RayDu0010 commited on
Commit
4c9823e
·
verified ·
1 Parent(s): 151eff8

Upload folder using huggingface_hub

Browse files
32_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: 32_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
+ # 32_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
32_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
+ "gate_proj",
28
+ "o_proj",
29
+ "k_proj",
30
+ "q_proj",
31
+ "down_proj",
32
+ "v_proj",
33
+ "up_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
32_128_e3_3e-5/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0854575877379413ea7fc3f5b3b2788eb0df703d300044f70ce1ed7073e08b0c
3
+ size 791751704
32_128_e3_3e-5/all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 9.445228084513997e+17,
4
+ "train_loss": 0.5761548168957233,
5
+ "train_runtime": 426.9308,
6
+ "train_samples": 7158,
7
+ "train_samples_per_second": 50.299,
8
+ "train_steps_per_second": 1.574
9
+ }
32_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
+ }
32_128_e3_3e-5/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
32_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
+ }
32_128_e3_3e-5/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
32_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
+ }
32_128_e3_3e-5/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 9.445228084513997e+17,
4
+ "train_loss": 0.5761548168957233,
5
+ "train_runtime": 426.9308,
6
+ "train_samples": 7158,
7
+ "train_samples_per_second": 50.299,
8
+ "train_steps_per_second": 1.574
9
+ }
32_128_e3_3e-5/trainer_state.json ADDED
@@ -0,0 +1,981 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 672,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.022321428571428572,
14
+ "grad_norm": 0.8767691254615784,
15
+ "learning_rate": 3.5294117647058825e-06,
16
+ "loss": 1.3368,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.044642857142857144,
21
+ "grad_norm": 0.7196887135505676,
22
+ "learning_rate": 7.941176470588236e-06,
23
+ "loss": 1.3431,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.06696428571428571,
28
+ "grad_norm": 0.5313777923583984,
29
+ "learning_rate": 1.2352941176470587e-05,
30
+ "loss": 1.3129,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.08928571428571429,
35
+ "grad_norm": 0.4857967793941498,
36
+ "learning_rate": 1.6764705882352943e-05,
37
+ "loss": 1.2441,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.11160714285714286,
42
+ "grad_norm": 0.5176280736923218,
43
+ "learning_rate": 2.1176470588235296e-05,
44
+ "loss": 1.2244,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.13392857142857142,
49
+ "grad_norm": 0.5243091583251953,
50
+ "learning_rate": 2.5588235294117648e-05,
51
+ "loss": 1.2858,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.15625,
56
+ "grad_norm": 0.5184972882270813,
57
+ "learning_rate": 3e-05,
58
+ "loss": 1.1641,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.17857142857142858,
63
+ "grad_norm": 0.47480347752571106,
64
+ "learning_rate": 2.9995453913220172e-05,
65
+ "loss": 1.2178,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.20089285714285715,
70
+ "grad_norm": 0.4492639899253845,
71
+ "learning_rate": 2.9981818408468026e-05,
72
+ "loss": 1.2153,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.22321428571428573,
77
+ "grad_norm": 0.5485384464263916,
78
+ "learning_rate": 2.995910175083527e-05,
79
+ "loss": 1.1243,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.24553571428571427,
84
+ "grad_norm": 0.5423436164855957,
85
+ "learning_rate": 2.992731770990817e-05,
86
+ "loss": 1.1299,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.26785714285714285,
91
+ "grad_norm": 0.51399827003479,
92
+ "learning_rate": 2.988648555142117e-05,
93
+ "loss": 1.1242,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.29017857142857145,
98
+ "grad_norm": 0.4775320291519165,
99
+ "learning_rate": 2.9836630025579043e-05,
100
+ "loss": 1.0684,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.3125,
105
+ "grad_norm": 0.5318741202354431,
106
+ "learning_rate": 2.9777781352054716e-05,
107
+ "loss": 1.1244,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.33482142857142855,
112
+ "grad_norm": 0.5451076030731201,
113
+ "learning_rate": 2.9709975201671755e-05,
114
+ "loss": 1.0655,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.35714285714285715,
119
+ "grad_norm": 0.5790611505508423,
120
+ "learning_rate": 2.963325267478267e-05,
121
+ "loss": 1.0067,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.3794642857142857,
126
+ "grad_norm": 0.5583548545837402,
127
+ "learning_rate": 2.954766027635616e-05,
128
+ "loss": 1.0443,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.4017857142857143,
133
+ "grad_norm": 0.626650333404541,
134
+ "learning_rate": 2.9453249887788343e-05,
135
+ "loss": 0.982,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.42410714285714285,
140
+ "grad_norm": 0.5689722299575806,
141
+ "learning_rate": 2.9350078735455142e-05,
142
+ "loss": 0.9762,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.44642857142857145,
147
+ "grad_norm": 0.6336188316345215,
148
+ "learning_rate": 2.923820935602477e-05,
149
+ "loss": 0.9688,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.46875,
154
+ "grad_norm": 0.5962265729904175,
155
+ "learning_rate": 2.9117709558551485e-05,
156
+ "loss": 1.0198,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.49107142857142855,
161
+ "grad_norm": 0.5901826024055481,
162
+ "learning_rate": 2.8988652383373452e-05,
163
+ "loss": 0.9047,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.5133928571428571,
168
+ "grad_norm": 0.676205039024353,
169
+ "learning_rate": 2.8851116057839732e-05,
170
+ "loss": 0.9436,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.5357142857142857,
175
+ "grad_norm": 0.7188044190406799,
176
+ "learning_rate": 2.870518394889316e-05,
177
+ "loss": 0.9111,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.5580357142857143,
182
+ "grad_norm": 0.7837942242622375,
183
+ "learning_rate": 2.8550944512537897e-05,
184
+ "loss": 0.9261,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.5803571428571429,
189
+ "grad_norm": 0.8304249048233032,
190
+ "learning_rate": 2.838849124022228e-05,
191
+ "loss": 0.9123,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.6026785714285714,
196
+ "grad_norm": 0.8110982179641724,
197
+ "learning_rate": 2.8217922602169464e-05,
198
+ "loss": 0.8538,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.625,
203
+ "grad_norm": 0.730595052242279,
204
+ "learning_rate": 2.8039341987690178e-05,
205
+ "loss": 0.8728,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.6473214285714286,
210
+ "grad_norm": 0.7840301394462585,
211
+ "learning_rate": 2.7852857642513838e-05,
212
+ "loss": 0.8464,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.6696428571428571,
217
+ "grad_norm": 0.8174706697463989,
218
+ "learning_rate": 2.7658582603175947e-05,
219
+ "loss": 0.8812,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.6919642857142857,
224
+ "grad_norm": 0.7730219960212708,
225
+ "learning_rate": 2.7456634628501568e-05,
226
+ "loss": 0.7867,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.7142857142857143,
231
+ "grad_norm": 0.8991721272468567,
232
+ "learning_rate": 2.7247136128226416e-05,
233
+ "loss": 0.8092,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.7366071428571429,
238
+ "grad_norm": 0.9227285385131836,
239
+ "learning_rate": 2.703021408879883e-05,
240
+ "loss": 0.7942,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.7589285714285714,
245
+ "grad_norm": 0.877221405506134,
246
+ "learning_rate": 2.680599999640756e-05,
247
+ "loss": 0.7174,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.78125,
252
+ "grad_norm": 0.8718916177749634,
253
+ "learning_rate": 2.6574629757282116e-05,
254
+ "loss": 0.7843,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.8035714285714286,
259
+ "grad_norm": 1.0385403633117676,
260
+ "learning_rate": 2.6336243615313876e-05,
261
+ "loss": 0.7527,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.8258928571428571,
266
+ "grad_norm": 0.9563890099525452,
267
+ "learning_rate": 2.6090986067047967e-05,
268
+ "loss": 0.7153,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.8482142857142857,
273
+ "grad_norm": 1.0046604871749878,
274
+ "learning_rate": 2.583900577409744e-05,
275
+ "loss": 0.7591,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.8705357142857143,
280
+ "grad_norm": 0.9808415770530701,
281
+ "learning_rate": 2.5580455473032763e-05,
282
+ "loss": 0.7536,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.8928571428571429,
287
+ "grad_norm": 1.0072885751724243,
288
+ "learning_rate": 2.531549188280135e-05,
289
+ "loss": 0.7691,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.9151785714285714,
294
+ "grad_norm": 0.925537645816803,
295
+ "learning_rate": 2.5044275609733162e-05,
296
+ "loss": 0.6722,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.9375,
301
+ "grad_norm": 1.1047004461288452,
302
+ "learning_rate": 2.476697105018999e-05,
303
+ "loss": 0.7228,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.9598214285714286,
308
+ "grad_norm": 0.9555965065956116,
309
+ "learning_rate": 2.448374629091746e-05,
310
+ "loss": 0.7044,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.9821428571428571,
315
+ "grad_norm": 0.9984466433525085,
316
+ "learning_rate": 2.4194773007160068e-05,
317
+ "loss": 0.7658,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 1.0044642857142858,
322
+ "grad_norm": 0.9915810823440552,
323
+ "learning_rate": 2.390022635860117e-05,
324
+ "loss": 0.6535,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 1.0267857142857142,
329
+ "grad_norm": 1.124132513999939,
330
+ "learning_rate": 2.3600284883190756e-05,
331
+ "loss": 0.6127,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 1.0491071428571428,
336
+ "grad_norm": 1.1176362037658691,
337
+ "learning_rate": 2.329513038892565e-05,
338
+ "loss": 0.6233,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 1.0714285714285714,
343
+ "grad_norm": 1.1315720081329346,
344
+ "learning_rate": 2.298494784364747e-05,
345
+ "loss": 0.5869,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 1.09375,
350
+ "grad_norm": 1.1865111589431763,
351
+ "learning_rate": 2.266992526292534e-05,
352
+ "loss": 0.563,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 1.1160714285714286,
357
+ "grad_norm": 1.1381595134735107,
358
+ "learning_rate": 2.2350253596091203e-05,
359
+ "loss": 0.508,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 1.1383928571428572,
364
+ "grad_norm": 1.1229127645492554,
365
+ "learning_rate": 2.2026126610496852e-05,
366
+ "loss": 0.5767,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 1.1607142857142858,
371
+ "grad_norm": 1.0976483821868896,
372
+ "learning_rate": 2.1697740774062858e-05,
373
+ "loss": 0.555,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 1.1830357142857142,
378
+ "grad_norm": 1.206329584121704,
379
+ "learning_rate": 2.13652951361905e-05,
380
+ "loss": 0.577,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 1.2053571428571428,
385
+ "grad_norm": 1.1963576078414917,
386
+ "learning_rate": 2.1028991207109032e-05,
387
+ "loss": 0.543,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 1.2276785714285714,
392
+ "grad_norm": 1.2085398435592651,
393
+ "learning_rate": 2.0689032835731246e-05,
394
+ "loss": 0.5444,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 1.25,
399
+ "grad_norm": 1.174570918083191,
400
+ "learning_rate": 2.0345626086091536e-05,
401
+ "loss": 0.5297,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 1.2723214285714286,
406
+ "grad_norm": 1.1196696758270264,
407
+ "learning_rate": 1.9998979112441166e-05,
408
+ "loss": 0.5095,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 1.2946428571428572,
413
+ "grad_norm": 1.3247411251068115,
414
+ "learning_rate": 1.9649302033076708e-05,
415
+ "loss": 0.5051,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 1.3169642857142856,
420
+ "grad_norm": 1.1289466619491577,
421
+ "learning_rate": 1.929680680297784e-05,
422
+ "loss": 0.5418,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 1.3392857142857144,
427
+ "grad_norm": 1.1605075597763062,
428
+ "learning_rate": 1.8941707085331977e-05,
429
+ "loss": 0.5224,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 1.3616071428571428,
434
+ "grad_norm": 1.096415638923645,
435
+ "learning_rate": 1.8584218122023377e-05,
436
+ "loss": 0.5411,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 1.3839285714285714,
441
+ "grad_norm": 1.1778031587600708,
442
+ "learning_rate": 1.8224556603165363e-05,
443
+ "loss": 0.4917,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 1.40625,
448
+ "grad_norm": 1.1422529220581055,
449
+ "learning_rate": 1.7862940535754754e-05,
450
+ "loss": 0.4894,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 1.4285714285714286,
455
+ "grad_norm": 1.2388246059417725,
456
+ "learning_rate": 1.7499589111528013e-05,
457
+ "loss": 0.4496,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 1.4508928571428572,
462
+ "grad_norm": 1.1976816654205322,
463
+ "learning_rate": 1.713472257409928e-05,
464
+ "loss": 0.4531,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 1.4732142857142856,
469
+ "grad_norm": 1.2926381826400757,
470
+ "learning_rate": 1.676856208546085e-05,
471
+ "loss": 0.4557,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 1.4955357142857144,
476
+ "grad_norm": 1.1342889070510864,
477
+ "learning_rate": 1.640132959192695e-05,
478
+ "loss": 0.4414,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 1.5178571428571428,
483
+ "grad_norm": 1.3249493837356567,
484
+ "learning_rate": 1.6033247689602116e-05,
485
+ "loss": 0.4868,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 1.5401785714285714,
490
+ "grad_norm": 1.2084228992462158,
491
+ "learning_rate": 1.5664539489455684e-05,
492
+ "loss": 0.4551,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 1.5625,
497
+ "grad_norm": 1.3247101306915283,
498
+ "learning_rate": 1.529542848208422e-05,
499
+ "loss": 0.4494,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 1.5848214285714286,
504
+ "grad_norm": 1.218238353729248,
505
+ "learning_rate": 1.4926138402243861e-05,
506
+ "loss": 0.4449,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 1.6071428571428572,
511
+ "grad_norm": 1.2270762920379639,
512
+ "learning_rate": 1.4556893093234569e-05,
513
+ "loss": 0.4322,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 1.6294642857142856,
518
+ "grad_norm": 1.5086091756820679,
519
+ "learning_rate": 1.4187916371218739e-05,
520
+ "loss": 0.4557,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 1.6517857142857144,
525
+ "grad_norm": 1.1575895547866821,
526
+ "learning_rate": 1.3819431889556092e-05,
527
+ "loss": 0.4417,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 1.6741071428571428,
532
+ "grad_norm": 1.1583666801452637,
533
+ "learning_rate": 1.3451663003237395e-05,
534
+ "loss": 0.4597,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 1.6964285714285714,
539
+ "grad_norm": 1.2947156429290771,
540
+ "learning_rate": 1.308483263349892e-05,
541
+ "loss": 0.4293,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 1.71875,
546
+ "grad_norm": 1.347031593322754,
547
+ "learning_rate": 1.2719163132699918e-05,
548
+ "loss": 0.4263,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 1.7410714285714286,
553
+ "grad_norm": 1.2187089920043945,
554
+ "learning_rate": 1.2354876149544831e-05,
555
+ "loss": 0.4054,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 1.7633928571428572,
560
+ "grad_norm": 1.206672191619873,
561
+ "learning_rate": 1.1992192494732083e-05,
562
+ "loss": 0.4062,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 1.7857142857142856,
567
+ "grad_norm": 1.2492778301239014,
568
+ "learning_rate": 1.1631332007110795e-05,
569
+ "loss": 0.4201,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 1.8080357142857144,
574
+ "grad_norm": 1.2433871030807495,
575
+ "learning_rate": 1.1272513420426589e-05,
576
+ "loss": 0.3788,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 1.8303571428571428,
581
+ "grad_norm": 1.2290749549865723,
582
+ "learning_rate": 1.0915954230737238e-05,
583
+ "loss": 0.4181,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 1.8526785714285714,
588
+ "grad_norm": 1.4849416017532349,
589
+ "learning_rate": 1.0561870564578535e-05,
590
+ "loss": 0.4373,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 1.875,
595
+ "grad_norm": 1.2702398300170898,
596
+ "learning_rate": 1.0210477047960303e-05,
597
+ "loss": 0.3983,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 1.8973214285714286,
602
+ "grad_norm": 1.891557216644287,
603
+ "learning_rate": 9.86198667627193e-06,
604
+ "loss": 0.3721,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 1.9196428571428572,
609
+ "grad_norm": 1.3252699375152588,
610
+ "learning_rate": 9.516610685176298e-06,
611
+ "loss": 0.458,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 1.9419642857142856,
616
+ "grad_norm": 1.251217246055603,
617
+ "learning_rate": 9.174558422570372e-06,
618
+ "loss": 0.3757,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 1.9642857142857144,
623
+ "grad_norm": 1.4009981155395508,
624
+ "learning_rate": 8.83603722169002e-06,
625
+ "loss": 0.3745,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 1.9866071428571428,
630
+ "grad_norm": 1.2171951532363892,
631
+ "learning_rate": 8.501252275436047e-06,
632
+ "loss": 0.3498,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 2.0089285714285716,
637
+ "grad_norm": 1.1374053955078125,
638
+ "learning_rate": 8.170406511997551e-06,
639
+ "loss": 0.3428,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 2.03125,
644
+ "grad_norm": 1.4344035387039185,
645
+ "learning_rate": 7.843700471848044e-06,
646
+ "loss": 0.3248,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 2.0535714285714284,
651
+ "grad_norm": 1.388619303703308,
652
+ "learning_rate": 7.521332186188859e-06,
653
+ "loss": 0.288,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 2.075892857142857,
658
+ "grad_norm": 1.2392041683197021,
659
+ "learning_rate": 7.203497056913553e-06,
660
+ "loss": 0.2978,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 2.0982142857142856,
665
+ "grad_norm": 1.2916345596313477,
666
+ "learning_rate": 6.890387738166042e-06,
667
+ "loss": 0.3027,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 2.1205357142857144,
672
+ "grad_norm": 1.3241705894470215,
673
+ "learning_rate": 6.582194019564266e-06,
674
+ "loss": 0.2931,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 2.142857142857143,
679
+ "grad_norm": 1.283165454864502,
680
+ "learning_rate": 6.2791027111602035e-06,
681
+ "loss": 0.3338,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 2.1651785714285716,
686
+ "grad_norm": 1.2019572257995605,
687
+ "learning_rate": 5.981297530205881e-06,
688
+ "loss": 0.2994,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 2.1875,
693
+ "grad_norm": 1.371954083442688,
694
+ "learning_rate": 5.688958989794102e-06,
695
+ "loss": 0.3147,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 2.2098214285714284,
700
+ "grad_norm": 1.4498229026794434,
701
+ "learning_rate": 5.402264289441387e-06,
702
+ "loss": 0.31,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 2.232142857142857,
707
+ "grad_norm": 1.2884076833724976,
708
+ "learning_rate": 5.121387207679347e-06,
709
+ "loss": 0.2832,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 2.2544642857142856,
714
+ "grad_norm": 1.2234337329864502,
715
+ "learning_rate": 4.846497996719734e-06,
716
+ "loss": 0.2898,
717
+ "step": 505
718
+ },
719
+ {
720
+ "epoch": 2.2767857142857144,
721
+ "grad_norm": 1.3806877136230469,
722
+ "learning_rate": 4.577763279256926e-06,
723
+ "loss": 0.2917,
724
+ "step": 510
725
+ },
726
+ {
727
+ "epoch": 2.299107142857143,
728
+ "grad_norm": 1.3858397006988525,
729
+ "learning_rate": 4.3153459474704446e-06,
730
+ "loss": 0.3058,
731
+ "step": 515
732
+ },
733
+ {
734
+ "epoch": 2.3214285714285716,
735
+ "grad_norm": 1.2962052822113037,
736
+ "learning_rate": 4.059405064288662e-06,
737
+ "loss": 0.2862,
738
+ "step": 520
739
+ },
740
+ {
741
+ "epoch": 2.34375,
742
+ "grad_norm": 1.2204980850219727,
743
+ "learning_rate": 3.810095766973638e-06,
744
+ "loss": 0.282,
745
+ "step": 525
746
+ },
747
+ {
748
+ "epoch": 2.3660714285714284,
749
+ "grad_norm": 1.3225136995315552,
750
+ "learning_rate": 3.567569173085455e-06,
751
+ "loss": 0.2988,
752
+ "step": 530
753
+ },
754
+ {
755
+ "epoch": 2.388392857142857,
756
+ "grad_norm": 1.4351136684417725,
757
+ "learning_rate": 3.3319722888830766e-06,
758
+ "loss": 0.3335,
759
+ "step": 535
760
+ },
761
+ {
762
+ "epoch": 2.4107142857142856,
763
+ "grad_norm": 1.4396522045135498,
764
+ "learning_rate": 3.103447920217255e-06,
765
+ "loss": 0.3156,
766
+ "step": 540
767
+ },
768
+ {
769
+ "epoch": 2.4330357142857144,
770
+ "grad_norm": 1.2662440538406372,
771
+ "learning_rate": 2.8821345859694914e-06,
772
+ "loss": 0.3234,
773
+ "step": 545
774
+ },
775
+ {
776
+ "epoch": 2.455357142857143,
777
+ "grad_norm": 1.2445207834243774,
778
+ "learning_rate": 2.6681664340895197e-06,
779
+ "loss": 0.2819,
780
+ "step": 550
781
+ },
782
+ {
783
+ "epoch": 2.4776785714285716,
784
+ "grad_norm": 1.3526782989501953,
785
+ "learning_rate": 2.4616731602822218e-06,
786
+ "loss": 0.2813,
787
+ "step": 555
788
+ },
789
+ {
790
+ "epoch": 2.5,
791
+ "grad_norm": 1.4886586666107178,
792
+ "learning_rate": 2.2627799293932144e-06,
793
+ "loss": 0.2952,
794
+ "step": 560
795
+ },
796
+ {
797
+ "epoch": 2.522321428571429,
798
+ "grad_norm": 1.2216873168945312,
799
+ "learning_rate": 2.0716072995408425e-06,
800
+ "loss": 0.2804,
801
+ "step": 565
802
+ },
803
+ {
804
+ "epoch": 2.544642857142857,
805
+ "grad_norm": 1.3416815996170044,
806
+ "learning_rate": 1.8882711490404692e-06,
807
+ "loss": 0.2836,
808
+ "step": 570
809
+ },
810
+ {
811
+ "epoch": 2.5669642857142856,
812
+ "grad_norm": 1.3410799503326416,
813
+ "learning_rate": 1.7128826061654346e-06,
814
+ "loss": 0.2598,
815
+ "step": 575
816
+ },
817
+ {
818
+ "epoch": 2.5892857142857144,
819
+ "grad_norm": 1.329782247543335,
820
+ "learning_rate": 1.5455479817872182e-06,
821
+ "loss": 0.2793,
822
+ "step": 580
823
+ },
824
+ {
825
+ "epoch": 2.611607142857143,
826
+ "grad_norm": 1.243699073791504,
827
+ "learning_rate": 1.3863687049356465e-06,
828
+ "loss": 0.296,
829
+ "step": 585
830
+ },
831
+ {
832
+ "epoch": 2.633928571428571,
833
+ "grad_norm": 1.2737727165222168,
834
+ "learning_rate": 1.235441261318197e-06,
835
+ "loss": 0.2664,
836
+ "step": 590
837
+ },
838
+ {
839
+ "epoch": 2.65625,
840
+ "grad_norm": 1.3997918367385864,
841
+ "learning_rate": 1.092857134835696e-06,
842
+ "loss": 0.2717,
843
+ "step": 595
844
+ },
845
+ {
846
+ "epoch": 2.678571428571429,
847
+ "grad_norm": 1.2120293378829956,
848
+ "learning_rate": 9.587027521297964e-07,
849
+ "loss": 0.2833,
850
+ "step": 600
851
+ },
852
+ {
853
+ "epoch": 2.700892857142857,
854
+ "grad_norm": 1.257831335067749,
855
+ "learning_rate": 8.330594301959194e-07,
856
+ "loss": 0.2985,
857
+ "step": 605
858
+ },
859
+ {
860
+ "epoch": 2.7232142857142856,
861
+ "grad_norm": 1.2658048868179321,
862
+ "learning_rate": 7.160033270933769e-07,
863
+ "loss": 0.288,
864
+ "step": 610
865
+ },
866
+ {
867
+ "epoch": 2.7455357142857144,
868
+ "grad_norm": 1.326066255569458,
869
+ "learning_rate": 6.076053957825411e-07,
870
+ "loss": 0.2691,
871
+ "step": 615
872
+ },
873
+ {
874
+ "epoch": 2.767857142857143,
875
+ "grad_norm": 1.2179077863693237,
876
+ "learning_rate": 5.079313411170783e-07,
877
+ "loss": 0.2894,
878
+ "step": 620
879
+ },
880
+ {
881
+ "epoch": 2.790178571428571,
882
+ "grad_norm": 1.213523268699646,
883
+ "learning_rate": 4.1704158001728333e-07,
884
+ "loss": 0.2954,
885
+ "step": 625
886
+ },
887
+ {
888
+ "epoch": 2.8125,
889
+ "grad_norm": 1.2045886516571045,
890
+ "learning_rate": 3.3499120484867083e-07,
891
+ "loss": 0.3008,
892
+ "step": 630
893
+ },
894
+ {
895
+ "epoch": 2.834821428571429,
896
+ "grad_norm": 1.3291288614273071,
897
+ "learning_rate": 2.618299500280208e-07,
898
+ "loss": 0.2982,
899
+ "step": 635
900
+ },
901
+ {
902
+ "epoch": 2.857142857142857,
903
+ "grad_norm": 1.3302098512649536,
904
+ "learning_rate": 1.9760216187710788e-07,
905
+ "loss": 0.2932,
906
+ "step": 640
907
+ },
908
+ {
909
+ "epoch": 2.8794642857142856,
910
+ "grad_norm": 1.3039062023162842,
911
+ "learning_rate": 1.4234677174241372e-07,
912
+ "loss": 0.262,
913
+ "step": 645
914
+ },
915
+ {
916
+ "epoch": 2.9017857142857144,
917
+ "grad_norm": 1.1974124908447266,
918
+ "learning_rate": 9.609727239708821e-08,
919
+ "loss": 0.2657,
920
+ "step": 650
921
+ },
922
+ {
923
+ "epoch": 2.924107142857143,
924
+ "grad_norm": 1.3114773035049438,
925
+ "learning_rate": 5.888169773946905e-08,
926
+ "loss": 0.2651,
927
+ "step": 655
928
+ },
929
+ {
930
+ "epoch": 2.946428571428571,
931
+ "grad_norm": 1.1701819896697998,
932
+ "learning_rate": 3.072260580048447e-08,
933
+ "loss": 0.2611,
934
+ "step": 660
935
+ },
936
+ {
937
+ "epoch": 2.96875,
938
+ "grad_norm": 1.2472351789474487,
939
+ "learning_rate": 1.1637065070210784e-08,
940
+ "loss": 0.2965,
941
+ "step": 665
942
+ },
943
+ {
944
+ "epoch": 2.991071428571429,
945
+ "grad_norm": 1.2813712358474731,
946
+ "learning_rate": 1.6366441519066744e-09,
947
+ "loss": 0.3116,
948
+ "step": 670
949
+ },
950
+ {
951
+ "epoch": 3.0,
952
+ "step": 672,
953
+ "total_flos": 9.445228084513997e+17,
954
+ "train_loss": 0.5761548168957233,
955
+ "train_runtime": 426.9308,
956
+ "train_samples_per_second": 50.299,
957
+ "train_steps_per_second": 1.574
958
+ }
959
+ ],
960
+ "logging_steps": 5,
961
+ "max_steps": 672,
962
+ "num_input_tokens_seen": 0,
963
+ "num_train_epochs": 3,
964
+ "save_steps": 2000,
965
+ "stateful_callbacks": {
966
+ "TrainerControl": {
967
+ "args": {
968
+ "should_epoch_stop": false,
969
+ "should_evaluate": false,
970
+ "should_log": false,
971
+ "should_save": false,
972
+ "should_training_stop": false
973
+ },
974
+ "attributes": {}
975
+ }
976
+ },
977
+ "total_flos": 9.445228084513997e+17,
978
+ "train_batch_size": 2,
979
+ "trial_name": null,
980
+ "trial_params": null
981
+ }
32_128_e3_3e-5/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e4dfd68c97f7e06cb490bc9d0758d28385c0e75d8f7f904ea352f34775c0f18
3
+ size 8145
32_128_e3_3e-5/vocab.json ADDED
The diff for this file is too large to render. See raw diff