akineAItech commited on
Commit
f152c40
1 Parent(s): b42bb6d

Upload 16 files

Browse files
README.md CHANGED
@@ -1,24 +1,57 @@
1
  ---
2
- license: mit
 
 
 
 
 
 
 
 
3
  ---
4
- cyberAgent社のCalm-7Bに対し、高品質なウェブ小説、青空文庫で構成されたおよそ3GBの厳選データセットでファインチューニングを施したモデルです。
5
- 以下の指示チューニングを活用し、生成される小説の方向性を調節することができます。
6
 
7
- ###指示:\n\n[キーワード:異世界転移、ファンタジー、異世界、魔法、シリアス]\n\n###出力:\n
 
8
 
9
- または、小説の題名や作者の名前を指定することもできます。
10
 
11
- ###指示:\n\n[作品名:ウェストミンスター寺院], [作者:アーヴィングワシントン]\n\n###出力:\n
12
 
 
13
 
14
- これらの指示は、各項目を空白にしても動作するように設計しています。少なくとも`[キーワード:]`とだけ書いておけば動作します。
15
 
16
- コンテキスト長3072
17
 
 
18
 
 
19
 
 
20
 
 
21
 
22
- # 免責事項
23
 
24
- 作者である私は、このモデルの使用によって起こったいかなる問題の責任も負いません。
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: other
3
+ base_model: calm2-7b
4
+ tags:
5
+ - llama-factory
6
+ - freeze
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: noberai-main-6
10
+ results: []
11
  ---
 
 
12
 
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
 
16
+ # noberai-main-6
17
 
18
+ This model is a fine-tuned version of [calm2-7b](https://huggingface.co/calm2-7b) on the super-jeneri-beta dataset.
19
 
20
+ ## Model description
21
 
22
+ More information needed
23
 
24
+ ## Intended uses & limitations
25
 
26
+ More information needed
27
 
28
+ ## Training and evaluation data
29
 
30
+ More information needed
31
 
32
+ ## Training procedure
33
 
34
+ ### Training hyperparameters
35
 
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
+ - train_batch_size: 8
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 16
42
+ - total_train_batch_size: 128
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: constant
45
+ - lr_scheduler_warmup_steps: 100
46
+ - num_epochs: 7.0
47
+
48
+ ### Training results
49
+
50
+
51
+
52
+ ### Framework versions
53
+
54
+ - Transformers 4.38.2
55
+ - Pytorch 2.2.0+cu121
56
+ - Datasets 2.18.0
57
+ - Tokenizers 0.15.2
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.93,
3
+ "train_loss": 0.048051854148181763,
4
+ "train_runtime": 5063.5443,
5
+ "train_samples_per_second": 54.75,
6
+ "train_steps_per_second": 0.427
7
+ }
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "calm2-7b",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "eos_token_id": 0,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 32,
19
+ "pad_token_id": 1,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.38.2",
27
+ "unsloth_version": "2024.3",
28
+ "use_cache": false,
29
+ "vocab_size": 65024
30
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.38.2"
7
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4858ea15b2bd273fead3640175401bc33f9d7f143293c924cc1d0fdaf750808a
3
+ size 4985122120
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18e696d9851eb0dffd043ae0db209349daaa205328bae8688ba5eb4ef153ed5f
3
+ size 4991431432
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1166eff786b0f9cb133c0a71fe9ea22679b43cceb7cb13068a65af84973f47f
3
+ size 4723000160
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f604669dbf371487ddad6c4900d678db81bd86bd510dccd9bd02d7ba89455a2
3
+ size 532676736
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15232196608
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
296
+ "model.norm.weight": "model-00003-of-00004.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|padding|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|padding|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "bos_token": "<|endoftext|>",
22
+ "chat_template": "{% set system_message = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '###指示:\\n' + content + '\\n\\n###出力:\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\\n\\n' }}{% endif %}{% endfor %}",
23
+ "clean_up_tokenization_spaces": true,
24
+ "eos_token": "<|endoftext|>",
25
+ "model_max_length": 1000000000000000019884624838656,
26
+ "pad_token": "<|padding|>",
27
+ "padding_side": "right",
28
+ "split_special_tokens": false,
29
+ "tokenizer_class": "GPTNeoXTokenizer",
30
+ "unk_token": "<|endoftext|>"
31
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.93,
3
+ "train_loss": 0.048051854148181763,
4
+ "train_runtime": 5063.5443,
5
+ "train_samples_per_second": 54.75,
6
+ "train_steps_per_second": 0.427
7
+ }
trainer_log.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
trainer_state.json ADDED
@@ -0,0 +1,2592 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.9274893960816,
5
+ "eval_steps": 500,
6
+ "global_step": 1832,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "grad_norm": 0.30875682830810547,
14
+ "learning_rate": 1.5e-06,
15
+ "loss": 3.2648,
16
+ "step": 5
17
+ },
18
+ {
19
+ "epoch": 0.03,
20
+ "grad_norm": 0.2472837269306183,
21
+ "learning_rate": 3e-06,
22
+ "loss": 3.2957,
23
+ "step": 10
24
+ },
25
+ {
26
+ "epoch": 0.05,
27
+ "grad_norm": 0.27992337942123413,
28
+ "learning_rate": 4.5e-06,
29
+ "loss": 3.3082,
30
+ "step": 15
31
+ },
32
+ {
33
+ "epoch": 0.06,
34
+ "grad_norm": 0.2051214873790741,
35
+ "learning_rate": 6e-06,
36
+ "loss": 3.2454,
37
+ "step": 20
38
+ },
39
+ {
40
+ "epoch": 0.08,
41
+ "grad_norm": 0.23398754000663757,
42
+ "learning_rate": 7.5e-06,
43
+ "loss": 3.2516,
44
+ "step": 25
45
+ },
46
+ {
47
+ "epoch": 0.1,
48
+ "grad_norm": 0.21358206868171692,
49
+ "learning_rate": 9e-06,
50
+ "loss": 3.2567,
51
+ "step": 30
52
+ },
53
+ {
54
+ "epoch": 0.11,
55
+ "grad_norm": 0.2220185399055481,
56
+ "learning_rate": 1.05e-05,
57
+ "loss": 3.2233,
58
+ "step": 35
59
+ },
60
+ {
61
+ "epoch": 0.13,
62
+ "grad_norm": 0.1718285083770752,
63
+ "learning_rate": 1.2e-05,
64
+ "loss": 3.2189,
65
+ "step": 40
66
+ },
67
+ {
68
+ "epoch": 0.15,
69
+ "grad_norm": 0.1586149036884308,
70
+ "learning_rate": 1.3500000000000001e-05,
71
+ "loss": 3.2114,
72
+ "step": 45
73
+ },
74
+ {
75
+ "epoch": 0.16,
76
+ "grad_norm": 0.1811351776123047,
77
+ "learning_rate": 1.5e-05,
78
+ "loss": 3.2512,
79
+ "step": 50
80
+ },
81
+ {
82
+ "epoch": 0.18,
83
+ "grad_norm": 0.14845654368400574,
84
+ "learning_rate": 1.65e-05,
85
+ "loss": 3.203,
86
+ "step": 55
87
+ },
88
+ {
89
+ "epoch": 0.19,
90
+ "grad_norm": 0.1642150580883026,
91
+ "learning_rate": 1.8e-05,
92
+ "loss": 3.2081,
93
+ "step": 60
94
+ },
95
+ {
96
+ "epoch": 0.21,
97
+ "grad_norm": 0.14407196640968323,
98
+ "learning_rate": 1.95e-05,
99
+ "loss": 3.255,
100
+ "step": 65
101
+ },
102
+ {
103
+ "epoch": 0.23,
104
+ "grad_norm": 0.13313639163970947,
105
+ "learning_rate": 2.1e-05,
106
+ "loss": 3.2154,
107
+ "step": 70
108
+ },
109
+ {
110
+ "epoch": 0.24,
111
+ "grad_norm": 0.14706526696681976,
112
+ "learning_rate": 2.25e-05,
113
+ "loss": 3.2013,
114
+ "step": 75
115
+ },
116
+ {
117
+ "epoch": 0.26,
118
+ "grad_norm": 0.14185847342014313,
119
+ "learning_rate": 2.4e-05,
120
+ "loss": 3.1885,
121
+ "step": 80
122
+ },
123
+ {
124
+ "epoch": 0.27,
125
+ "grad_norm": 0.14037567377090454,
126
+ "learning_rate": 2.55e-05,
127
+ "loss": 3.2362,
128
+ "step": 85
129
+ },
130
+ {
131
+ "epoch": 0.29,
132
+ "grad_norm": 0.14292936027050018,
133
+ "learning_rate": 2.7000000000000002e-05,
134
+ "loss": 3.1896,
135
+ "step": 90
136
+ },
137
+ {
138
+ "epoch": 0.31,
139
+ "grad_norm": 0.1628720611333847,
140
+ "learning_rate": 2.8499999999999998e-05,
141
+ "loss": 3.2099,
142
+ "step": 95
143
+ },
144
+ {
145
+ "epoch": 0.32,
146
+ "grad_norm": 0.14814336597919464,
147
+ "learning_rate": 3e-05,
148
+ "loss": 3.2269,
149
+ "step": 100
150
+ },
151
+ {
152
+ "epoch": 0.34,
153
+ "grad_norm": 0.14351879060268402,
154
+ "learning_rate": 2.991448118586089e-05,
155
+ "loss": 3.1992,
156
+ "step": 105
157
+ },
158
+ {
159
+ "epoch": 0.36,
160
+ "grad_norm": 0.14756764471530914,
161
+ "learning_rate": 2.982896237172178e-05,
162
+ "loss": 3.1756,
163
+ "step": 110
164
+ },
165
+ {
166
+ "epoch": 0.37,
167
+ "grad_norm": 0.1422564834356308,
168
+ "learning_rate": 2.9743443557582668e-05,
169
+ "loss": 3.1774,
170
+ "step": 115
171
+ },
172
+ {
173
+ "epoch": 0.39,
174
+ "grad_norm": 0.13317522406578064,
175
+ "learning_rate": 2.9657924743443557e-05,
176
+ "loss": 3.1923,
177
+ "step": 120
178
+ },
179
+ {
180
+ "epoch": 0.4,
181
+ "grad_norm": 0.14658209681510925,
182
+ "learning_rate": 2.9572405929304446e-05,
183
+ "loss": 3.2007,
184
+ "step": 125
185
+ },
186
+ {
187
+ "epoch": 0.42,
188
+ "grad_norm": 0.1425113081932068,
189
+ "learning_rate": 2.948688711516534e-05,
190
+ "loss": 3.1538,
191
+ "step": 130
192
+ },
193
+ {
194
+ "epoch": 0.44,
195
+ "grad_norm": 0.13603942096233368,
196
+ "learning_rate": 2.9401368301026228e-05,
197
+ "loss": 3.1756,
198
+ "step": 135
199
+ },
200
+ {
201
+ "epoch": 0.45,
202
+ "grad_norm": 0.14405600726604462,
203
+ "learning_rate": 2.9315849486887117e-05,
204
+ "loss": 3.1855,
205
+ "step": 140
206
+ },
207
+ {
208
+ "epoch": 0.47,
209
+ "grad_norm": 0.14144060015678406,
210
+ "learning_rate": 2.9230330672748006e-05,
211
+ "loss": 3.1821,
212
+ "step": 145
213
+ },
214
+ {
215
+ "epoch": 0.48,
216
+ "grad_norm": 0.13670259714126587,
217
+ "learning_rate": 2.9144811858608895e-05,
218
+ "loss": 3.1469,
219
+ "step": 150
220
+ },
221
+ {
222
+ "epoch": 0.5,
223
+ "grad_norm": 0.14555875957012177,
224
+ "learning_rate": 2.9059293044469784e-05,
225
+ "loss": 3.1334,
226
+ "step": 155
227
+ },
228
+ {
229
+ "epoch": 0.52,
230
+ "grad_norm": 0.14179597795009613,
231
+ "learning_rate": 2.8973774230330673e-05,
232
+ "loss": 3.1912,
233
+ "step": 160
234
+ },
235
+ {
236
+ "epoch": 0.53,
237
+ "grad_norm": 0.13467080891132355,
238
+ "learning_rate": 2.8888255416191563e-05,
239
+ "loss": 3.1573,
240
+ "step": 165
241
+ },
242
+ {
243
+ "epoch": 0.55,
244
+ "grad_norm": 0.1724693775177002,
245
+ "learning_rate": 2.880273660205245e-05,
246
+ "loss": 3.1717,
247
+ "step": 170
248
+ },
249
+ {
250
+ "epoch": 0.57,
251
+ "grad_norm": 0.1808375120162964,
252
+ "learning_rate": 2.871721778791334e-05,
253
+ "loss": 3.1606,
254
+ "step": 175
255
+ },
256
+ {
257
+ "epoch": 0.58,
258
+ "grad_norm": 0.1484830379486084,
259
+ "learning_rate": 2.8631698973774233e-05,
260
+ "loss": 3.153,
261
+ "step": 180
262
+ },
263
+ {
264
+ "epoch": 0.6,
265
+ "grad_norm": 0.15217700600624084,
266
+ "learning_rate": 2.8546180159635122e-05,
267
+ "loss": 3.127,
268
+ "step": 185
269
+ },
270
+ {
271
+ "epoch": 0.61,
272
+ "grad_norm": 0.16882199048995972,
273
+ "learning_rate": 2.846066134549601e-05,
274
+ "loss": 3.1582,
275
+ "step": 190
276
+ },
277
+ {
278
+ "epoch": 0.63,
279
+ "grad_norm": 0.1615631878376007,
280
+ "learning_rate": 2.83751425313569e-05,
281
+ "loss": 3.1462,
282
+ "step": 195
283
+ },
284
+ {
285
+ "epoch": 0.65,
286
+ "grad_norm": 0.14329533278942108,
287
+ "learning_rate": 2.828962371721779e-05,
288
+ "loss": 3.1041,
289
+ "step": 200
290
+ },
291
+ {
292
+ "epoch": 0.66,
293
+ "grad_norm": 0.15113158524036407,
294
+ "learning_rate": 2.820410490307868e-05,
295
+ "loss": 3.184,
296
+ "step": 205
297
+ },
298
+ {
299
+ "epoch": 0.68,
300
+ "grad_norm": 0.1513780653476715,
301
+ "learning_rate": 2.8118586088939568e-05,
302
+ "loss": 3.1227,
303
+ "step": 210
304
+ },
305
+ {
306
+ "epoch": 0.69,
307
+ "grad_norm": 0.16015127301216125,
308
+ "learning_rate": 2.8033067274800457e-05,
309
+ "loss": 3.1548,
310
+ "step": 215
311
+ },
312
+ {
313
+ "epoch": 0.71,
314
+ "grad_norm": 0.14768767356872559,
315
+ "learning_rate": 2.7947548460661346e-05,
316
+ "loss": 3.1377,
317
+ "step": 220
318
+ },
319
+ {
320
+ "epoch": 0.73,
321
+ "grad_norm": 0.148753359913826,
322
+ "learning_rate": 2.7862029646522235e-05,
323
+ "loss": 3.162,
324
+ "step": 225
325
+ },
326
+ {
327
+ "epoch": 0.74,
328
+ "grad_norm": 0.17637503147125244,
329
+ "learning_rate": 2.7776510832383128e-05,
330
+ "loss": 3.1687,
331
+ "step": 230
332
+ },
333
+ {
334
+ "epoch": 0.76,
335
+ "grad_norm": 0.13954448699951172,
336
+ "learning_rate": 2.7690992018244017e-05,
337
+ "loss": 3.1667,
338
+ "step": 235
339
+ },
340
+ {
341
+ "epoch": 0.78,
342
+ "grad_norm": 0.14189836382865906,
343
+ "learning_rate": 2.7605473204104906e-05,
344
+ "loss": 3.1399,
345
+ "step": 240
346
+ },
347
+ {
348
+ "epoch": 0.79,
349
+ "grad_norm": 0.1491958051919937,
350
+ "learning_rate": 2.7519954389965795e-05,
351
+ "loss": 3.1121,
352
+ "step": 245
353
+ },
354
+ {
355
+ "epoch": 0.81,
356
+ "grad_norm": 0.14595240354537964,
357
+ "learning_rate": 2.7434435575826684e-05,
358
+ "loss": 3.1527,
359
+ "step": 250
360
+ },
361
+ {
362
+ "epoch": 0.82,
363
+ "grad_norm": 0.15809328854084015,
364
+ "learning_rate": 2.7348916761687573e-05,
365
+ "loss": 3.1609,
366
+ "step": 255
367
+ },
368
+ {
369
+ "epoch": 0.84,
370
+ "grad_norm": 0.14767523109912872,
371
+ "learning_rate": 2.7263397947548462e-05,
372
+ "loss": 3.1475,
373
+ "step": 260
374
+ },
375
+ {
376
+ "epoch": 0.86,
377
+ "grad_norm": 0.15313534438610077,
378
+ "learning_rate": 2.717787913340935e-05,
379
+ "loss": 3.127,
380
+ "step": 265
381
+ },
382
+ {
383
+ "epoch": 0.87,
384
+ "grad_norm": 0.15991611778736115,
385
+ "learning_rate": 2.7092360319270237e-05,
386
+ "loss": 3.1614,
387
+ "step": 270
388
+ },
389
+ {
390
+ "epoch": 0.89,
391
+ "grad_norm": 0.14508678019046783,
392
+ "learning_rate": 2.700684150513113e-05,
393
+ "loss": 3.1323,
394
+ "step": 275
395
+ },
396
+ {
397
+ "epoch": 0.9,
398
+ "grad_norm": 0.14730039238929749,
399
+ "learning_rate": 2.692132269099202e-05,
400
+ "loss": 3.1293,
401
+ "step": 280
402
+ },
403
+ {
404
+ "epoch": 0.92,
405
+ "grad_norm": 0.14069867134094238,
406
+ "learning_rate": 2.6835803876852908e-05,
407
+ "loss": 3.1154,
408
+ "step": 285
409
+ },
410
+ {
411
+ "epoch": 0.94,
412
+ "grad_norm": 0.1483781933784485,
413
+ "learning_rate": 2.6750285062713797e-05,
414
+ "loss": 3.1513,
415
+ "step": 290
416
+ },
417
+ {
418
+ "epoch": 0.95,
419
+ "grad_norm": 0.14479319751262665,
420
+ "learning_rate": 2.6664766248574686e-05,
421
+ "loss": 3.1129,
422
+ "step": 295
423
+ },
424
+ {
425
+ "epoch": 0.97,
426
+ "grad_norm": 0.13547484576702118,
427
+ "learning_rate": 2.6579247434435575e-05,
428
+ "loss": 3.1569,
429
+ "step": 300
430
+ },
431
+ {
432
+ "epoch": 0.99,
433
+ "grad_norm": 0.14407330751419067,
434
+ "learning_rate": 2.6493728620296464e-05,
435
+ "loss": 3.1319,
436
+ "step": 305
437
+ },
438
+ {
439
+ "epoch": 1.0,
440
+ "grad_norm": 0.15453161299228668,
441
+ "learning_rate": 2.6408209806157353e-05,
442
+ "loss": 3.1203,
443
+ "step": 310
444
+ },
445
+ {
446
+ "epoch": 1.02,
447
+ "grad_norm": 0.13878263533115387,
448
+ "learning_rate": 2.6322690992018242e-05,
449
+ "loss": 3.1042,
450
+ "step": 315
451
+ },
452
+ {
453
+ "epoch": 1.03,
454
+ "grad_norm": 0.14512255787849426,
455
+ "learning_rate": 2.623717217787913e-05,
456
+ "loss": 3.0954,
457
+ "step": 320
458
+ },
459
+ {
460
+ "epoch": 1.05,
461
+ "grad_norm": 0.15042366087436676,
462
+ "learning_rate": 2.615165336374002e-05,
463
+ "loss": 3.0634,
464
+ "step": 325
465
+ },
466
+ {
467
+ "epoch": 1.07,
468
+ "grad_norm": 0.16962555050849915,
469
+ "learning_rate": 2.6066134549600913e-05,
470
+ "loss": 3.0815,
471
+ "step": 330
472
+ },
473
+ {
474
+ "epoch": 1.08,
475
+ "grad_norm": 0.14756160974502563,
476
+ "learning_rate": 2.5980615735461802e-05,
477
+ "loss": 3.0923,
478
+ "step": 335
479
+ },
480
+ {
481
+ "epoch": 1.1,
482
+ "grad_norm": 0.14769217371940613,
483
+ "learning_rate": 2.589509692132269e-05,
484
+ "loss": 3.0942,
485
+ "step": 340
486
+ },
487
+ {
488
+ "epoch": 1.11,
489
+ "grad_norm": 0.15603114664554596,
490
+ "learning_rate": 2.580957810718358e-05,
491
+ "loss": 3.0863,
492
+ "step": 345
493
+ },
494
+ {
495
+ "epoch": 1.13,
496
+ "grad_norm": 0.14204762876033783,
497
+ "learning_rate": 2.572405929304447e-05,
498
+ "loss": 3.0707,
499
+ "step": 350
500
+ },
501
+ {
502
+ "epoch": 1.15,
503
+ "grad_norm": 0.1573951095342636,
504
+ "learning_rate": 2.563854047890536e-05,
505
+ "loss": 3.0755,
506
+ "step": 355
507
+ },
508
+ {
509
+ "epoch": 1.16,
510
+ "grad_norm": 0.1641531139612198,
511
+ "learning_rate": 2.5553021664766248e-05,
512
+ "loss": 3.0549,
513
+ "step": 360
514
+ },
515
+ {
516
+ "epoch": 1.18,
517
+ "grad_norm": 0.16347742080688477,
518
+ "learning_rate": 2.5467502850627137e-05,
519
+ "loss": 3.0753,
520
+ "step": 365
521
+ },
522
+ {
523
+ "epoch": 1.2,
524
+ "grad_norm": 0.1477546989917755,
525
+ "learning_rate": 2.5381984036488026e-05,
526
+ "loss": 3.1141,
527
+ "step": 370
528
+ },
529
+ {
530
+ "epoch": 1.21,
531
+ "grad_norm": 0.15331922471523285,
532
+ "learning_rate": 2.5296465222348915e-05,
533
+ "loss": 3.0359,
534
+ "step": 375
535
+ },
536
+ {
537
+ "epoch": 1.23,
538
+ "grad_norm": 0.14977489411830902,
539
+ "learning_rate": 2.5210946408209808e-05,
540
+ "loss": 3.0921,
541
+ "step": 380
542
+ },
543
+ {
544
+ "epoch": 1.24,
545
+ "grad_norm": 0.15610727667808533,
546
+ "learning_rate": 2.5125427594070697e-05,
547
+ "loss": 3.0766,
548
+ "step": 385
549
+ },
550
+ {
551
+ "epoch": 1.26,
552
+ "grad_norm": 0.16113075613975525,
553
+ "learning_rate": 2.5039908779931586e-05,
554
+ "loss": 3.0792,
555
+ "step": 390
556
+ },
557
+ {
558
+ "epoch": 1.28,
559
+ "grad_norm": 0.16325776278972626,
560
+ "learning_rate": 2.4954389965792475e-05,
561
+ "loss": 3.0633,
562
+ "step": 395
563
+ },
564
+ {
565
+ "epoch": 1.29,
566
+ "grad_norm": 0.14828483760356903,
567
+ "learning_rate": 2.4868871151653364e-05,
568
+ "loss": 3.0537,
569
+ "step": 400
570
+ },
571
+ {
572
+ "epoch": 1.31,
573
+ "grad_norm": 0.14972282946109772,
574
+ "learning_rate": 2.4783352337514253e-05,
575
+ "loss": 3.0487,
576
+ "step": 405
577
+ },
578
+ {
579
+ "epoch": 1.32,
580
+ "grad_norm": 0.15230616927146912,
581
+ "learning_rate": 2.4697833523375142e-05,
582
+ "loss": 3.0619,
583
+ "step": 410
584
+ },
585
+ {
586
+ "epoch": 1.34,
587
+ "grad_norm": 0.1488548368215561,
588
+ "learning_rate": 2.461231470923603e-05,
589
+ "loss": 3.0887,
590
+ "step": 415
591
+ },
592
+ {
593
+ "epoch": 1.36,
594
+ "grad_norm": 0.17049625515937805,
595
+ "learning_rate": 2.452679589509692e-05,
596
+ "loss": 3.078,
597
+ "step": 420
598
+ },
599
+ {
600
+ "epoch": 1.37,
601
+ "grad_norm": 0.1818585842847824,
602
+ "learning_rate": 2.444127708095781e-05,
603
+ "loss": 3.0933,
604
+ "step": 425
605
+ },
606
+ {
607
+ "epoch": 1.39,
608
+ "grad_norm": 0.15089115500450134,
609
+ "learning_rate": 2.4355758266818702e-05,
610
+ "loss": 3.0542,
611
+ "step": 430
612
+ },
613
+ {
614
+ "epoch": 1.41,
615
+ "grad_norm": 0.16785630583763123,
616
+ "learning_rate": 2.427023945267959e-05,
617
+ "loss": 3.0591,
618
+ "step": 435
619
+ },
620
+ {
621
+ "epoch": 1.42,
622
+ "grad_norm": 0.15143312513828278,
623
+ "learning_rate": 2.418472063854048e-05,
624
+ "loss": 3.0896,
625
+ "step": 440
626
+ },
627
+ {
628
+ "epoch": 1.44,
629
+ "grad_norm": 0.14978434145450592,
630
+ "learning_rate": 2.409920182440137e-05,
631
+ "loss": 3.0589,
632
+ "step": 445
633
+ },
634
+ {
635
+ "epoch": 1.45,
636
+ "grad_norm": 0.16092675924301147,
637
+ "learning_rate": 2.401368301026226e-05,
638
+ "loss": 3.0444,
639
+ "step": 450
640
+ },
641
+ {
642
+ "epoch": 1.47,
643
+ "grad_norm": 0.15623970329761505,
644
+ "learning_rate": 2.3928164196123148e-05,
645
+ "loss": 3.0959,
646
+ "step": 455
647
+ },
648
+ {
649
+ "epoch": 1.49,
650
+ "grad_norm": 0.15813413262367249,
651
+ "learning_rate": 2.3842645381984037e-05,
652
+ "loss": 3.0444,
653
+ "step": 460
654
+ },
655
+ {
656
+ "epoch": 1.5,
657
+ "grad_norm": 0.1623263657093048,
658
+ "learning_rate": 2.3757126567844926e-05,
659
+ "loss": 3.0753,
660
+ "step": 465
661
+ },
662
+ {
663
+ "epoch": 1.52,
664
+ "grad_norm": 0.16919799149036407,
665
+ "learning_rate": 2.3671607753705815e-05,
666
+ "loss": 3.0481,
667
+ "step": 470
668
+ },
669
+ {
670
+ "epoch": 1.54,
671
+ "grad_norm": 0.1622595638036728,
672
+ "learning_rate": 2.3586088939566704e-05,
673
+ "loss": 3.065,
674
+ "step": 475
675
+ },
676
+ {
677
+ "epoch": 1.55,
678
+ "grad_norm": 0.15223100781440735,
679
+ "learning_rate": 2.3500570125427597e-05,
680
+ "loss": 3.0647,
681
+ "step": 480
682
+ },
683
+ {
684
+ "epoch": 1.57,
685
+ "grad_norm": 0.1645466536283493,
686
+ "learning_rate": 2.3415051311288486e-05,
687
+ "loss": 3.0444,
688
+ "step": 485
689
+ },
690
+ {
691
+ "epoch": 1.58,
692
+ "grad_norm": 0.14715692400932312,
693
+ "learning_rate": 2.3329532497149375e-05,
694
+ "loss": 3.0299,
695
+ "step": 490
696
+ },
697
+ {
698
+ "epoch": 1.6,
699
+ "grad_norm": 0.17336295545101166,
700
+ "learning_rate": 2.3244013683010264e-05,
701
+ "loss": 3.071,
702
+ "step": 495
703
+ },
704
+ {
705
+ "epoch": 1.62,
706
+ "grad_norm": 0.1599658727645874,
707
+ "learning_rate": 2.3158494868871153e-05,
708
+ "loss": 3.0644,
709
+ "step": 500
710
+ },
711
+ {
712
+ "epoch": 1.63,
713
+ "grad_norm": 0.16342023015022278,
714
+ "learning_rate": 2.3072976054732042e-05,
715
+ "loss": 3.0447,
716
+ "step": 505
717
+ },
718
+ {
719
+ "epoch": 1.65,
720
+ "grad_norm": 0.16088004410266876,
721
+ "learning_rate": 2.298745724059293e-05,
722
+ "loss": 3.0885,
723
+ "step": 510
724
+ },
725
+ {
726
+ "epoch": 1.66,
727
+ "grad_norm": 0.15718434751033783,
728
+ "learning_rate": 2.290193842645382e-05,
729
+ "loss": 3.0667,
730
+ "step": 515
731
+ },
732
+ {
733
+ "epoch": 1.68,
734
+ "grad_norm": 0.16234581172466278,
735
+ "learning_rate": 2.281641961231471e-05,
736
+ "loss": 3.0954,
737
+ "step": 520
738
+ },
739
+ {
740
+ "epoch": 1.7,
741
+ "grad_norm": 0.15279100835323334,
742
+ "learning_rate": 2.27309007981756e-05,
743
+ "loss": 3.0609,
744
+ "step": 525
745
+ },
746
+ {
747
+ "epoch": 1.71,
748
+ "grad_norm": 0.1524941623210907,
749
+ "learning_rate": 2.264538198403649e-05,
750
+ "loss": 3.0233,
751
+ "step": 530
752
+ },
753
+ {
754
+ "epoch": 1.73,
755
+ "grad_norm": 0.15686309337615967,
756
+ "learning_rate": 2.255986316989738e-05,
757
+ "loss": 3.0486,
758
+ "step": 535
759
+ },
760
+ {
761
+ "epoch": 1.75,
762
+ "grad_norm": 0.16973251104354858,
763
+ "learning_rate": 2.247434435575827e-05,
764
+ "loss": 3.036,
765
+ "step": 540
766
+ },
767
+ {
768
+ "epoch": 1.76,
769
+ "grad_norm": 0.16990025341510773,
770
+ "learning_rate": 2.2388825541619158e-05,
771
+ "loss": 3.014,
772
+ "step": 545
773
+ },
774
+ {
775
+ "epoch": 1.78,
776
+ "grad_norm": 0.17086321115493774,
777
+ "learning_rate": 2.2303306727480047e-05,
778
+ "loss": 3.0311,
779
+ "step": 550
780
+ },
781
+ {
782
+ "epoch": 1.79,
783
+ "grad_norm": 0.15396995842456818,
784
+ "learning_rate": 2.2217787913340936e-05,
785
+ "loss": 3.0324,
786
+ "step": 555
787
+ },
788
+ {
789
+ "epoch": 1.81,
790
+ "grad_norm": 0.16492833197116852,
791
+ "learning_rate": 2.2132269099201826e-05,
792
+ "loss": 3.0421,
793
+ "step": 560
794
+ },
795
+ {
796
+ "epoch": 1.83,
797
+ "grad_norm": 0.15703165531158447,
798
+ "learning_rate": 2.2046750285062715e-05,
799
+ "loss": 3.0424,
800
+ "step": 565
801
+ },
802
+ {
803
+ "epoch": 1.84,
804
+ "grad_norm": 0.17821280658245087,
805
+ "learning_rate": 2.1961231470923604e-05,
806
+ "loss": 3.0318,
807
+ "step": 570
808
+ },
809
+ {
810
+ "epoch": 1.86,
811
+ "grad_norm": 0.1624838411808014,
812
+ "learning_rate": 2.1875712656784493e-05,
813
+ "loss": 3.0359,
814
+ "step": 575
815
+ },
816
+ {
817
+ "epoch": 1.87,
818
+ "grad_norm": 0.16541211307048798,
819
+ "learning_rate": 2.1790193842645385e-05,
820
+ "loss": 3.0248,
821
+ "step": 580
822
+ },
823
+ {
824
+ "epoch": 1.89,
825
+ "grad_norm": 0.17508499324321747,
826
+ "learning_rate": 2.1704675028506275e-05,
827
+ "loss": 3.0131,
828
+ "step": 585
829
+ },
830
+ {
831
+ "epoch": 1.91,
832
+ "grad_norm": 0.1695563644170761,
833
+ "learning_rate": 2.1619156214367164e-05,
834
+ "loss": 3.0272,
835
+ "step": 590
836
+ },
837
+ {
838
+ "epoch": 1.92,
839
+ "grad_norm": 0.17492899298667908,
840
+ "learning_rate": 2.1533637400228053e-05,
841
+ "loss": 3.0173,
842
+ "step": 595
843
+ },
844
+ {
845
+ "epoch": 1.94,
846
+ "grad_norm": 0.1568179726600647,
847
+ "learning_rate": 2.1448118586088942e-05,
848
+ "loss": 3.0046,
849
+ "step": 600
850
+ },
851
+ {
852
+ "epoch": 1.96,
853
+ "grad_norm": 0.15557514131069183,
854
+ "learning_rate": 2.136259977194983e-05,
855
+ "loss": 3.0124,
856
+ "step": 605
857
+ },
858
+ {
859
+ "epoch": 1.97,
860
+ "grad_norm": 0.16714046895503998,
861
+ "learning_rate": 2.1277080957810717e-05,
862
+ "loss": 3.0674,
863
+ "step": 610
864
+ },
865
+ {
866
+ "epoch": 1.99,
867
+ "grad_norm": 0.16147108376026154,
868
+ "learning_rate": 2.1191562143671606e-05,
869
+ "loss": 3.0534,
870
+ "step": 615
871
+ },
872
+ {
873
+ "epoch": 2.0,
874
+ "grad_norm": 0.20646385848522186,
875
+ "learning_rate": 2.1106043329532495e-05,
876
+ "loss": 3.0084,
877
+ "step": 620
878
+ },
879
+ {
880
+ "epoch": 2.02,
881
+ "grad_norm": 0.18532122671604156,
882
+ "learning_rate": 2.1020524515393384e-05,
883
+ "loss": 3.0369,
884
+ "step": 625
885
+ },
886
+ {
887
+ "epoch": 2.04,
888
+ "grad_norm": 0.17400296032428741,
889
+ "learning_rate": 2.0935005701254276e-05,
890
+ "loss": 2.9915,
891
+ "step": 630
892
+ },
893
+ {
894
+ "epoch": 2.05,
895
+ "grad_norm": 0.17704206705093384,
896
+ "learning_rate": 2.0849486887115166e-05,
897
+ "loss": 2.9672,
898
+ "step": 635
899
+ },
900
+ {
901
+ "epoch": 2.07,
902
+ "grad_norm": 0.17726150155067444,
903
+ "learning_rate": 2.0763968072976055e-05,
904
+ "loss": 3.0192,
905
+ "step": 640
906
+ },
907
+ {
908
+ "epoch": 2.08,
909
+ "grad_norm": 0.190839946269989,
910
+ "learning_rate": 2.0678449258836944e-05,
911
+ "loss": 2.9942,
912
+ "step": 645
913
+ },
914
+ {
915
+ "epoch": 2.1,
916
+ "grad_norm": 0.1717444211244583,
917
+ "learning_rate": 2.0592930444697833e-05,
918
+ "loss": 2.9427,
919
+ "step": 650
920
+ },
921
+ {
922
+ "epoch": 2.12,
923
+ "grad_norm": 0.1715097725391388,
924
+ "learning_rate": 2.0507411630558722e-05,
925
+ "loss": 3.0079,
926
+ "step": 655
927
+ },
928
+ {
929
+ "epoch": 2.13,
930
+ "grad_norm": 0.17741073668003082,
931
+ "learning_rate": 2.042189281641961e-05,
932
+ "loss": 2.9878,
933
+ "step": 660
934
+ },
935
+ {
936
+ "epoch": 2.15,
937
+ "grad_norm": 0.16402089595794678,
938
+ "learning_rate": 2.03363740022805e-05,
939
+ "loss": 2.9606,
940
+ "step": 665
941
+ },
942
+ {
943
+ "epoch": 2.17,
944
+ "grad_norm": 0.17002873122692108,
945
+ "learning_rate": 2.025085518814139e-05,
946
+ "loss": 2.9774,
947
+ "step": 670
948
+ },
949
+ {
950
+ "epoch": 2.18,
951
+ "grad_norm": 0.17261062562465668,
952
+ "learning_rate": 2.016533637400228e-05,
953
+ "loss": 2.9691,
954
+ "step": 675
955
+ },
956
+ {
957
+ "epoch": 2.2,
958
+ "grad_norm": 0.16659089922904968,
959
+ "learning_rate": 2.007981755986317e-05,
960
+ "loss": 2.9814,
961
+ "step": 680
962
+ },
963
+ {
964
+ "epoch": 2.21,
965
+ "grad_norm": 0.181407630443573,
966
+ "learning_rate": 1.999429874572406e-05,
967
+ "loss": 2.9819,
968
+ "step": 685
969
+ },
970
+ {
971
+ "epoch": 2.23,
972
+ "grad_norm": 0.18762464821338654,
973
+ "learning_rate": 1.990877993158495e-05,
974
+ "loss": 2.9845,
975
+ "step": 690
976
+ },
977
+ {
978
+ "epoch": 2.25,
979
+ "grad_norm": 0.17215465009212494,
980
+ "learning_rate": 1.9823261117445838e-05,
981
+ "loss": 2.9697,
982
+ "step": 695
983
+ },
984
+ {
985
+ "epoch": 2.26,
986
+ "grad_norm": 0.17270050942897797,
987
+ "learning_rate": 1.9737742303306727e-05,
988
+ "loss": 2.9408,
989
+ "step": 700
990
+ },
991
+ {
992
+ "epoch": 2.28,
993
+ "grad_norm": 0.20069903135299683,
994
+ "learning_rate": 1.9652223489167616e-05,
995
+ "loss": 2.9579,
996
+ "step": 705
997
+ },
998
+ {
999
+ "epoch": 2.29,
1000
+ "grad_norm": 0.17869950830936432,
1001
+ "learning_rate": 1.9566704675028506e-05,
1002
+ "loss": 2.9771,
1003
+ "step": 710
1004
+ },
1005
+ {
1006
+ "epoch": 2.31,
1007
+ "grad_norm": 0.17995081841945648,
1008
+ "learning_rate": 1.9481185860889395e-05,
1009
+ "loss": 2.9371,
1010
+ "step": 715
1011
+ },
1012
+ {
1013
+ "epoch": 2.33,
1014
+ "grad_norm": 0.1739899218082428,
1015
+ "learning_rate": 1.9395667046750284e-05,
1016
+ "loss": 2.9447,
1017
+ "step": 720
1018
+ },
1019
+ {
1020
+ "epoch": 2.34,
1021
+ "grad_norm": 0.17162194848060608,
1022
+ "learning_rate": 1.9310148232611173e-05,
1023
+ "loss": 2.972,
1024
+ "step": 725
1025
+ },
1026
+ {
1027
+ "epoch": 2.36,
1028
+ "grad_norm": 0.17730017006397247,
1029
+ "learning_rate": 1.9224629418472065e-05,
1030
+ "loss": 2.9458,
1031
+ "step": 730
1032
+ },
1033
+ {
1034
+ "epoch": 2.38,
1035
+ "grad_norm": 0.18780378997325897,
1036
+ "learning_rate": 1.9139110604332954e-05,
1037
+ "loss": 2.9893,
1038
+ "step": 735
1039
+ },
1040
+ {
1041
+ "epoch": 2.39,
1042
+ "grad_norm": 0.17871220409870148,
1043
+ "learning_rate": 1.9053591790193844e-05,
1044
+ "loss": 3.0007,
1045
+ "step": 740
1046
+ },
1047
+ {
1048
+ "epoch": 2.41,
1049
+ "grad_norm": 0.16773036122322083,
1050
+ "learning_rate": 1.8968072976054733e-05,
1051
+ "loss": 2.9678,
1052
+ "step": 745
1053
+ },
1054
+ {
1055
+ "epoch": 2.42,
1056
+ "grad_norm": 0.1990986317396164,
1057
+ "learning_rate": 1.8882554161915622e-05,
1058
+ "loss": 2.9688,
1059
+ "step": 750
1060
+ },
1061
+ {
1062
+ "epoch": 2.44,
1063
+ "grad_norm": 0.16836166381835938,
1064
+ "learning_rate": 1.879703534777651e-05,
1065
+ "loss": 2.9485,
1066
+ "step": 755
1067
+ },
1068
+ {
1069
+ "epoch": 2.46,
1070
+ "grad_norm": 0.17354542016983032,
1071
+ "learning_rate": 1.87115165336374e-05,
1072
+ "loss": 2.9727,
1073
+ "step": 760
1074
+ },
1075
+ {
1076
+ "epoch": 2.47,
1077
+ "grad_norm": 0.17101739346981049,
1078
+ "learning_rate": 1.862599771949829e-05,
1079
+ "loss": 2.9571,
1080
+ "step": 765
1081
+ },
1082
+ {
1083
+ "epoch": 2.49,
1084
+ "grad_norm": 0.1743125468492508,
1085
+ "learning_rate": 1.8540478905359178e-05,
1086
+ "loss": 2.9398,
1087
+ "step": 770
1088
+ },
1089
+ {
1090
+ "epoch": 2.5,
1091
+ "grad_norm": 0.17796063423156738,
1092
+ "learning_rate": 1.8454960091220067e-05,
1093
+ "loss": 2.9513,
1094
+ "step": 775
1095
+ },
1096
+ {
1097
+ "epoch": 2.52,
1098
+ "grad_norm": 0.16847650706768036,
1099
+ "learning_rate": 1.836944127708096e-05,
1100
+ "loss": 2.9892,
1101
+ "step": 780
1102
+ },
1103
+ {
1104
+ "epoch": 2.54,
1105
+ "grad_norm": 0.18287205696105957,
1106
+ "learning_rate": 1.828392246294185e-05,
1107
+ "loss": 2.9718,
1108
+ "step": 785
1109
+ },
1110
+ {
1111
+ "epoch": 2.55,
1112
+ "grad_norm": 0.1805015206336975,
1113
+ "learning_rate": 1.8198403648802738e-05,
1114
+ "loss": 2.9718,
1115
+ "step": 790
1116
+ },
1117
+ {
1118
+ "epoch": 2.57,
1119
+ "grad_norm": 0.18497325479984283,
1120
+ "learning_rate": 1.8112884834663627e-05,
1121
+ "loss": 2.962,
1122
+ "step": 795
1123
+ },
1124
+ {
1125
+ "epoch": 2.59,
1126
+ "grad_norm": 0.17345541715621948,
1127
+ "learning_rate": 1.8027366020524516e-05,
1128
+ "loss": 3.0038,
1129
+ "step": 800
1130
+ },
1131
+ {
1132
+ "epoch": 2.6,
1133
+ "grad_norm": 0.19061264395713806,
1134
+ "learning_rate": 1.7941847206385405e-05,
1135
+ "loss": 2.9932,
1136
+ "step": 805
1137
+ },
1138
+ {
1139
+ "epoch": 2.62,
1140
+ "grad_norm": 0.17812280356884003,
1141
+ "learning_rate": 1.7856328392246294e-05,
1142
+ "loss": 2.9394,
1143
+ "step": 810
1144
+ },
1145
+ {
1146
+ "epoch": 2.63,
1147
+ "grad_norm": 0.184650257229805,
1148
+ "learning_rate": 1.7770809578107184e-05,
1149
+ "loss": 2.9747,
1150
+ "step": 815
1151
+ },
1152
+ {
1153
+ "epoch": 2.65,
1154
+ "grad_norm": 0.18826904892921448,
1155
+ "learning_rate": 1.7685290763968073e-05,
1156
+ "loss": 2.9636,
1157
+ "step": 820
1158
+ },
1159
+ {
1160
+ "epoch": 2.67,
1161
+ "grad_norm": 0.17561104893684387,
1162
+ "learning_rate": 1.7599771949828962e-05,
1163
+ "loss": 2.9477,
1164
+ "step": 825
1165
+ },
1166
+ {
1167
+ "epoch": 2.68,
1168
+ "grad_norm": 0.17117257416248322,
1169
+ "learning_rate": 1.7514253135689854e-05,
1170
+ "loss": 2.9691,
1171
+ "step": 830
1172
+ },
1173
+ {
1174
+ "epoch": 2.7,
1175
+ "grad_norm": 0.17985746264457703,
1176
+ "learning_rate": 1.7428734321550743e-05,
1177
+ "loss": 2.9648,
1178
+ "step": 835
1179
+ },
1180
+ {
1181
+ "epoch": 2.71,
1182
+ "grad_norm": 0.18568694591522217,
1183
+ "learning_rate": 1.7343215507411632e-05,
1184
+ "loss": 2.9571,
1185
+ "step": 840
1186
+ },
1187
+ {
1188
+ "epoch": 2.73,
1189
+ "grad_norm": 0.18761347234249115,
1190
+ "learning_rate": 1.725769669327252e-05,
1191
+ "loss": 2.928,
1192
+ "step": 845
1193
+ },
1194
+ {
1195
+ "epoch": 2.75,
1196
+ "grad_norm": 0.1732112318277359,
1197
+ "learning_rate": 1.717217787913341e-05,
1198
+ "loss": 2.9474,
1199
+ "step": 850
1200
+ },
1201
+ {
1202
+ "epoch": 2.76,
1203
+ "grad_norm": 0.1749856323003769,
1204
+ "learning_rate": 1.70866590649943e-05,
1205
+ "loss": 2.9514,
1206
+ "step": 855
1207
+ },
1208
+ {
1209
+ "epoch": 2.78,
1210
+ "grad_norm": 0.1849680095911026,
1211
+ "learning_rate": 1.700114025085519e-05,
1212
+ "loss": 2.9327,
1213
+ "step": 860
1214
+ },
1215
+ {
1216
+ "epoch": 2.8,
1217
+ "grad_norm": 0.17794924974441528,
1218
+ "learning_rate": 1.6915621436716078e-05,
1219
+ "loss": 2.9644,
1220
+ "step": 865
1221
+ },
1222
+ {
1223
+ "epoch": 2.81,
1224
+ "grad_norm": 0.18736787140369415,
1225
+ "learning_rate": 1.6830102622576967e-05,
1226
+ "loss": 2.9353,
1227
+ "step": 870
1228
+ },
1229
+ {
1230
+ "epoch": 2.83,
1231
+ "grad_norm": 0.1925778090953827,
1232
+ "learning_rate": 1.6744583808437856e-05,
1233
+ "loss": 2.9446,
1234
+ "step": 875
1235
+ },
1236
+ {
1237
+ "epoch": 2.84,
1238
+ "grad_norm": 0.21187719702720642,
1239
+ "learning_rate": 1.665906499429875e-05,
1240
+ "loss": 2.9451,
1241
+ "step": 880
1242
+ },
1243
+ {
1244
+ "epoch": 2.86,
1245
+ "grad_norm": 0.17500068247318268,
1246
+ "learning_rate": 1.6573546180159638e-05,
1247
+ "loss": 2.9715,
1248
+ "step": 885
1249
+ },
1250
+ {
1251
+ "epoch": 2.88,
1252
+ "grad_norm": 0.18147456645965576,
1253
+ "learning_rate": 1.6488027366020527e-05,
1254
+ "loss": 2.9393,
1255
+ "step": 890
1256
+ },
1257
+ {
1258
+ "epoch": 2.89,
1259
+ "grad_norm": 0.17849037051200867,
1260
+ "learning_rate": 1.6402508551881416e-05,
1261
+ "loss": 2.9391,
1262
+ "step": 895
1263
+ },
1264
+ {
1265
+ "epoch": 2.91,
1266
+ "grad_norm": 0.1820787936449051,
1267
+ "learning_rate": 1.6316989737742305e-05,
1268
+ "loss": 2.9692,
1269
+ "step": 900
1270
+ },
1271
+ {
1272
+ "epoch": 2.92,
1273
+ "grad_norm": 0.18852904438972473,
1274
+ "learning_rate": 1.6231470923603194e-05,
1275
+ "loss": 2.9525,
1276
+ "step": 905
1277
+ },
1278
+ {
1279
+ "epoch": 2.94,
1280
+ "grad_norm": 0.17656317353248596,
1281
+ "learning_rate": 1.6145952109464083e-05,
1282
+ "loss": 2.9816,
1283
+ "step": 910
1284
+ },
1285
+ {
1286
+ "epoch": 2.96,
1287
+ "grad_norm": 0.17851251363754272,
1288
+ "learning_rate": 1.6060433295324972e-05,
1289
+ "loss": 2.9253,
1290
+ "step": 915
1291
+ },
1292
+ {
1293
+ "epoch": 2.97,
1294
+ "grad_norm": 0.18870405852794647,
1295
+ "learning_rate": 1.597491448118586e-05,
1296
+ "loss": 2.938,
1297
+ "step": 920
1298
+ },
1299
+ {
1300
+ "epoch": 2.99,
1301
+ "grad_norm": 0.1780102699995041,
1302
+ "learning_rate": 1.588939566704675e-05,
1303
+ "loss": 2.9252,
1304
+ "step": 925
1305
+ },
1306
+ {
1307
+ "epoch": 3.01,
1308
+ "grad_norm": 0.1899801790714264,
1309
+ "learning_rate": 1.5803876852907643e-05,
1310
+ "loss": 2.9285,
1311
+ "step": 930
1312
+ },
1313
+ {
1314
+ "epoch": 3.02,
1315
+ "grad_norm": 0.19754503667354584,
1316
+ "learning_rate": 1.5718358038768532e-05,
1317
+ "loss": 2.8888,
1318
+ "step": 935
1319
+ },
1320
+ {
1321
+ "epoch": 3.04,
1322
+ "grad_norm": 0.17948701977729797,
1323
+ "learning_rate": 1.563283922462942e-05,
1324
+ "loss": 2.8812,
1325
+ "step": 940
1326
+ },
1327
+ {
1328
+ "epoch": 3.05,
1329
+ "grad_norm": 0.18633098900318146,
1330
+ "learning_rate": 1.5547320410490307e-05,
1331
+ "loss": 2.9063,
1332
+ "step": 945
1333
+ },
1334
+ {
1335
+ "epoch": 3.07,
1336
+ "grad_norm": 0.1805902123451233,
1337
+ "learning_rate": 1.5461801596351196e-05,
1338
+ "loss": 2.8998,
1339
+ "step": 950
1340
+ },
1341
+ {
1342
+ "epoch": 3.09,
1343
+ "grad_norm": 0.19559837877750397,
1344
+ "learning_rate": 1.5376282782212085e-05,
1345
+ "loss": 2.8877,
1346
+ "step": 955
1347
+ },
1348
+ {
1349
+ "epoch": 3.1,
1350
+ "grad_norm": 0.1801781952381134,
1351
+ "learning_rate": 1.5290763968072974e-05,
1352
+ "loss": 2.9265,
1353
+ "step": 960
1354
+ },
1355
+ {
1356
+ "epoch": 3.12,
1357
+ "grad_norm": 0.18338532745838165,
1358
+ "learning_rate": 1.5205245153933865e-05,
1359
+ "loss": 2.9025,
1360
+ "step": 965
1361
+ },
1362
+ {
1363
+ "epoch": 3.13,
1364
+ "grad_norm": 0.1971079260110855,
1365
+ "learning_rate": 1.5119726339794754e-05,
1366
+ "loss": 2.8788,
1367
+ "step": 970
1368
+ },
1369
+ {
1370
+ "epoch": 3.15,
1371
+ "grad_norm": 0.19317658245563507,
1372
+ "learning_rate": 1.5034207525655643e-05,
1373
+ "loss": 2.9048,
1374
+ "step": 975
1375
+ },
1376
+ {
1377
+ "epoch": 3.17,
1378
+ "grad_norm": 0.2028065323829651,
1379
+ "learning_rate": 1.4948688711516534e-05,
1380
+ "loss": 2.9021,
1381
+ "step": 980
1382
+ },
1383
+ {
1384
+ "epoch": 3.18,
1385
+ "grad_norm": 0.19364020228385925,
1386
+ "learning_rate": 1.4863169897377423e-05,
1387
+ "loss": 2.8742,
1388
+ "step": 985
1389
+ },
1390
+ {
1391
+ "epoch": 3.2,
1392
+ "grad_norm": 0.19389031827449799,
1393
+ "learning_rate": 1.4777651083238314e-05,
1394
+ "loss": 2.8769,
1395
+ "step": 990
1396
+ },
1397
+ {
1398
+ "epoch": 3.22,
1399
+ "grad_norm": 0.18738117814064026,
1400
+ "learning_rate": 1.4692132269099203e-05,
1401
+ "loss": 2.8896,
1402
+ "step": 995
1403
+ },
1404
+ {
1405
+ "epoch": 3.23,
1406
+ "grad_norm": 0.19338880479335785,
1407
+ "learning_rate": 1.4606613454960092e-05,
1408
+ "loss": 2.9101,
1409
+ "step": 1000
1410
+ },
1411
+ {
1412
+ "epoch": 3.25,
1413
+ "grad_norm": 0.211032897233963,
1414
+ "learning_rate": 1.4521094640820981e-05,
1415
+ "loss": 2.8706,
1416
+ "step": 1005
1417
+ },
1418
+ {
1419
+ "epoch": 3.26,
1420
+ "grad_norm": 0.19349248707294464,
1421
+ "learning_rate": 1.443557582668187e-05,
1422
+ "loss": 2.8723,
1423
+ "step": 1010
1424
+ },
1425
+ {
1426
+ "epoch": 3.28,
1427
+ "grad_norm": 0.18660078942775726,
1428
+ "learning_rate": 1.4350057012542761e-05,
1429
+ "loss": 2.859,
1430
+ "step": 1015
1431
+ },
1432
+ {
1433
+ "epoch": 3.3,
1434
+ "grad_norm": 0.20884543657302856,
1435
+ "learning_rate": 1.426453819840365e-05,
1436
+ "loss": 2.9178,
1437
+ "step": 1020
1438
+ },
1439
+ {
1440
+ "epoch": 3.31,
1441
+ "grad_norm": 0.19792766869068146,
1442
+ "learning_rate": 1.417901938426454e-05,
1443
+ "loss": 2.8876,
1444
+ "step": 1025
1445
+ },
1446
+ {
1447
+ "epoch": 3.33,
1448
+ "grad_norm": 0.18087029457092285,
1449
+ "learning_rate": 1.4093500570125427e-05,
1450
+ "loss": 2.8858,
1451
+ "step": 1030
1452
+ },
1453
+ {
1454
+ "epoch": 3.34,
1455
+ "grad_norm": 0.20698681473731995,
1456
+ "learning_rate": 1.4007981755986316e-05,
1457
+ "loss": 2.8902,
1458
+ "step": 1035
1459
+ },
1460
+ {
1461
+ "epoch": 3.36,
1462
+ "grad_norm": 0.19386625289916992,
1463
+ "learning_rate": 1.3922462941847207e-05,
1464
+ "loss": 2.9174,
1465
+ "step": 1040
1466
+ },
1467
+ {
1468
+ "epoch": 3.38,
1469
+ "grad_norm": 0.19532999396324158,
1470
+ "learning_rate": 1.3836944127708096e-05,
1471
+ "loss": 2.8899,
1472
+ "step": 1045
1473
+ },
1474
+ {
1475
+ "epoch": 3.39,
1476
+ "grad_norm": 0.19565771520137787,
1477
+ "learning_rate": 1.3751425313568985e-05,
1478
+ "loss": 2.8784,
1479
+ "step": 1050
1480
+ },
1481
+ {
1482
+ "epoch": 3.41,
1483
+ "grad_norm": 0.193053737282753,
1484
+ "learning_rate": 1.3665906499429874e-05,
1485
+ "loss": 2.8943,
1486
+ "step": 1055
1487
+ },
1488
+ {
1489
+ "epoch": 3.43,
1490
+ "grad_norm": 0.1953536421060562,
1491
+ "learning_rate": 1.3580387685290763e-05,
1492
+ "loss": 2.8789,
1493
+ "step": 1060
1494
+ },
1495
+ {
1496
+ "epoch": 3.44,
1497
+ "grad_norm": 0.19460298120975494,
1498
+ "learning_rate": 1.3494868871151654e-05,
1499
+ "loss": 2.869,
1500
+ "step": 1065
1501
+ },
1502
+ {
1503
+ "epoch": 3.46,
1504
+ "grad_norm": 0.21567782759666443,
1505
+ "learning_rate": 1.3409350057012543e-05,
1506
+ "loss": 2.8993,
1507
+ "step": 1070
1508
+ },
1509
+ {
1510
+ "epoch": 3.47,
1511
+ "grad_norm": 0.20107676088809967,
1512
+ "learning_rate": 1.3323831242873432e-05,
1513
+ "loss": 2.8874,
1514
+ "step": 1075
1515
+ },
1516
+ {
1517
+ "epoch": 3.49,
1518
+ "grad_norm": 0.20253504812717438,
1519
+ "learning_rate": 1.3238312428734321e-05,
1520
+ "loss": 2.8715,
1521
+ "step": 1080
1522
+ },
1523
+ {
1524
+ "epoch": 3.51,
1525
+ "grad_norm": 0.203015998005867,
1526
+ "learning_rate": 1.315279361459521e-05,
1527
+ "loss": 2.8761,
1528
+ "step": 1085
1529
+ },
1530
+ {
1531
+ "epoch": 3.52,
1532
+ "grad_norm": 0.18808282911777496,
1533
+ "learning_rate": 1.3067274800456101e-05,
1534
+ "loss": 2.9125,
1535
+ "step": 1090
1536
+ },
1537
+ {
1538
+ "epoch": 3.54,
1539
+ "grad_norm": 0.20760120451450348,
1540
+ "learning_rate": 1.298175598631699e-05,
1541
+ "loss": 2.9097,
1542
+ "step": 1095
1543
+ },
1544
+ {
1545
+ "epoch": 3.55,
1546
+ "grad_norm": 0.2105015069246292,
1547
+ "learning_rate": 1.289623717217788e-05,
1548
+ "loss": 2.8776,
1549
+ "step": 1100
1550
+ },
1551
+ {
1552
+ "epoch": 3.57,
1553
+ "grad_norm": 0.19079047441482544,
1554
+ "learning_rate": 1.2810718358038769e-05,
1555
+ "loss": 2.8638,
1556
+ "step": 1105
1557
+ },
1558
+ {
1559
+ "epoch": 3.59,
1560
+ "grad_norm": 0.18677778542041779,
1561
+ "learning_rate": 1.2725199543899658e-05,
1562
+ "loss": 2.8611,
1563
+ "step": 1110
1564
+ },
1565
+ {
1566
+ "epoch": 3.6,
1567
+ "grad_norm": 0.19675646722316742,
1568
+ "learning_rate": 1.2639680729760549e-05,
1569
+ "loss": 2.8915,
1570
+ "step": 1115
1571
+ },
1572
+ {
1573
+ "epoch": 3.62,
1574
+ "grad_norm": 0.18953052163124084,
1575
+ "learning_rate": 1.2554161915621438e-05,
1576
+ "loss": 2.8717,
1577
+ "step": 1120
1578
+ },
1579
+ {
1580
+ "epoch": 3.64,
1581
+ "grad_norm": 0.19209244847297668,
1582
+ "learning_rate": 1.2468643101482327e-05,
1583
+ "loss": 2.8872,
1584
+ "step": 1125
1585
+ },
1586
+ {
1587
+ "epoch": 3.65,
1588
+ "grad_norm": 0.1874540001153946,
1589
+ "learning_rate": 1.2383124287343216e-05,
1590
+ "loss": 2.8752,
1591
+ "step": 1130
1592
+ },
1593
+ {
1594
+ "epoch": 3.67,
1595
+ "grad_norm": 0.19191692769527435,
1596
+ "learning_rate": 1.2297605473204105e-05,
1597
+ "loss": 2.874,
1598
+ "step": 1135
1599
+ },
1600
+ {
1601
+ "epoch": 3.68,
1602
+ "grad_norm": 0.19061529636383057,
1603
+ "learning_rate": 1.2212086659064996e-05,
1604
+ "loss": 2.8571,
1605
+ "step": 1140
1606
+ },
1607
+ {
1608
+ "epoch": 3.7,
1609
+ "grad_norm": 0.20083603262901306,
1610
+ "learning_rate": 1.2126567844925885e-05,
1611
+ "loss": 2.8681,
1612
+ "step": 1145
1613
+ },
1614
+ {
1615
+ "epoch": 3.72,
1616
+ "grad_norm": 0.20946206152439117,
1617
+ "learning_rate": 1.2041049030786774e-05,
1618
+ "loss": 2.8843,
1619
+ "step": 1150
1620
+ },
1621
+ {
1622
+ "epoch": 3.73,
1623
+ "grad_norm": 0.20480531454086304,
1624
+ "learning_rate": 1.1955530216647663e-05,
1625
+ "loss": 2.888,
1626
+ "step": 1155
1627
+ },
1628
+ {
1629
+ "epoch": 3.75,
1630
+ "grad_norm": 0.19144266843795776,
1631
+ "learning_rate": 1.1870011402508552e-05,
1632
+ "loss": 2.8637,
1633
+ "step": 1160
1634
+ },
1635
+ {
1636
+ "epoch": 3.76,
1637
+ "grad_norm": 0.20213666558265686,
1638
+ "learning_rate": 1.1784492588369441e-05,
1639
+ "loss": 2.8995,
1640
+ "step": 1165
1641
+ },
1642
+ {
1643
+ "epoch": 3.78,
1644
+ "grad_norm": 0.18854743242263794,
1645
+ "learning_rate": 1.1698973774230332e-05,
1646
+ "loss": 2.8914,
1647
+ "step": 1170
1648
+ },
1649
+ {
1650
+ "epoch": 3.8,
1651
+ "grad_norm": 0.19319185614585876,
1652
+ "learning_rate": 1.1613454960091221e-05,
1653
+ "loss": 2.8919,
1654
+ "step": 1175
1655
+ },
1656
+ {
1657
+ "epoch": 3.81,
1658
+ "grad_norm": 0.20369315147399902,
1659
+ "learning_rate": 1.152793614595211e-05,
1660
+ "loss": 2.8563,
1661
+ "step": 1180
1662
+ },
1663
+ {
1664
+ "epoch": 3.83,
1665
+ "grad_norm": 0.19648641347885132,
1666
+ "learning_rate": 1.1442417331813e-05,
1667
+ "loss": 2.8929,
1668
+ "step": 1185
1669
+ },
1670
+ {
1671
+ "epoch": 3.85,
1672
+ "grad_norm": 0.20386841893196106,
1673
+ "learning_rate": 1.1356898517673888e-05,
1674
+ "loss": 2.8548,
1675
+ "step": 1190
1676
+ },
1677
+ {
1678
+ "epoch": 3.86,
1679
+ "grad_norm": 0.19758112728595734,
1680
+ "learning_rate": 1.127137970353478e-05,
1681
+ "loss": 2.8811,
1682
+ "step": 1195
1683
+ },
1684
+ {
1685
+ "epoch": 3.88,
1686
+ "grad_norm": 0.21303939819335938,
1687
+ "learning_rate": 1.1185860889395667e-05,
1688
+ "loss": 2.879,
1689
+ "step": 1200
1690
+ },
1691
+ {
1692
+ "epoch": 3.89,
1693
+ "grad_norm": 0.1993599683046341,
1694
+ "learning_rate": 1.1100342075256556e-05,
1695
+ "loss": 2.8718,
1696
+ "step": 1205
1697
+ },
1698
+ {
1699
+ "epoch": 3.91,
1700
+ "grad_norm": 0.20202603936195374,
1701
+ "learning_rate": 1.1014823261117445e-05,
1702
+ "loss": 2.8337,
1703
+ "step": 1210
1704
+ },
1705
+ {
1706
+ "epoch": 3.93,
1707
+ "grad_norm": 0.20566709339618683,
1708
+ "learning_rate": 1.0929304446978336e-05,
1709
+ "loss": 2.8658,
1710
+ "step": 1215
1711
+ },
1712
+ {
1713
+ "epoch": 3.94,
1714
+ "grad_norm": 0.18417729437351227,
1715
+ "learning_rate": 1.0843785632839225e-05,
1716
+ "loss": 2.853,
1717
+ "step": 1220
1718
+ },
1719
+ {
1720
+ "epoch": 3.96,
1721
+ "grad_norm": 0.19506323337554932,
1722
+ "learning_rate": 1.0758266818700114e-05,
1723
+ "loss": 2.84,
1724
+ "step": 1225
1725
+ },
1726
+ {
1727
+ "epoch": 3.97,
1728
+ "grad_norm": 0.20047935843467712,
1729
+ "learning_rate": 1.0672748004561003e-05,
1730
+ "loss": 2.8488,
1731
+ "step": 1230
1732
+ },
1733
+ {
1734
+ "epoch": 3.99,
1735
+ "grad_norm": 0.187282994389534,
1736
+ "learning_rate": 1.0587229190421892e-05,
1737
+ "loss": 2.84,
1738
+ "step": 1235
1739
+ },
1740
+ {
1741
+ "epoch": 4.01,
1742
+ "grad_norm": 0.19961225986480713,
1743
+ "learning_rate": 1.0501710376282783e-05,
1744
+ "loss": 2.873,
1745
+ "step": 1240
1746
+ },
1747
+ {
1748
+ "epoch": 4.02,
1749
+ "grad_norm": 0.20117315649986267,
1750
+ "learning_rate": 1.0416191562143672e-05,
1751
+ "loss": 2.8046,
1752
+ "step": 1245
1753
+ },
1754
+ {
1755
+ "epoch": 4.04,
1756
+ "grad_norm": 0.19239380955696106,
1757
+ "learning_rate": 1.0330672748004561e-05,
1758
+ "loss": 2.8576,
1759
+ "step": 1250
1760
+ },
1761
+ {
1762
+ "epoch": 4.06,
1763
+ "grad_norm": 0.19857007265090942,
1764
+ "learning_rate": 1.024515393386545e-05,
1765
+ "loss": 2.8165,
1766
+ "step": 1255
1767
+ },
1768
+ {
1769
+ "epoch": 4.07,
1770
+ "grad_norm": 0.2090427130460739,
1771
+ "learning_rate": 1.015963511972634e-05,
1772
+ "loss": 2.8076,
1773
+ "step": 1260
1774
+ },
1775
+ {
1776
+ "epoch": 4.09,
1777
+ "grad_norm": 0.1895773708820343,
1778
+ "learning_rate": 1.0074116305587228e-05,
1779
+ "loss": 2.792,
1780
+ "step": 1265
1781
+ },
1782
+ {
1783
+ "epoch": 4.1,
1784
+ "grad_norm": 0.20731306076049805,
1785
+ "learning_rate": 9.98859749144812e-06,
1786
+ "loss": 2.8121,
1787
+ "step": 1270
1788
+ },
1789
+ {
1790
+ "epoch": 4.12,
1791
+ "grad_norm": 0.19480618834495544,
1792
+ "learning_rate": 9.903078677309008e-06,
1793
+ "loss": 2.8261,
1794
+ "step": 1275
1795
+ },
1796
+ {
1797
+ "epoch": 4.14,
1798
+ "grad_norm": 0.1925288587808609,
1799
+ "learning_rate": 9.817559863169897e-06,
1800
+ "loss": 2.8131,
1801
+ "step": 1280
1802
+ },
1803
+ {
1804
+ "epoch": 4.15,
1805
+ "grad_norm": 0.21479365229606628,
1806
+ "learning_rate": 9.732041049030787e-06,
1807
+ "loss": 2.8021,
1808
+ "step": 1285
1809
+ },
1810
+ {
1811
+ "epoch": 4.17,
1812
+ "grad_norm": 0.19130577147006989,
1813
+ "learning_rate": 9.646522234891676e-06,
1814
+ "loss": 2.8115,
1815
+ "step": 1290
1816
+ },
1817
+ {
1818
+ "epoch": 4.19,
1819
+ "grad_norm": 0.22513242065906525,
1820
+ "learning_rate": 9.561003420752566e-06,
1821
+ "loss": 2.8134,
1822
+ "step": 1295
1823
+ },
1824
+ {
1825
+ "epoch": 4.2,
1826
+ "grad_norm": 0.204105406999588,
1827
+ "learning_rate": 9.475484606613456e-06,
1828
+ "loss": 2.8208,
1829
+ "step": 1300
1830
+ },
1831
+ {
1832
+ "epoch": 4.22,
1833
+ "grad_norm": 0.2156701236963272,
1834
+ "learning_rate": 9.389965792474345e-06,
1835
+ "loss": 2.8246,
1836
+ "step": 1305
1837
+ },
1838
+ {
1839
+ "epoch": 4.23,
1840
+ "grad_norm": 0.2150842398405075,
1841
+ "learning_rate": 9.304446978335234e-06,
1842
+ "loss": 2.8054,
1843
+ "step": 1310
1844
+ },
1845
+ {
1846
+ "epoch": 4.25,
1847
+ "grad_norm": 0.19922739267349243,
1848
+ "learning_rate": 9.218928164196123e-06,
1849
+ "loss": 2.7994,
1850
+ "step": 1315
1851
+ },
1852
+ {
1853
+ "epoch": 4.27,
1854
+ "grad_norm": 0.20415738224983215,
1855
+ "learning_rate": 9.133409350057014e-06,
1856
+ "loss": 2.7762,
1857
+ "step": 1320
1858
+ },
1859
+ {
1860
+ "epoch": 4.28,
1861
+ "grad_norm": 0.21822912991046906,
1862
+ "learning_rate": 9.047890535917903e-06,
1863
+ "loss": 2.8363,
1864
+ "step": 1325
1865
+ },
1866
+ {
1867
+ "epoch": 4.3,
1868
+ "grad_norm": 0.1866757571697235,
1869
+ "learning_rate": 8.962371721778792e-06,
1870
+ "loss": 2.8213,
1871
+ "step": 1330
1872
+ },
1873
+ {
1874
+ "epoch": 4.31,
1875
+ "grad_norm": 0.18803808093070984,
1876
+ "learning_rate": 8.876852907639681e-06,
1877
+ "loss": 2.8232,
1878
+ "step": 1335
1879
+ },
1880
+ {
1881
+ "epoch": 4.33,
1882
+ "grad_norm": 0.2101515531539917,
1883
+ "learning_rate": 8.79133409350057e-06,
1884
+ "loss": 2.8275,
1885
+ "step": 1340
1886
+ },
1887
+ {
1888
+ "epoch": 4.35,
1889
+ "grad_norm": 0.2047651708126068,
1890
+ "learning_rate": 8.705815279361461e-06,
1891
+ "loss": 2.8112,
1892
+ "step": 1345
1893
+ },
1894
+ {
1895
+ "epoch": 4.36,
1896
+ "grad_norm": 0.1994614452123642,
1897
+ "learning_rate": 8.62029646522235e-06,
1898
+ "loss": 2.8344,
1899
+ "step": 1350
1900
+ },
1901
+ {
1902
+ "epoch": 4.38,
1903
+ "grad_norm": 0.21065644919872284,
1904
+ "learning_rate": 8.534777651083239e-06,
1905
+ "loss": 2.811,
1906
+ "step": 1355
1907
+ },
1908
+ {
1909
+ "epoch": 4.4,
1910
+ "grad_norm": 0.21383103728294373,
1911
+ "learning_rate": 8.449258836944128e-06,
1912
+ "loss": 2.8073,
1913
+ "step": 1360
1914
+ },
1915
+ {
1916
+ "epoch": 4.41,
1917
+ "grad_norm": 0.20263946056365967,
1918
+ "learning_rate": 8.363740022805016e-06,
1919
+ "loss": 2.8115,
1920
+ "step": 1365
1921
+ },
1922
+ {
1923
+ "epoch": 4.43,
1924
+ "grad_norm": 0.19944559037685394,
1925
+ "learning_rate": 8.278221208665906e-06,
1926
+ "loss": 2.8155,
1927
+ "step": 1370
1928
+ },
1929
+ {
1930
+ "epoch": 4.44,
1931
+ "grad_norm": 0.18889665603637695,
1932
+ "learning_rate": 8.192702394526796e-06,
1933
+ "loss": 2.8307,
1934
+ "step": 1375
1935
+ },
1936
+ {
1937
+ "epoch": 4.46,
1938
+ "grad_norm": 0.20692084729671478,
1939
+ "learning_rate": 8.107183580387685e-06,
1940
+ "loss": 2.8126,
1941
+ "step": 1380
1942
+ },
1943
+ {
1944
+ "epoch": 4.48,
1945
+ "grad_norm": 0.21253955364227295,
1946
+ "learning_rate": 8.021664766248574e-06,
1947
+ "loss": 2.8035,
1948
+ "step": 1385
1949
+ },
1950
+ {
1951
+ "epoch": 4.49,
1952
+ "grad_norm": 0.20105835795402527,
1953
+ "learning_rate": 7.936145952109463e-06,
1954
+ "loss": 2.8426,
1955
+ "step": 1390
1956
+ },
1957
+ {
1958
+ "epoch": 4.51,
1959
+ "grad_norm": 0.21002836525440216,
1960
+ "learning_rate": 7.850627137970354e-06,
1961
+ "loss": 2.8018,
1962
+ "step": 1395
1963
+ },
1964
+ {
1965
+ "epoch": 4.52,
1966
+ "grad_norm": 0.22299815714359283,
1967
+ "learning_rate": 7.765108323831243e-06,
1968
+ "loss": 2.8413,
1969
+ "step": 1400
1970
+ },
1971
+ {
1972
+ "epoch": 4.54,
1973
+ "grad_norm": 0.20295199751853943,
1974
+ "learning_rate": 7.679589509692132e-06,
1975
+ "loss": 2.8411,
1976
+ "step": 1405
1977
+ },
1978
+ {
1979
+ "epoch": 4.56,
1980
+ "grad_norm": 0.20713861286640167,
1981
+ "learning_rate": 7.594070695553022e-06,
1982
+ "loss": 2.8258,
1983
+ "step": 1410
1984
+ },
1985
+ {
1986
+ "epoch": 4.57,
1987
+ "grad_norm": 0.21353642642498016,
1988
+ "learning_rate": 7.508551881413911e-06,
1989
+ "loss": 2.8142,
1990
+ "step": 1415
1991
+ },
1992
+ {
1993
+ "epoch": 4.59,
1994
+ "grad_norm": 0.2093668282032013,
1995
+ "learning_rate": 7.4230330672748e-06,
1996
+ "loss": 2.8135,
1997
+ "step": 1420
1998
+ },
1999
+ {
2000
+ "epoch": 4.61,
2001
+ "grad_norm": 0.2017381191253662,
2002
+ "learning_rate": 7.33751425313569e-06,
2003
+ "loss": 2.8181,
2004
+ "step": 1425
2005
+ },
2006
+ {
2007
+ "epoch": 4.62,
2008
+ "grad_norm": 0.2110336720943451,
2009
+ "learning_rate": 7.251995438996579e-06,
2010
+ "loss": 2.8025,
2011
+ "step": 1430
2012
+ },
2013
+ {
2014
+ "epoch": 4.64,
2015
+ "grad_norm": 0.20439700782299042,
2016
+ "learning_rate": 7.166476624857469e-06,
2017
+ "loss": 2.8214,
2018
+ "step": 1435
2019
+ },
2020
+ {
2021
+ "epoch": 4.65,
2022
+ "grad_norm": 0.22022387385368347,
2023
+ "learning_rate": 7.080957810718358e-06,
2024
+ "loss": 2.8007,
2025
+ "step": 1440
2026
+ },
2027
+ {
2028
+ "epoch": 4.67,
2029
+ "grad_norm": 0.19444230198860168,
2030
+ "learning_rate": 6.995438996579247e-06,
2031
+ "loss": 2.8183,
2032
+ "step": 1445
2033
+ },
2034
+ {
2035
+ "epoch": 4.69,
2036
+ "grad_norm": 0.20547039806842804,
2037
+ "learning_rate": 6.909920182440137e-06,
2038
+ "loss": 2.8066,
2039
+ "step": 1450
2040
+ },
2041
+ {
2042
+ "epoch": 4.7,
2043
+ "grad_norm": 0.20443764328956604,
2044
+ "learning_rate": 6.824401368301026e-06,
2045
+ "loss": 2.8312,
2046
+ "step": 1455
2047
+ },
2048
+ {
2049
+ "epoch": 4.72,
2050
+ "grad_norm": 0.20165589451789856,
2051
+ "learning_rate": 6.738882554161916e-06,
2052
+ "loss": 2.8389,
2053
+ "step": 1460
2054
+ },
2055
+ {
2056
+ "epoch": 4.73,
2057
+ "grad_norm": 0.222417414188385,
2058
+ "learning_rate": 6.653363740022805e-06,
2059
+ "loss": 2.8186,
2060
+ "step": 1465
2061
+ },
2062
+ {
2063
+ "epoch": 4.75,
2064
+ "grad_norm": 0.21495650708675385,
2065
+ "learning_rate": 6.5678449258836945e-06,
2066
+ "loss": 2.8433,
2067
+ "step": 1470
2068
+ },
2069
+ {
2070
+ "epoch": 4.77,
2071
+ "grad_norm": 0.2121262550354004,
2072
+ "learning_rate": 6.4823261117445844e-06,
2073
+ "loss": 2.8128,
2074
+ "step": 1475
2075
+ },
2076
+ {
2077
+ "epoch": 4.78,
2078
+ "grad_norm": 0.2040678709745407,
2079
+ "learning_rate": 6.3968072976054735e-06,
2080
+ "loss": 2.8367,
2081
+ "step": 1480
2082
+ },
2083
+ {
2084
+ "epoch": 4.8,
2085
+ "grad_norm": 0.19694024324417114,
2086
+ "learning_rate": 6.3112884834663635e-06,
2087
+ "loss": 2.782,
2088
+ "step": 1485
2089
+ },
2090
+ {
2091
+ "epoch": 4.82,
2092
+ "grad_norm": 0.20558282732963562,
2093
+ "learning_rate": 6.225769669327253e-06,
2094
+ "loss": 2.805,
2095
+ "step": 1490
2096
+ },
2097
+ {
2098
+ "epoch": 4.83,
2099
+ "grad_norm": 0.2115090787410736,
2100
+ "learning_rate": 6.140250855188141e-06,
2101
+ "loss": 2.8085,
2102
+ "step": 1495
2103
+ },
2104
+ {
2105
+ "epoch": 4.85,
2106
+ "grad_norm": 0.2121584117412567,
2107
+ "learning_rate": 6.054732041049031e-06,
2108
+ "loss": 2.7917,
2109
+ "step": 1500
2110
+ },
2111
+ {
2112
+ "epoch": 4.86,
2113
+ "grad_norm": 0.200391486287117,
2114
+ "learning_rate": 5.96921322690992e-06,
2115
+ "loss": 2.7941,
2116
+ "step": 1505
2117
+ },
2118
+ {
2119
+ "epoch": 4.88,
2120
+ "grad_norm": 0.21317771077156067,
2121
+ "learning_rate": 5.88369441277081e-06,
2122
+ "loss": 2.7956,
2123
+ "step": 1510
2124
+ },
2125
+ {
2126
+ "epoch": 4.9,
2127
+ "grad_norm": 0.21627019345760345,
2128
+ "learning_rate": 5.798175598631699e-06,
2129
+ "loss": 2.8107,
2130
+ "step": 1515
2131
+ },
2132
+ {
2133
+ "epoch": 4.91,
2134
+ "grad_norm": 0.2093602418899536,
2135
+ "learning_rate": 5.712656784492588e-06,
2136
+ "loss": 2.8022,
2137
+ "step": 1520
2138
+ },
2139
+ {
2140
+ "epoch": 4.93,
2141
+ "grad_norm": 0.1991538405418396,
2142
+ "learning_rate": 5.627137970353478e-06,
2143
+ "loss": 2.8011,
2144
+ "step": 1525
2145
+ },
2146
+ {
2147
+ "epoch": 4.94,
2148
+ "grad_norm": 0.20621471107006073,
2149
+ "learning_rate": 5.541619156214367e-06,
2150
+ "loss": 2.7987,
2151
+ "step": 1530
2152
+ },
2153
+ {
2154
+ "epoch": 4.96,
2155
+ "grad_norm": 0.21053887903690338,
2156
+ "learning_rate": 5.456100342075257e-06,
2157
+ "loss": 2.8148,
2158
+ "step": 1535
2159
+ },
2160
+ {
2161
+ "epoch": 4.98,
2162
+ "grad_norm": 0.19427061080932617,
2163
+ "learning_rate": 5.370581527936146e-06,
2164
+ "loss": 2.8302,
2165
+ "step": 1540
2166
+ },
2167
+ {
2168
+ "epoch": 4.99,
2169
+ "grad_norm": 0.20684009790420532,
2170
+ "learning_rate": 5.285062713797035e-06,
2171
+ "loss": 2.8071,
2172
+ "step": 1545
2173
+ },
2174
+ {
2175
+ "epoch": 5.01,
2176
+ "grad_norm": 0.2079547643661499,
2177
+ "learning_rate": 5.199543899657925e-06,
2178
+ "loss": 2.7831,
2179
+ "step": 1550
2180
+ },
2181
+ {
2182
+ "epoch": 5.03,
2183
+ "grad_norm": 0.2271408885717392,
2184
+ "learning_rate": 5.114025085518814e-06,
2185
+ "loss": 2.7772,
2186
+ "step": 1555
2187
+ },
2188
+ {
2189
+ "epoch": 5.04,
2190
+ "grad_norm": 0.21122708916664124,
2191
+ "learning_rate": 5.028506271379704e-06,
2192
+ "loss": 2.7941,
2193
+ "step": 1560
2194
+ },
2195
+ {
2196
+ "epoch": 5.06,
2197
+ "grad_norm": 0.20626038312911987,
2198
+ "learning_rate": 4.9429874572405934e-06,
2199
+ "loss": 2.7601,
2200
+ "step": 1565
2201
+ },
2202
+ {
2203
+ "epoch": 5.07,
2204
+ "grad_norm": 0.21984724700450897,
2205
+ "learning_rate": 4.8574686431014825e-06,
2206
+ "loss": 2.7797,
2207
+ "step": 1570
2208
+ },
2209
+ {
2210
+ "epoch": 5.09,
2211
+ "grad_norm": 0.24193266034126282,
2212
+ "learning_rate": 4.7719498289623725e-06,
2213
+ "loss": 2.7841,
2214
+ "step": 1575
2215
+ },
2216
+ {
2217
+ "epoch": 5.11,
2218
+ "grad_norm": 0.2213587611913681,
2219
+ "learning_rate": 4.686431014823261e-06,
2220
+ "loss": 2.7867,
2221
+ "step": 1580
2222
+ },
2223
+ {
2224
+ "epoch": 5.12,
2225
+ "grad_norm": 0.20624710619449615,
2226
+ "learning_rate": 4.600912200684151e-06,
2227
+ "loss": 2.7814,
2228
+ "step": 1585
2229
+ },
2230
+ {
2231
+ "epoch": 5.14,
2232
+ "grad_norm": 0.21868358552455902,
2233
+ "learning_rate": 4.51539338654504e-06,
2234
+ "loss": 2.8011,
2235
+ "step": 1590
2236
+ },
2237
+ {
2238
+ "epoch": 5.15,
2239
+ "grad_norm": 0.22464773058891296,
2240
+ "learning_rate": 4.429874572405929e-06,
2241
+ "loss": 2.7808,
2242
+ "step": 1595
2243
+ },
2244
+ {
2245
+ "epoch": 5.17,
2246
+ "grad_norm": 0.21239249408245087,
2247
+ "learning_rate": 4.344355758266819e-06,
2248
+ "loss": 2.7682,
2249
+ "step": 1600
2250
+ },
2251
+ {
2252
+ "epoch": 5.19,
2253
+ "grad_norm": 0.2032070755958557,
2254
+ "learning_rate": 3e-05,
2255
+ "loss": 2.7738,
2256
+ "step": 1605
2257
+ },
2258
+ {
2259
+ "epoch": 5.21,
2260
+ "grad_norm": 0.24147231876850128,
2261
+ "learning_rate": 3e-05,
2262
+ "loss": 2.8026,
2263
+ "step": 1610
2264
+ },
2265
+ {
2266
+ "epoch": 5.23,
2267
+ "grad_norm": 0.21959525346755981,
2268
+ "learning_rate": 3e-05,
2269
+ "loss": 2.7317,
2270
+ "step": 1615
2271
+ },
2272
+ {
2273
+ "epoch": 5.24,
2274
+ "grad_norm": 0.22994889318943024,
2275
+ "learning_rate": 3e-05,
2276
+ "loss": 2.7574,
2277
+ "step": 1620
2278
+ },
2279
+ {
2280
+ "epoch": 5.26,
2281
+ "grad_norm": 0.22466912865638733,
2282
+ "learning_rate": 3e-05,
2283
+ "loss": 2.7974,
2284
+ "step": 1625
2285
+ },
2286
+ {
2287
+ "epoch": 5.27,
2288
+ "grad_norm": 0.23403416574001312,
2289
+ "learning_rate": 3e-05,
2290
+ "loss": 2.771,
2291
+ "step": 1630
2292
+ },
2293
+ {
2294
+ "epoch": 5.29,
2295
+ "grad_norm": 0.22054152190685272,
2296
+ "learning_rate": 3e-05,
2297
+ "loss": 2.792,
2298
+ "step": 1635
2299
+ },
2300
+ {
2301
+ "epoch": 5.31,
2302
+ "grad_norm": 0.2172236293554306,
2303
+ "learning_rate": 3e-05,
2304
+ "loss": 2.7555,
2305
+ "step": 1640
2306
+ },
2307
+ {
2308
+ "epoch": 5.32,
2309
+ "grad_norm": 0.21500498056411743,
2310
+ "learning_rate": 3e-05,
2311
+ "loss": 2.8126,
2312
+ "step": 1645
2313
+ },
2314
+ {
2315
+ "epoch": 5.34,
2316
+ "grad_norm": 0.2480950951576233,
2317
+ "learning_rate": 3e-05,
2318
+ "loss": 2.7834,
2319
+ "step": 1650
2320
+ },
2321
+ {
2322
+ "epoch": 5.36,
2323
+ "grad_norm": 0.22709690034389496,
2324
+ "learning_rate": 3e-05,
2325
+ "loss": 2.7954,
2326
+ "step": 1655
2327
+ },
2328
+ {
2329
+ "epoch": 5.37,
2330
+ "grad_norm": 0.22354279458522797,
2331
+ "learning_rate": 3e-05,
2332
+ "loss": 2.7705,
2333
+ "step": 1660
2334
+ },
2335
+ {
2336
+ "epoch": 5.39,
2337
+ "grad_norm": 0.26233839988708496,
2338
+ "learning_rate": 3e-05,
2339
+ "loss": 2.7603,
2340
+ "step": 1665
2341
+ },
2342
+ {
2343
+ "epoch": 5.4,
2344
+ "grad_norm": 0.23743155598640442,
2345
+ "learning_rate": 3e-05,
2346
+ "loss": 2.7997,
2347
+ "step": 1670
2348
+ },
2349
+ {
2350
+ "epoch": 5.42,
2351
+ "grad_norm": 0.23243878781795502,
2352
+ "learning_rate": 3e-05,
2353
+ "loss": 2.7624,
2354
+ "step": 1675
2355
+ },
2356
+ {
2357
+ "epoch": 5.44,
2358
+ "grad_norm": 0.2384800910949707,
2359
+ "learning_rate": 3e-05,
2360
+ "loss": 2.7781,
2361
+ "step": 1680
2362
+ },
2363
+ {
2364
+ "epoch": 5.45,
2365
+ "grad_norm": 0.2814362347126007,
2366
+ "learning_rate": 3e-05,
2367
+ "loss": 2.7528,
2368
+ "step": 1685
2369
+ },
2370
+ {
2371
+ "epoch": 5.47,
2372
+ "grad_norm": 0.2459874302148819,
2373
+ "learning_rate": 3e-05,
2374
+ "loss": 2.8155,
2375
+ "step": 1690
2376
+ },
2377
+ {
2378
+ "epoch": 5.48,
2379
+ "grad_norm": 0.25781503319740295,
2380
+ "learning_rate": 3e-05,
2381
+ "loss": 2.7466,
2382
+ "step": 1695
2383
+ },
2384
+ {
2385
+ "epoch": 5.5,
2386
+ "grad_norm": 0.24334032833576202,
2387
+ "learning_rate": 3e-05,
2388
+ "loss": 2.8122,
2389
+ "step": 1700
2390
+ },
2391
+ {
2392
+ "epoch": 5.52,
2393
+ "grad_norm": 0.24697226285934448,
2394
+ "learning_rate": 3e-05,
2395
+ "loss": 2.7956,
2396
+ "step": 1705
2397
+ },
2398
+ {
2399
+ "epoch": 5.53,
2400
+ "grad_norm": 0.24803857505321503,
2401
+ "learning_rate": 3e-05,
2402
+ "loss": 2.7465,
2403
+ "step": 1710
2404
+ },
2405
+ {
2406
+ "epoch": 5.55,
2407
+ "grad_norm": 0.24284283816814423,
2408
+ "learning_rate": 3e-05,
2409
+ "loss": 2.7559,
2410
+ "step": 1715
2411
+ },
2412
+ {
2413
+ "epoch": 5.57,
2414
+ "grad_norm": 0.23661333322525024,
2415
+ "learning_rate": 3e-05,
2416
+ "loss": 2.7692,
2417
+ "step": 1720
2418
+ },
2419
+ {
2420
+ "epoch": 5.58,
2421
+ "grad_norm": 0.2449016571044922,
2422
+ "learning_rate": 3e-05,
2423
+ "loss": 2.7318,
2424
+ "step": 1725
2425
+ },
2426
+ {
2427
+ "epoch": 5.6,
2428
+ "grad_norm": 0.2179490625858307,
2429
+ "learning_rate": 3e-05,
2430
+ "loss": 2.7636,
2431
+ "step": 1730
2432
+ },
2433
+ {
2434
+ "epoch": 5.61,
2435
+ "grad_norm": 0.22239655256271362,
2436
+ "learning_rate": 3e-05,
2437
+ "loss": 2.7878,
2438
+ "step": 1735
2439
+ },
2440
+ {
2441
+ "epoch": 5.63,
2442
+ "grad_norm": 0.23438027501106262,
2443
+ "learning_rate": 3e-05,
2444
+ "loss": 2.7741,
2445
+ "step": 1740
2446
+ },
2447
+ {
2448
+ "epoch": 5.65,
2449
+ "grad_norm": 0.24237991869449615,
2450
+ "learning_rate": 3e-05,
2451
+ "loss": 2.7865,
2452
+ "step": 1745
2453
+ },
2454
+ {
2455
+ "epoch": 5.66,
2456
+ "grad_norm": 0.2225206047296524,
2457
+ "learning_rate": 3e-05,
2458
+ "loss": 2.7905,
2459
+ "step": 1750
2460
+ },
2461
+ {
2462
+ "epoch": 5.68,
2463
+ "grad_norm": 0.2413685917854309,
2464
+ "learning_rate": 3e-05,
2465
+ "loss": 2.745,
2466
+ "step": 1755
2467
+ },
2468
+ {
2469
+ "epoch": 5.69,
2470
+ "grad_norm": 0.23114730417728424,
2471
+ "learning_rate": 3e-05,
2472
+ "loss": 2.7465,
2473
+ "step": 1760
2474
+ },
2475
+ {
2476
+ "epoch": 5.71,
2477
+ "grad_norm": 0.2584913969039917,
2478
+ "learning_rate": 3e-05,
2479
+ "loss": 2.7599,
2480
+ "step": 1765
2481
+ },
2482
+ {
2483
+ "epoch": 5.73,
2484
+ "grad_norm": 0.2540834844112396,
2485
+ "learning_rate": 3e-05,
2486
+ "loss": 2.7412,
2487
+ "step": 1770
2488
+ },
2489
+ {
2490
+ "epoch": 5.74,
2491
+ "grad_norm": 0.28105732798576355,
2492
+ "learning_rate": 3e-05,
2493
+ "loss": 2.7226,
2494
+ "step": 1775
2495
+ },
2496
+ {
2497
+ "epoch": 5.76,
2498
+ "grad_norm": 0.24792756140232086,
2499
+ "learning_rate": 3e-05,
2500
+ "loss": 2.7304,
2501
+ "step": 1780
2502
+ },
2503
+ {
2504
+ "epoch": 5.78,
2505
+ "grad_norm": 0.2415696680545807,
2506
+ "learning_rate": 3e-05,
2507
+ "loss": 2.7635,
2508
+ "step": 1785
2509
+ },
2510
+ {
2511
+ "epoch": 5.79,
2512
+ "grad_norm": 0.264769971370697,
2513
+ "learning_rate": 3e-05,
2514
+ "loss": 2.7464,
2515
+ "step": 1790
2516
+ },
2517
+ {
2518
+ "epoch": 5.81,
2519
+ "grad_norm": 0.23595955967903137,
2520
+ "learning_rate": 5e-05,
2521
+ "loss": 2.745,
2522
+ "step": 1795
2523
+ },
2524
+ {
2525
+ "epoch": 5.82,
2526
+ "grad_norm": 0.24608966708183289,
2527
+ "learning_rate": 5e-05,
2528
+ "loss": 2.7633,
2529
+ "step": 1800
2530
+ },
2531
+ {
2532
+ "epoch": 5.84,
2533
+ "grad_norm": 0.2487153708934784,
2534
+ "learning_rate": 3e-05,
2535
+ "loss": 2.7586,
2536
+ "step": 1805
2537
+ },
2538
+ {
2539
+ "epoch": 5.86,
2540
+ "grad_norm": 0.24857081472873688,
2541
+ "learning_rate": 3e-05,
2542
+ "loss": 2.7464,
2543
+ "step": 1810
2544
+ },
2545
+ {
2546
+ "epoch": 5.87,
2547
+ "grad_norm": 0.2426629513502121,
2548
+ "learning_rate": 3e-05,
2549
+ "loss": 2.7385,
2550
+ "step": 1815
2551
+ },
2552
+ {
2553
+ "epoch": 5.89,
2554
+ "grad_norm": 0.23641450703144073,
2555
+ "learning_rate": 3e-05,
2556
+ "loss": 2.7677,
2557
+ "step": 1820
2558
+ },
2559
+ {
2560
+ "epoch": 5.9,
2561
+ "grad_norm": 0.23726724088191986,
2562
+ "learning_rate": 3e-05,
2563
+ "loss": 2.7348,
2564
+ "step": 1825
2565
+ },
2566
+ {
2567
+ "epoch": 5.92,
2568
+ "grad_norm": 0.26856401562690735,
2569
+ "learning_rate": 3e-05,
2570
+ "loss": 2.7428,
2571
+ "step": 1830
2572
+ },
2573
+ {
2574
+ "epoch": 5.93,
2575
+ "step": 1832,
2576
+ "total_flos": 2.9122521101461094e+19,
2577
+ "train_loss": 0.048051854148181763,
2578
+ "train_runtime": 5063.5443,
2579
+ "train_samples_per_second": 54.75,
2580
+ "train_steps_per_second": 0.427
2581
+ }
2582
+ ],
2583
+ "logging_steps": 5,
2584
+ "max_steps": 2163,
2585
+ "num_input_tokens_seen": 0,
2586
+ "num_train_epochs": 7,
2587
+ "save_steps": 200,
2588
+ "total_flos": 2.9122521101461094e+19,
2589
+ "train_batch_size": 8,
2590
+ "trial_name": null,
2591
+ "trial_params": null
2592
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c74447e73949de815ee16e8b0446c4452b54de282d9d694bf33539c2386a0bda
3
+ size 5112