LoneStriker commited on
Commit
d7e1ce4
1 Parent(s): b09cec7

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: gemma-terms-of-use
4
+ license_link: https://ai.google.dev/gemma/terms
5
+ base_model: google/gemma-7b
6
+ tags:
7
+ - alignment-handbook
8
+ - trl
9
+ - sft
10
+ - generated_from_trainer
11
+ - trl
12
+ - sft
13
+ - generated_from_trainer
14
+ datasets:
15
+ - HuggingFaceH4/deita-10k-v0-sft
16
+ model-index:
17
+ - name: zephyr-7b-gemma-sft
18
+ results: []
19
+ language:
20
+ - en
21
+ ---
22
+
23
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
24
+ should probably proofread and complete it, then remove this comment. -->
25
+
26
+ # zephyr-7b-gemma-sft
27
+
28
+ This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the HuggingFaceH4/deita-10k-v0-sft dataset.
29
+ It achieves the following results on the evaluation set:
30
+ - Loss: 0.9732
31
+
32
+ ## Model description
33
+
34
+ More information needed
35
+
36
+ ## Intended uses & limitations
37
+
38
+ More information needed
39
+
40
+ ## Training and evaluation data
41
+
42
+ More information needed
43
+
44
+ ## Training procedure
45
+
46
+ ### Training hyperparameters
47
+
48
+ The following hyperparameters were used during training:
49
+ - learning_rate: 2e-05
50
+ - train_batch_size: 4
51
+ - eval_batch_size: 4
52
+ - seed: 42
53
+ - distributed_type: multi-GPU
54
+ - num_devices: 16
55
+ - gradient_accumulation_steps: 2
56
+ - total_train_batch_size: 128
57
+ - total_eval_batch_size: 64
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: cosine
60
+ - lr_scheduler_warmup_ratio: 0.1
61
+ - num_epochs: 3
62
+
63
+ ### Training results
64
+
65
+ | Training Loss | Epoch | Step | Validation Loss |
66
+ |:-------------:|:-----:|:----:|:---------------:|
67
+ | 0.9482 | 1.0 | 299 | 0.9848 |
68
+ | 0.8139 | 2.0 | 599 | 0.9610 |
69
+ | 0.722 | 2.99 | 897 | 0.9732 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.39.0.dev0
75
+ - Pytorch 2.1.2+cu121
76
+ - Datasets 2.14.6
77
+ - Tokenizers 0.15.1
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.99,
3
+ "eval_loss": 0.973169207572937,
4
+ "eval_runtime": 22.1864,
5
+ "eval_samples": 500,
6
+ "eval_samples_per_second": 86.224,
7
+ "eval_steps_per_second": 1.352,
8
+ "train_loss": 1.0022602648772259,
9
+ "train_runtime": 5184.357,
10
+ "train_samples": 9500,
11
+ "train_samples_per_second": 22.178,
12
+ "train_steps_per_second": 0.173
13
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/gemma-7b",
3
+ "architectures": [
4
+ "GemmaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 2,
9
+ "eos_token_id": 1,
10
+ "head_dim": 256,
11
+ "hidden_act": "gelu",
12
+ "hidden_size": 3072,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 24576,
15
+ "max_position_embeddings": 8192,
16
+ "model_type": "gemma",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 16,
20
+ "pad_token_id": 0,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.39.0.dev0",
26
+ "use_cache": true,
27
+ "vocab_size": 256000
28
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.99,
3
+ "eval_loss": 0.973169207572937,
4
+ "eval_runtime": 22.1864,
5
+ "eval_samples": 500,
6
+ "eval_samples_per_second": 86.224,
7
+ "eval_steps_per_second": 1.352
8
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.39.0.dev0"
7
+ }
huggingface-metadata.txt ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ url: https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-sft-v0.1
2
+ branch: main
3
+ download date: 2024-03-01 22:09:44
4
+ sha256sum:
5
+ 10276a0f87e08f62e2829230be70ff541d6e234ffe356ddbf25abeb57433c01b model-00001-of-00004.safetensors
6
+ ad38dd72c60feb83f5f94b7c637f876a74d27a50fc122da30bf35b3213802a41 model-00002-of-00004.safetensors
7
+ 291250b5d90bd318addab6e1df790bf70cb702814540fbeff26a67d06ee5371c model-00003-of-00004.safetensors
8
+ 809106cf81c8dfa99d1e3e223e42289fc3b51f1227bfdf9070c4fd113858a448 model-00004-of-00004.safetensors
9
+ 22449cb9ef4bad0db7dd93b46ddff7ab7d6a654dd4f903e130ddb6361eac3af5 tokenizer.json
model.safetensors.index.json ADDED
@@ -0,0 +1,261 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 17075361792
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
97
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
98
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
99
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
100
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
101
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
102
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
103
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
104
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
105
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
106
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
107
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
108
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
109
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
110
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
111
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
112
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
113
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
114
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
115
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
116
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
125
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00004.safetensors",
161
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
162
+ "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
163
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
164
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
165
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors",
170
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
171
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
172
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
173
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
174
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
175
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
176
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
177
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
178
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
179
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
180
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
181
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
182
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
183
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
184
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
185
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
186
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
187
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
188
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
189
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
190
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
191
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
192
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
193
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
194
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
195
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
196
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
197
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
198
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
199
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
200
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
201
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
202
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
203
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
204
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
205
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
206
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
207
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
208
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
209
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
210
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
211
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
212
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
213
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
214
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
215
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
224
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
225
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
226
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
227
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
228
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
229
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
230
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
231
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
232
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
233
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
234
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
235
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
236
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
237
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
238
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
239
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
240
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
241
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
242
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
243
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
244
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
245
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
246
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
247
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
248
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
249
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
250
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
251
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
252
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
253
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
254
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
255
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
256
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
257
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
258
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
259
+ "model.norm.weight": "model-00004-of-00004.safetensors"
260
+ }
261
+ }
output.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d5420c31f63f3f1db61c4b3f76e5c9fb76c5b3ad15c5ef184b647ab85388e76
3
+ size 8006712152
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<bos>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<pad>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22449cb9ef4bad0db7dd93b46ddff7ab7d6a654dd4f903e130ddb6361eac3af5
3
+ size 17477473
tokenizer_config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<bos>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "106": {
38
+ "content": "<|im_start|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "107": {
46
+ "content": "<|im_end|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ }
53
+ },
54
+ "additional_special_tokens": [
55
+ "<|im_start|>",
56
+ "<|im_end|>"
57
+ ],
58
+ "bos_token": "<bos>",
59
+ "chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}",
60
+ "clean_up_tokenization_spaces": false,
61
+ "eos_token": "<eos>",
62
+ "legacy": null,
63
+ "model_max_length": 2048,
64
+ "pad_token": "<pad>",
65
+ "sp_model_kwargs": {},
66
+ "spaces_between_special_tokens": false,
67
+ "tokenizer_class": "GemmaTokenizer",
68
+ "unk_token": "<unk>",
69
+ "use_default_system_prompt": false
70
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.99,
3
+ "train_loss": 1.0022602648772259,
4
+ "train_runtime": 5184.357,
5
+ "train_samples": 9500,
6
+ "train_samples_per_second": 22.178,
7
+ "train_steps_per_second": 0.173
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1314 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.994991652754591,
5
+ "eval_steps": 500,
6
+ "global_step": 897,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 1554.4859195078177,
14
+ "learning_rate": 2.2222222222222224e-07,
15
+ "loss": 13.9835,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.02,
20
+ "grad_norm": 1214.7457310015889,
21
+ "learning_rate": 1.111111111111111e-06,
22
+ "loss": 13.3423,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.03,
27
+ "grad_norm": 319.25263582700893,
28
+ "learning_rate": 2.222222222222222e-06,
29
+ "loss": 7.1598,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.05,
34
+ "grad_norm": 101.74884085779856,
35
+ "learning_rate": 3.3333333333333333e-06,
36
+ "loss": 3.257,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.07,
41
+ "grad_norm": 39.750398897218815,
42
+ "learning_rate": 4.444444444444444e-06,
43
+ "loss": 2.3046,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.08,
48
+ "grad_norm": 39.73415841304385,
49
+ "learning_rate": 5.555555555555557e-06,
50
+ "loss": 2.0193,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.1,
55
+ "grad_norm": 22.603785465724318,
56
+ "learning_rate": 6.666666666666667e-06,
57
+ "loss": 1.803,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.12,
62
+ "grad_norm": 13.57277760359388,
63
+ "learning_rate": 7.77777777777778e-06,
64
+ "loss": 1.6723,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.13,
69
+ "grad_norm": 10.745675701951754,
70
+ "learning_rate": 8.888888888888888e-06,
71
+ "loss": 1.6164,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.15,
76
+ "grad_norm": 11.48936807248645,
77
+ "learning_rate": 1e-05,
78
+ "loss": 1.5651,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.17,
83
+ "grad_norm": 6.759355981336981,
84
+ "learning_rate": 1.1111111111111113e-05,
85
+ "loss": 1.5031,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.18,
90
+ "grad_norm": 9.542982258251046,
91
+ "learning_rate": 1.2222222222222224e-05,
92
+ "loss": 1.4295,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.2,
97
+ "grad_norm": 7.960957372064927,
98
+ "learning_rate": 1.3333333333333333e-05,
99
+ "loss": 1.3752,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.22,
104
+ "grad_norm": 65.24876161518675,
105
+ "learning_rate": 1.4444444444444446e-05,
106
+ "loss": 1.3768,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.23,
111
+ "grad_norm": 127.017819160354,
112
+ "learning_rate": 1.555555555555556e-05,
113
+ "loss": 1.3837,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.25,
118
+ "grad_norm": 66.80311438981465,
119
+ "learning_rate": 1.6666666666666667e-05,
120
+ "loss": 1.2844,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.27,
125
+ "grad_norm": 45.06752723588582,
126
+ "learning_rate": 1.7777777777777777e-05,
127
+ "loss": 1.1568,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.28,
132
+ "grad_norm": 16.607018601484466,
133
+ "learning_rate": 1.888888888888889e-05,
134
+ "loss": 1.1208,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.3,
139
+ "grad_norm": 6.20855793840101,
140
+ "learning_rate": 2e-05,
141
+ "loss": 1.0982,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.32,
146
+ "grad_norm": 5.970187327270322,
147
+ "learning_rate": 1.9998105699049984e-05,
148
+ "loss": 1.087,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.33,
153
+ "grad_norm": 9.207660040111582,
154
+ "learning_rate": 1.9992423513875158e-05,
155
+ "loss": 1.0611,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.35,
160
+ "grad_norm": 11.032251244972851,
161
+ "learning_rate": 1.9982955597229275e-05,
162
+ "loss": 1.055,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.37,
167
+ "grad_norm": 7.70794959419036,
168
+ "learning_rate": 1.9969705536129033e-05,
169
+ "loss": 1.0494,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.38,
174
+ "grad_norm": 5.115775243109966,
175
+ "learning_rate": 1.9952678350495104e-05,
176
+ "loss": 1.03,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.4,
181
+ "grad_norm": 6.185703416946629,
182
+ "learning_rate": 1.9931880491250263e-05,
183
+ "loss": 1.0341,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.42,
188
+ "grad_norm": 5.719162959123087,
189
+ "learning_rate": 1.990731983787542e-05,
190
+ "loss": 1.0433,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.43,
195
+ "grad_norm": 12.405446493626323,
196
+ "learning_rate": 1.987900569542438e-05,
197
+ "loss": 1.0496,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.45,
202
+ "grad_norm": 13.49655125076312,
203
+ "learning_rate": 1.9846948790998532e-05,
204
+ "loss": 1.0155,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.47,
209
+ "grad_norm": 7.942566346935867,
210
+ "learning_rate": 1.9811161269682776e-05,
211
+ "loss": 1.0249,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.48,
216
+ "grad_norm": 4.540779868090953,
217
+ "learning_rate": 1.9771656689944238e-05,
218
+ "loss": 1.0094,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.5,
223
+ "grad_norm": 5.71935614128467,
224
+ "learning_rate": 1.9728450018495506e-05,
225
+ "loss": 1.0363,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.52,
230
+ "grad_norm": 8.301612111722024,
231
+ "learning_rate": 1.968155762462433e-05,
232
+ "loss": 0.9804,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.53,
237
+ "grad_norm": 4.611128256903672,
238
+ "learning_rate": 1.9630997273991964e-05,
239
+ "loss": 0.99,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.55,
244
+ "grad_norm": 6.349166471933137,
245
+ "learning_rate": 1.9576788121902457e-05,
246
+ "loss": 0.974,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.57,
251
+ "grad_norm": 4.709847602929964,
252
+ "learning_rate": 1.951895070604547e-05,
253
+ "loss": 0.9771,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.58,
258
+ "grad_norm": 4.952845884539213,
259
+ "learning_rate": 1.9457506938715357e-05,
260
+ "loss": 1.0052,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.6,
265
+ "grad_norm": 5.4487385859558914,
266
+ "learning_rate": 1.9392480098509488e-05,
267
+ "loss": 0.9863,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.62,
272
+ "grad_norm": 5.258252581584813,
273
+ "learning_rate": 1.93238948215089e-05,
274
+ "loss": 0.9766,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.63,
279
+ "grad_norm": 4.480190590593033,
280
+ "learning_rate": 1.9251777091944665e-05,
281
+ "loss": 0.9981,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.65,
286
+ "grad_norm": 7.433883383226472,
287
+ "learning_rate": 1.9176154232353513e-05,
288
+ "loss": 0.9985,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.67,
293
+ "grad_norm": 4.227680033826242,
294
+ "learning_rate": 1.9097054893226395e-05,
295
+ "loss": 0.9709,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.68,
300
+ "grad_norm": 3.5498806463564025,
301
+ "learning_rate": 1.9014509042153964e-05,
302
+ "loss": 1.0064,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.7,
307
+ "grad_norm": 3.8662258274644032,
308
+ "learning_rate": 1.8928547952473037e-05,
309
+ "loss": 0.9557,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.72,
314
+ "grad_norm": 6.516418186408566,
315
+ "learning_rate": 1.8839204191418386e-05,
316
+ "loss": 0.9499,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.73,
321
+ "grad_norm": 6.638325575394558,
322
+ "learning_rate": 1.8746511607784298e-05,
323
+ "loss": 0.9832,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.75,
328
+ "grad_norm": 7.49893501725385,
329
+ "learning_rate": 1.865050531910062e-05,
330
+ "loss": 0.9535,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.77,
335
+ "grad_norm": 6.04469353811688,
336
+ "learning_rate": 1.855122169832813e-05,
337
+ "loss": 0.947,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.78,
342
+ "grad_norm": 3.3984302418422536,
343
+ "learning_rate": 1.844869836007825e-05,
344
+ "loss": 0.9592,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.8,
349
+ "grad_norm": 3.599537518194927,
350
+ "learning_rate": 1.8342974146362397e-05,
351
+ "loss": 0.9938,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.82,
356
+ "grad_norm": 3.5743133672120875,
357
+ "learning_rate": 1.8234089111876256e-05,
358
+ "loss": 0.9375,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.83,
363
+ "grad_norm": 4.153578666049746,
364
+ "learning_rate": 1.8122084508824692e-05,
365
+ "loss": 0.9503,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.85,
370
+ "grad_norm": 4.358976477421789,
371
+ "learning_rate": 1.80070027712929e-05,
372
+ "loss": 0.9405,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.87,
377
+ "grad_norm": 4.715023563708574,
378
+ "learning_rate": 1.7888887499169816e-05,
379
+ "loss": 0.9448,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.88,
384
+ "grad_norm": 3.540308197945189,
385
+ "learning_rate": 1.7767783441629883e-05,
386
+ "loss": 0.9518,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.9,
391
+ "grad_norm": 4.61899118162512,
392
+ "learning_rate": 1.7643736480179353e-05,
393
+ "loss": 0.9331,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.92,
398
+ "grad_norm": 3.8933823492498987,
399
+ "learning_rate": 1.7516793611273614e-05,
400
+ "loss": 0.9402,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.93,
405
+ "grad_norm": 4.402077716843347,
406
+ "learning_rate": 1.7387002928512093e-05,
407
+ "loss": 0.9427,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.95,
412
+ "grad_norm": 4.439064477908216,
413
+ "learning_rate": 1.725441360441752e-05,
414
+ "loss": 0.9689,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.97,
419
+ "grad_norm": 4.228994650655801,
420
+ "learning_rate": 1.711907587180642e-05,
421
+ "loss": 0.922,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.98,
426
+ "grad_norm": 4.352694277486445,
427
+ "learning_rate": 1.698104100475788e-05,
428
+ "loss": 0.9482,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 1.0,
433
+ "eval_loss": 0.9848138093948364,
434
+ "eval_runtime": 21.922,
435
+ "eval_samples_per_second": 87.264,
436
+ "eval_steps_per_second": 1.368,
437
+ "step": 299
438
+ },
439
+ {
440
+ "epoch": 1.0,
441
+ "grad_norm": 3.7344611256762605,
442
+ "learning_rate": 1.684036129918786e-05,
443
+ "loss": 0.9147,
444
+ "step": 300
445
+ },
446
+ {
447
+ "epoch": 1.02,
448
+ "grad_norm": 7.808442765171335,
449
+ "learning_rate": 1.6697090053036344e-05,
450
+ "loss": 0.872,
451
+ "step": 305
452
+ },
453
+ {
454
+ "epoch": 1.04,
455
+ "grad_norm": 4.265041320808819,
456
+ "learning_rate": 1.6551281546074863e-05,
457
+ "loss": 0.8276,
458
+ "step": 310
459
+ },
460
+ {
461
+ "epoch": 1.05,
462
+ "grad_norm": 11.609187861418906,
463
+ "learning_rate": 1.6402991019342073e-05,
464
+ "loss": 0.8501,
465
+ "step": 315
466
+ },
467
+ {
468
+ "epoch": 1.07,
469
+ "grad_norm": 6.4050483054707765,
470
+ "learning_rate": 1.625227465421511e-05,
471
+ "loss": 0.8722,
472
+ "step": 320
473
+ },
474
+ {
475
+ "epoch": 1.09,
476
+ "grad_norm": 4.007163655718817,
477
+ "learning_rate": 1.60991895511247e-05,
478
+ "loss": 0.8791,
479
+ "step": 325
480
+ },
481
+ {
482
+ "epoch": 1.1,
483
+ "grad_norm": 6.169584899822902,
484
+ "learning_rate": 1.5943793707922086e-05,
485
+ "loss": 0.8378,
486
+ "step": 330
487
+ },
488
+ {
489
+ "epoch": 1.12,
490
+ "grad_norm": 5.702556304345057,
491
+ "learning_rate": 1.5786145997905952e-05,
492
+ "loss": 0.8529,
493
+ "step": 335
494
+ },
495
+ {
496
+ "epoch": 1.14,
497
+ "grad_norm": 3.666829882865862,
498
+ "learning_rate": 1.5626306147517665e-05,
499
+ "loss": 0.8625,
500
+ "step": 340
501
+ },
502
+ {
503
+ "epoch": 1.15,
504
+ "grad_norm": 7.196219177199569,
505
+ "learning_rate": 1.5464334713713312e-05,
506
+ "loss": 0.846,
507
+ "step": 345
508
+ },
509
+ {
510
+ "epoch": 1.17,
511
+ "grad_norm": 4.360948957874904,
512
+ "learning_rate": 1.5300293061021084e-05,
513
+ "loss": 0.8504,
514
+ "step": 350
515
+ },
516
+ {
517
+ "epoch": 1.19,
518
+ "grad_norm": 3.985490385252694,
519
+ "learning_rate": 1.5134243338292686e-05,
520
+ "loss": 0.8722,
521
+ "step": 355
522
+ },
523
+ {
524
+ "epoch": 1.2,
525
+ "grad_norm": 4.45100120259278,
526
+ "learning_rate": 1.4966248455157622e-05,
527
+ "loss": 0.8322,
528
+ "step": 360
529
+ },
530
+ {
531
+ "epoch": 1.22,
532
+ "grad_norm": 5.266623346917125,
533
+ "learning_rate": 1.4796372058189235e-05,
534
+ "loss": 0.8284,
535
+ "step": 365
536
+ },
537
+ {
538
+ "epoch": 1.24,
539
+ "grad_norm": 3.8641643965703647,
540
+ "learning_rate": 1.4624678506791556e-05,
541
+ "loss": 0.8482,
542
+ "step": 370
543
+ },
544
+ {
545
+ "epoch": 1.25,
546
+ "grad_norm": 5.041022068055208,
547
+ "learning_rate": 1.445123284881609e-05,
548
+ "loss": 0.8301,
549
+ "step": 375
550
+ },
551
+ {
552
+ "epoch": 1.27,
553
+ "grad_norm": 3.3180915430698654,
554
+ "learning_rate": 1.4276100795917777e-05,
555
+ "loss": 0.8208,
556
+ "step": 380
557
+ },
558
+ {
559
+ "epoch": 1.29,
560
+ "grad_norm": 6.201419840904921,
561
+ "learning_rate": 1.409934869865945e-05,
562
+ "loss": 0.8571,
563
+ "step": 385
564
+ },
565
+ {
566
+ "epoch": 1.3,
567
+ "grad_norm": 7.459788747214111,
568
+ "learning_rate": 1.392104352137426e-05,
569
+ "loss": 0.8569,
570
+ "step": 390
571
+ },
572
+ {
573
+ "epoch": 1.32,
574
+ "grad_norm": 6.709652163052175,
575
+ "learning_rate": 1.3741252816795552e-05,
576
+ "loss": 0.8622,
577
+ "step": 395
578
+ },
579
+ {
580
+ "epoch": 1.34,
581
+ "grad_norm": 3.473788351536053,
582
+ "learning_rate": 1.3560044700463824e-05,
583
+ "loss": 0.8577,
584
+ "step": 400
585
+ },
586
+ {
587
+ "epoch": 1.35,
588
+ "grad_norm": 3.5872538636448805,
589
+ "learning_rate": 1.3377487824920459e-05,
590
+ "loss": 0.86,
591
+ "step": 405
592
+ },
593
+ {
594
+ "epoch": 1.37,
595
+ "grad_norm": 5.307258675746272,
596
+ "learning_rate": 1.3193651353698012e-05,
597
+ "loss": 0.8229,
598
+ "step": 410
599
+ },
600
+ {
601
+ "epoch": 1.39,
602
+ "grad_norm": 4.804376190916538,
603
+ "learning_rate": 1.30086049351169e-05,
604
+ "loss": 0.8249,
605
+ "step": 415
606
+ },
607
+ {
608
+ "epoch": 1.4,
609
+ "grad_norm": 4.476642767728941,
610
+ "learning_rate": 1.2822418675898428e-05,
611
+ "loss": 0.815,
612
+ "step": 420
613
+ },
614
+ {
615
+ "epoch": 1.42,
616
+ "grad_norm": 3.662676271025836,
617
+ "learning_rate": 1.2635163114604131e-05,
618
+ "loss": 0.8322,
619
+ "step": 425
620
+ },
621
+ {
622
+ "epoch": 1.44,
623
+ "grad_norm": 5.33760518542071,
624
+ "learning_rate": 1.2446909194911552e-05,
625
+ "loss": 0.8283,
626
+ "step": 430
627
+ },
628
+ {
629
+ "epoch": 1.45,
630
+ "grad_norm": 3.6241603881416093,
631
+ "learning_rate": 1.2257728238736468e-05,
632
+ "loss": 0.8419,
633
+ "step": 435
634
+ },
635
+ {
636
+ "epoch": 1.47,
637
+ "grad_norm": 8.345200463380893,
638
+ "learning_rate": 1.2067691919211879e-05,
639
+ "loss": 0.8431,
640
+ "step": 440
641
+ },
642
+ {
643
+ "epoch": 1.49,
644
+ "grad_norm": 5.157020256989829,
645
+ "learning_rate": 1.1876872233533909e-05,
646
+ "loss": 0.8341,
647
+ "step": 445
648
+ },
649
+ {
650
+ "epoch": 1.5,
651
+ "grad_norm": 3.22959672388336,
652
+ "learning_rate": 1.1685341475684935e-05,
653
+ "loss": 0.8238,
654
+ "step": 450
655
+ },
656
+ {
657
+ "epoch": 1.52,
658
+ "grad_norm": 4.075617092942542,
659
+ "learning_rate": 1.1493172209044259e-05,
660
+ "loss": 0.8246,
661
+ "step": 455
662
+ },
663
+ {
664
+ "epoch": 1.54,
665
+ "grad_norm": 4.130669786993403,
666
+ "learning_rate": 1.1300437238896758e-05,
667
+ "loss": 0.8587,
668
+ "step": 460
669
+ },
670
+ {
671
+ "epoch": 1.55,
672
+ "grad_norm": 3.8344057909806653,
673
+ "learning_rate": 1.1107209584849845e-05,
674
+ "loss": 0.8405,
675
+ "step": 465
676
+ },
677
+ {
678
+ "epoch": 1.57,
679
+ "grad_norm": 4.419191495305873,
680
+ "learning_rate": 1.0913562453169241e-05,
681
+ "loss": 0.8513,
682
+ "step": 470
683
+ },
684
+ {
685
+ "epoch": 1.59,
686
+ "grad_norm": 3.639847517010915,
687
+ "learning_rate": 1.0719569209044047e-05,
688
+ "loss": 0.8268,
689
+ "step": 475
690
+ },
691
+ {
692
+ "epoch": 1.6,
693
+ "grad_norm": 6.0850406807943695,
694
+ "learning_rate": 1.0525303348791599e-05,
695
+ "loss": 0.835,
696
+ "step": 480
697
+ },
698
+ {
699
+ "epoch": 1.62,
700
+ "grad_norm": 4.663234575938155,
701
+ "learning_rate": 1.0330838472012617e-05,
702
+ "loss": 0.8297,
703
+ "step": 485
704
+ },
705
+ {
706
+ "epoch": 1.64,
707
+ "grad_norm": 2.952245938431757,
708
+ "learning_rate": 1.0136248253707267e-05,
709
+ "loss": 0.8435,
710
+ "step": 490
711
+ },
712
+ {
713
+ "epoch": 1.65,
714
+ "grad_norm": 3.1679752592105435,
715
+ "learning_rate": 9.94160641636263e-06,
716
+ "loss": 0.8409,
717
+ "step": 495
718
+ },
719
+ {
720
+ "epoch": 1.67,
721
+ "grad_norm": 3.2886951326936753,
722
+ "learning_rate": 9.74698670202218e-06,
723
+ "loss": 0.811,
724
+ "step": 500
725
+ },
726
+ {
727
+ "epoch": 1.69,
728
+ "grad_norm": 3.114045037749334,
729
+ "learning_rate": 9.552462844347883e-06,
730
+ "loss": 0.847,
731
+ "step": 505
732
+ },
733
+ {
734
+ "epoch": 1.7,
735
+ "grad_norm": 3.537647563076529,
736
+ "learning_rate": 9.358108540685406e-06,
737
+ "loss": 0.8272,
738
+ "step": 510
739
+ },
740
+ {
741
+ "epoch": 1.72,
742
+ "grad_norm": 3.41342205194864,
743
+ "learning_rate": 9.163997424143167e-06,
744
+ "loss": 0.8435,
745
+ "step": 515
746
+ },
747
+ {
748
+ "epoch": 1.74,
749
+ "grad_norm": 4.382615756695022,
750
+ "learning_rate": 8.970203035695662e-06,
751
+ "loss": 0.8241,
752
+ "step": 520
753
+ },
754
+ {
755
+ "epoch": 1.75,
756
+ "grad_norm": 6.06775300616703,
757
+ "learning_rate": 8.776798796321715e-06,
758
+ "loss": 0.8328,
759
+ "step": 525
760
+ },
761
+ {
762
+ "epoch": 1.77,
763
+ "grad_norm": 6.410082659319438,
764
+ "learning_rate": 8.583857979188203e-06,
765
+ "loss": 0.832,
766
+ "step": 530
767
+ },
768
+ {
769
+ "epoch": 1.79,
770
+ "grad_norm": 5.6018541648497715,
771
+ "learning_rate": 8.391453681889772e-06,
772
+ "loss": 0.8477,
773
+ "step": 535
774
+ },
775
+ {
776
+ "epoch": 1.8,
777
+ "grad_norm": 4.110209003561718,
778
+ "learning_rate": 8.199658798755048e-06,
779
+ "loss": 0.8365,
780
+ "step": 540
781
+ },
782
+ {
783
+ "epoch": 1.82,
784
+ "grad_norm": 3.2444930006535078,
785
+ "learning_rate": 8.008545993229897e-06,
786
+ "loss": 0.8519,
787
+ "step": 545
788
+ },
789
+ {
790
+ "epoch": 1.84,
791
+ "grad_norm": 3.25930172152866,
792
+ "learning_rate": 7.818187670348133e-06,
793
+ "loss": 0.8455,
794
+ "step": 550
795
+ },
796
+ {
797
+ "epoch": 1.85,
798
+ "grad_norm": 3.1738586241269706,
799
+ "learning_rate": 7.628655949300133e-06,
800
+ "loss": 0.8451,
801
+ "step": 555
802
+ },
803
+ {
804
+ "epoch": 1.87,
805
+ "grad_norm": 3.1977554967249144,
806
+ "learning_rate": 7.440022636109742e-06,
807
+ "loss": 0.8263,
808
+ "step": 560
809
+ },
810
+ {
811
+ "epoch": 1.89,
812
+ "grad_norm": 5.738948608123997,
813
+ "learning_rate": 7.2523591964298345e-06,
814
+ "loss": 0.8246,
815
+ "step": 565
816
+ },
817
+ {
818
+ "epoch": 1.9,
819
+ "grad_norm": 3.650496523890181,
820
+ "learning_rate": 7.065736728466832e-06,
821
+ "loss": 0.821,
822
+ "step": 570
823
+ },
824
+ {
825
+ "epoch": 1.92,
826
+ "grad_norm": 3.3610021866091073,
827
+ "learning_rate": 6.880225936044402e-06,
828
+ "loss": 0.8039,
829
+ "step": 575
830
+ },
831
+ {
832
+ "epoch": 1.94,
833
+ "grad_norm": 3.4144579406106996,
834
+ "learning_rate": 6.695897101816606e-06,
835
+ "loss": 0.8081,
836
+ "step": 580
837
+ },
838
+ {
839
+ "epoch": 1.95,
840
+ "grad_norm": 4.538437452063136,
841
+ "learning_rate": 6.512820060640608e-06,
842
+ "loss": 0.8334,
843
+ "step": 585
844
+ },
845
+ {
846
+ "epoch": 1.97,
847
+ "grad_norm": 4.895649774301149,
848
+ "learning_rate": 6.331064173119008e-06,
849
+ "loss": 0.8063,
850
+ "step": 590
851
+ },
852
+ {
853
+ "epoch": 1.99,
854
+ "grad_norm": 3.373177420856697,
855
+ "learning_rate": 6.150698299321889e-06,
856
+ "loss": 0.8139,
857
+ "step": 595
858
+ },
859
+ {
860
+ "epoch": 2.0,
861
+ "eval_loss": 0.9609715938568115,
862
+ "eval_runtime": 23.563,
863
+ "eval_samples_per_second": 81.187,
864
+ "eval_steps_per_second": 1.273,
865
+ "step": 599
866
+ },
867
+ {
868
+ "epoch": 2.0,
869
+ "grad_norm": 4.9256303288824705,
870
+ "learning_rate": 5.971790772698467e-06,
871
+ "loss": 0.7915,
872
+ "step": 600
873
+ },
874
+ {
875
+ "epoch": 2.02,
876
+ "grad_norm": 4.385016578281952,
877
+ "learning_rate": 5.794409374188272e-06,
878
+ "loss": 0.7106,
879
+ "step": 605
880
+ },
881
+ {
882
+ "epoch": 2.04,
883
+ "grad_norm": 4.602412318513612,
884
+ "learning_rate": 5.61862130654165e-06,
885
+ "loss": 0.701,
886
+ "step": 610
887
+ },
888
+ {
889
+ "epoch": 2.05,
890
+ "grad_norm": 4.466214253217951,
891
+ "learning_rate": 5.444493168859304e-06,
892
+ "loss": 0.7118,
893
+ "step": 615
894
+ },
895
+ {
896
+ "epoch": 2.07,
897
+ "grad_norm": 3.3100514145049678,
898
+ "learning_rate": 5.272090931360564e-06,
899
+ "loss": 0.7004,
900
+ "step": 620
901
+ },
902
+ {
903
+ "epoch": 2.09,
904
+ "grad_norm": 2.9902764365530023,
905
+ "learning_rate": 5.101479910389888e-06,
906
+ "loss": 0.7177,
907
+ "step": 625
908
+ },
909
+ {
910
+ "epoch": 2.1,
911
+ "grad_norm": 2.960756149194766,
912
+ "learning_rate": 4.932724743671089e-06,
913
+ "loss": 0.7061,
914
+ "step": 630
915
+ },
916
+ {
917
+ "epoch": 2.12,
918
+ "grad_norm": 3.3796322175614093,
919
+ "learning_rate": 4.765889365818708e-06,
920
+ "loss": 0.7243,
921
+ "step": 635
922
+ },
923
+ {
924
+ "epoch": 2.14,
925
+ "grad_norm": 3.068706242207435,
926
+ "learning_rate": 4.601036984115684e-06,
927
+ "loss": 0.7138,
928
+ "step": 640
929
+ },
930
+ {
931
+ "epoch": 2.15,
932
+ "grad_norm": 2.949462217015265,
933
+ "learning_rate": 4.438230054566678e-06,
934
+ "loss": 0.6921,
935
+ "step": 645
936
+ },
937
+ {
938
+ "epoch": 2.17,
939
+ "grad_norm": 2.9285837942249935,
940
+ "learning_rate": 4.277530258235955e-06,
941
+ "loss": 0.7087,
942
+ "step": 650
943
+ },
944
+ {
945
+ "epoch": 2.19,
946
+ "grad_norm": 2.8241960382183517,
947
+ "learning_rate": 4.118998477878879e-06,
948
+ "loss": 0.692,
949
+ "step": 655
950
+ },
951
+ {
952
+ "epoch": 2.2,
953
+ "grad_norm": 3.754111606827016,
954
+ "learning_rate": 3.96269477487588e-06,
955
+ "loss": 0.7036,
956
+ "step": 660
957
+ },
958
+ {
959
+ "epoch": 2.22,
960
+ "grad_norm": 2.801260790695992,
961
+ "learning_rate": 3.8086783664775827e-06,
962
+ "loss": 0.703,
963
+ "step": 665
964
+ },
965
+ {
966
+ "epoch": 2.24,
967
+ "grad_norm": 3.5205014160146484,
968
+ "learning_rate": 3.657007603369728e-06,
969
+ "loss": 0.6837,
970
+ "step": 670
971
+ },
972
+ {
973
+ "epoch": 2.25,
974
+ "grad_norm": 2.957347255235954,
975
+ "learning_rate": 3.5077399475664474e-06,
976
+ "loss": 0.716,
977
+ "step": 675
978
+ },
979
+ {
980
+ "epoch": 2.27,
981
+ "grad_norm": 3.0699352110382394,
982
+ "learning_rate": 3.360931950640185e-06,
983
+ "loss": 0.7159,
984
+ "step": 680
985
+ },
986
+ {
987
+ "epoch": 2.29,
988
+ "grad_norm": 2.8837481146108077,
989
+ "learning_rate": 3.2166392322965423e-06,
990
+ "loss": 0.688,
991
+ "step": 685
992
+ },
993
+ {
994
+ "epoch": 2.3,
995
+ "grad_norm": 2.763237253733171,
996
+ "learning_rate": 3.074916459302211e-06,
997
+ "loss": 0.7158,
998
+ "step": 690
999
+ },
1000
+ {
1001
+ "epoch": 2.32,
1002
+ "grad_norm": 3.355328029300809,
1003
+ "learning_rate": 2.935817324773893e-06,
1004
+ "loss": 0.7046,
1005
+ "step": 695
1006
+ },
1007
+ {
1008
+ "epoch": 2.34,
1009
+ "grad_norm": 2.8914814523547587,
1010
+ "learning_rate": 2.799394527836129e-06,
1011
+ "loss": 0.7096,
1012
+ "step": 700
1013
+ },
1014
+ {
1015
+ "epoch": 2.35,
1016
+ "grad_norm": 3.5718163510342014,
1017
+ "learning_rate": 2.665699753655684e-06,
1018
+ "loss": 0.6984,
1019
+ "step": 705
1020
+ },
1021
+ {
1022
+ "epoch": 2.37,
1023
+ "grad_norm": 3.2223677480030157,
1024
+ "learning_rate": 2.5347836538601113e-06,
1025
+ "loss": 0.6906,
1026
+ "step": 710
1027
+ },
1028
+ {
1029
+ "epoch": 2.39,
1030
+ "grad_norm": 2.7101631013279373,
1031
+ "learning_rate": 2.406695827347848e-06,
1032
+ "loss": 0.7229,
1033
+ "step": 715
1034
+ },
1035
+ {
1036
+ "epoch": 2.4,
1037
+ "grad_norm": 2.9181738000190482,
1038
+ "learning_rate": 2.281484801497186e-06,
1039
+ "loss": 0.7161,
1040
+ "step": 720
1041
+ },
1042
+ {
1043
+ "epoch": 2.42,
1044
+ "grad_norm": 2.7148342264509067,
1045
+ "learning_rate": 2.1591980137811684e-06,
1046
+ "loss": 0.6911,
1047
+ "step": 725
1048
+ },
1049
+ {
1050
+ "epoch": 2.44,
1051
+ "grad_norm": 2.645866837308739,
1052
+ "learning_rate": 2.0398817937954275e-06,
1053
+ "loss": 0.6935,
1054
+ "step": 730
1055
+ },
1056
+ {
1057
+ "epoch": 2.45,
1058
+ "grad_norm": 2.923721171986238,
1059
+ "learning_rate": 1.923581345705736e-06,
1060
+ "loss": 0.7012,
1061
+ "step": 735
1062
+ },
1063
+ {
1064
+ "epoch": 2.47,
1065
+ "grad_norm": 2.5730130782483767,
1066
+ "learning_rate": 1.8103407311219523e-06,
1067
+ "loss": 0.7001,
1068
+ "step": 740
1069
+ },
1070
+ {
1071
+ "epoch": 2.49,
1072
+ "grad_norm": 3.1294946465675535,
1073
+ "learning_rate": 1.7002028524048354e-06,
1074
+ "loss": 0.6849,
1075
+ "step": 745
1076
+ },
1077
+ {
1078
+ "epoch": 2.5,
1079
+ "grad_norm": 2.9432875746786955,
1080
+ "learning_rate": 1.5932094364120453e-06,
1081
+ "loss": 0.6834,
1082
+ "step": 750
1083
+ },
1084
+ {
1085
+ "epoch": 2.52,
1086
+ "grad_norm": 2.951328262763639,
1087
+ "learning_rate": 1.489401018689488e-06,
1088
+ "loss": 0.6893,
1089
+ "step": 755
1090
+ },
1091
+ {
1092
+ "epoch": 2.54,
1093
+ "grad_norm": 3.0873225694591886,
1094
+ "learning_rate": 1.3888169281140284e-06,
1095
+ "loss": 0.6672,
1096
+ "step": 760
1097
+ },
1098
+ {
1099
+ "epoch": 2.55,
1100
+ "grad_norm": 2.9951086396524285,
1101
+ "learning_rate": 1.291495271993337e-06,
1102
+ "loss": 0.7005,
1103
+ "step": 765
1104
+ },
1105
+ {
1106
+ "epoch": 2.57,
1107
+ "grad_norm": 2.6961455349482057,
1108
+ "learning_rate": 1.1974729216285386e-06,
1109
+ "loss": 0.7047,
1110
+ "step": 770
1111
+ },
1112
+ {
1113
+ "epoch": 2.59,
1114
+ "grad_norm": 2.7063424423455777,
1115
+ "learning_rate": 1.1067854983451575e-06,
1116
+ "loss": 0.6874,
1117
+ "step": 775
1118
+ },
1119
+ {
1120
+ "epoch": 2.6,
1121
+ "grad_norm": 2.969350173180754,
1122
+ "learning_rate": 1.0194673599976134e-06,
1123
+ "loss": 0.6954,
1124
+ "step": 780
1125
+ },
1126
+ {
1127
+ "epoch": 2.62,
1128
+ "grad_norm": 2.8241124873176804,
1129
+ "learning_rate": 9.355515879523858e-07,
1130
+ "loss": 0.7151,
1131
+ "step": 785
1132
+ },
1133
+ {
1134
+ "epoch": 2.64,
1135
+ "grad_norm": 2.703842291084545,
1136
+ "learning_rate": 8.550699745548196e-07,
1137
+ "loss": 0.7051,
1138
+ "step": 790
1139
+ },
1140
+ {
1141
+ "epoch": 2.65,
1142
+ "grad_norm": 2.52014475737678,
1143
+ "learning_rate": 7.780530110842566e-07,
1144
+ "loss": 0.7032,
1145
+ "step": 795
1146
+ },
1147
+ {
1148
+ "epoch": 2.67,
1149
+ "grad_norm": 2.8940329465111967,
1150
+ "learning_rate": 7.045298762021125e-07,
1151
+ "loss": 0.696,
1152
+ "step": 800
1153
+ },
1154
+ {
1155
+ "epoch": 2.69,
1156
+ "grad_norm": 2.715730102462268,
1157
+ "learning_rate": 6.345284248972383e-07,
1158
+ "loss": 0.6594,
1159
+ "step": 805
1160
+ },
1161
+ {
1162
+ "epoch": 2.7,
1163
+ "grad_norm": 2.562152086335658,
1164
+ "learning_rate": 5.680751779327742e-07,
1165
+ "loss": 0.6882,
1166
+ "step": 810
1167
+ },
1168
+ {
1169
+ "epoch": 2.72,
1170
+ "grad_norm": 2.753866693209901,
1171
+ "learning_rate": 5.05195311798491e-07,
1172
+ "loss": 0.6929,
1173
+ "step": 815
1174
+ },
1175
+ {
1176
+ "epoch": 2.74,
1177
+ "grad_norm": 2.5848331829143225,
1178
+ "learning_rate": 4.4591264917242195e-07,
1179
+ "loss": 0.6914,
1180
+ "step": 820
1181
+ },
1182
+ {
1183
+ "epoch": 2.75,
1184
+ "grad_norm": 2.656019725897738,
1185
+ "learning_rate": 3.9024964989539227e-07,
1186
+ "loss": 0.6997,
1187
+ "step": 825
1188
+ },
1189
+ {
1190
+ "epoch": 2.77,
1191
+ "grad_norm": 2.6710040716803927,
1192
+ "learning_rate": 3.3822740246188477e-07,
1193
+ "loss": 0.7042,
1194
+ "step": 830
1195
+ },
1196
+ {
1197
+ "epoch": 2.79,
1198
+ "grad_norm": 2.797959120368719,
1199
+ "learning_rate": 2.8986561603044694e-07,
1200
+ "loss": 0.717,
1201
+ "step": 835
1202
+ },
1203
+ {
1204
+ "epoch": 2.8,
1205
+ "grad_norm": 2.6446312241054803,
1206
+ "learning_rate": 2.4518261295667255e-07,
1207
+ "loss": 0.6838,
1208
+ "step": 840
1209
+ },
1210
+ {
1211
+ "epoch": 2.82,
1212
+ "grad_norm": 2.6673940520178836,
1213
+ "learning_rate": 2.0419532185159796e-07,
1214
+ "loss": 0.7003,
1215
+ "step": 845
1216
+ },
1217
+ {
1218
+ "epoch": 2.84,
1219
+ "grad_norm": 2.697047820136764,
1220
+ "learning_rate": 1.6691927116812002e-07,
1221
+ "loss": 0.6936,
1222
+ "step": 850
1223
+ },
1224
+ {
1225
+ "epoch": 2.85,
1226
+ "grad_norm": 2.5372070358560843,
1227
+ "learning_rate": 1.3336858331787993e-07,
1228
+ "loss": 0.6913,
1229
+ "step": 855
1230
+ },
1231
+ {
1232
+ "epoch": 2.87,
1233
+ "grad_norm": 2.5976068799798187,
1234
+ "learning_rate": 1.0355596932085432e-07,
1235
+ "loss": 0.694,
1236
+ "step": 860
1237
+ },
1238
+ {
1239
+ "epoch": 2.89,
1240
+ "grad_norm": 2.922996849182434,
1241
+ "learning_rate": 7.749272398964613e-08,
1242
+ "loss": 0.703,
1243
+ "step": 865
1244
+ },
1245
+ {
1246
+ "epoch": 2.9,
1247
+ "grad_norm": 2.53597875366406,
1248
+ "learning_rate": 5.518872165033329e-08,
1249
+ "loss": 0.6936,
1250
+ "step": 870
1251
+ },
1252
+ {
1253
+ "epoch": 2.92,
1254
+ "grad_norm": 2.7025680089043584,
1255
+ "learning_rate": 3.6652412401478875e-08,
1256
+ "loss": 0.6911,
1257
+ "step": 875
1258
+ },
1259
+ {
1260
+ "epoch": 2.94,
1261
+ "grad_norm": 2.6197435490839873,
1262
+ "learning_rate": 2.1890818912728706e-08,
1263
+ "loss": 0.7137,
1264
+ "step": 880
1265
+ },
1266
+ {
1267
+ "epoch": 2.95,
1268
+ "grad_norm": 2.6370913398207825,
1269
+ "learning_rate": 1.0909533764194013e-08,
1270
+ "loss": 0.7064,
1271
+ "step": 885
1272
+ },
1273
+ {
1274
+ "epoch": 2.97,
1275
+ "grad_norm": 2.7175545973145687,
1276
+ "learning_rate": 3.7127173276563234e-09,
1277
+ "loss": 0.7116,
1278
+ "step": 890
1279
+ },
1280
+ {
1281
+ "epoch": 2.99,
1282
+ "grad_norm": 2.796693677065229,
1283
+ "learning_rate": 3.0309619035495675e-10,
1284
+ "loss": 0.722,
1285
+ "step": 895
1286
+ },
1287
+ {
1288
+ "epoch": 2.99,
1289
+ "eval_loss": 0.973169207572937,
1290
+ "eval_runtime": 24.5227,
1291
+ "eval_samples_per_second": 78.009,
1292
+ "eval_steps_per_second": 1.223,
1293
+ "step": 897
1294
+ },
1295
+ {
1296
+ "epoch": 2.99,
1297
+ "step": 897,
1298
+ "total_flos": 246909348347904.0,
1299
+ "train_loss": 1.0022602648772259,
1300
+ "train_runtime": 5184.357,
1301
+ "train_samples_per_second": 22.178,
1302
+ "train_steps_per_second": 0.173
1303
+ }
1304
+ ],
1305
+ "logging_steps": 5,
1306
+ "max_steps": 897,
1307
+ "num_input_tokens_seen": 0,
1308
+ "num_train_epochs": 3,
1309
+ "save_steps": 500,
1310
+ "total_flos": 246909348347904.0,
1311
+ "train_batch_size": 4,
1312
+ "trial_name": null,
1313
+ "trial_params": null
1314
+ }