RayDu0010 commited on
Commit
6e27617
·
verified ·
1 Parent(s): c5fd0be

Upload folder using huggingface_hub

Browse files
45_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: 45_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
+ # 45_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
45_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
+ "v_proj",
28
+ "down_proj",
29
+ "k_proj",
30
+ "o_proj",
31
+ "up_proj",
32
+ "q_proj",
33
+ "gate_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
45_128_e3_3e-5/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:836d2378d50051d12ccd87801e8b0e3d7a0d82f0cc5ea97d7bac2b32fdec590d
3
+ size 791751704
45_128_e3_3e-5/all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.0916597908300104e+18,
4
+ "train_loss": 0.5215313880515278,
5
+ "train_runtime": 500.1586,
6
+ "train_samples": 8484,
7
+ "train_samples_per_second": 50.888,
8
+ "train_steps_per_second": 1.595
9
+ }
45_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
+ }
45_128_e3_3e-5/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
45_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
+ }
45_128_e3_3e-5/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
45_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
+ }
45_128_e3_3e-5/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.0916597908300104e+18,
4
+ "train_loss": 0.5215313880515278,
5
+ "train_runtime": 500.1586,
6
+ "train_samples": 8484,
7
+ "train_samples_per_second": 50.888,
8
+ "train_steps_per_second": 1.595
9
+ }
45_128_e3_3e-5/trainer_state.json ADDED
@@ -0,0 +1,1156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 798,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.018832391713747645,
14
+ "grad_norm": 1.0734755992889404,
15
+ "learning_rate": 3e-06,
16
+ "loss": 1.3646,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.03766478342749529,
21
+ "grad_norm": 0.7297686338424683,
22
+ "learning_rate": 6.750000000000001e-06,
23
+ "loss": 1.3246,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.05649717514124294,
28
+ "grad_norm": 0.6240422129631042,
29
+ "learning_rate": 1.05e-05,
30
+ "loss": 1.2719,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.07532956685499058,
35
+ "grad_norm": 0.5441795587539673,
36
+ "learning_rate": 1.4249999999999999e-05,
37
+ "loss": 1.2563,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.09416195856873823,
42
+ "grad_norm": 0.733296811580658,
43
+ "learning_rate": 1.8e-05,
44
+ "loss": 1.2723,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.11299435028248588,
49
+ "grad_norm": 0.5026394724845886,
50
+ "learning_rate": 2.175e-05,
51
+ "loss": 1.1914,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.1318267419962335,
56
+ "grad_norm": 0.527673602104187,
57
+ "learning_rate": 2.55e-05,
58
+ "loss": 1.2051,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.15065913370998116,
63
+ "grad_norm": 0.4926808774471283,
64
+ "learning_rate": 2.925e-05,
65
+ "loss": 1.1856,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.1694915254237288,
70
+ "grad_norm": 0.5903722047805786,
71
+ "learning_rate": 2.999793874067524e-05,
72
+ "loss": 1.1338,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.18832391713747645,
77
+ "grad_norm": 0.5489956736564636,
78
+ "learning_rate": 2.9989565845573844e-05,
79
+ "loss": 1.1138,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.2071563088512241,
84
+ "grad_norm": 0.5231617093086243,
85
+ "learning_rate": 2.9974756078739654e-05,
86
+ "loss": 1.1531,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.22598870056497175,
91
+ "grad_norm": 0.5471754670143127,
92
+ "learning_rate": 2.995351579983447e-05,
93
+ "loss": 1.0455,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.2448210922787194,
98
+ "grad_norm": 0.6348717212677002,
99
+ "learning_rate": 2.992585412993307e-05,
100
+ "loss": 1.1278,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.263653483992467,
105
+ "grad_norm": 0.6748208999633789,
106
+ "learning_rate": 2.989178294760638e-05,
107
+ "loss": 1.122,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.2824858757062147,
112
+ "grad_norm": 0.5450621843338013,
113
+ "learning_rate": 2.985131688382055e-05,
114
+ "loss": 1.0659,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.3013182674199623,
119
+ "grad_norm": 0.5509811639785767,
120
+ "learning_rate": 2.980447331565406e-05,
121
+ "loss": 1.0793,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.32015065913371,
126
+ "grad_norm": 0.6285695433616638,
127
+ "learning_rate": 2.97512723588356e-05,
128
+ "loss": 0.9792,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.3389830508474576,
133
+ "grad_norm": 0.6516168117523193,
134
+ "learning_rate": 2.9691736859105915e-05,
135
+ "loss": 1.002,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.3578154425612053,
140
+ "grad_norm": 0.6705228686332703,
141
+ "learning_rate": 2.962589238240729e-05,
142
+ "loss": 0.9748,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.3766478342749529,
147
+ "grad_norm": 0.6621777415275574,
148
+ "learning_rate": 2.9553767203904945e-05,
149
+ "loss": 0.945,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.3954802259887006,
154
+ "grad_norm": 0.6489184498786926,
155
+ "learning_rate": 2.9475392295845004e-05,
156
+ "loss": 0.9721,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.4143126177024482,
161
+ "grad_norm": 0.7519004344940186,
162
+ "learning_rate": 2.9390801314254295e-05,
163
+ "loss": 0.9584,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.4331450094161959,
168
+ "grad_norm": 0.6505439281463623,
169
+ "learning_rate": 2.9300030584487665e-05,
170
+ "loss": 0.9412,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.4519774011299435,
175
+ "grad_norm": 0.730772078037262,
176
+ "learning_rate": 2.9203119085629e-05,
177
+ "loss": 0.9337,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.4708097928436911,
182
+ "grad_norm": 0.7869782447814941,
183
+ "learning_rate": 2.910010843375271e-05,
184
+ "loss": 0.9408,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.4896421845574388,
189
+ "grad_norm": 0.7324037551879883,
190
+ "learning_rate": 2.8991042864052803e-05,
191
+ "loss": 0.8858,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.5084745762711864,
196
+ "grad_norm": 0.7512471675872803,
197
+ "learning_rate": 2.887596921184725e-05,
198
+ "loss": 0.9077,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.527306967984934,
203
+ "grad_norm": 0.8756352066993713,
204
+ "learning_rate": 2.87549368924658e-05,
205
+ "loss": 0.8662,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.5461393596986818,
210
+ "grad_norm": 0.989099383354187,
211
+ "learning_rate": 2.8627997880029878e-05,
212
+ "loss": 0.8667,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.5649717514124294,
217
+ "grad_norm": 0.797034740447998,
218
+ "learning_rate": 2.8495206685133676e-05,
219
+ "loss": 0.8353,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.583804143126177,
224
+ "grad_norm": 0.8909806609153748,
225
+ "learning_rate": 2.8356620331436027e-05,
226
+ "loss": 0.7804,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.6026365348399246,
231
+ "grad_norm": 0.8512744903564453,
232
+ "learning_rate": 2.8212298331173103e-05,
233
+ "loss": 0.8162,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.6214689265536724,
238
+ "grad_norm": 0.8743810057640076,
239
+ "learning_rate": 2.8062302659602455e-05,
240
+ "loss": 0.7879,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.64030131826742,
245
+ "grad_norm": 0.8847618103027344,
246
+ "learning_rate": 2.790669772838939e-05,
247
+ "loss": 0.7469,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.6591337099811676,
252
+ "grad_norm": 0.936867356300354,
253
+ "learning_rate": 2.774555035794709e-05,
254
+ "loss": 0.7628,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.6779661016949152,
259
+ "grad_norm": 0.8083466291427612,
260
+ "learning_rate": 2.757892974874236e-05,
261
+ "loss": 0.7237,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.696798493408663,
266
+ "grad_norm": 0.9002861976623535,
267
+ "learning_rate": 2.7406907451579298e-05,
268
+ "loss": 0.7291,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.7156308851224106,
273
+ "grad_norm": 0.9855697751045227,
274
+ "learning_rate": 2.7229557336873738e-05,
275
+ "loss": 0.7104,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.7344632768361582,
280
+ "grad_norm": 0.8617397546768188,
281
+ "learning_rate": 2.7046955562931514e-05,
282
+ "loss": 0.7495,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.7532956685499058,
287
+ "grad_norm": 0.8617110252380371,
288
+ "learning_rate": 2.685918054324434e-05,
289
+ "loss": 0.7172,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.7721280602636534,
294
+ "grad_norm": 0.939177930355072,
295
+ "learning_rate": 2.6666312912817174e-05,
296
+ "loss": 0.6232,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.7909604519774012,
301
+ "grad_norm": 0.8513920903205872,
302
+ "learning_rate": 2.6468435493541664e-05,
303
+ "loss": 0.7192,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.8097928436911488,
308
+ "grad_norm": 1.0072907209396362,
309
+ "learning_rate": 2.6265633258630514e-05,
310
+ "loss": 0.7151,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.8286252354048964,
315
+ "grad_norm": 1.0025373697280884,
316
+ "learning_rate": 2.605799329612794e-05,
317
+ "loss": 0.6186,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.847457627118644,
322
+ "grad_norm": 0.9493770003318787,
323
+ "learning_rate": 2.584560477151205e-05,
324
+ "loss": 0.6747,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 0.8662900188323918,
329
+ "grad_norm": 0.9953824281692505,
330
+ "learning_rate": 2.5628558889405085e-05,
331
+ "loss": 0.6703,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 0.8851224105461394,
336
+ "grad_norm": 1.0024815797805786,
337
+ "learning_rate": 2.5406948854408e-05,
338
+ "loss": 0.6315,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 0.903954802259887,
343
+ "grad_norm": 0.9452266693115234,
344
+ "learning_rate": 2.5180869831076246e-05,
345
+ "loss": 0.6719,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 0.9227871939736346,
350
+ "grad_norm": 1.2162435054779053,
351
+ "learning_rate": 2.495041890305385e-05,
352
+ "loss": 0.6241,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 0.9416195856873822,
357
+ "grad_norm": 1.0212266445159912,
358
+ "learning_rate": 2.4715695031383415e-05,
359
+ "loss": 0.6329,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 0.96045197740113,
364
+ "grad_norm": 0.9524599313735962,
365
+ "learning_rate": 2.4476799012009958e-05,
366
+ "loss": 0.6243,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 0.9792843691148776,
371
+ "grad_norm": 0.8733709454536438,
372
+ "learning_rate": 2.4233833432496712e-05,
373
+ "loss": 0.6464,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 0.9981167608286252,
378
+ "grad_norm": 1.0193301439285278,
379
+ "learning_rate": 2.3986902627971658e-05,
380
+ "loss": 0.6016,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 1.015065913370998,
385
+ "grad_norm": 1.3856611251831055,
386
+ "learning_rate": 2.3736112636323545e-05,
387
+ "loss": 0.5352,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 1.0338983050847457,
392
+ "grad_norm": 1.2353637218475342,
393
+ "learning_rate": 2.3481571152666748e-05,
394
+ "loss": 0.5454,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 1.0527306967984935,
399
+ "grad_norm": 1.0892200469970703,
400
+ "learning_rate": 2.322338748309444e-05,
401
+ "loss": 0.4742,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 1.0715630885122411,
406
+ "grad_norm": 0.9863163828849792,
407
+ "learning_rate": 2.2961672497740006e-05,
408
+ "loss": 0.4905,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 1.0903954802259888,
413
+ "grad_norm": 1.1391054391860962,
414
+ "learning_rate": 2.2696538583166764e-05,
415
+ "loss": 0.4708,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 1.1092278719397364,
420
+ "grad_norm": 1.1893314123153687,
421
+ "learning_rate": 2.2428099594106592e-05,
422
+ "loss": 0.5013,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 1.128060263653484,
427
+ "grad_norm": 1.170778751373291,
428
+ "learning_rate": 2.215647080456799e-05,
429
+ "loss": 0.5099,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 1.1468926553672316,
434
+ "grad_norm": 0.9944795966148376,
435
+ "learning_rate": 2.1881768858334715e-05,
436
+ "loss": 0.5225,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 1.1657250470809792,
441
+ "grad_norm": 1.006633996963501,
442
+ "learning_rate": 2.1604111718876214e-05,
443
+ "loss": 0.516,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 1.1845574387947269,
448
+ "grad_norm": 1.0187243223190308,
449
+ "learning_rate": 2.1323618618691336e-05,
450
+ "loss": 0.4551,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 1.2033898305084745,
455
+ "grad_norm": 1.1175583600997925,
456
+ "learning_rate": 2.1040410008107088e-05,
457
+ "loss": 0.4553,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 1.2222222222222223,
462
+ "grad_norm": 1.1109064817428589,
463
+ "learning_rate": 2.0754607503554445e-05,
464
+ "loss": 0.4886,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 1.24105461393597,
469
+ "grad_norm": 1.351647138595581,
470
+ "learning_rate": 2.0466333835343386e-05,
471
+ "loss": 0.4886,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 1.2598870056497176,
476
+ "grad_norm": 1.1731328964233398,
477
+ "learning_rate": 2.017571279495963e-05,
478
+ "loss": 0.461,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 1.2787193973634652,
483
+ "grad_norm": 1.0673614740371704,
484
+ "learning_rate": 1.9882869181905642e-05,
485
+ "loss": 0.4396,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 1.2975517890772128,
490
+ "grad_norm": 1.0351790189743042,
491
+ "learning_rate": 1.9587928750108816e-05,
492
+ "loss": 0.4401,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 1.3163841807909604,
497
+ "grad_norm": 1.1836857795715332,
498
+ "learning_rate": 1.9291018153919783e-05,
499
+ "loss": 0.4396,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 1.335216572504708,
504
+ "grad_norm": 1.4216283559799194,
505
+ "learning_rate": 1.8992264893724025e-05,
506
+ "loss": 0.4913,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 1.3540489642184557,
511
+ "grad_norm": 1.1144357919692993,
512
+ "learning_rate": 1.8691797261190278e-05,
513
+ "loss": 0.4531,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 1.3728813559322033,
518
+ "grad_norm": 1.3879287242889404,
519
+ "learning_rate": 1.8389744284179003e-05,
520
+ "loss": 0.4333,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 1.3917137476459511,
525
+ "grad_norm": 1.0819048881530762,
526
+ "learning_rate": 1.8086235671334833e-05,
527
+ "loss": 0.4316,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 1.4105461393596987,
532
+ "grad_norm": 1.2135930061340332,
533
+ "learning_rate": 1.7781401756386644e-05,
534
+ "loss": 0.3854,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 1.4293785310734464,
539
+ "grad_norm": 1.0153731107711792,
540
+ "learning_rate": 1.747537344217915e-05,
541
+ "loss": 0.3942,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 1.448210922787194,
546
+ "grad_norm": 1.1075345277786255,
547
+ "learning_rate": 1.716828214446017e-05,
548
+ "loss": 0.3991,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 1.4670433145009416,
553
+ "grad_norm": 1.036792278289795,
554
+ "learning_rate": 1.6860259735447632e-05,
555
+ "loss": 0.4385,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 1.4858757062146892,
560
+ "grad_norm": 1.2058098316192627,
561
+ "learning_rate": 1.6551438487200513e-05,
562
+ "loss": 0.4025,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 1.5047080979284368,
567
+ "grad_norm": 1.218522310256958,
568
+ "learning_rate": 1.624195101481813e-05,
569
+ "loss": 0.3973,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 1.5235404896421847,
574
+ "grad_norm": 1.1260173320770264,
575
+ "learning_rate": 1.59319302194921e-05,
576
+ "loss": 0.4723,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 1.542372881355932,
581
+ "grad_norm": 1.2498077154159546,
582
+ "learning_rate": 1.562150923143543e-05,
583
+ "loss": 0.3664,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 1.56120527306968,
588
+ "grad_norm": 1.2564117908477783,
589
+ "learning_rate": 1.5310821352713294e-05,
590
+ "loss": 0.4133,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 1.5800376647834273,
595
+ "grad_norm": 1.6053489446640015,
596
+ "learning_rate": 1.5e-05,
597
+ "loss": 0.4089,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 1.5988700564971752,
602
+ "grad_norm": 1.1478886604309082,
603
+ "learning_rate": 1.4689178647286703e-05,
604
+ "loss": 0.3783,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 1.6177024482109228,
609
+ "grad_norm": 1.1518490314483643,
610
+ "learning_rate": 1.4378490768564576e-05,
611
+ "loss": 0.4112,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 1.6365348399246704,
616
+ "grad_norm": 1.336392879486084,
617
+ "learning_rate": 1.4068069780507905e-05,
618
+ "loss": 0.3864,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 1.655367231638418,
623
+ "grad_norm": 1.1056026220321655,
624
+ "learning_rate": 1.3758048985181869e-05,
625
+ "loss": 0.4011,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 1.6741996233521657,
630
+ "grad_norm": 1.1735364198684692,
631
+ "learning_rate": 1.3448561512799491e-05,
632
+ "loss": 0.4017,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 1.6930320150659135,
637
+ "grad_norm": 1.2853727340698242,
638
+ "learning_rate": 1.3139740264552372e-05,
639
+ "loss": 0.4042,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 1.711864406779661,
644
+ "grad_norm": 1.3241996765136719,
645
+ "learning_rate": 1.283171785553983e-05,
646
+ "loss": 0.3632,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 1.7306967984934087,
651
+ "grad_norm": 1.2329045534133911,
652
+ "learning_rate": 1.2524626557820859e-05,
653
+ "loss": 0.3708,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 1.7495291902071564,
658
+ "grad_norm": 1.3574268817901611,
659
+ "learning_rate": 1.221859824361336e-05,
660
+ "loss": 0.3709,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 1.768361581920904,
665
+ "grad_norm": 1.0887680053710938,
666
+ "learning_rate": 1.1913764328665166e-05,
667
+ "loss": 0.3681,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 1.7871939736346516,
672
+ "grad_norm": 1.0611759424209595,
673
+ "learning_rate": 1.1610255715821006e-05,
674
+ "loss": 0.3496,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 1.8060263653483992,
679
+ "grad_norm": 1.1780134439468384,
680
+ "learning_rate": 1.1308202738809726e-05,
681
+ "loss": 0.3597,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 1.8248587570621468,
686
+ "grad_norm": 1.227927565574646,
687
+ "learning_rate": 1.1007735106275972e-05,
688
+ "loss": 0.3451,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 1.8436911487758945,
693
+ "grad_norm": 1.1551780700683594,
694
+ "learning_rate": 1.0708981846080227e-05,
695
+ "loss": 0.3828,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 1.8625235404896423,
700
+ "grad_norm": 1.1733975410461426,
701
+ "learning_rate": 1.0412071249891185e-05,
702
+ "loss": 0.3863,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 1.8813559322033897,
707
+ "grad_norm": 1.2903079986572266,
708
+ "learning_rate": 1.011713081809436e-05,
709
+ "loss": 0.335,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 1.9001883239171375,
714
+ "grad_norm": 1.3224095106124878,
715
+ "learning_rate": 9.824287205040372e-06,
716
+ "loss": 0.362,
717
+ "step": 505
718
+ },
719
+ {
720
+ "epoch": 1.9190207156308852,
721
+ "grad_norm": 1.0794068574905396,
722
+ "learning_rate": 9.533666164656614e-06,
723
+ "loss": 0.311,
724
+ "step": 510
725
+ },
726
+ {
727
+ "epoch": 1.9378531073446328,
728
+ "grad_norm": 1.2064406871795654,
729
+ "learning_rate": 9.245392496445554e-06,
730
+ "loss": 0.3274,
731
+ "step": 515
732
+ },
733
+ {
734
+ "epoch": 1.9566854990583804,
735
+ "grad_norm": 1.4218037128448486,
736
+ "learning_rate": 8.959589991892915e-06,
737
+ "loss": 0.3296,
738
+ "step": 520
739
+ },
740
+ {
741
+ "epoch": 1.975517890772128,
742
+ "grad_norm": 1.107397198677063,
743
+ "learning_rate": 8.676381381308668e-06,
744
+ "loss": 0.2827,
745
+ "step": 525
746
+ },
747
+ {
748
+ "epoch": 1.9943502824858759,
749
+ "grad_norm": 1.1499818563461304,
750
+ "learning_rate": 8.395888281123787e-06,
751
+ "loss": 0.335,
752
+ "step": 530
753
+ },
754
+ {
755
+ "epoch": 2.0112994350282487,
756
+ "grad_norm": 1.1968824863433838,
757
+ "learning_rate": 8.118231141665289e-06,
758
+ "loss": 0.3037,
759
+ "step": 535
760
+ },
761
+ {
762
+ "epoch": 2.030131826741996,
763
+ "grad_norm": 1.28793466091156,
764
+ "learning_rate": 7.84352919543201e-06,
765
+ "loss": 0.2503,
766
+ "step": 540
767
+ },
768
+ {
769
+ "epoch": 2.048964218455744,
770
+ "grad_norm": 1.106563925743103,
771
+ "learning_rate": 7.571900405893404e-06,
772
+ "loss": 0.2479,
773
+ "step": 545
774
+ },
775
+ {
776
+ "epoch": 2.0677966101694913,
777
+ "grad_norm": 1.1500860452651978,
778
+ "learning_rate": 7.3034614168332384e-06,
779
+ "loss": 0.271,
780
+ "step": 550
781
+ },
782
+ {
783
+ "epoch": 2.086629001883239,
784
+ "grad_norm": 1.2108525037765503,
785
+ "learning_rate": 7.038327502259999e-06,
786
+ "loss": 0.243,
787
+ "step": 555
788
+ },
789
+ {
790
+ "epoch": 2.105461393596987,
791
+ "grad_norm": 1.3466237783432007,
792
+ "learning_rate": 6.7766125169055576e-06,
793
+ "loss": 0.2907,
794
+ "step": 560
795
+ },
796
+ {
797
+ "epoch": 2.1242937853107344,
798
+ "grad_norm": 1.1116546392440796,
799
+ "learning_rate": 6.518428847333255e-06,
800
+ "loss": 0.2486,
801
+ "step": 565
802
+ },
803
+ {
804
+ "epoch": 2.1431261770244823,
805
+ "grad_norm": 1.0786916017532349,
806
+ "learning_rate": 6.263887363676457e-06,
807
+ "loss": 0.2756,
808
+ "step": 570
809
+ },
810
+ {
811
+ "epoch": 2.1619585687382297,
812
+ "grad_norm": 1.318480134010315,
813
+ "learning_rate": 6.013097372028343e-06,
814
+ "loss": 0.2536,
815
+ "step": 575
816
+ },
817
+ {
818
+ "epoch": 2.1807909604519775,
819
+ "grad_norm": 1.221173882484436,
820
+ "learning_rate": 5.7661665675032895e-06,
821
+ "loss": 0.2541,
822
+ "step": 580
823
+ },
824
+ {
825
+ "epoch": 2.199623352165725,
826
+ "grad_norm": 1.191026210784912,
827
+ "learning_rate": 5.523200987990041e-06,
828
+ "loss": 0.2494,
829
+ "step": 585
830
+ },
831
+ {
832
+ "epoch": 2.2184557438794728,
833
+ "grad_norm": 1.1432058811187744,
834
+ "learning_rate": 5.284304968616585e-06,
835
+ "loss": 0.2145,
836
+ "step": 590
837
+ },
838
+ {
839
+ "epoch": 2.23728813559322,
840
+ "grad_norm": 1.5543437004089355,
841
+ "learning_rate": 5.049581096946152e-06,
842
+ "loss": 0.264,
843
+ "step": 595
844
+ },
845
+ {
846
+ "epoch": 2.256120527306968,
847
+ "grad_norm": 1.0167546272277832,
848
+ "learning_rate": 4.8191301689237575e-06,
849
+ "loss": 0.259,
850
+ "step": 600
851
+ },
852
+ {
853
+ "epoch": 2.2749529190207154,
854
+ "grad_norm": 1.1914974451065063,
855
+ "learning_rate": 4.593051145592002e-06,
856
+ "loss": 0.2549,
857
+ "step": 605
858
+ },
859
+ {
860
+ "epoch": 2.2937853107344632,
861
+ "grad_norm": 1.4684791564941406,
862
+ "learning_rate": 4.3714411105949225e-06,
863
+ "loss": 0.2714,
864
+ "step": 610
865
+ },
866
+ {
867
+ "epoch": 2.312617702448211,
868
+ "grad_norm": 1.1496062278747559,
869
+ "learning_rate": 4.1543952284879524e-06,
870
+ "loss": 0.2669,
871
+ "step": 615
872
+ },
873
+ {
874
+ "epoch": 2.3314500941619585,
875
+ "grad_norm": 1.2566370964050293,
876
+ "learning_rate": 3.9420067038720644e-06,
877
+ "loss": 0.2826,
878
+ "step": 620
879
+ },
880
+ {
881
+ "epoch": 2.3502824858757063,
882
+ "grad_norm": 1.3730446100234985,
883
+ "learning_rate": 3.734366741369488e-06,
884
+ "loss": 0.2937,
885
+ "step": 625
886
+ },
887
+ {
888
+ "epoch": 2.3691148775894537,
889
+ "grad_norm": 1.1194416284561157,
890
+ "learning_rate": 3.531564506458336e-06,
891
+ "loss": 0.2507,
892
+ "step": 630
893
+ },
894
+ {
895
+ "epoch": 2.3879472693032016,
896
+ "grad_norm": 1.125894546508789,
897
+ "learning_rate": 3.3336870871828336e-06,
898
+ "loss": 0.2694,
899
+ "step": 635
900
+ },
901
+ {
902
+ "epoch": 2.406779661016949,
903
+ "grad_norm": 1.1157947778701782,
904
+ "learning_rate": 3.1408194567556626e-06,
905
+ "loss": 0.2728,
906
+ "step": 640
907
+ },
908
+ {
909
+ "epoch": 2.425612052730697,
910
+ "grad_norm": 1.0681735277175903,
911
+ "learning_rate": 2.9530444370684844e-06,
912
+ "loss": 0.2451,
913
+ "step": 645
914
+ },
915
+ {
916
+ "epoch": 2.4444444444444446,
917
+ "grad_norm": 1.311170220375061,
918
+ "learning_rate": 2.770442663126266e-06,
919
+ "loss": 0.2489,
920
+ "step": 650
921
+ },
922
+ {
923
+ "epoch": 2.463276836158192,
924
+ "grad_norm": 1.1938273906707764,
925
+ "learning_rate": 2.5930925484207012e-06,
926
+ "loss": 0.264,
927
+ "step": 655
928
+ },
929
+ {
930
+ "epoch": 2.48210922787194,
931
+ "grad_norm": 1.172761082649231,
932
+ "learning_rate": 2.421070251257641e-06,
933
+ "loss": 0.2237,
934
+ "step": 660
935
+ },
936
+ {
937
+ "epoch": 2.5009416195856873,
938
+ "grad_norm": 1.0871483087539673,
939
+ "learning_rate": 2.254449642052911e-06,
940
+ "loss": 0.2313,
941
+ "step": 665
942
+ },
943
+ {
944
+ "epoch": 2.519774011299435,
945
+ "grad_norm": 1.2270407676696777,
946
+ "learning_rate": 2.093302271610611e-06,
947
+ "loss": 0.2185,
948
+ "step": 670
949
+ },
950
+ {
951
+ "epoch": 2.5386064030131825,
952
+ "grad_norm": 1.2886481285095215,
953
+ "learning_rate": 1.937697340397546e-06,
954
+ "loss": 0.2595,
955
+ "step": 675
956
+ },
957
+ {
958
+ "epoch": 2.5574387947269304,
959
+ "grad_norm": 1.0732762813568115,
960
+ "learning_rate": 1.7877016688268977e-06,
961
+ "loss": 0.2324,
962
+ "step": 680
963
+ },
964
+ {
965
+ "epoch": 2.576271186440678,
966
+ "grad_norm": 1.3096768856048584,
967
+ "learning_rate": 1.6433796685639718e-06,
968
+ "loss": 0.2057,
969
+ "step": 685
970
+ },
971
+ {
972
+ "epoch": 2.5951035781544256,
973
+ "grad_norm": 1.1926066875457764,
974
+ "learning_rate": 1.504793314866323e-06,
975
+ "loss": 0.2634,
976
+ "step": 690
977
+ },
978
+ {
979
+ "epoch": 2.613935969868173,
980
+ "grad_norm": 1.1384515762329102,
981
+ "learning_rate": 1.372002119970125e-06,
982
+ "loss": 0.2605,
983
+ "step": 695
984
+ },
985
+ {
986
+ "epoch": 2.632768361581921,
987
+ "grad_norm": 1.1027590036392212,
988
+ "learning_rate": 1.2450631075342028e-06,
989
+ "loss": 0.2451,
990
+ "step": 700
991
+ },
992
+ {
993
+ "epoch": 2.6516007532956687,
994
+ "grad_norm": 1.2659372091293335,
995
+ "learning_rate": 1.1240307881527516e-06,
996
+ "loss": 0.2319,
997
+ "step": 705
998
+ },
999
+ {
1000
+ "epoch": 2.670433145009416,
1001
+ "grad_norm": 1.0542691946029663,
1002
+ "learning_rate": 1.0089571359471982e-06,
1003
+ "loss": 0.2183,
1004
+ "step": 710
1005
+ },
1006
+ {
1007
+ "epoch": 2.689265536723164,
1008
+ "grad_norm": 1.2748476266860962,
1009
+ "learning_rate": 8.998915662472906e-07,
1010
+ "loss": 0.2422,
1011
+ "step": 715
1012
+ },
1013
+ {
1014
+ "epoch": 2.7080979284369113,
1015
+ "grad_norm": 1.0726091861724854,
1016
+ "learning_rate": 7.968809143710026e-07,
1017
+ "loss": 0.2387,
1018
+ "step": 720
1019
+ },
1020
+ {
1021
+ "epoch": 2.726930320150659,
1022
+ "grad_norm": 1.2320191860198975,
1023
+ "learning_rate": 6.999694155123371e-07,
1024
+ "loss": 0.2474,
1025
+ "step": 725
1026
+ },
1027
+ {
1028
+ "epoch": 2.7457627118644066,
1029
+ "grad_norm": 1.1145159006118774,
1030
+ "learning_rate": 6.091986857457072e-07,
1031
+ "loss": 0.2428,
1032
+ "step": 730
1033
+ },
1034
+ {
1035
+ "epoch": 2.7645951035781544,
1036
+ "grad_norm": 1.1936031579971313,
1037
+ "learning_rate": 5.246077041549985e-07,
1038
+ "loss": 0.2145,
1039
+ "step": 735
1040
+ },
1041
+ {
1042
+ "epoch": 2.7834274952919023,
1043
+ "grad_norm": 1.0269960165023804,
1044
+ "learning_rate": 4.4623279609505687e-07,
1045
+ "loss": 0.2141,
1046
+ "step": 740
1047
+ },
1048
+ {
1049
+ "epoch": 2.8022598870056497,
1050
+ "grad_norm": 1.1695008277893066,
1051
+ "learning_rate": 3.741076175927094e-07,
1052
+ "loss": 0.2348,
1053
+ "step": 745
1054
+ },
1055
+ {
1056
+ "epoch": 2.8210922787193975,
1057
+ "grad_norm": 1.065690517425537,
1058
+ "learning_rate": 3.082631408940839e-07,
1059
+ "loss": 0.21,
1060
+ "step": 750
1061
+ },
1062
+ {
1063
+ "epoch": 2.839924670433145,
1064
+ "grad_norm": 1.0519464015960693,
1065
+ "learning_rate": 2.487276411643996e-07,
1066
+ "loss": 0.2332,
1067
+ "step": 755
1068
+ },
1069
+ {
1070
+ "epoch": 2.8587570621468927,
1071
+ "grad_norm": 1.259289264678955,
1072
+ "learning_rate": 1.9552668434594135e-07,
1073
+ "loss": 0.2533,
1074
+ "step": 760
1075
+ },
1076
+ {
1077
+ "epoch": 2.87758945386064,
1078
+ "grad_norm": 1.1110637187957764,
1079
+ "learning_rate": 1.4868311617944997e-07,
1080
+ "loss": 0.2112,
1081
+ "step": 765
1082
+ },
1083
+ {
1084
+ "epoch": 2.896421845574388,
1085
+ "grad_norm": 1.0146106481552124,
1086
+ "learning_rate": 1.082170523936199e-07,
1087
+ "loss": 0.2466,
1088
+ "step": 770
1089
+ },
1090
+ {
1091
+ "epoch": 2.915254237288136,
1092
+ "grad_norm": 1.0824241638183594,
1093
+ "learning_rate": 7.414587006693064e-08,
1094
+ "loss": 0.2281,
1095
+ "step": 775
1096
+ },
1097
+ {
1098
+ "epoch": 2.934086629001883,
1099
+ "grad_norm": 1.0280976295471191,
1100
+ "learning_rate": 4.648420016553245e-08,
1101
+ "loss": 0.2626,
1102
+ "step": 780
1103
+ },
1104
+ {
1105
+ "epoch": 2.9529190207156306,
1106
+ "grad_norm": 1.2150380611419678,
1107
+ "learning_rate": 2.5243921260348913e-08,
1108
+ "loss": 0.2348,
1109
+ "step": 785
1110
+ },
1111
+ {
1112
+ "epoch": 2.9717514124293785,
1113
+ "grad_norm": 1.143435001373291,
1114
+ "learning_rate": 1.0434154426155473e-08,
1115
+ "loss": 0.2279,
1116
+ "step": 790
1117
+ },
1118
+ {
1119
+ "epoch": 2.9905838041431263,
1120
+ "grad_norm": 1.232460856437683,
1121
+ "learning_rate": 2.061259324762643e-09,
1122
+ "loss": 0.2322,
1123
+ "step": 795
1124
+ },
1125
+ {
1126
+ "epoch": 3.0,
1127
+ "step": 798,
1128
+ "total_flos": 1.0916597908300104e+18,
1129
+ "train_loss": 0.5215313880515278,
1130
+ "train_runtime": 500.1586,
1131
+ "train_samples_per_second": 50.888,
1132
+ "train_steps_per_second": 1.595
1133
+ }
1134
+ ],
1135
+ "logging_steps": 5,
1136
+ "max_steps": 798,
1137
+ "num_input_tokens_seen": 0,
1138
+ "num_train_epochs": 3,
1139
+ "save_steps": 2000,
1140
+ "stateful_callbacks": {
1141
+ "TrainerControl": {
1142
+ "args": {
1143
+ "should_epoch_stop": false,
1144
+ "should_evaluate": false,
1145
+ "should_log": false,
1146
+ "should_save": false,
1147
+ "should_training_stop": false
1148
+ },
1149
+ "attributes": {}
1150
+ }
1151
+ },
1152
+ "total_flos": 1.0916597908300104e+18,
1153
+ "train_batch_size": 2,
1154
+ "trial_name": null,
1155
+ "trial_params": null
1156
+ }
45_128_e3_3e-5/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f52bee8c8e5dd67e0e4a946c809ca5513a644f52a0e05ca707e3988b9e30477
3
+ size 8145
45_128_e3_3e-5/vocab.json ADDED
The diff for this file is too large to render. See raw diff