RayDu0010 commited on
Commit
bdef590
·
verified ·
1 Parent(s): 51ab1ab

Upload folder using huggingface_hub

Browse files
48_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: 48_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
+ # 48_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
48_128_e3_3e-5/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "ibm-granite/granite-3.3-8b-base",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 256,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 128,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "k_proj",
28
+ "up_proj",
29
+ "gate_proj",
30
+ "v_proj",
31
+ "q_proj",
32
+ "o_proj",
33
+ "down_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
48_128_e3_3e-5/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b956c0cb43ba9e01f0197219dd6b9439666222d8319d202fb60cbdab0c6dc478
3
+ size 791751704
48_128_e3_3e-5/all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.273900111881044e+18,
4
+ "train_loss": 0.571772654588991,
5
+ "train_runtime": 581.8624,
6
+ "train_samples": 9666,
7
+ "train_samples_per_second": 49.837,
8
+ "train_steps_per_second": 1.562
9
+ }
48_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
+ }
48_128_e3_3e-5/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
48_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
+ }
48_128_e3_3e-5/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
48_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
+ }
48_128_e3_3e-5/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.273900111881044e+18,
4
+ "train_loss": 0.571772654588991,
5
+ "train_runtime": 581.8624,
6
+ "train_samples": 9666,
7
+ "train_samples_per_second": 49.837,
8
+ "train_steps_per_second": 1.562
9
+ }
48_128_e3_3e-5/trainer_state.json ADDED
@@ -0,0 +1,1310 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 909,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.01652892561983471,
14
+ "grad_norm": 1.3831015825271606,
15
+ "learning_rate": 2.6086956521739132e-06,
16
+ "loss": 1.3336,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.03305785123966942,
21
+ "grad_norm": 0.7098184823989868,
22
+ "learning_rate": 5.869565217391305e-06,
23
+ "loss": 1.3505,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.049586776859504134,
28
+ "grad_norm": 0.6232060194015503,
29
+ "learning_rate": 9.130434782608697e-06,
30
+ "loss": 1.3319,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.06611570247933884,
35
+ "grad_norm": 0.6442826390266418,
36
+ "learning_rate": 1.2391304347826088e-05,
37
+ "loss": 1.2733,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.08264462809917356,
42
+ "grad_norm": 0.5439983010292053,
43
+ "learning_rate": 1.5652173913043477e-05,
44
+ "loss": 1.3119,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.09917355371900827,
49
+ "grad_norm": 0.5362527370452881,
50
+ "learning_rate": 1.891304347826087e-05,
51
+ "loss": 1.2365,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.11570247933884298,
56
+ "grad_norm": 0.5195441246032715,
57
+ "learning_rate": 2.217391304347826e-05,
58
+ "loss": 1.2603,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.1322314049586777,
63
+ "grad_norm": 0.5031000375747681,
64
+ "learning_rate": 2.5434782608695653e-05,
65
+ "loss": 1.2659,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.1487603305785124,
70
+ "grad_norm": 0.4853697419166565,
71
+ "learning_rate": 2.8695652173913044e-05,
72
+ "loss": 1.248,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.1652892561983471,
77
+ "grad_norm": 0.4460432529449463,
78
+ "learning_rate": 2.999910550563221e-05,
79
+ "loss": 1.175,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.18181818181818182,
84
+ "grad_norm": 0.488101601600647,
85
+ "learning_rate": 2.9993639537498208e-05,
86
+ "loss": 1.1665,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.19834710743801653,
91
+ "grad_norm": 0.6104041934013367,
92
+ "learning_rate": 2.9983206351162094e-05,
93
+ "loss": 1.1775,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.21487603305785125,
98
+ "grad_norm": 0.49601423740386963,
99
+ "learning_rate": 2.9967809403017022e-05,
100
+ "loss": 1.1435,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.23140495867768596,
105
+ "grad_norm": 0.5215215086936951,
106
+ "learning_rate": 2.9947453793892644e-05,
107
+ "loss": 1.18,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.24793388429752067,
112
+ "grad_norm": 0.6732470393180847,
113
+ "learning_rate": 2.992214626736525e-05,
114
+ "loss": 1.107,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.2644628099173554,
119
+ "grad_norm": 0.4841562509536743,
120
+ "learning_rate": 2.9891895207523713e-05,
121
+ "loss": 1.0892,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.2809917355371901,
126
+ "grad_norm": 0.5512502789497375,
127
+ "learning_rate": 2.985671063619194e-05,
128
+ "loss": 1.0827,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.2975206611570248,
133
+ "grad_norm": 0.6520716547966003,
134
+ "learning_rate": 2.9816604209608744e-05,
135
+ "loss": 1.0575,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.3140495867768595,
140
+ "grad_norm": 0.5574434995651245,
141
+ "learning_rate": 2.9771589214566274e-05,
142
+ "loss": 1.0648,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.3305785123966942,
147
+ "grad_norm": 0.5233076810836792,
148
+ "learning_rate": 2.9721680564008264e-05,
149
+ "loss": 1.0955,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.34710743801652894,
154
+ "grad_norm": 0.6986305117607117,
155
+ "learning_rate": 2.9666894792089538e-05,
156
+ "loss": 1.0185,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.36363636363636365,
161
+ "grad_norm": 0.628684401512146,
162
+ "learning_rate": 2.9607250048698438e-05,
163
+ "loss": 1.0259,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.38016528925619836,
168
+ "grad_norm": 0.5662065744400024,
169
+ "learning_rate": 2.954276609344399e-05,
170
+ "loss": 1.0174,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.39669421487603307,
175
+ "grad_norm": 0.6545687317848206,
176
+ "learning_rate": 2.9473464289109746e-05,
177
+ "loss": 0.9881,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.4132231404958678,
182
+ "grad_norm": 0.6962680220603943,
183
+ "learning_rate": 2.9399367594576588e-05,
184
+ "loss": 0.9667,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.4297520661157025,
189
+ "grad_norm": 0.6917610168457031,
190
+ "learning_rate": 2.9320500557216672e-05,
191
+ "loss": 1.0016,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.4462809917355372,
196
+ "grad_norm": 0.6968785524368286,
197
+ "learning_rate": 2.92368893047612e-05,
198
+ "loss": 1.0067,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.4628099173553719,
203
+ "grad_norm": 0.690639078617096,
204
+ "learning_rate": 2.914856153664459e-05,
205
+ "loss": 0.9132,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.4793388429752066,
210
+ "grad_norm": 0.734661877155304,
211
+ "learning_rate": 2.905554651482798e-05,
212
+ "loss": 0.9474,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.49586776859504134,
217
+ "grad_norm": 0.7354484796524048,
218
+ "learning_rate": 2.8957875054105098e-05,
219
+ "loss": 0.9368,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.512396694214876,
224
+ "grad_norm": 0.7630740404129028,
225
+ "learning_rate": 2.8855579511893653e-05,
226
+ "loss": 0.9324,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.5289256198347108,
231
+ "grad_norm": 0.7361947894096375,
232
+ "learning_rate": 2.874869377751571e-05,
233
+ "loss": 0.905,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.5454545454545454,
238
+ "grad_norm": 0.704692542552948,
239
+ "learning_rate": 2.863725326097056e-05,
240
+ "loss": 0.9494,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.5619834710743802,
245
+ "grad_norm": 0.8412842154502869,
246
+ "learning_rate": 2.8521294881203792e-05,
247
+ "loss": 0.868,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.5785123966942148,
252
+ "grad_norm": 0.863633930683136,
253
+ "learning_rate": 2.840085705387647e-05,
254
+ "loss": 0.8822,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.5950413223140496,
259
+ "grad_norm": 0.8332576751708984,
260
+ "learning_rate": 2.8275979678638485e-05,
261
+ "loss": 0.8624,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.6115702479338843,
266
+ "grad_norm": 0.8531330823898315,
267
+ "learning_rate": 2.814670412591026e-05,
268
+ "loss": 0.8288,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.628099173553719,
273
+ "grad_norm": 0.9115040898323059,
274
+ "learning_rate": 2.8013073223177207e-05,
275
+ "loss": 0.8904,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.6446280991735537,
280
+ "grad_norm": 0.8175347447395325,
281
+ "learning_rate": 2.7875131240801494e-05,
282
+ "loss": 0.8584,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.6611570247933884,
287
+ "grad_norm": 0.8207992315292358,
288
+ "learning_rate": 2.7732923877355764e-05,
289
+ "loss": 0.8296,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.6776859504132231,
294
+ "grad_norm": 0.9442360997200012,
295
+ "learning_rate": 2.7586498244483746e-05,
296
+ "loss": 0.8551,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.6942148760330579,
301
+ "grad_norm": 0.8399072885513306,
302
+ "learning_rate": 2.7435902851292735e-05,
303
+ "loss": 0.8044,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.7107438016528925,
308
+ "grad_norm": 0.8840962648391724,
309
+ "learning_rate": 2.7281187588283047e-05,
310
+ "loss": 0.8239,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.7272727272727273,
315
+ "grad_norm": 0.9720616936683655,
316
+ "learning_rate": 2.712240371081991e-05,
317
+ "loss": 0.797,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.743801652892562,
322
+ "grad_norm": 0.922126293182373,
323
+ "learning_rate": 2.6959603822153147e-05,
324
+ "loss": 0.763,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 0.7603305785123967,
329
+ "grad_norm": 1.0185389518737793,
330
+ "learning_rate": 2.6792841855990325e-05,
331
+ "loss": 0.7521,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 0.7768595041322314,
336
+ "grad_norm": 1.1431677341461182,
337
+ "learning_rate": 2.6622173058629178e-05,
338
+ "loss": 0.7847,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 0.7933884297520661,
343
+ "grad_norm": 0.9715793132781982,
344
+ "learning_rate": 2.644765397065509e-05,
345
+ "loss": 0.7447,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 0.8099173553719008,
350
+ "grad_norm": 1.0262930393218994,
351
+ "learning_rate": 2.626934240820993e-05,
352
+ "loss": 0.7593,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 0.8264462809917356,
357
+ "grad_norm": 0.9361246824264526,
358
+ "learning_rate": 2.608729744383817e-05,
359
+ "loss": 0.7346,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 0.8429752066115702,
364
+ "grad_norm": 1.1547300815582275,
365
+ "learning_rate": 2.590157938691691e-05,
366
+ "loss": 0.7273,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 0.859504132231405,
371
+ "grad_norm": 1.0726925134658813,
372
+ "learning_rate": 2.5712249763676003e-05,
373
+ "loss": 0.7315,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 0.8760330578512396,
378
+ "grad_norm": 1.0144833326339722,
379
+ "learning_rate": 2.5519371296815197e-05,
380
+ "loss": 0.6952,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 0.8925619834710744,
385
+ "grad_norm": 1.1299502849578857,
386
+ "learning_rate": 2.532300788472481e-05,
387
+ "loss": 0.7149,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 0.9090909090909091,
392
+ "grad_norm": 1.034497618675232,
393
+ "learning_rate": 2.512322458031693e-05,
394
+ "loss": 0.6787,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 0.9256198347107438,
399
+ "grad_norm": 1.2203060388565063,
400
+ "learning_rate": 2.4920087569474145e-05,
401
+ "loss": 0.709,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 0.9421487603305785,
406
+ "grad_norm": 0.9873307347297668,
407
+ "learning_rate": 2.4713664149122964e-05,
408
+ "loss": 0.7434,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 0.9586776859504132,
413
+ "grad_norm": 1.0340741872787476,
414
+ "learning_rate": 2.4504022704939075e-05,
415
+ "loss": 0.662,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 0.9752066115702479,
420
+ "grad_norm": 1.0096772909164429,
421
+ "learning_rate": 2.4291232688691996e-05,
422
+ "loss": 0.6921,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 0.9917355371900827,
427
+ "grad_norm": 1.0512659549713135,
428
+ "learning_rate": 2.4075364595236515e-05,
429
+ "loss": 0.716,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 1.006611570247934,
434
+ "grad_norm": 1.0512038469314575,
435
+ "learning_rate": 2.3856489939158566e-05,
436
+ "loss": 0.7193,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 1.0231404958677686,
441
+ "grad_norm": 1.073168396949768,
442
+ "learning_rate": 2.363468123108326e-05,
443
+ "loss": 0.547,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 1.0396694214876032,
448
+ "grad_norm": 1.0484970808029175,
449
+ "learning_rate": 2.341001195365298e-05,
450
+ "loss": 0.5766,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 1.056198347107438,
455
+ "grad_norm": 1.3234968185424805,
456
+ "learning_rate": 2.3182556537183437e-05,
457
+ "loss": 0.5844,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 1.0727272727272728,
462
+ "grad_norm": 1.0770665407180786,
463
+ "learning_rate": 2.2952390335005742e-05,
464
+ "loss": 0.5496,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 1.0892561983471074,
469
+ "grad_norm": 1.1759930849075317,
470
+ "learning_rate": 2.2719589598502776e-05,
471
+ "loss": 0.5549,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 1.105785123966942,
476
+ "grad_norm": 1.1473444700241089,
477
+ "learning_rate": 2.2484231451847952e-05,
478
+ "loss": 0.5656,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 1.122314049586777,
483
+ "grad_norm": 1.1218301057815552,
484
+ "learning_rate": 2.2246393866454893e-05,
485
+ "loss": 0.5663,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 1.1388429752066116,
490
+ "grad_norm": 1.324342966079712,
491
+ "learning_rate": 2.2006155635146398e-05,
492
+ "loss": 0.5479,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 1.1553719008264463,
497
+ "grad_norm": 1.2391122579574585,
498
+ "learning_rate": 2.176359634605132e-05,
499
+ "loss": 0.5655,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 1.171900826446281,
504
+ "grad_norm": 0.9759783148765564,
505
+ "learning_rate": 2.151879635623793e-05,
506
+ "loss": 0.5415,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 1.1884297520661158,
511
+ "grad_norm": 1.1686252355575562,
512
+ "learning_rate": 2.1271836765092552e-05,
513
+ "loss": 0.5068,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 1.2049586776859504,
518
+ "grad_norm": 1.2139272689819336,
519
+ "learning_rate": 2.1022799387452276e-05,
520
+ "loss": 0.5295,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 1.221487603305785,
525
+ "grad_norm": 1.2539520263671875,
526
+ "learning_rate": 2.0771766726500698e-05,
527
+ "loss": 0.5389,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 1.2380165289256198,
532
+ "grad_norm": 1.1020694971084595,
533
+ "learning_rate": 2.05188219464355e-05,
534
+ "loss": 0.5341,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 1.2545454545454544,
539
+ "grad_norm": 1.029186487197876,
540
+ "learning_rate": 2.0264048844917204e-05,
541
+ "loss": 0.5168,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 1.2710743801652893,
546
+ "grad_norm": 1.19265878200531,
547
+ "learning_rate": 2.000753182530791e-05,
548
+ "loss": 0.5223,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 1.287603305785124,
553
+ "grad_norm": 1.1817671060562134,
554
+ "learning_rate": 1.9749355868709497e-05,
555
+ "loss": 0.512,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 1.3041322314049586,
560
+ "grad_norm": 1.246814489364624,
561
+ "learning_rate": 1.948960650581034e-05,
562
+ "loss": 0.5491,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 1.3206611570247935,
567
+ "grad_norm": 1.4044491052627563,
568
+ "learning_rate": 1.9228369788550004e-05,
569
+ "loss": 0.5321,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 1.3371900826446281,
574
+ "grad_norm": 1.1388851404190063,
575
+ "learning_rate": 1.8965732261611246e-05,
576
+ "loss": 0.5175,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 1.3537190082644628,
581
+ "grad_norm": 1.1884291172027588,
582
+ "learning_rate": 1.870178093374875e-05,
583
+ "loss": 0.5522,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 1.3702479338842974,
588
+ "grad_norm": 1.1615290641784668,
589
+ "learning_rate": 1.843660324896415e-05,
590
+ "loss": 0.483,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 1.386776859504132,
595
+ "grad_norm": 1.1628854274749756,
596
+ "learning_rate": 1.817028705753685e-05,
597
+ "loss": 0.4992,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 1.403305785123967,
602
+ "grad_norm": 1.163860559463501,
603
+ "learning_rate": 1.7902920586920248e-05,
604
+ "loss": 0.4997,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 1.4198347107438016,
609
+ "grad_norm": 1.249915361404419,
610
+ "learning_rate": 1.7634592412513008e-05,
611
+ "loss": 0.4936,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 1.4363636363636363,
616
+ "grad_norm": 1.1150130033493042,
617
+ "learning_rate": 1.7365391428315068e-05,
618
+ "loss": 0.4403,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 1.4528925619834712,
623
+ "grad_norm": 1.2004356384277344,
624
+ "learning_rate": 1.7095406817478083e-05,
625
+ "loss": 0.5046,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 1.4694214876033058,
630
+ "grad_norm": 1.265571117401123,
631
+ "learning_rate": 1.6824728022760085e-05,
632
+ "loss": 0.4732,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 1.4859504132231405,
637
+ "grad_norm": 1.3377974033355713,
638
+ "learning_rate": 1.6553444716894155e-05,
639
+ "loss": 0.4405,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 1.5024793388429751,
644
+ "grad_norm": 1.2106013298034668,
645
+ "learning_rate": 1.628164677288086e-05,
646
+ "loss": 0.4906,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 1.5190082644628098,
651
+ "grad_norm": 1.2407844066619873,
652
+ "learning_rate": 1.600942423421442e-05,
653
+ "loss": 0.4584,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 1.5355371900826447,
658
+ "grad_norm": 1.1791411638259888,
659
+ "learning_rate": 1.573686728505229e-05,
660
+ "loss": 0.4661,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 1.5520661157024793,
665
+ "grad_norm": 1.275108814239502,
666
+ "learning_rate": 1.5464066220338247e-05,
667
+ "loss": 0.4865,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 1.5685950413223142,
672
+ "grad_norm": 1.1702497005462646,
673
+ "learning_rate": 1.5191111415888718e-05,
674
+ "loss": 0.4755,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 1.5851239669421489,
679
+ "grad_norm": 1.5265661478042603,
680
+ "learning_rate": 1.4918093298452279e-05,
681
+ "loss": 0.4614,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 1.6016528925619835,
686
+ "grad_norm": 1.2412056922912598,
687
+ "learning_rate": 1.464510231575239e-05,
688
+ "loss": 0.4653,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 1.6181818181818182,
693
+ "grad_norm": 1.3541052341461182,
694
+ "learning_rate": 1.4372228906523086e-05,
695
+ "loss": 0.4012,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 1.6347107438016528,
700
+ "grad_norm": 1.1902379989624023,
701
+ "learning_rate": 1.4099563470547673e-05,
702
+ "loss": 0.444,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 1.6512396694214875,
707
+ "grad_norm": 1.2285325527191162,
708
+ "learning_rate": 1.382719633871034e-05,
709
+ "loss": 0.4585,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 1.6677685950413224,
714
+ "grad_norm": 1.4228185415267944,
715
+ "learning_rate": 1.3555217743070593e-05,
716
+ "loss": 0.4272,
717
+ "step": 505
718
+ },
719
+ {
720
+ "epoch": 1.684297520661157,
721
+ "grad_norm": 1.268658995628357,
722
+ "learning_rate": 1.3283717786970421e-05,
723
+ "loss": 0.3885,
724
+ "step": 510
725
+ },
726
+ {
727
+ "epoch": 1.7008264462809919,
728
+ "grad_norm": 1.2212035655975342,
729
+ "learning_rate": 1.3012786415184087e-05,
730
+ "loss": 0.4023,
731
+ "step": 515
732
+ },
733
+ {
734
+ "epoch": 1.7173553719008265,
735
+ "grad_norm": 1.1776573657989502,
736
+ "learning_rate": 1.2742513384120528e-05,
737
+ "loss": 0.4295,
738
+ "step": 520
739
+ },
740
+ {
741
+ "epoch": 1.7338842975206612,
742
+ "grad_norm": 1.295913815498352,
743
+ "learning_rate": 1.2472988232088027e-05,
744
+ "loss": 0.4626,
745
+ "step": 525
746
+ },
747
+ {
748
+ "epoch": 1.7504132231404959,
749
+ "grad_norm": 1.1968791484832764,
750
+ "learning_rate": 1.2204300249631276e-05,
751
+ "loss": 0.4138,
752
+ "step": 530
753
+ },
754
+ {
755
+ "epoch": 1.7669421487603305,
756
+ "grad_norm": 1.395003318786621,
757
+ "learning_rate": 1.193653844995042e-05,
758
+ "loss": 0.4174,
759
+ "step": 535
760
+ },
761
+ {
762
+ "epoch": 1.7834710743801652,
763
+ "grad_norm": 1.2571361064910889,
764
+ "learning_rate": 1.166979153941205e-05,
765
+ "loss": 0.4136,
766
+ "step": 540
767
+ },
768
+ {
769
+ "epoch": 1.8,
770
+ "grad_norm": 1.2398642301559448,
771
+ "learning_rate": 1.1404147888161787e-05,
772
+ "loss": 0.3862,
773
+ "step": 545
774
+ },
775
+ {
776
+ "epoch": 1.8165289256198347,
777
+ "grad_norm": 1.38470458984375,
778
+ "learning_rate": 1.1139695500848289e-05,
779
+ "loss": 0.4012,
780
+ "step": 550
781
+ },
782
+ {
783
+ "epoch": 1.8330578512396696,
784
+ "grad_norm": 1.3475830554962158,
785
+ "learning_rate": 1.0876521987468375e-05,
786
+ "loss": 0.4093,
787
+ "step": 555
788
+ },
789
+ {
790
+ "epoch": 1.8495867768595042,
791
+ "grad_norm": 1.2676841020584106,
792
+ "learning_rate": 1.061471453434278e-05,
793
+ "loss": 0.4011,
794
+ "step": 560
795
+ },
796
+ {
797
+ "epoch": 1.866115702479339,
798
+ "grad_norm": 1.324524164199829,
799
+ "learning_rate": 1.0354359875232404e-05,
800
+ "loss": 0.4045,
801
+ "step": 565
802
+ },
803
+ {
804
+ "epoch": 1.8826446280991735,
805
+ "grad_norm": 1.2812235355377197,
806
+ "learning_rate": 1.0095544262604409e-05,
807
+ "loss": 0.3747,
808
+ "step": 570
809
+ },
810
+ {
811
+ "epoch": 1.8991735537190082,
812
+ "grad_norm": 1.3111671209335327,
813
+ "learning_rate": 9.838353439057763e-06,
814
+ "loss": 0.3689,
815
+ "step": 575
816
+ },
817
+ {
818
+ "epoch": 1.9157024793388429,
819
+ "grad_norm": 1.297474980354309,
820
+ "learning_rate": 9.582872608917738e-06,
821
+ "loss": 0.4218,
822
+ "step": 580
823
+ },
824
+ {
825
+ "epoch": 1.9322314049586777,
826
+ "grad_norm": 1.283281683921814,
827
+ "learning_rate": 9.3291864100087e-06,
828
+ "loss": 0.3647,
829
+ "step": 585
830
+ },
831
+ {
832
+ "epoch": 1.9487603305785124,
833
+ "grad_norm": 1.2572720050811768,
834
+ "learning_rate": 9.077378885614589e-06,
835
+ "loss": 0.3772,
836
+ "step": 590
837
+ },
838
+ {
839
+ "epoch": 1.9652892561983473,
840
+ "grad_norm": 1.2468287944793701,
841
+ "learning_rate": 8.827533456636326e-06,
842
+ "loss": 0.3794,
843
+ "step": 595
844
+ },
845
+ {
846
+ "epoch": 1.981818181818182,
847
+ "grad_norm": 1.250914216041565,
848
+ "learning_rate": 8.579732893955506e-06,
849
+ "loss": 0.3579,
850
+ "step": 600
851
+ },
852
+ {
853
+ "epoch": 1.9983471074380166,
854
+ "grad_norm": 1.2372207641601562,
855
+ "learning_rate": 8.334059291013297e-06,
856
+ "loss": 0.3954,
857
+ "step": 605
858
+ },
859
+ {
860
+ "epoch": 2.013223140495868,
861
+ "grad_norm": 1.3838112354278564,
862
+ "learning_rate": 8.09059403661389e-06,
863
+ "loss": 0.3406,
864
+ "step": 610
865
+ },
866
+ {
867
+ "epoch": 2.0297520661157025,
868
+ "grad_norm": 1.3364596366882324,
869
+ "learning_rate": 7.849417787961301e-06,
870
+ "loss": 0.328,
871
+ "step": 615
872
+ },
873
+ {
874
+ "epoch": 2.046280991735537,
875
+ "grad_norm": 1.2164885997772217,
876
+ "learning_rate": 7.610610443938613e-06,
877
+ "loss": 0.3243,
878
+ "step": 620
879
+ },
880
+ {
881
+ "epoch": 2.062809917355372,
882
+ "grad_norm": 1.371264934539795,
883
+ "learning_rate": 7.374251118638359e-06,
884
+ "loss": 0.2965,
885
+ "step": 625
886
+ },
887
+ {
888
+ "epoch": 2.0793388429752064,
889
+ "grad_norm": 1.362658143043518,
890
+ "learning_rate": 7.140418115153002e-06,
891
+ "loss": 0.2769,
892
+ "step": 630
893
+ },
894
+ {
895
+ "epoch": 2.0958677685950415,
896
+ "grad_norm": 1.2558574676513672,
897
+ "learning_rate": 6.90918889963399e-06,
898
+ "loss": 0.3218,
899
+ "step": 635
900
+ },
901
+ {
902
+ "epoch": 2.112396694214876,
903
+ "grad_norm": 1.3430614471435547,
904
+ "learning_rate": 6.680640075628127e-06,
905
+ "loss": 0.2896,
906
+ "step": 640
907
+ },
908
+ {
909
+ "epoch": 2.128925619834711,
910
+ "grad_norm": 1.3200640678405762,
911
+ "learning_rate": 6.454847358699728e-06,
912
+ "loss": 0.303,
913
+ "step": 645
914
+ },
915
+ {
916
+ "epoch": 2.1454545454545455,
917
+ "grad_norm": 1.313966155052185,
918
+ "learning_rate": 6.231885551346929e-06,
919
+ "loss": 0.3082,
920
+ "step": 650
921
+ },
922
+ {
923
+ "epoch": 2.16198347107438,
924
+ "grad_norm": 1.317543864250183,
925
+ "learning_rate": 6.011828518220467e-06,
926
+ "loss": 0.2737,
927
+ "step": 655
928
+ },
929
+ {
930
+ "epoch": 2.178512396694215,
931
+ "grad_norm": 1.511826992034912,
932
+ "learning_rate": 5.794749161653201e-06,
933
+ "loss": 0.316,
934
+ "step": 660
935
+ },
936
+ {
937
+ "epoch": 2.1950413223140495,
938
+ "grad_norm": 1.2921308279037476,
939
+ "learning_rate": 5.580719397508446e-06,
940
+ "loss": 0.3149,
941
+ "step": 665
942
+ },
943
+ {
944
+ "epoch": 2.211570247933884,
945
+ "grad_norm": 1.3625119924545288,
946
+ "learning_rate": 5.369810131355022e-06,
947
+ "loss": 0.2986,
948
+ "step": 670
949
+ },
950
+ {
951
+ "epoch": 2.2280991735537192,
952
+ "grad_norm": 1.486613154411316,
953
+ "learning_rate": 5.162091234977103e-06,
954
+ "loss": 0.3031,
955
+ "step": 675
956
+ },
957
+ {
958
+ "epoch": 2.244628099173554,
959
+ "grad_norm": 1.3193362951278687,
960
+ "learning_rate": 4.957631523226512e-06,
961
+ "loss": 0.2925,
962
+ "step": 680
963
+ },
964
+ {
965
+ "epoch": 2.2611570247933885,
966
+ "grad_norm": 1.3618298768997192,
967
+ "learning_rate": 4.756498731225157e-06,
968
+ "loss": 0.284,
969
+ "step": 685
970
+ },
971
+ {
972
+ "epoch": 2.277685950413223,
973
+ "grad_norm": 1.2601497173309326,
974
+ "learning_rate": 4.5587594919251565e-06,
975
+ "loss": 0.3003,
976
+ "step": 690
977
+ },
978
+ {
979
+ "epoch": 2.294214876033058,
980
+ "grad_norm": 1.2634460926055908,
981
+ "learning_rate": 4.364479314034129e-06,
982
+ "loss": 0.3091,
983
+ "step": 695
984
+ },
985
+ {
986
+ "epoch": 2.3107438016528925,
987
+ "grad_norm": 1.3098965883255005,
988
+ "learning_rate": 4.173722560312947e-06,
989
+ "loss": 0.281,
990
+ "step": 700
991
+ },
992
+ {
993
+ "epoch": 2.327272727272727,
994
+ "grad_norm": 1.2892374992370605,
995
+ "learning_rate": 3.98655242625306e-06,
996
+ "loss": 0.2854,
997
+ "step": 705
998
+ },
999
+ {
1000
+ "epoch": 2.343801652892562,
1001
+ "grad_norm": 1.3915247917175293,
1002
+ "learning_rate": 3.8030309191405802e-06,
1003
+ "loss": 0.2745,
1004
+ "step": 710
1005
+ },
1006
+ {
1007
+ "epoch": 2.3603305785123965,
1008
+ "grad_norm": 1.3079394102096558,
1009
+ "learning_rate": 3.623218837514011e-06,
1010
+ "loss": 0.2861,
1011
+ "step": 715
1012
+ },
1013
+ {
1014
+ "epoch": 2.3768595041322316,
1015
+ "grad_norm": 1.3242440223693848,
1016
+ "learning_rate": 3.4471757510223774e-06,
1017
+ "loss": 0.2991,
1018
+ "step": 720
1019
+ },
1020
+ {
1021
+ "epoch": 2.3933884297520662,
1022
+ "grad_norm": 1.0953946113586426,
1023
+ "learning_rate": 3.2749599806904878e-06,
1024
+ "loss": 0.2871,
1025
+ "step": 725
1026
+ },
1027
+ {
1028
+ "epoch": 2.409917355371901,
1029
+ "grad_norm": 1.4852635860443115,
1030
+ "learning_rate": 3.1066285795978833e-06,
1031
+ "loss": 0.2992,
1032
+ "step": 730
1033
+ },
1034
+ {
1035
+ "epoch": 2.4264462809917355,
1036
+ "grad_norm": 1.294978141784668,
1037
+ "learning_rate": 2.9422373139778065e-06,
1038
+ "loss": 0.2686,
1039
+ "step": 735
1040
+ },
1041
+ {
1042
+ "epoch": 2.44297520661157,
1043
+ "grad_norm": 1.4800472259521484,
1044
+ "learning_rate": 2.7818406447424805e-06,
1045
+ "loss": 0.3113,
1046
+ "step": 740
1047
+ },
1048
+ {
1049
+ "epoch": 2.459504132231405,
1050
+ "grad_norm": 1.24534010887146,
1051
+ "learning_rate": 2.6254917094408565e-06,
1052
+ "loss": 0.3078,
1053
+ "step": 745
1054
+ },
1055
+ {
1056
+ "epoch": 2.4760330578512395,
1057
+ "grad_norm": 1.306331753730774,
1058
+ "learning_rate": 2.473242304654783e-06,
1059
+ "loss": 0.3373,
1060
+ "step": 750
1061
+ },
1062
+ {
1063
+ "epoch": 2.4925619834710746,
1064
+ "grad_norm": 1.260591983795166,
1065
+ "learning_rate": 2.3251428688393627e-06,
1066
+ "loss": 0.2945,
1067
+ "step": 755
1068
+ },
1069
+ {
1070
+ "epoch": 2.509090909090909,
1071
+ "grad_norm": 1.201499342918396,
1072
+ "learning_rate": 2.1812424656133003e-06,
1073
+ "loss": 0.2686,
1074
+ "step": 760
1075
+ },
1076
+ {
1077
+ "epoch": 2.525619834710744,
1078
+ "grad_norm": 1.202189326286316,
1079
+ "learning_rate": 2.0415887675046966e-06,
1080
+ "loss": 0.2604,
1081
+ "step": 765
1082
+ },
1083
+ {
1084
+ "epoch": 2.5421487603305786,
1085
+ "grad_norm": 1.4685600996017456,
1086
+ "learning_rate": 1.906228040157702e-06,
1087
+ "loss": 0.2844,
1088
+ "step": 770
1089
+ },
1090
+ {
1091
+ "epoch": 2.5586776859504132,
1092
+ "grad_norm": 1.2637609243392944,
1093
+ "learning_rate": 1.7752051270052194e-06,
1094
+ "loss": 0.2851,
1095
+ "step": 775
1096
+ },
1097
+ {
1098
+ "epoch": 2.575206611570248,
1099
+ "grad_norm": 1.3588604927062988,
1100
+ "learning_rate": 1.6485634344128325e-06,
1101
+ "loss": 0.2872,
1102
+ "step": 780
1103
+ },
1104
+ {
1105
+ "epoch": 2.5917355371900825,
1106
+ "grad_norm": 1.1751164197921753,
1107
+ "learning_rate": 1.526344917298761e-06,
1108
+ "loss": 0.2578,
1109
+ "step": 785
1110
+ },
1111
+ {
1112
+ "epoch": 2.608264462809917,
1113
+ "grad_norm": 1.256611704826355,
1114
+ "learning_rate": 1.4085900652346834e-06,
1115
+ "loss": 0.2816,
1116
+ "step": 790
1117
+ },
1118
+ {
1119
+ "epoch": 2.624793388429752,
1120
+ "grad_norm": 1.2114397287368774,
1121
+ "learning_rate": 1.2953378890320278e-06,
1122
+ "loss": 0.3006,
1123
+ "step": 795
1124
+ },
1125
+ {
1126
+ "epoch": 2.641322314049587,
1127
+ "grad_norm": 1.2731175422668457,
1128
+ "learning_rate": 1.1866259078181274e-06,
1129
+ "loss": 0.2668,
1130
+ "step": 800
1131
+ },
1132
+ {
1133
+ "epoch": 2.6578512396694216,
1134
+ "grad_norm": 1.3774311542510986,
1135
+ "learning_rate": 1.082490136606587e-06,
1136
+ "loss": 0.2715,
1137
+ "step": 805
1138
+ },
1139
+ {
1140
+ "epoch": 2.6743801652892563,
1141
+ "grad_norm": 1.2104158401489258,
1142
+ "learning_rate": 9.829650743659185e-07,
1143
+ "loss": 0.294,
1144
+ "step": 810
1145
+ },
1146
+ {
1147
+ "epoch": 2.690909090909091,
1148
+ "grad_norm": 1.1546332836151123,
1149
+ "learning_rate": 8.880836925904284e-07,
1150
+ "loss": 0.2714,
1151
+ "step": 815
1152
+ },
1153
+ {
1154
+ "epoch": 2.7074380165289256,
1155
+ "grad_norm": 1.2266736030578613,
1156
+ "learning_rate": 7.978774243771636e-07,
1157
+ "loss": 0.2867,
1158
+ "step": 820
1159
+ },
1160
+ {
1161
+ "epoch": 2.7239669421487602,
1162
+ "grad_norm": 1.2701377868652344,
1163
+ "learning_rate": 7.123761540124729e-07,
1164
+ "loss": 0.3008,
1165
+ "step": 825
1166
+ },
1167
+ {
1168
+ "epoch": 2.740495867768595,
1169
+ "grad_norm": 1.2228130102157593,
1170
+ "learning_rate": 6.316082070717083e-07,
1171
+ "loss": 0.272,
1172
+ "step": 830
1173
+ },
1174
+ {
1175
+ "epoch": 2.75702479338843,
1176
+ "grad_norm": 1.3307437896728516,
1177
+ "learning_rate": 5.556003410352762e-07,
1178
+ "loss": 0.287,
1179
+ "step": 835
1180
+ },
1181
+ {
1182
+ "epoch": 2.773553719008264,
1183
+ "grad_norm": 1.4137649536132812,
1184
+ "learning_rate": 4.843777364242064e-07,
1185
+ "loss": 0.279,
1186
+ "step": 840
1187
+ },
1188
+ {
1189
+ "epoch": 2.7900826446280993,
1190
+ "grad_norm": 1.3000072240829468,
1191
+ "learning_rate": 4.179639884581371e-07,
1192
+ "loss": 0.2768,
1193
+ "step": 845
1194
+ },
1195
+ {
1196
+ "epoch": 2.806611570247934,
1197
+ "grad_norm": 1.2189329862594604,
1198
+ "learning_rate": 3.563810992384858e-07,
1199
+ "loss": 0.2695,
1200
+ "step": 850
1201
+ },
1202
+ {
1203
+ "epoch": 2.8231404958677686,
1204
+ "grad_norm": 1.1713279485702515,
1205
+ "learning_rate": 2.996494704594183e-07,
1206
+ "loss": 0.3059,
1207
+ "step": 855
1208
+ },
1209
+ {
1210
+ "epoch": 2.8396694214876033,
1211
+ "grad_norm": 4.241643905639648,
1212
+ "learning_rate": 2.477878966490049e-07,
1213
+ "loss": 0.2362,
1214
+ "step": 860
1215
+ },
1216
+ {
1217
+ "epoch": 2.856198347107438,
1218
+ "grad_norm": 1.2542489767074585,
1219
+ "learning_rate": 2.0081355894280008e-07,
1220
+ "loss": 0.3209,
1221
+ "step": 865
1222
+ },
1223
+ {
1224
+ "epoch": 2.8727272727272726,
1225
+ "grad_norm": 1.1765050888061523,
1226
+ "learning_rate": 1.587420193919481e-07,
1227
+ "loss": 0.2759,
1228
+ "step": 870
1229
+ },
1230
+ {
1231
+ "epoch": 2.8892561983471072,
1232
+ "grad_norm": 1.19680655002594,
1233
+ "learning_rate": 1.2158721580764753e-07,
1234
+ "loss": 0.2926,
1235
+ "step": 875
1236
+ },
1237
+ {
1238
+ "epoch": 2.9057851239669423,
1239
+ "grad_norm": 1.3726508617401123,
1240
+ "learning_rate": 8.936145714371624e-08,
1241
+ "loss": 0.2599,
1242
+ "step": 880
1243
+ },
1244
+ {
1245
+ "epoch": 2.922314049586777,
1246
+ "grad_norm": 1.3616031408309937,
1247
+ "learning_rate": 6.207541941878503e-08,
1248
+ "loss": 0.2823,
1249
+ "step": 885
1250
+ },
1251
+ {
1252
+ "epoch": 2.9388429752066116,
1253
+ "grad_norm": 1.4766091108322144,
1254
+ "learning_rate": 3.973814217945016e-08,
1255
+ "loss": 0.2905,
1256
+ "step": 890
1257
+ },
1258
+ {
1259
+ "epoch": 2.9553719008264463,
1260
+ "grad_norm": 1.2850749492645264,
1261
+ "learning_rate": 2.2357025505577165e-08,
1262
+ "loss": 0.2481,
1263
+ "step": 895
1264
+ },
1265
+ {
1266
+ "epoch": 2.971900826446281,
1267
+ "grad_norm": 1.1268725395202637,
1268
+ "learning_rate": 9.937827558748613e-09,
1269
+ "loss": 0.284,
1270
+ "step": 900
1271
+ },
1272
+ {
1273
+ "epoch": 2.9884297520661156,
1274
+ "grad_norm": 1.3954100608825684,
1275
+ "learning_rate": 2.4846626746399812e-09,
1276
+ "loss": 0.2483,
1277
+ "step": 905
1278
+ },
1279
+ {
1280
+ "epoch": 3.0,
1281
+ "step": 909,
1282
+ "total_flos": 1.273900111881044e+18,
1283
+ "train_loss": 0.571772654588991,
1284
+ "train_runtime": 581.8624,
1285
+ "train_samples_per_second": 49.837,
1286
+ "train_steps_per_second": 1.562
1287
+ }
1288
+ ],
1289
+ "logging_steps": 5,
1290
+ "max_steps": 909,
1291
+ "num_input_tokens_seen": 0,
1292
+ "num_train_epochs": 3,
1293
+ "save_steps": 2000,
1294
+ "stateful_callbacks": {
1295
+ "TrainerControl": {
1296
+ "args": {
1297
+ "should_epoch_stop": false,
1298
+ "should_evaluate": false,
1299
+ "should_log": false,
1300
+ "should_save": false,
1301
+ "should_training_stop": false
1302
+ },
1303
+ "attributes": {}
1304
+ }
1305
+ },
1306
+ "total_flos": 1.273900111881044e+18,
1307
+ "train_batch_size": 2,
1308
+ "trial_name": null,
1309
+ "trial_params": null
1310
+ }
48_128_e3_3e-5/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f163d3723476b34aaac4d3acd2824eefa5e4a07ceb42e44c2bf1267e196fbf8
3
+ size 8145
48_128_e3_3e-5/vocab.json ADDED
The diff for this file is too large to render. See raw diff