817139,
442
+ "learning_rate": 2.2584544164715078e-05,
443
+ "loss": 0.5655,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 1.1172291296625223,
448
+ "grad_norm": 1.0909093618392944,
449
+ "learning_rate": 2.2329958641798192e-05,
450
+ "loss": 0.5455,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 1.1349911190053286,
455
+ "grad_norm": 1.0680902004241943,
456
+ "learning_rate": 2.207256835478834e-05,
457
+ "loss": 0.5415,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 1.152753108348135,
462
+ "grad_norm": 1.130262851715088,
463
+ "learning_rate": 2.1812471792513386e-05,
464
+ "loss": 0.5076,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 1.1705150976909413,
469
+ "grad_norm": 1.3649592399597168,
470
+ "learning_rate": 2.154976847934096e-05,
471
+ "loss": 0.5141,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 1.1882770870337478,
476
+ "grad_norm": 1.0753296613693237,
477
+ "learning_rate": 2.128455893709606e-05,
478
+ "loss": 0.4977,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 1.206039076376554,
483
+ "grad_norm": 1.146614670753479,
484
+ "learning_rate": 2.1016944646597012e-05,
485
+ "loss": 0.5256,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 1.2238010657193605,
490
+ "grad_norm": 1.0820695161819458,
491
+ "learning_rate": 2.074702800882442e-05,
492
+ "loss": 0.52,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 1.241563055062167,
497
+ "grad_norm": 1.0902920961380005,
498
+ "learning_rate": 2.047491230573808e-05,
499
+ "loss": 0.5706,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 1.2593250444049733,
504
+ "grad_norm": 1.0888701677322388,
505
+ "learning_rate": 2.0200701660756745e-05,
506
+ "loss": 0.5051,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 1.2770870337477798,
511
+ "grad_norm": 1.1430457830429077,
512
+ "learning_rate": 1.992450099891596e-05,
513
+ "loss": 0.5092,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 1.294849023090586,
518
+ "grad_norm": 1.441771149635315,
519
+ "learning_rate": 1.9646416006719095e-05,
520
+ "loss": 0.5154,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 1.3126110124333925,
525
+ "grad_norm": 1.199514389038086,
526
+ "learning_rate": 1.9366553091697083e-05,
527
+ "loss": 0.5809,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 1.330373001776199,
532
+ "grad_norm": 1.2213622331619263,
533
+ "learning_rate": 1.9085019341692223e-05,
534
+ "loss": 0.5116,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 1.3481349911190053,
539
+ "grad_norm": 1.081356406211853,
540
+ "learning_rate": 1.8801922483881632e-05,
541
+ "loss": 0.4906,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 1.3658969804618117,
546
+ "grad_norm": 1.151087760925293,
547
+ "learning_rate": 1.8517370843556146e-05,
548
+ "loss": 0.4389,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 1.383658969804618,
553
+ "grad_norm": 1.05121910572052,
554
+ "learning_rate": 1.823147330267027e-05,
555
+ "loss": 0.4825,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 1.4014209591474245,
560
+ "grad_norm": 1.185630440711975,
561
+ "learning_rate": 1.7944339258179173e-05,
562
+ "loss": 0.4623,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 1.419182948490231,
567
+ "grad_norm": 1.810645580291748,
568
+ "learning_rate": 1.765607858017861e-05,
569
+ "loss": 0.4714,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 1.4369449378330372,
574
+ "grad_norm": 1.272497296333313,
575
+ "learning_rate": 1.7366801569863798e-05,
576
+ "loss": 0.4916,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 1.4547069271758437,
581
+ "grad_norm": 1.321583867073059,
582
+ "learning_rate": 1.707661891732333e-05,
583
+ "loss": 0.432,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 1.47246891651865,
588
+ "grad_norm": 1.1273342370986938,
589
+ "learning_rate": 1.6785641659184292e-05,
590
+ "loss": 0.4509,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 1.4902309058614565,
595
+ "grad_norm": 1.0571781396865845,
596
+ "learning_rate": 1.6493981136124767e-05,
597
+ "loss": 0.4251,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 1.507992895204263,
602
+ "grad_norm": 1.2970434427261353,
603
+ "learning_rate": 1.6201748950269993e-05,
604
+ "loss": 0.4495,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 1.5257548845470694,
609
+ "grad_norm": 1.1398073434829712,
610
+ "learning_rate": 1.590905692248853e-05,
611
+ "loss": 0.4211,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 1.5435168738898757,
616
+ "grad_norm": 1.2868608236312866,
617
+ "learning_rate": 1.561601704960462e-05,
618
+ "loss": 0.444,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 1.561278863232682,
623
+ "grad_norm": 1.1401524543762207,
624
+ "learning_rate": 1.5322741461543334e-05,
625
+ "loss": 0.4599,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 1.5790408525754884,
630
+ "grad_norm": 1.1858832836151123,
631
+ "learning_rate": 1.5029342378424729e-05,
632
+ "loss": 0.4511,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 1.596802841918295,
637
+ "grad_norm": 3.851574420928955,
638
+ "learning_rate": 1.4735932067623478e-05,
639
+ "loss": 0.428,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 1.6145648312611014,
644
+ "grad_norm": 1.306156039237976,
645
+ "learning_rate": 1.4442622800810476e-05,
646
+ "loss": 0.4302,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 1.6323268206039077,
651
+ "grad_norm": 1.6123629808425903,
652
+ "learning_rate": 1.4149526810992737e-05,
653
+ "loss": 0.4882,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 1.650088809946714,
658
+ "grad_norm": 1.4006987810134888,
659
+ "learning_rate": 1.3856756249568131e-05,
660
+ "loss": 0.449,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 1.6678507992895204,
665
+ "grad_norm": 1.1376513242721558,
666
+ "learning_rate": 1.3564423143411341e-05,
667
+ "loss": 0.3954,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 1.6856127886323269,
672
+ "grad_norm": 1.3232742547988892,
673
+ "learning_rate": 1.3272639352007442e-05,
674
+ "loss": 0.4156,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 1.7033747779751334,
679
+ "grad_norm": 1.4243301153182983,
680
+ "learning_rate": 1.2981516524649575e-05,
681
+ "loss": 0.3988,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 1.7211367673179396,
686
+ "grad_norm": 1.2779264450073242,
687
+ "learning_rate": 1.269116605771699e-05,
688
+ "loss": 0.4164,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 1.738898756660746,
693
+ "grad_norm": 1.2109707593917847,
694
+ "learning_rate": 1.240169905204993e-05,
695
+ "loss": 0.457,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 1.7566607460035524,
700
+ "grad_norm": 1.2897119522094727,
701
+ "learning_rate": 1.2113226270437551e-05,
702
+ "loss": 0.4535,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 1.7744227353463589,
707
+ "grad_norm": 1.2221955060958862,
708
+ "learning_rate": 1.182585809523523e-05,
709
+ "loss": 0.3886,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 1.7921847246891653,
714
+ "grad_norm": 1.1318753957748413,
715
+ "learning_rate": 1.1539704486127423e-05,
716
+ "loss": 0.3635,
717
+ "step": 505
718
+ },
719
+ {
720
+ "epoch": 1.8099467140319716,
721
+ "grad_norm": 1.1975198984146118,
722
+ "learning_rate": 1.1254874938052231e-05,
723
+ "loss": 0.4042,
724
+ "step": 510
725
+ },
726
+ {
727
+ "epoch": 1.8277087033747779,
728
+ "grad_norm": 1.1606299877166748,
729
+ "learning_rate": 1.097147843930388e-05,
730
+ "loss": 0.3812,
731
+ "step": 515
732
+ },
733
+ {
734
+ "epoch": 1.8454706927175843,
735
+ "grad_norm": 1.1118510961532593,
736
+ "learning_rate": 1.068962342982898e-05,
737
+ "loss": 0.3869,
738
+ "step": 520
739
+ },
740
+ {
741
+ "epoch": 1.8632326820603908,
742
+ "grad_norm": 1.0953401327133179,
743
+ "learning_rate": 1.040941775973265e-05,
744
+ "loss": 0.3903,
745
+ "step": 525
746
+ },
747
+ {
748
+ "epoch": 1.8809946714031973,
749
+ "grad_norm": 1.3009462356567383,
750
+ "learning_rate": 1.0130968648010307e-05,
751
+ "loss": 0.3621,
752
+ "step": 530
753
+ },
754
+ {
755
+ "epoch": 1.8987566607460036,
756
+ "grad_norm": 1.1924844980239868,
757
+ "learning_rate": 9.854382641521017e-06,
758
+ "loss": 0.4229,
759
+ "step": 535
760
+ },
761
+ {
762
+ "epoch": 1.9165186500888098,
763
+ "grad_norm": 1.3684569597244263,
764
+ "learning_rate": 9.579765574217943e-06,
765
+ "loss": 0.378,
766
+ "step": 540
767
+ },
768
+ {
769
+ "epoch": 1.9342806394316163,
770
+ "grad_norm": 1.234144926071167,
771
+ "learning_rate": 9.307222526651649e-06,
772
+ "loss": 0.3585,
773
+ "step": 545
774
+ },
775
+ {
776
+ "epoch": 1.9520426287744228,
777
+ "grad_norm": 1.1517488956451416,
778
+ "learning_rate": 9.036857785761664e-06,
779
+ "loss": 0.3664,
780
+ "step": 550
781
+ },
782
+ {
783
+ "epoch": 1.9698046181172293,
784
+ "grad_norm": 1.2272323369979858,
785
+ "learning_rate": 8.768774804971705e-06,
786
+ "loss": 0.3907,
787
+ "step": 555
788
+ },
789
+ {
790
+ "epoch": 1.9875666074600356,
791
+ "grad_norm": 1.1386855840682983,
792
+ "learning_rate": 8.503076164603873e-06,
793
+ "loss": 0.3457,
794
+ "step": 560
795
+ },
796
+ {
797
+ "epoch": 2.003552397868561,
798
+ "grad_norm": 1.290396809577942,
799
+ "learning_rate": 8.239863532626914e-06,
800
+ "loss": 0.3526,
801
+ "step": 565
802
+ },
803
+ {
804
+ "epoch": 2.0213143872113677,
805
+ "grad_norm": 1.2628382444381714,
806
+ "learning_rate": 7.979237625753575e-06,
807
+ "loss": 0.2756,
808
+ "step": 570
809
+ },
810
+ {
811
+ "epoch": 2.039076376554174,
812
+ "grad_norm": 1.2747254371643066,
813
+ "learning_rate": 7.721298170901968e-06,
814
+ "loss": 0.3108,
815
+ "step": 575
816
+ },
817
+ {
818
+ "epoch": 2.0568383658969807,
819
+ "grad_norm": 1.2029812335968018,
820
+ "learning_rate": 7.46614386703569e-06,
821
+ "loss": 0.3084,
822
+ "step": 580
823
+ },
824
+ {
825
+ "epoch": 2.0746003552397867,
826
+ "grad_norm": 1.3086997270584106,
827
+ "learning_rate": 7.213872347397252e-06,
828
+ "loss": 0.3092,
829
+ "step": 585
830
+ },
831
+ {
832
+ "epoch": 2.092362344582593,
833
+ "grad_norm": 1.2387416362762451,
834
+ "learning_rate": 6.964580142149306e-06,
835
+ "loss": 0.3155,
836
+ "step": 590
837
+ },
838
+ {
839
+ "epoch": 2.1101243339253997,
840
+ "grad_norm": 1.3628038167953491,
841
+ "learning_rate": 6.718362641437983e-06,
842
+ "loss": 0.2964,
843
+ "step": 595
844
+ },
845
+ {
846
+ "epoch": 2.127886323268206,
847
+ "grad_norm": 1.1450494527816772,
848
+ "learning_rate": 6.475314058892414e-06,
849
+ "loss": 0.3173,
850
+ "step": 600
851
+ },
852
+ {
853
+ "epoch": 2.1456483126110126,
854
+ "grad_norm": 1.2115252017974854,
855
+ "learning_rate": 6.235527395574473e-06,
856
+ "loss": 0.2965,
857
+ "step": 605
858
+ },
859
+ {
860
+ "epoch": 2.1634103019538187,
861
+ "grad_norm": 1.2262935638427734,
862
+ "learning_rate": 5.999094404392479e-06,
863
+ "loss": 0.2663,
864
+ "step": 610
865
+ },
866
+ {
867
+ "epoch": 2.181172291296625,
868
+ "grad_norm": 1.1969001293182373,
869
+ "learning_rate": 5.766105554992511e-06,
870
+ "loss": 0.3013,
871
+ "step": 615
872
+ },
873
+ {
874
+ "epoch": 2.1989342806394316,
875
+ "grad_norm": 1.1103568077087402,
876
+ "learning_rate": 5.536649999140728e-06,
877
+ "loss": 0.2982,
878
+ "step": 620
879
+ },
880
+ {
881
+ "epoch": 2.216696269982238,
882
+ "grad_norm": 1.3679698705673218,
883
+ "learning_rate": 5.310815536610015e-06,
884
+ "loss": 0.2713,
885
+ "step": 625
886
+ },
887
+ {
888
+ "epoch": 2.2344582593250446,
889
+ "grad_norm": 1.2028425931930542,
890
+ "learning_rate": 5.088688581583921e-06,
891
+ "loss": 0.2822,
892
+ "step": 630
893
+ },
894
+ {
895
+ "epoch": 2.2522202486678506,
896
+ "grad_norm": 1.2171648740768433,
897
+ "learning_rate": 4.8703541295907885e-06,
898
+ "loss": 0.2772,
899
+ "step": 635
900
+ },
901
+ {
902
+ "epoch": 2.269982238010657,
903
+ "grad_norm": 1.2585508823394775,
904
+ "learning_rate": 4.655895724980761e-06,
905
+ "loss": 0.2765,
906
+ "step": 640
907
+ },
908
+ {
909
+ "epoch": 2.2877442273534636,
910
+ "grad_norm": 1.300795316696167,
911
+ "learning_rate": 4.445395428958e-06,
912
+ "loss": 0.2563,
913
+ "step": 645
914
+ },
915
+ {
916
+ "epoch": 2.30550621669627,
917
+ "grad_norm": 1.1971309185028076,
918
+ "learning_rate": 4.238933788180502e-06,
919
+ "loss": 0.3082,
920
+ "step": 650
921
+ },
922
+ {
923
+ "epoch": 2.323268206039076,
924
+ "grad_norm": 1.1617590188980103,
925
+ "learning_rate": 4.0365898039393985e-06,
926
+ "loss": 0.305,
927
+ "step": 655
928
+ },
929
+ {
930
+ "epoch": 2.3410301953818826,
931
+ "grad_norm": 1.2532880306243896,
932
+ "learning_rate": 3.8384409019295945e-06,
933
+ "loss": 0.2928,
934
+ "step": 660
935
+ },
936
+ {
937
+ "epoch": 2.358792184724689,
938
+ "grad_norm": 1.252830147743225,
939
+ "learning_rate": 3.6445629026232736e-06,
940
+ "loss": 0.2775,
941
+ "step": 665
942
+ },
943
+ {
944
+ "epoch": 2.3765541740674956,
945
+ "grad_norm": 1.2107690572738647,
946
+ "learning_rate": 3.455029992257705e-06,
947
+ "loss": 0.2773,
948
+ "step": 670
949
+ },
950
+ {
951
+ "epoch": 2.394316163410302,
952
+ "grad_norm": 1.2647984027862549,
953
+ "learning_rate": 3.269914694448282e-06,
954
+ "loss": 0.2908,
955
+ "step": 675
956
+ },
957
+ {
958
+ "epoch": 2.412078152753108,
959
+ "grad_norm": 1.391261100769043,
960
+ "learning_rate": 3.0892878424378313e-06,
961
+ "loss": 0.2658,
962
+ "step": 680
963
+ },
964
+ {
965
+ "epoch": 2.4298401420959146,
966
+ "grad_norm": 1.3045754432678223,
967
+ "learning_rate": 2.913218551992684e-06,
968
+ "loss": 0.2931,
969
+ "step": 685
970
+ },
971
+ {
972
+ "epoch": 2.447602131438721,
973
+ "grad_norm": 1.2543214559555054,
974
+ "learning_rate": 2.7417741949559634e-06,
975
+ "loss": 0.2609,
976
+ "step": 690
977
+ },
978
+ {
979
+ "epoch": 2.4653641207815276,
980
+ "grad_norm": 1.2797883749008179,
981
+ "learning_rate": 2.5750203734681555e-06,
982
+ "loss": 0.2745,
983
+ "step": 695
984
+ },
985
+ {
986
+ "epoch": 2.483126110124334,
987
+ "grad_norm": 1.2370916604995728,
988
+ "learning_rate": 2.413020894864844e-06,
989
+ "loss": 0.2903,
990
+ "step": 700
991
+ },
992
+ {
993
+ "epoch": 2.50088809946714,
994
+ "grad_norm": 1.0997259616851807,
995
+ "learning_rate": 2.2558377472612236e-06,
996
+ "loss": 0.2752,
997
+ "step": 705
998
+ },
999
+ {
1000
+ "epoch": 2.5186500888099466,
1001
+ "grad_norm": 1.2443797588348389,
1002
+ "learning_rate": 2.103531075832727e-06,
1003
+ "loss": 0.2867,
1004
+ "step": 710
1005
+ },
1006
+ {
1007
+ "epoch": 2.536412078152753,
1008
+ "grad_norm": 1.3215539455413818,
1009
+ "learning_rate": 1.956159159800835e-06,
1010
+ "loss": 0.2617,
1011
+ "step": 715
1012
+ },
1013
+ {
1014
+ "epoch": 2.5541740674955595,
1015
+ "grad_norm": 1.339474081993103,
1016
+ "learning_rate": 1.813778390132893e-06,
1017
+ "loss": 0.253,
1018
+ "step": 720
1019
+ },
1020
+ {
1021
+ "epoch": 2.571936056838366,
1022
+ "grad_norm": 1.1505285501480103,
1023
+ "learning_rate": 1.6764432479644442e-06,
1024
+ "loss": 0.2703,
1025
+ "step": 725
1026
+ },
1027
+ {
1028
+ "epoch": 2.589698046181172,
1029
+ "grad_norm": 1.2844033241271973,
1030
+ "learning_rate": 1.5442062837523546e-06,
1031
+ "loss": 0.3137,
1032
+ "step": 730
1033
+ },
1034
+ {
1035
+ "epoch": 2.6074600355239785,
1036
+ "grad_norm": 1.2572717666625977,
1037
+ "learning_rate": 1.4171180971667063e-06,
1038
+ "loss": 0.2562,
1039
+ "step": 735
1040
+ },
1041
+ {
1042
+ "epoch": 2.625222024866785,
1043
+ "grad_norm": 1.2211933135986328,
1044
+ "learning_rate": 1.2952273177291374e-06,
1045
+ "loss": 0.2752,
1046
+ "step": 740
1047
+ },
1048
+ {
1049
+ "epoch": 2.6429840142095915,
1050
+ "grad_norm": 1.2600083351135254,
1051
+ "learning_rate": 1.1785805862050524e-06,
1052
+ "loss": 0.2903,
1053
+ "step": 745
1054
+ },
1055
+ {
1056
+ "epoch": 2.660746003552398,
1057
+ "grad_norm": 1.0863158702850342,
1058
+ "learning_rate": 1.0672225367568194e-06,
1059
+ "loss": 0.2876,
1060
+ "step": 750
1061
+ },
1062
+ {
1063
+ "epoch": 2.678507992895204,
1064
+ "grad_norm": 1.1689404249191284,
1065
+ "learning_rate": 9.611957798647641e-07,
1066
+ "loss": 0.2589,
1067
+ "step": 755
1068
+ },
1069
+ {
1070
+ "epoch": 2.6962699822380105,
1071
+ "grad_norm": 1.2573766708374023,
1072
+ "learning_rate": 8.605408860225544e-07,
1073
+ "loss": 0.2966,
1074
+ "step": 760
1075
+ },
1076
+ {
1077
+ "epoch": 2.714031971580817,
1078
+ "grad_norm": 1.3061907291412354,
1079
+ "learning_rate": 7.652963702131266e-07,
1080
+ "loss": 0.2846,
1081
+ "step": 765
1082
+ },
1083
+ {
1084
+ "epoch": 2.7317939609236235,
1085
+ "grad_norm": 1.1642416715621948,
1086
+ "learning_rate": 6.754986771711724e-07,
1087
+ "loss": 0.2613,
1088
+ "step": 770
1089
+ },
1090
+ {
1091
+ "epoch": 2.74955595026643,
1092
+ "grad_norm": 1.2969051599502563,
1093
+ "learning_rate": 5.911821674377776e-07,
1094
+ "loss": 0.2812,
1095
+ "step": 775
1096
+ },
1097
+ {
1098
+ "epoch": 2.767317939609236,
1099
+ "grad_norm": 1.124867558479309,
1100
+ "learning_rate": 5.123791042125742e-07,
1101
+ "loss": 0.2726,
1102
+ "step": 780
1103
+ },
1104
+ {
1105
+ "epoch": 2.7850799289520425,
1106
+ "grad_norm": 1.2344129085540771,
1107
+ "learning_rate": 4.391196410084186e-07,
1108
+ "loss": 0.2638,
1109
+ "step": 785
1110
+ },
1111
+ {
1112
+ "epoch": 2.802841918294849,
1113
+ "grad_norm": 1.174248456954956,
1114
+ "learning_rate": 3.714318101133368e-07,
1115
+ "loss": 0.2661,
1116
+ "step": 790
1117
+ },
1118
+ {
1119
+ "epoch": 2.8206039076376554,
1120
+ "grad_norm": 1.3222744464874268,
1121
+ "learning_rate": 3.093415118641407e-07,
1122
+ "loss": 0.2746,
1123
+ "step": 795
1124
+ },
1125
+ {
1126
+ "epoch": 2.838365896980462,
1127
+ "grad_norm": 1.2366849184036255,
1128
+ "learning_rate": 2.5287250473581434e-07,
1129
+ "loss": 0.2642,
1130
+ "step": 800
1131
+ },
1132
+ {
1133
+ "epoch": 2.856127886323268,
1134
+ "grad_norm": 1.3464922904968262,
1135
+ "learning_rate": 2.020463962504876e-07,
1136
+ "loss": 0.2775,
1137
+ "step": 805
1138
+ },
1139
+ {
1140
+ "epoch": 2.8738898756660745,
1141
+ "grad_norm": 1.2246798276901245,
1142
+ "learning_rate": 1.5688263470944654e-07,
1143
+ "loss": 0.2996,
1144
+ "step": 810
1145
+ },
1146
+ {
1147
+ "epoch": 2.891651865008881,
1148
+ "grad_norm": 1.2219206094741821,
1149
+ "learning_rate": 1.1739850175135457e-07,
1150
+ "loss": 0.241,
1151
+ "step": 815
1152
+ },
1153
+ {
1154
+ "epoch": 2.9094138543516874,
1155
+ "grad_norm": 1.1566717624664307,
1156
+ "learning_rate": 8.360910573954216e-08,
1157
+ "loss": 0.2725,
1158
+ "step": 820
1159
+ },
1160
+ {
1161
+ "epoch": 2.927175843694494,
1162
+ "grad_norm": 1.202154278755188,
1163
+ "learning_rate": 5.5527375980882756e-08,
1164
+ "loss": 0.2525,
1165
+ "step": 825
1166
+ },
1167
+ {
1168
+ "epoch": 2.9449378330373,
1169
+ "grad_norm": 1.2614991664886475,
1170
+ "learning_rate": 3.316405777847697e-08,
1171
+ "loss": 0.2747,
1172
+ "step": 830
1173
+ },
1174
+ {
1175
+ "epoch": 2.9626998223801064,
1176
+ "grad_norm": 1.2126753330230713,
1177
+ "learning_rate": 1.6527708320018266e-08,
1178
+ "loss": 0.2731,
1179
+ "step": 835
1180
+ },
1181
+ {
1182
+ "epoch": 2.980461811722913,
1183
+ "grad_norm": 1.1563338041305542,
1184
+ "learning_rate": 5.624693403442072e-09,
1185
+ "loss": 0.2974,
1186
+ "step": 840
1187
+ },
1188
+ {
1189
+ "epoch": 2.9982238010657194,
1190
+ "grad_norm": 1.399437427520752,
1191
+ "learning_rate": 4.591850010926546e-10,
1192
+ "loss": 0.3024,
1193
+ "step": 845
1194
+ },
1195
+ {
1196
+ "epoch": 3.0,
1197
+ "step": 846,
1198
+ "total_flos": 1.2069706775889183e+18,
1199
+ "train_loss": 0.5579275732626588,
1200
+ "train_runtime": 555.4859,
1201
+ "train_samples_per_second": 48.574,
1202
+ "train_steps_per_second": 1.523
1203
+ }
1204
+ ],
1205
+ "logging_steps": 5,
1206
+ "max_steps": 846,
1207
+ "num_input_tokens_seen": 0,
1208
+ "num_train_epochs": 3,
1209
+ "save_steps": 2000,
1210
+ "stateful_callbacks": {
1211
+ "TrainerControl": {
1212
+ "args": {
1213
+ "should_epoch_stop": false,
1214
+ "should_evaluate": false,
1215
+ "should_log": false,
1216
+ "should_save": false,
1217
+ "should_training_stop": false
1218
+ },
1219
+ "attributes": {}
1220
+ }
1221
+ },
1222
+ "total_flos": 1.2069706775889183e+18,
1223
+ "train_batch_size": 2,
1224
+ "trial_name": null,
1225
+ "trial_params": null
1226
+ }
25_128_e3_3e-5/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9d0ab9cf9195ce3cfc7a0930282cca9f2b58d50a2b084396d0c1924102167e9
3
+ size 8145
25_128_e3_3e-5/vocab.json ADDED
The diff for this file is too large to render. See raw diff