RayDu0010 commited on
Commit
c0854f2
·
verified ·
1 Parent(s): 4c9823e

Upload folder using huggingface_hub

Browse files
33_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: 33_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
+ # 33_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
33_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
+ "down_proj",
28
+ "v_proj",
29
+ "q_proj",
30
+ "gate_proj",
31
+ "o_proj",
32
+ "k_proj",
33
+ "up_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
33_128_e3_3e-5/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f1ae68a1523a986151d071a85bcaf8db230c2062b594bd1a2159fbe042e3b14
3
+ size 791751704
33_128_e3_3e-5/all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.3800424090768507e+18,
4
+ "train_loss": 0.5697189306420577,
5
+ "train_runtime": 626.2457,
6
+ "train_samples": 10257,
7
+ "train_samples_per_second": 49.136,
8
+ "train_steps_per_second": 1.538
9
+ }
33_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
+ }
33_128_e3_3e-5/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
33_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
+ }
33_128_e3_3e-5/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
33_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
+ }
33_128_e3_3e-5/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.3800424090768507e+18,
4
+ "train_loss": 0.5697189306420577,
5
+ "train_runtime": 626.2457,
6
+ "train_samples": 10257,
7
+ "train_samples_per_second": 49.136,
8
+ "train_steps_per_second": 1.538
9
+ }
33_128_e3_3e-5/trainer_state.json ADDED
@@ -0,0 +1,1387 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 963,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.01557632398753894,
14
+ "grad_norm": 1.1502965688705444,
15
+ "learning_rate": 2.4489795918367347e-06,
16
+ "loss": 1.3358,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.03115264797507788,
21
+ "grad_norm": 0.761232316493988,
22
+ "learning_rate": 5.510204081632653e-06,
23
+ "loss": 1.3212,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.04672897196261682,
28
+ "grad_norm": 0.7245500087738037,
29
+ "learning_rate": 8.571428571428571e-06,
30
+ "loss": 1.2547,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.06230529595015576,
35
+ "grad_norm": 0.5405107736587524,
36
+ "learning_rate": 1.163265306122449e-05,
37
+ "loss": 1.2769,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.0778816199376947,
42
+ "grad_norm": 0.7426033616065979,
43
+ "learning_rate": 1.4693877551020408e-05,
44
+ "loss": 1.2794,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.09345794392523364,
49
+ "grad_norm": 0.5645145177841187,
50
+ "learning_rate": 1.7755102040816327e-05,
51
+ "loss": 1.2649,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.10903426791277258,
56
+ "grad_norm": 0.6525325179100037,
57
+ "learning_rate": 2.0816326530612247e-05,
58
+ "loss": 1.2677,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.12461059190031153,
63
+ "grad_norm": 0.5359835624694824,
64
+ "learning_rate": 2.3877551020408164e-05,
65
+ "loss": 1.2419,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.14018691588785046,
70
+ "grad_norm": 0.4492732584476471,
71
+ "learning_rate": 2.6938775510204084e-05,
72
+ "loss": 1.1733,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.1557632398753894,
77
+ "grad_norm": 0.4969276189804077,
78
+ "learning_rate": 3e-05,
79
+ "loss": 1.1958,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.17133956386292834,
84
+ "grad_norm": 0.44175365567207336,
85
+ "learning_rate": 2.999778487654013e-05,
86
+ "loss": 1.1953,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.18691588785046728,
91
+ "grad_norm": 0.6045664548873901,
92
+ "learning_rate": 2.9991140160396782e-05,
93
+ "loss": 1.1968,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.20249221183800623,
98
+ "grad_norm": 0.5227835178375244,
99
+ "learning_rate": 2.9980067814085504e-05,
100
+ "loss": 1.1381,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.21806853582554517,
105
+ "grad_norm": 0.4581258296966553,
106
+ "learning_rate": 2.99645711078215e-05,
107
+ "loss": 1.1304,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.2336448598130841,
112
+ "grad_norm": 0.6694484353065491,
113
+ "learning_rate": 2.9944654618553784e-05,
114
+ "loss": 1.077,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.24922118380062305,
119
+ "grad_norm": 0.5050034523010254,
120
+ "learning_rate": 2.992032422861338e-05,
121
+ "loss": 1.1284,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.26479750778816197,
126
+ "grad_norm": 0.516563355922699,
127
+ "learning_rate": 2.9891587123975948e-05,
128
+ "loss": 1.1051,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.2803738317757009,
133
+ "grad_norm": 0.5861562490463257,
134
+ "learning_rate": 2.9858451792139457e-05,
135
+ "loss": 1.1124,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.29595015576323985,
140
+ "grad_norm": 0.5458567142486572,
141
+ "learning_rate": 2.9820928019617345e-05,
142
+ "loss": 1.0063,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.3115264797507788,
147
+ "grad_norm": 0.5098647475242615,
148
+ "learning_rate": 2.9779026889048135e-05,
149
+ "loss": 1.0753,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.32710280373831774,
154
+ "grad_norm": 0.5402958393096924,
155
+ "learning_rate": 2.973276077592212e-05,
156
+ "loss": 1.049,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.3426791277258567,
161
+ "grad_norm": 0.5702635645866394,
162
+ "learning_rate": 2.9682143344926323e-05,
163
+ "loss": 1.0316,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.3582554517133956,
168
+ "grad_norm": 0.5786664485931396,
169
+ "learning_rate": 2.962718954590859e-05,
170
+ "loss": 1.0079,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.37383177570093457,
175
+ "grad_norm": 0.6042742729187012,
176
+ "learning_rate": 2.9567915609462177e-05,
177
+ "loss": 1.0158,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.3894080996884735,
182
+ "grad_norm": 0.6460011005401611,
183
+ "learning_rate": 2.9504339042132044e-05,
184
+ "loss": 0.9763,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.40498442367601245,
189
+ "grad_norm": 0.697295606136322,
190
+ "learning_rate": 2.9436478621244292e-05,
191
+ "loss": 0.9667,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.4205607476635514,
196
+ "grad_norm": 0.6564842462539673,
197
+ "learning_rate": 2.93643543893603e-05,
198
+ "loss": 0.9318,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.43613707165109034,
203
+ "grad_norm": 0.6846672892570496,
204
+ "learning_rate": 2.9287987648357137e-05,
205
+ "loss": 0.9503,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.4517133956386293,
210
+ "grad_norm": 0.7228031158447266,
211
+ "learning_rate": 2.9207400953136083e-05,
212
+ "loss": 0.8943,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.4672897196261682,
217
+ "grad_norm": 0.6400267481803894,
218
+ "learning_rate": 2.9122618104961023e-05,
219
+ "loss": 1.0079,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.48286604361370716,
224
+ "grad_norm": 0.6918800473213196,
225
+ "learning_rate": 2.9033664144428748e-05,
226
+ "loss": 0.9265,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.4984423676012461,
231
+ "grad_norm": 0.7210898995399475,
232
+ "learning_rate": 2.894056534407324e-05,
233
+ "loss": 0.9512,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.514018691588785,
238
+ "grad_norm": 0.7842053771018982,
239
+ "learning_rate": 2.884334920060607e-05,
240
+ "loss": 0.9059,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.5295950155763239,
245
+ "grad_norm": 0.7233600616455078,
246
+ "learning_rate": 2.8742044426795237e-05,
247
+ "loss": 0.9035,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.5451713395638629,
252
+ "grad_norm": 0.7246789932250977,
253
+ "learning_rate": 2.8636680942984892e-05,
254
+ "loss": 0.8573,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.5607476635514018,
259
+ "grad_norm": 0.8453109264373779,
260
+ "learning_rate": 2.852728986825834e-05,
261
+ "loss": 0.8937,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.5763239875389408,
266
+ "grad_norm": 0.8369421362876892,
267
+ "learning_rate": 2.8413903511247034e-05,
268
+ "loss": 0.8279,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.5919003115264797,
273
+ "grad_norm": 0.8420252799987793,
274
+ "learning_rate": 2.8296555360588237e-05,
275
+ "loss": 0.8874,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.6074766355140186,
280
+ "grad_norm": 0.7969822287559509,
281
+ "learning_rate": 2.8175280075034152e-05,
282
+ "loss": 0.8059,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.6230529595015576,
287
+ "grad_norm": 1.0191549062728882,
288
+ "learning_rate": 2.8050113473215454e-05,
289
+ "loss": 0.8833,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.6386292834890965,
294
+ "grad_norm": 0.8808915019035339,
295
+ "learning_rate": 2.7921092523062294e-05,
296
+ "loss": 0.8565,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.6542056074766355,
301
+ "grad_norm": 0.9159283638000488,
302
+ "learning_rate": 2.7788255330885804e-05,
303
+ "loss": 0.8682,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.6697819314641744,
308
+ "grad_norm": 0.9436246156692505,
309
+ "learning_rate": 2.7651641130123414e-05,
310
+ "loss": 0.8068,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.6853582554517134,
315
+ "grad_norm": 0.8632054328918457,
316
+ "learning_rate": 2.7511290269751264e-05,
317
+ "loss": 0.8475,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.7009345794392523,
322
+ "grad_norm": 0.9796780347824097,
323
+ "learning_rate": 2.736724420236715e-05,
324
+ "loss": 0.8371,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 0.7165109034267912,
329
+ "grad_norm": 0.8720173239707947,
330
+ "learning_rate": 2.7219545471947485e-05,
331
+ "loss": 0.7898,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 0.7320872274143302,
336
+ "grad_norm": 0.9333558082580566,
337
+ "learning_rate": 2.7068237701281976e-05,
338
+ "loss": 0.7875,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 0.7476635514018691,
343
+ "grad_norm": 0.9077138304710388,
344
+ "learning_rate": 2.6913365579089616e-05,
345
+ "loss": 0.7725,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 0.7632398753894081,
350
+ "grad_norm": 1.0266997814178467,
351
+ "learning_rate": 2.6754974846819887e-05,
352
+ "loss": 0.7764,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 0.778816199376947,
357
+ "grad_norm": 0.9908666610717773,
358
+ "learning_rate": 2.6593112285143044e-05,
359
+ "loss": 0.7866,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 0.794392523364486,
364
+ "grad_norm": 0.9393789768218994,
365
+ "learning_rate": 2.642782570013344e-05,
366
+ "loss": 0.755,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 0.8099688473520249,
371
+ "grad_norm": 0.9551516175270081,
372
+ "learning_rate": 2.625916390915001e-05,
373
+ "loss": 0.7174,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 0.8255451713395638,
378
+ "grad_norm": 0.8765639662742615,
379
+ "learning_rate": 2.6087176726418092e-05,
380
+ "loss": 0.7012,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 0.8411214953271028,
385
+ "grad_norm": 0.8521721959114075,
386
+ "learning_rate": 2.5911914948316787e-05,
387
+ "loss": 0.7209,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 0.8566978193146417,
392
+ "grad_norm": 0.9204537868499756,
393
+ "learning_rate": 2.5733430338376264e-05,
394
+ "loss": 0.7372,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 0.8722741433021807,
399
+ "grad_norm": 1.2297322750091553,
400
+ "learning_rate": 2.5551775611989426e-05,
401
+ "loss": 0.738,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 0.8878504672897196,
406
+ "grad_norm": 1.0030170679092407,
407
+ "learning_rate": 2.5367004420842395e-05,
408
+ "loss": 0.7052,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 0.9034267912772586,
413
+ "grad_norm": 1.0532103776931763,
414
+ "learning_rate": 2.517917133706854e-05,
415
+ "loss": 0.6701,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 0.9190031152647975,
420
+ "grad_norm": 1.0796500444412231,
421
+ "learning_rate": 2.4988331837130587e-05,
422
+ "loss": 0.7567,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 0.9345794392523364,
427
+ "grad_norm": 0.9697847366333008,
428
+ "learning_rate": 2.479454228543565e-05,
429
+ "loss": 0.7006,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 0.9501557632398754,
434
+ "grad_norm": 0.996569812297821,
435
+ "learning_rate": 2.459785991768802e-05,
436
+ "loss": 0.7042,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 0.9657320872274143,
441
+ "grad_norm": 1.055556058883667,
442
+ "learning_rate": 2.4398342823984633e-05,
443
+ "loss": 0.6725,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 0.9813084112149533,
448
+ "grad_norm": 0.9701163172721863,
449
+ "learning_rate": 2.4196049931658136e-05,
450
+ "loss": 0.6663,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 0.9968847352024922,
455
+ "grad_norm": 1.0469231605529785,
456
+ "learning_rate": 2.3991040987872738e-05,
457
+ "loss": 0.6662,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 1.0124610591900312,
462
+ "grad_norm": 0.9825913310050964,
463
+ "learning_rate": 2.378337654197789e-05,
464
+ "loss": 0.6321,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 1.02803738317757,
469
+ "grad_norm": 0.9752982258796692,
470
+ "learning_rate": 2.3573117927625045e-05,
471
+ "loss": 0.5961,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 1.043613707165109,
476
+ "grad_norm": 1.0990300178527832,
477
+ "learning_rate": 2.336032724465277e-05,
478
+ "loss": 0.5781,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 1.0591900311526479,
483
+ "grad_norm": 1.0978039503097534,
484
+ "learning_rate": 2.3145067340745582e-05,
485
+ "loss": 0.53,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 1.074766355140187,
490
+ "grad_norm": 1.1662368774414062,
491
+ "learning_rate": 2.292740179287191e-05,
492
+ "loss": 0.5721,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 1.0903426791277258,
497
+ "grad_norm": 1.1578783988952637,
498
+ "learning_rate": 2.2707394888506603e-05,
499
+ "loss": 0.5373,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 1.1059190031152648,
504
+ "grad_norm": 1.047257900238037,
505
+ "learning_rate": 2.2485111606643695e-05,
506
+ "loss": 0.5594,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 1.1214953271028036,
511
+ "grad_norm": 1.0481206178665161,
512
+ "learning_rate": 2.2260617598604843e-05,
513
+ "loss": 0.5629,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 1.1370716510903427,
518
+ "grad_norm": 1.2490763664245605,
519
+ "learning_rate": 2.2033979168649215e-05,
520
+ "loss": 0.5185,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 1.1526479750778815,
525
+ "grad_norm": 1.2029680013656616,
526
+ "learning_rate": 2.1805263254390555e-05,
527
+ "loss": 0.5419,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 1.1682242990654206,
532
+ "grad_norm": 1.1961748600006104,
533
+ "learning_rate": 2.1574537407027178e-05,
534
+ "loss": 0.5271,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 1.1838006230529594,
539
+ "grad_norm": 1.0883921384811401,
540
+ "learning_rate": 2.1341869771390725e-05,
541
+ "loss": 0.5402,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 1.1993769470404985,
546
+ "grad_norm": 1.1722567081451416,
547
+ "learning_rate": 2.1107329065819596e-05,
548
+ "loss": 0.5802,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 1.2149532710280373,
553
+ "grad_norm": 1.2599680423736572,
554
+ "learning_rate": 2.0870984561863026e-05,
555
+ "loss": 0.5441,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 1.2305295950155763,
560
+ "grad_norm": 1.4320626258850098,
561
+ "learning_rate": 2.0632906063821713e-05,
562
+ "loss": 0.5204,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 1.2461059190031152,
567
+ "grad_norm": 1.134704828262329,
568
+ "learning_rate": 2.0393163888131178e-05,
569
+ "loss": 0.5699,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 1.2616822429906542,
574
+ "grad_norm": 1.3641544580459595,
575
+ "learning_rate": 2.0151828842593772e-05,
576
+ "loss": 0.5727,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 1.277258566978193,
581
+ "grad_norm": 1.26175856590271,
582
+ "learning_rate": 1.9908972205465638e-05,
583
+ "loss": 0.5318,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 1.2928348909657321,
588
+ "grad_norm": 1.270642638206482,
589
+ "learning_rate": 1.966466570440468e-05,
590
+ "loss": 0.5578,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 1.308411214953271,
595
+ "grad_norm": 1.2094162702560425,
596
+ "learning_rate": 1.941898149528582e-05,
597
+ "loss": 0.5514,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 1.32398753894081,
602
+ "grad_norm": 1.164954662322998,
603
+ "learning_rate": 1.917199214088977e-05,
604
+ "loss": 0.4921,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 1.3395638629283488,
609
+ "grad_norm": 1.1267497539520264,
610
+ "learning_rate": 1.892377058947163e-05,
611
+ "loss": 0.4909,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 1.355140186915888,
616
+ "grad_norm": 1.1822401285171509,
617
+ "learning_rate": 1.8674390153215634e-05,
618
+ "loss": 0.4914,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 1.3707165109034267,
623
+ "grad_norm": 1.1231619119644165,
624
+ "learning_rate": 1.8423924486582424e-05,
625
+ "loss": 0.5119,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 1.3862928348909658,
630
+ "grad_norm": 1.1804649829864502,
631
+ "learning_rate": 1.8172447564555212e-05,
632
+ "loss": 0.4742,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 1.4018691588785046,
637
+ "grad_norm": 1.1495426893234253,
638
+ "learning_rate": 1.7920033660791275e-05,
639
+ "loss": 0.4842,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 1.4174454828660437,
644
+ "grad_norm": 1.2221136093139648,
645
+ "learning_rate": 1.7666757325685246e-05,
646
+ "loss": 0.4703,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 1.4330218068535825,
651
+ "grad_norm": 1.2306239604949951,
652
+ "learning_rate": 1.7412693364350705e-05,
653
+ "loss": 0.4771,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 1.4485981308411215,
658
+ "grad_norm": 1.2699083089828491,
659
+ "learning_rate": 1.7157916814526443e-05,
660
+ "loss": 0.4954,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 1.4641744548286604,
665
+ "grad_norm": 1.1597747802734375,
666
+ "learning_rate": 1.690250292441415e-05,
667
+ "loss": 0.4831,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 1.4797507788161994,
672
+ "grad_norm": 1.0943628549575806,
673
+ "learning_rate": 1.6646527130453805e-05,
674
+ "loss": 0.4654,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 1.4953271028037383,
679
+ "grad_norm": 1.1199864149093628,
680
+ "learning_rate": 1.6390065035043598e-05,
681
+ "loss": 0.4817,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 1.5109034267912773,
686
+ "grad_norm": 1.3075653314590454,
687
+ "learning_rate": 1.613319238421074e-05,
688
+ "loss": 0.4572,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 1.5264797507788161,
693
+ "grad_norm": 1.1975387334823608,
694
+ "learning_rate": 1.587598504523991e-05,
695
+ "loss": 0.4897,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 1.542056074766355,
700
+ "grad_norm": 1.2261122465133667,
701
+ "learning_rate": 1.5618518984265853e-05,
702
+ "loss": 0.4071,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 1.557632398753894,
707
+ "grad_norm": 1.163928747177124,
708
+ "learning_rate": 1.5360870243836803e-05,
709
+ "loss": 0.4982,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 1.573208722741433,
714
+ "grad_norm": 1.5599970817565918,
715
+ "learning_rate": 1.5103114920455345e-05,
716
+ "loss": 0.4351,
717
+ "step": 505
718
+ },
719
+ {
720
+ "epoch": 1.588785046728972,
721
+ "grad_norm": 1.1019141674041748,
722
+ "learning_rate": 1.4845329142103302e-05,
723
+ "loss": 0.4698,
724
+ "step": 510
725
+ },
726
+ {
727
+ "epoch": 1.6043613707165107,
728
+ "grad_norm": 1.4539151191711426,
729
+ "learning_rate": 1.4587589045757374e-05,
730
+ "loss": 0.4309,
731
+ "step": 515
732
+ },
733
+ {
734
+ "epoch": 1.6199376947040498,
735
+ "grad_norm": 1.1775527000427246,
736
+ "learning_rate": 1.4329970754902098e-05,
737
+ "loss": 0.4464,
738
+ "step": 520
739
+ },
740
+ {
741
+ "epoch": 1.6355140186915889,
742
+ "grad_norm": 1.1652404069900513,
743
+ "learning_rate": 1.4072550357046767e-05,
744
+ "loss": 0.4516,
745
+ "step": 525
746
+ },
747
+ {
748
+ "epoch": 1.6510903426791277,
749
+ "grad_norm": 1.1336963176727295,
750
+ "learning_rate": 1.3815403881253034e-05,
751
+ "loss": 0.4344,
752
+ "step": 530
753
+ },
754
+ {
755
+ "epoch": 1.6666666666666665,
756
+ "grad_norm": 1.1567862033843994,
757
+ "learning_rate": 1.3558607275679712e-05,
758
+ "loss": 0.4186,
759
+ "step": 535
760
+ },
761
+ {
762
+ "epoch": 1.6822429906542056,
763
+ "grad_norm": 1.4150336980819702,
764
+ "learning_rate": 1.3302236385151527e-05,
765
+ "loss": 0.4004,
766
+ "step": 540
767
+ },
768
+ {
769
+ "epoch": 1.6978193146417446,
770
+ "grad_norm": 1.2483351230621338,
771
+ "learning_rate": 1.304636692875835e-05,
772
+ "loss": 0.4352,
773
+ "step": 545
774
+ },
775
+ {
776
+ "epoch": 1.7133956386292835,
777
+ "grad_norm": 1.328258752822876,
778
+ "learning_rate": 1.279107447749159e-05,
779
+ "loss": 0.4097,
780
+ "step": 550
781
+ },
782
+ {
783
+ "epoch": 1.7289719626168223,
784
+ "grad_norm": 1.2045174837112427,
785
+ "learning_rate": 1.2536434431924294e-05,
786
+ "loss": 0.4446,
787
+ "step": 555
788
+ },
789
+ {
790
+ "epoch": 1.7445482866043613,
791
+ "grad_norm": 1.2496081590652466,
792
+ "learning_rate": 1.2282521999941631e-05,
793
+ "loss": 0.4144,
794
+ "step": 560
795
+ },
796
+ {
797
+ "epoch": 1.7601246105919004,
798
+ "grad_norm": 1.20028817653656,
799
+ "learning_rate": 1.202941217452825e-05,
800
+ "loss": 0.4224,
801
+ "step": 565
802
+ },
803
+ {
804
+ "epoch": 1.7757009345794392,
805
+ "grad_norm": 1.3421413898468018,
806
+ "learning_rate": 1.1777179711619119e-05,
807
+ "loss": 0.4318,
808
+ "step": 570
809
+ },
810
+ {
811
+ "epoch": 1.791277258566978,
812
+ "grad_norm": 1.1531528234481812,
813
+ "learning_rate": 1.1525899108020346e-05,
814
+ "loss": 0.4071,
815
+ "step": 575
816
+ },
817
+ {
818
+ "epoch": 1.8068535825545171,
819
+ "grad_norm": 1.2624865770339966,
820
+ "learning_rate": 1.1275644579406607e-05,
821
+ "loss": 0.4301,
822
+ "step": 580
823
+ },
824
+ {
825
+ "epoch": 1.8224299065420562,
826
+ "grad_norm": 1.1009992361068726,
827
+ "learning_rate": 1.1026490038401541e-05,
828
+ "loss": 0.4225,
829
+ "step": 585
830
+ },
831
+ {
832
+ "epoch": 1.838006230529595,
833
+ "grad_norm": 1.118433952331543,
834
+ "learning_rate": 1.0778509072747679e-05,
835
+ "loss": 0.4254,
836
+ "step": 590
837
+ },
838
+ {
839
+ "epoch": 1.8535825545171338,
840
+ "grad_norm": 1.2376115322113037,
841
+ "learning_rate": 1.0531774923572286e-05,
842
+ "loss": 0.4142,
843
+ "step": 595
844
+ },
845
+ {
846
+ "epoch": 1.8691588785046729,
847
+ "grad_norm": 1.2524000406265259,
848
+ "learning_rate": 1.0286360463755664e-05,
849
+ "loss": 0.3975,
850
+ "step": 600
851
+ },
852
+ {
853
+ "epoch": 1.884735202492212,
854
+ "grad_norm": 1.5249426364898682,
855
+ "learning_rate": 1.0042338176408124e-05,
856
+ "loss": 0.3894,
857
+ "step": 605
858
+ },
859
+ {
860
+ "epoch": 1.9003115264797508,
861
+ "grad_norm": 1.2415817975997925,
862
+ "learning_rate": 9.799780133462124e-06,
863
+ "loss": 0.3631,
864
+ "step": 610
865
+ },
866
+ {
867
+ "epoch": 1.9158878504672896,
868
+ "grad_norm": 1.3600504398345947,
869
+ "learning_rate": 9.558757974385833e-06,
870
+ "loss": 0.3801,
871
+ "step": 615
872
+ },
873
+ {
874
+ "epoch": 1.9314641744548287,
875
+ "grad_norm": 1.3747203350067139,
876
+ "learning_rate": 9.319342885024446e-06,
877
+ "loss": 0.3901,
878
+ "step": 620
879
+ },
880
+ {
881
+ "epoch": 1.9470404984423677,
882
+ "grad_norm": 1.2653244733810425,
883
+ "learning_rate": 9.081605576575437e-06,
884
+ "loss": 0.3929,
885
+ "step": 625
886
+ },
887
+ {
888
+ "epoch": 1.9626168224299065,
889
+ "grad_norm": 1.3194959163665771,
890
+ "learning_rate": 8.845616264704046e-06,
891
+ "loss": 0.3731,
892
+ "step": 630
893
+ },
894
+ {
895
+ "epoch": 1.9781931464174454,
896
+ "grad_norm": 1.365678310394287,
897
+ "learning_rate": 8.611444648805061e-06,
898
+ "loss": 0.3923,
899
+ "step": 635
900
+ },
901
+ {
902
+ "epoch": 1.9937694704049844,
903
+ "grad_norm": 1.2362958192825317,
904
+ "learning_rate": 8.379159891417163e-06,
905
+ "loss": 0.3706,
906
+ "step": 640
907
+ },
908
+ {
909
+ "epoch": 2.0093457943925235,
910
+ "grad_norm": 1.2486878633499146,
911
+ "learning_rate": 8.148830597795735e-06,
912
+ "loss": 0.3218,
913
+ "step": 645
914
+ },
915
+ {
916
+ "epoch": 2.0249221183800623,
917
+ "grad_norm": 1.206761360168457,
918
+ "learning_rate": 7.920524795650359e-06,
919
+ "loss": 0.3584,
920
+ "step": 650
921
+ },
922
+ {
923
+ "epoch": 2.040498442367601,
924
+ "grad_norm": 1.239185094833374,
925
+ "learning_rate": 7.694309915052813e-06,
926
+ "loss": 0.3177,
927
+ "step": 655
928
+ },
929
+ {
930
+ "epoch": 2.05607476635514,
931
+ "grad_norm": 1.09977126121521,
932
+ "learning_rate": 7.470252768521621e-06,
933
+ "loss": 0.3372,
934
+ "step": 660
935
+ },
936
+ {
937
+ "epoch": 2.0716510903426792,
938
+ "grad_norm": 1.2492647171020508,
939
+ "learning_rate": 7.248419531289013e-06,
940
+ "loss": 0.3125,
941
+ "step": 665
942
+ },
943
+ {
944
+ "epoch": 2.087227414330218,
945
+ "grad_norm": 1.2557836771011353,
946
+ "learning_rate": 7.0288757217560464e-06,
947
+ "loss": 0.3147,
948
+ "step": 670
949
+ },
950
+ {
951
+ "epoch": 2.102803738317757,
952
+ "grad_norm": 1.2350633144378662,
953
+ "learning_rate": 6.811686182141777e-06,
954
+ "loss": 0.3187,
955
+ "step": 675
956
+ },
957
+ {
958
+ "epoch": 2.1183800623052957,
959
+ "grad_norm": 1.4249355792999268,
960
+ "learning_rate": 6.59691505933214e-06,
961
+ "loss": 0.3087,
962
+ "step": 680
963
+ },
964
+ {
965
+ "epoch": 2.133956386292835,
966
+ "grad_norm": 1.2877665758132935,
967
+ "learning_rate": 6.384625785934152e-06,
968
+ "loss": 0.3085,
969
+ "step": 685
970
+ },
971
+ {
972
+ "epoch": 2.149532710280374,
973
+ "grad_norm": 1.3396496772766113,
974
+ "learning_rate": 6.174881061541108e-06,
975
+ "loss": 0.3124,
976
+ "step": 690
977
+ },
978
+ {
979
+ "epoch": 2.1651090342679127,
980
+ "grad_norm": 1.2408440113067627,
981
+ "learning_rate": 5.967742834214299e-06,
982
+ "loss": 0.2855,
983
+ "step": 695
984
+ },
985
+ {
986
+ "epoch": 2.1806853582554515,
987
+ "grad_norm": 1.3344892263412476,
988
+ "learning_rate": 5.763272282186617e-06,
989
+ "loss": 0.3506,
990
+ "step": 700
991
+ },
992
+ {
993
+ "epoch": 2.196261682242991,
994
+ "grad_norm": 1.2928617000579834,
995
+ "learning_rate": 5.5615297957936316e-06,
996
+ "loss": 0.3007,
997
+ "step": 705
998
+ },
999
+ {
1000
+ "epoch": 2.2118380062305296,
1001
+ "grad_norm": 1.475799322128296,
1002
+ "learning_rate": 5.362574959637258e-06,
1003
+ "loss": 0.3283,
1004
+ "step": 710
1005
+ },
1006
+ {
1007
+ "epoch": 2.2274143302180685,
1008
+ "grad_norm": 1.273529052734375,
1009
+ "learning_rate": 5.166466534987499e-06,
1010
+ "loss": 0.3112,
1011
+ "step": 715
1012
+ },
1013
+ {
1014
+ "epoch": 2.2429906542056073,
1015
+ "grad_norm": 1.1576861143112183,
1016
+ "learning_rate": 4.973262442427314e-06,
1017
+ "loss": 0.2947,
1018
+ "step": 720
1019
+ },
1020
+ {
1021
+ "epoch": 2.2585669781931466,
1022
+ "grad_norm": 1.2360608577728271,
1023
+ "learning_rate": 4.783019744745759e-06,
1024
+ "loss": 0.3001,
1025
+ "step": 725
1026
+ },
1027
+ {
1028
+ "epoch": 2.2741433021806854,
1029
+ "grad_norm": 1.2671312093734741,
1030
+ "learning_rate": 4.59579463008453e-06,
1031
+ "loss": 0.3228,
1032
+ "step": 730
1033
+ },
1034
+ {
1035
+ "epoch": 2.289719626168224,
1036
+ "grad_norm": 1.430251955986023,
1037
+ "learning_rate": 4.411642395342789e-06,
1038
+ "loss": 0.256,
1039
+ "step": 735
1040
+ },
1041
+ {
1042
+ "epoch": 2.305295950155763,
1043
+ "grad_norm": 1.228069543838501,
1044
+ "learning_rate": 4.230617429845257e-06,
1045
+ "loss": 0.2703,
1046
+ "step": 740
1047
+ },
1048
+ {
1049
+ "epoch": 2.3208722741433023,
1050
+ "grad_norm": 1.2439641952514648,
1051
+ "learning_rate": 4.052773199278327e-06,
1052
+ "loss": 0.2703,
1053
+ "step": 745
1054
+ },
1055
+ {
1056
+ "epoch": 2.336448598130841,
1057
+ "grad_norm": 1.2345188856124878,
1058
+ "learning_rate": 3.8781622298989625e-06,
1059
+ "loss": 0.2896,
1060
+ "step": 750
1061
+ },
1062
+ {
1063
+ "epoch": 2.35202492211838,
1064
+ "grad_norm": 1.1543601751327515,
1065
+ "learning_rate": 3.7068360930211222e-06,
1066
+ "loss": 0.2866,
1067
+ "step": 755
1068
+ },
1069
+ {
1070
+ "epoch": 2.367601246105919,
1071
+ "grad_norm": 1.1969873905181885,
1072
+ "learning_rate": 3.538845389784145e-06,
1073
+ "loss": 0.3185,
1074
+ "step": 760
1075
+ },
1076
+ {
1077
+ "epoch": 2.383177570093458,
1078
+ "grad_norm": 1.3594342470169067,
1079
+ "learning_rate": 3.374239736207742e-06,
1080
+ "loss": 0.2915,
1081
+ "step": 765
1082
+ },
1083
+ {
1084
+ "epoch": 2.398753894080997,
1085
+ "grad_norm": 1.4823335409164429,
1086
+ "learning_rate": 3.2130677485378923e-06,
1087
+ "loss": 0.2843,
1088
+ "step": 770
1089
+ },
1090
+ {
1091
+ "epoch": 2.4143302180685358,
1092
+ "grad_norm": 1.2552200555801392,
1093
+ "learning_rate": 3.055377028888052e-06,
1094
+ "loss": 0.3039,
1095
+ "step": 775
1096
+ },
1097
+ {
1098
+ "epoch": 2.4299065420560746,
1099
+ "grad_norm": 1.364571213722229,
1100
+ "learning_rate": 2.9012141511798963e-06,
1101
+ "loss": 0.2792,
1102
+ "step": 780
1103
+ },
1104
+ {
1105
+ "epoch": 2.445482866043614,
1106
+ "grad_norm": 1.3701204061508179,
1107
+ "learning_rate": 2.750624647387697e-06,
1108
+ "loss": 0.3161,
1109
+ "step": 785
1110
+ },
1111
+ {
1112
+ "epoch": 2.4610591900311527,
1113
+ "grad_norm": 1.3332101106643677,
1114
+ "learning_rate": 2.603652994090468e-06,
1115
+ "loss": 0.2969,
1116
+ "step": 790
1117
+ },
1118
+ {
1119
+ "epoch": 2.4766355140186915,
1120
+ "grad_norm": 1.329770803451538,
1121
+ "learning_rate": 2.460342599335838e-06,
1122
+ "loss": 0.3036,
1123
+ "step": 795
1124
+ },
1125
+ {
1126
+ "epoch": 2.4922118380062304,
1127
+ "grad_norm": 1.1008788347244263,
1128
+ "learning_rate": 2.320735789819465e-06,
1129
+ "loss": 0.257,
1130
+ "step": 800
1131
+ },
1132
+ {
1133
+ "epoch": 2.507788161993769,
1134
+ "grad_norm": 1.2777901887893677,
1135
+ "learning_rate": 2.184873798383875e-06,
1136
+ "loss": 0.2658,
1137
+ "step": 805
1138
+ },
1139
+ {
1140
+ "epoch": 2.5233644859813085,
1141
+ "grad_norm": 1.1616297960281372,
1142
+ "learning_rate": 2.052796751840336e-06,
1143
+ "loss": 0.2637,
1144
+ "step": 810
1145
+ },
1146
+ {
1147
+ "epoch": 2.5389408099688473,
1148
+ "grad_norm": 1.2732651233673096,
1149
+ "learning_rate": 1.924543659117421e-06,
1150
+ "loss": 0.2811,
1151
+ "step": 815
1152
+ },
1153
+ {
1154
+ "epoch": 2.554517133956386,
1155
+ "grad_norm": 1.3196008205413818,
1156
+ "learning_rate": 1.8001523997397329e-06,
1157
+ "loss": 0.2509,
1158
+ "step": 820
1159
+ },
1160
+ {
1161
+ "epoch": 2.5700934579439254,
1162
+ "grad_norm": 1.1744121313095093,
1163
+ "learning_rate": 1.6796597126401847e-06,
1164
+ "loss": 0.2732,
1165
+ "step": 825
1166
+ },
1167
+ {
1168
+ "epoch": 2.5856697819314642,
1169
+ "grad_norm": 1.252385139465332,
1170
+ "learning_rate": 1.5631011853091627e-06,
1171
+ "loss": 0.2734,
1172
+ "step": 830
1173
+ },
1174
+ {
1175
+ "epoch": 2.601246105919003,
1176
+ "grad_norm": 1.1457668542861938,
1177
+ "learning_rate": 1.4505112432837858e-06,
1178
+ "loss": 0.28,
1179
+ "step": 835
1180
+ },
1181
+ {
1182
+ "epoch": 2.616822429906542,
1183
+ "grad_norm": 1.4043269157409668,
1184
+ "learning_rate": 1.341923139980305e-06,
1185
+ "loss": 0.3023,
1186
+ "step": 840
1187
+ },
1188
+ {
1189
+ "epoch": 2.6323987538940807,
1190
+ "grad_norm": 1.087550163269043,
1191
+ "learning_rate": 1.23736894687274e-06,
1192
+ "loss": 0.2601,
1193
+ "step": 845
1194
+ },
1195
+ {
1196
+ "epoch": 2.64797507788162,
1197
+ "grad_norm": 1.205032229423523,
1198
+ "learning_rate": 1.1368795440205437e-06,
1199
+ "loss": 0.2911,
1200
+ "step": 850
1201
+ },
1202
+ {
1203
+ "epoch": 2.663551401869159,
1204
+ "grad_norm": 1.228340983390808,
1205
+ "learning_rate": 1.0404846109482192e-06,
1206
+ "loss": 0.2841,
1207
+ "step": 855
1208
+ },
1209
+ {
1210
+ "epoch": 2.6791277258566977,
1211
+ "grad_norm": 1.2469404935836792,
1212
+ "learning_rate": 9.482126178794564e-07,
1213
+ "loss": 0.2724,
1214
+ "step": 860
1215
+ },
1216
+ {
1217
+ "epoch": 2.694704049844237,
1218
+ "grad_norm": 1.2445036172866821,
1219
+ "learning_rate": 8.600908173284594e-07,
1220
+ "loss": 0.2835,
1221
+ "step": 865
1222
+ },
1223
+ {
1224
+ "epoch": 2.710280373831776,
1225
+ "grad_norm": 1.2120599746704102,
1226
+ "learning_rate": 7.761452360509219e-07,
1227
+ "loss": 0.2611,
1228
+ "step": 870
1229
+ },
1230
+ {
1231
+ "epoch": 2.7258566978193146,
1232
+ "grad_norm": 1.5249335765838623,
1233
+ "learning_rate": 6.964006673570372e-07,
1234
+ "loss": 0.2936,
1235
+ "step": 875
1236
+ },
1237
+ {
1238
+ "epoch": 2.7414330218068534,
1239
+ "grad_norm": 1.376591682434082,
1240
+ "learning_rate": 6.208806637887937e-07,
1241
+ "loss": 0.2907,
1242
+ "step": 880
1243
+ },
1244
+ {
1245
+ "epoch": 2.7570093457943923,
1246
+ "grad_norm": 1.16581392288208,
1247
+ "learning_rate": 5.496075301637393e-07,
1248
+ "loss": 0.2812,
1249
+ "step": 885
1250
+ },
1251
+ {
1252
+ "epoch": 2.7725856697819315,
1253
+ "grad_norm": 1.1972694396972656,
1254
+ "learning_rate": 4.826023169872512e-07,
1255
+ "loss": 0.2736,
1256
+ "step": 890
1257
+ },
1258
+ {
1259
+ "epoch": 2.7881619937694704,
1260
+ "grad_norm": 1.2056807279586792,
1261
+ "learning_rate": 4.1988481423528237e-07,
1262
+ "loss": 0.2846,
1263
+ "step": 895
1264
+ },
1265
+ {
1266
+ "epoch": 2.803738317757009,
1267
+ "grad_norm": 1.2468408346176147,
1268
+ "learning_rate": 3.61473545509392e-07,
1269
+ "loss": 0.2871,
1270
+ "step": 900
1271
+ },
1272
+ {
1273
+ "epoch": 2.8193146417445485,
1274
+ "grad_norm": 1.2749580144882202,
1275
+ "learning_rate": 3.073857625658022e-07,
1276
+ "loss": 0.2976,
1277
+ "step": 905
1278
+ },
1279
+ {
1280
+ "epoch": 2.8348909657320873,
1281
+ "grad_norm": 1.2277045249938965,
1282
+ "learning_rate": 2.576374402201015e-07,
1283
+ "loss": 0.3121,
1284
+ "step": 910
1285
+ },
1286
+ {
1287
+ "epoch": 2.850467289719626,
1288
+ "grad_norm": 1.199859380722046,
1289
+ "learning_rate": 2.1224327162907454e-07,
1290
+ "loss": 0.2733,
1291
+ "step": 915
1292
+ },
1293
+ {
1294
+ "epoch": 2.866043613707165,
1295
+ "grad_norm": 1.2017391920089722,
1296
+ "learning_rate": 1.7121666395109646e-07,
1297
+ "loss": 0.27,
1298
+ "step": 920
1299
+ },
1300
+ {
1301
+ "epoch": 2.881619937694704,
1302
+ "grad_norm": 1.1672242879867554,
1303
+ "learning_rate": 1.3456973438631892e-07,
1304
+ "loss": 0.275,
1305
+ "step": 925
1306
+ },
1307
+ {
1308
+ "epoch": 2.897196261682243,
1309
+ "grad_norm": 1.3370112180709839,
1310
+ "learning_rate": 1.0231330659786098e-07,
1311
+ "loss": 0.3118,
1312
+ "step": 930
1313
+ },
1314
+ {
1315
+ "epoch": 2.912772585669782,
1316
+ "grad_norm": 1.1771081686019897,
1317
+ "learning_rate": 7.44569075150514e-08,
1318
+ "loss": 0.2621,
1319
+ "step": 935
1320
+ },
1321
+ {
1322
+ "epoch": 2.9283489096573208,
1323
+ "grad_norm": 1.2882983684539795,
1324
+ "learning_rate": 5.100876451963443e-08,
1325
+ "loss": 0.2628,
1326
+ "step": 940
1327
+ },
1328
+ {
1329
+ "epoch": 2.94392523364486,
1330
+ "grad_norm": 1.250350832939148,
1331
+ "learning_rate": 3.197580301583014e-08,
1332
+ "loss": 0.2744,
1333
+ "step": 945
1334
+ },
1335
+ {
1336
+ "epoch": 2.959501557632399,
1337
+ "grad_norm": 1.3165779113769531,
1338
+ "learning_rate": 1.7363644384910672e-08,
1339
+ "loss": 0.2897,
1340
+ "step": 950
1341
+ },
1342
+ {
1343
+ "epoch": 2.9750778816199377,
1344
+ "grad_norm": 1.1710705757141113,
1345
+ "learning_rate": 7.176604324926617e-09,
1346
+ "loss": 0.3235,
1347
+ "step": 955
1348
+ },
1349
+ {
1350
+ "epoch": 2.9906542056074765,
1351
+ "grad_norm": 1.0860249996185303,
1352
+ "learning_rate": 1.417691576068303e-09,
1353
+ "loss": 0.2558,
1354
+ "step": 960
1355
+ },
1356
+ {
1357
+ "epoch": 3.0,
1358
+ "step": 963,
1359
+ "total_flos": 1.3800424090768507e+18,
1360
+ "train_loss": 0.5697189306420577,
1361
+ "train_runtime": 626.2457,
1362
+ "train_samples_per_second": 49.136,
1363
+ "train_steps_per_second": 1.538
1364
+ }
1365
+ ],
1366
+ "logging_steps": 5,
1367
+ "max_steps": 963,
1368
+ "num_input_tokens_seen": 0,
1369
+ "num_train_epochs": 3,
1370
+ "save_steps": 2000,
1371
+ "stateful_callbacks": {
1372
+ "TrainerControl": {
1373
+ "args": {
1374
+ "should_epoch_stop": false,
1375
+ "should_evaluate": false,
1376
+ "should_log": false,
1377
+ "should_save": false,
1378
+ "should_training_stop": false
1379
+ },
1380
+ "attributes": {}
1381
+ }
1382
+ },
1383
+ "total_flos": 1.3800424090768507e+18,
1384
+ "train_batch_size": 2,
1385
+ "trial_name": null,
1386
+ "trial_params": null
1387
+ }
33_128_e3_3e-5/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b048f0eab241c803b7d8e26971a1f5cffa68800e65ce1f4cfcbb1b75cca4ae46
3
+ size 8145
33_128_e3_3e-5/vocab.json ADDED
The diff for this file is too large to render. See raw diff