marianna13 commited on
Commit
b671ab4
·
verified ·
1 Parent(s): 0e8aa5d

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 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: Qwen/Qwen2.5-7B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: qos_boost_qos_bprod_Qwen2.5-7B-Instruct_openthoughts2_100k
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # qos_boost_qos_bprod_Qwen2.5-7B-Instruct_openthoughts2_100k
18
+
19
+ This model is a fine-tuned version of [/leonardo_work/EUHPC_E03_068/DCFT_shared/hub/models--Qwen--Qwen2.5-7B-Instruct/snapshots/a09a35458c702b33eeacc393d103063234e8bc28](https://huggingface.co//leonardo_work/EUHPC_E03_068/DCFT_shared/hub/models--Qwen--Qwen2.5-7B-Instruct/snapshots/a09a35458c702b33eeacc393d103063234e8bc28) on the mlfoundations-dev/openthoughts2_100k dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 8e-05
39
+ - train_batch_size: 1
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 512
44
+ - total_train_batch_size: 512
45
+ - total_eval_batch_size: 4096
46
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 5.0
50
+
51
+ ### Training results
52
+
53
+
54
+
55
+ ### Framework versions
56
+
57
+ - Transformers 4.46.1
58
+ - Pytorch 2.6.0+cu124
59
+ - Datasets 3.1.0
60
+ - Tokenizers 0.20.0
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "total_flos": 5032842677452800.0,
4
+ "train_loss": 0.4754675631721815,
5
+ "train_runtime": 6942.3427,
6
+ "train_samples_per_second": 21.922,
7
+ "train_steps_per_second": 0.043
8
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/leonardo_work/EUHPC_E03_068/DCFT_shared/hub/models--Qwen--Qwen2.5-7B-Instruct/snapshots/a09a35458c702b33eeacc393d103063234e8bc28",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.46.1",
26
+ "use_cache": false,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 152064
29
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.46.1"
14
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ccacee9ae652624f2ff3051b2eb0cb8da66371183977e0702006ba043a404e2
3
+ size 4877660776
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c67e24b0355cbfc2753b25643d86fd66884863e0b4a4d7e9bbbd7385b6a224b
3
+ size 4932751008
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b9e60c0e882b94f6e3db45b337f47ab1b9c53b11153a4ef85a43517967a07de
3
+ size 4330865200
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dcac83a8652206ade658a7d8880d069d3f9986d2cb92b0a0b38ac89e0ed63e4
3
+ size 1089994880
model.safetensors.index.json ADDED
@@ -0,0 +1,346 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15231233024
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.bias": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
260
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
289
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
296
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
297
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
298
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
299
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
300
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
301
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
303
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
304
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
306
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
308
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
309
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
310
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
311
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
312
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
313
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
315
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
316
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
318
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
320
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
321
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
327
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
328
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
330
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
332
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
344
+ "model.norm.weight": "model-00003-of-00004.safetensors"
345
+ }
346
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|endoftext|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "right",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "total_flos": 5032842677452800.0,
4
+ "train_loss": 0.4754675631721815,
5
+ "train_runtime": 6942.3427,
6
+ "train_samples_per_second": 21.922,
7
+ "train_steps_per_second": 0.043
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,301 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 300, "loss": 0.8776, "lr": 2.666666666666667e-06, "epoch": 0.016666666666666666, "percentage": 0.33, "elapsed_time": "0:01:27", "remaining_time": "7:14:48"}
2
+ {"current_steps": 2, "total_steps": 300, "loss": 0.8699, "lr": 5.333333333333334e-06, "epoch": 0.03333333333333333, "percentage": 0.67, "elapsed_time": "0:01:48", "remaining_time": "4:30:19"}
3
+ {"current_steps": 3, "total_steps": 300, "loss": 0.8757, "lr": 8.000000000000001e-06, "epoch": 0.05, "percentage": 1.0, "elapsed_time": "0:02:10", "remaining_time": "3:34:42"}
4
+ {"current_steps": 4, "total_steps": 300, "loss": 0.7787, "lr": 1.0666666666666667e-05, "epoch": 0.06666666666666667, "percentage": 1.33, "elapsed_time": "0:02:31", "remaining_time": "3:06:58"}
5
+ {"current_steps": 5, "total_steps": 300, "loss": 0.761, "lr": 1.3333333333333333e-05, "epoch": 0.08333333333333333, "percentage": 1.67, "elapsed_time": "0:02:52", "remaining_time": "2:49:50"}
6
+ {"current_steps": 6, "total_steps": 300, "loss": 0.7651, "lr": 1.6000000000000003e-05, "epoch": 0.1, "percentage": 2.0, "elapsed_time": "0:03:13", "remaining_time": "2:38:14"}
7
+ {"current_steps": 7, "total_steps": 300, "loss": 0.7356, "lr": 1.866666666666667e-05, "epoch": 0.11666666666666667, "percentage": 2.33, "elapsed_time": "0:03:35", "remaining_time": "2:30:06"}
8
+ {"current_steps": 8, "total_steps": 300, "loss": 0.6935, "lr": 2.1333333333333335e-05, "epoch": 0.13333333333333333, "percentage": 2.67, "elapsed_time": "0:03:56", "remaining_time": "2:23:38"}
9
+ {"current_steps": 9, "total_steps": 300, "loss": 0.6894, "lr": 2.4e-05, "epoch": 0.15, "percentage": 3.0, "elapsed_time": "0:04:17", "remaining_time": "2:18:39"}
10
+ {"current_steps": 10, "total_steps": 300, "loss": 0.6534, "lr": 2.6666666666666667e-05, "epoch": 0.16666666666666666, "percentage": 3.33, "elapsed_time": "0:04:37", "remaining_time": "2:14:20"}
11
+ {"current_steps": 11, "total_steps": 300, "loss": 0.6564, "lr": 2.9333333333333333e-05, "epoch": 0.18333333333333332, "percentage": 3.67, "elapsed_time": "0:04:58", "remaining_time": "2:10:54"}
12
+ {"current_steps": 12, "total_steps": 300, "loss": 0.637, "lr": 3.2000000000000005e-05, "epoch": 0.2, "percentage": 4.0, "elapsed_time": "0:05:18", "remaining_time": "2:07:12"}
13
+ {"current_steps": 13, "total_steps": 300, "loss": 0.6096, "lr": 3.466666666666667e-05, "epoch": 0.21666666666666667, "percentage": 4.33, "elapsed_time": "0:05:39", "remaining_time": "2:04:56"}
14
+ {"current_steps": 14, "total_steps": 300, "loss": 0.6146, "lr": 3.733333333333334e-05, "epoch": 0.23333333333333334, "percentage": 4.67, "elapsed_time": "0:06:01", "remaining_time": "2:02:58"}
15
+ {"current_steps": 15, "total_steps": 300, "loss": 0.5966, "lr": 4e-05, "epoch": 0.25, "percentage": 5.0, "elapsed_time": "0:06:22", "remaining_time": "2:01:07"}
16
+ {"current_steps": 16, "total_steps": 300, "loss": 0.5894, "lr": 4.266666666666667e-05, "epoch": 0.26666666666666666, "percentage": 5.33, "elapsed_time": "0:06:43", "remaining_time": "1:59:25"}
17
+ {"current_steps": 17, "total_steps": 300, "loss": 0.5883, "lr": 4.5333333333333335e-05, "epoch": 0.2833333333333333, "percentage": 5.67, "elapsed_time": "0:07:05", "remaining_time": "1:58:05"}
18
+ {"current_steps": 18, "total_steps": 300, "loss": 0.5857, "lr": 4.8e-05, "epoch": 0.3, "percentage": 6.0, "elapsed_time": "0:07:26", "remaining_time": "1:56:40"}
19
+ {"current_steps": 19, "total_steps": 300, "loss": 0.5799, "lr": 5.066666666666667e-05, "epoch": 0.31666666666666665, "percentage": 6.33, "elapsed_time": "0:07:48", "remaining_time": "1:55:23"}
20
+ {"current_steps": 20, "total_steps": 300, "loss": 0.5833, "lr": 5.333333333333333e-05, "epoch": 0.3333333333333333, "percentage": 6.67, "elapsed_time": "0:08:09", "remaining_time": "1:54:07"}
21
+ {"current_steps": 21, "total_steps": 300, "loss": 0.5691, "lr": 5.6e-05, "epoch": 0.35, "percentage": 7.0, "elapsed_time": "0:08:31", "remaining_time": "1:53:10"}
22
+ {"current_steps": 22, "total_steps": 300, "loss": 0.5801, "lr": 5.8666666666666665e-05, "epoch": 0.36666666666666664, "percentage": 7.33, "elapsed_time": "0:08:52", "remaining_time": "1:52:11"}
23
+ {"current_steps": 23, "total_steps": 300, "loss": 0.5703, "lr": 6.133333333333334e-05, "epoch": 0.38333333333333336, "percentage": 7.67, "elapsed_time": "0:09:14", "remaining_time": "1:51:12"}
24
+ {"current_steps": 24, "total_steps": 300, "loss": 0.5597, "lr": 6.400000000000001e-05, "epoch": 0.4, "percentage": 8.0, "elapsed_time": "0:09:35", "remaining_time": "1:50:19"}
25
+ {"current_steps": 25, "total_steps": 300, "loss": 0.5603, "lr": 6.666666666666667e-05, "epoch": 0.4166666666666667, "percentage": 8.33, "elapsed_time": "0:09:57", "remaining_time": "1:49:28"}
26
+ {"current_steps": 26, "total_steps": 300, "loss": 0.5565, "lr": 6.933333333333334e-05, "epoch": 0.43333333333333335, "percentage": 8.67, "elapsed_time": "0:10:18", "remaining_time": "1:48:39"}
27
+ {"current_steps": 27, "total_steps": 300, "loss": 0.5543, "lr": 7.2e-05, "epoch": 0.45, "percentage": 9.0, "elapsed_time": "0:10:39", "remaining_time": "1:47:45"}
28
+ {"current_steps": 28, "total_steps": 300, "loss": 0.5545, "lr": 7.466666666666667e-05, "epoch": 0.4666666666666667, "percentage": 9.33, "elapsed_time": "0:11:00", "remaining_time": "1:46:57"}
29
+ {"current_steps": 29, "total_steps": 300, "loss": 0.5499, "lr": 7.733333333333333e-05, "epoch": 0.48333333333333334, "percentage": 9.67, "elapsed_time": "0:11:21", "remaining_time": "1:46:12"}
30
+ {"current_steps": 30, "total_steps": 300, "loss": 0.5466, "lr": 8e-05, "epoch": 0.5, "percentage": 10.0, "elapsed_time": "0:11:43", "remaining_time": "1:45:32"}
31
+ {"current_steps": 31, "total_steps": 300, "loss": 0.5549, "lr": 7.99972923201505e-05, "epoch": 0.5166666666666667, "percentage": 10.33, "elapsed_time": "0:12:05", "remaining_time": "1:44:51"}
32
+ {"current_steps": 32, "total_steps": 300, "loss": 0.5886, "lr": 7.998916964717848e-05, "epoch": 0.5333333333333333, "percentage": 10.67, "elapsed_time": "0:12:26", "remaining_time": "1:44:12"}
33
+ {"current_steps": 33, "total_steps": 300, "loss": 0.5638, "lr": 7.997563308076384e-05, "epoch": 0.55, "percentage": 11.0, "elapsed_time": "0:12:43", "remaining_time": "1:43:01"}
34
+ {"current_steps": 34, "total_steps": 300, "loss": 0.5635, "lr": 7.9956684453541e-05, "epoch": 0.5666666666666667, "percentage": 11.33, "elapsed_time": "0:13:00", "remaining_time": "1:41:47"}
35
+ {"current_steps": 35, "total_steps": 300, "loss": 0.5569, "lr": 7.993232633085074e-05, "epoch": 0.5833333333333334, "percentage": 11.67, "elapsed_time": "0:13:16", "remaining_time": "1:40:32"}
36
+ {"current_steps": 36, "total_steps": 300, "loss": 0.5466, "lr": 7.990256201039297e-05, "epoch": 0.6, "percentage": 12.0, "elapsed_time": "0:13:32", "remaining_time": "1:39:16"}
37
+ {"current_steps": 37, "total_steps": 300, "loss": 0.5497, "lr": 7.986739552178024e-05, "epoch": 0.6166666666666667, "percentage": 12.33, "elapsed_time": "0:13:48", "remaining_time": "1:38:06"}
38
+ {"current_steps": 38, "total_steps": 300, "loss": 0.5501, "lr": 7.982683162599218e-05, "epoch": 0.6333333333333333, "percentage": 12.67, "elapsed_time": "0:14:03", "remaining_time": "1:36:57"}
39
+ {"current_steps": 39, "total_steps": 300, "loss": 0.5319, "lr": 7.978087581473094e-05, "epoch": 0.65, "percentage": 13.0, "elapsed_time": "0:14:19", "remaining_time": "1:35:52"}
40
+ {"current_steps": 40, "total_steps": 300, "loss": 0.529, "lr": 7.972953430967773e-05, "epoch": 0.6666666666666666, "percentage": 13.33, "elapsed_time": "0:14:40", "remaining_time": "1:35:21"}
41
+ {"current_steps": 41, "total_steps": 300, "loss": 0.5341, "lr": 7.967281406165047e-05, "epoch": 0.6833333333333333, "percentage": 13.67, "elapsed_time": "0:17:29", "remaining_time": "1:50:30"}
42
+ {"current_steps": 42, "total_steps": 300, "loss": 0.5422, "lr": 7.961072274966282e-05, "epoch": 0.7, "percentage": 14.0, "elapsed_time": "0:17:51", "remaining_time": "1:49:42"}
43
+ {"current_steps": 43, "total_steps": 300, "loss": 0.5375, "lr": 7.954326877988446e-05, "epoch": 0.7166666666666667, "percentage": 14.33, "elapsed_time": "0:18:12", "remaining_time": "1:48:49"}
44
+ {"current_steps": 44, "total_steps": 300, "loss": 0.5354, "lr": 7.947046128450319e-05, "epoch": 0.7333333333333333, "percentage": 14.67, "elapsed_time": "0:18:33", "remaining_time": "1:48:00"}
45
+ {"current_steps": 45, "total_steps": 300, "loss": 0.5368, "lr": 7.939231012048833e-05, "epoch": 0.75, "percentage": 15.0, "elapsed_time": "0:18:54", "remaining_time": "1:47:10"}
46
+ {"current_steps": 46, "total_steps": 300, "loss": 0.5325, "lr": 7.930882586825653e-05, "epoch": 0.7666666666666667, "percentage": 15.33, "elapsed_time": "0:19:16", "remaining_time": "1:46:28"}
47
+ {"current_steps": 47, "total_steps": 300, "loss": 0.5263, "lr": 7.922001983023918e-05, "epoch": 0.7833333333333333, "percentage": 15.67, "elapsed_time": "0:19:37", "remaining_time": "1:45:40"}
48
+ {"current_steps": 48, "total_steps": 300, "loss": 0.5198, "lr": 7.912590402935223e-05, "epoch": 0.8, "percentage": 16.0, "elapsed_time": "0:19:59", "remaining_time": "1:44:56"}
49
+ {"current_steps": 49, "total_steps": 300, "loss": 0.5271, "lr": 7.902649120736858e-05, "epoch": 0.8166666666666667, "percentage": 16.33, "elapsed_time": "0:20:21", "remaining_time": "1:44:15"}
50
+ {"current_steps": 50, "total_steps": 300, "loss": 0.5306, "lr": 7.892179482319297e-05, "epoch": 0.8333333333333334, "percentage": 16.67, "elapsed_time": "0:20:43", "remaining_time": "1:43:36"}
51
+ {"current_steps": 51, "total_steps": 300, "loss": 0.5304, "lr": 7.881182905103986e-05, "epoch": 0.85, "percentage": 17.0, "elapsed_time": "0:21:05", "remaining_time": "1:42:58"}
52
+ {"current_steps": 52, "total_steps": 300, "loss": 0.5303, "lr": 7.869660877851456e-05, "epoch": 0.8666666666666667, "percentage": 17.33, "elapsed_time": "0:21:27", "remaining_time": "1:42:18"}
53
+ {"current_steps": 53, "total_steps": 300, "loss": 0.5191, "lr": 7.857614960459756e-05, "epoch": 0.8833333333333333, "percentage": 17.67, "elapsed_time": "0:21:47", "remaining_time": "1:41:33"}
54
+ {"current_steps": 54, "total_steps": 300, "loss": 0.5527, "lr": 7.845046783753276e-05, "epoch": 0.9, "percentage": 18.0, "elapsed_time": "0:22:10", "remaining_time": "1:41:02"}
55
+ {"current_steps": 55, "total_steps": 300, "loss": 0.5317, "lr": 7.831958049261956e-05, "epoch": 0.9166666666666666, "percentage": 18.33, "elapsed_time": "0:22:32", "remaining_time": "1:40:23"}
56
+ {"current_steps": 56, "total_steps": 300, "loss": 0.5257, "lr": 7.818350528990929e-05, "epoch": 0.9333333333333333, "percentage": 18.67, "elapsed_time": "0:22:54", "remaining_time": "1:39:49"}
57
+ {"current_steps": 57, "total_steps": 300, "loss": 0.5142, "lr": 7.804226065180615e-05, "epoch": 0.95, "percentage": 19.0, "elapsed_time": "0:23:15", "remaining_time": "1:39:11"}
58
+ {"current_steps": 58, "total_steps": 300, "loss": 0.5224, "lr": 7.789586570057317e-05, "epoch": 0.9666666666666667, "percentage": 19.33, "elapsed_time": "0:23:38", "remaining_time": "1:38:39"}
59
+ {"current_steps": 59, "total_steps": 300, "loss": 0.52, "lr": 7.774434025574335e-05, "epoch": 0.9833333333333333, "percentage": 19.67, "elapsed_time": "0:24:01", "remaining_time": "1:38:07"}
60
+ {"current_steps": 60, "total_steps": 300, "loss": 0.5222, "lr": 7.758770483143634e-05, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "0:24:23", "remaining_time": "1:37:33"}
61
+ {"current_steps": 61, "total_steps": 300, "loss": 0.4969, "lr": 7.742598063358127e-05, "epoch": 1.0166666666666666, "percentage": 20.33, "elapsed_time": "0:25:39", "remaining_time": "1:40:32"}
62
+ {"current_steps": 62, "total_steps": 300, "loss": 0.5029, "lr": 7.72591895570457e-05, "epoch": 1.0333333333333334, "percentage": 20.67, "elapsed_time": "0:26:01", "remaining_time": "1:39:53"}
63
+ {"current_steps": 63, "total_steps": 300, "loss": 0.5371, "lr": 7.70873541826715e-05, "epoch": 1.05, "percentage": 21.0, "elapsed_time": "0:26:23", "remaining_time": "1:39:18"}
64
+ {"current_steps": 64, "total_steps": 300, "loss": 0.6454, "lr": 7.69104977742177e-05, "epoch": 1.0666666666666667, "percentage": 21.33, "elapsed_time": "0:26:45", "remaining_time": "1:38:40"}
65
+ {"current_steps": 65, "total_steps": 300, "loss": 5.1073, "lr": 7.672864427521097e-05, "epoch": 1.0833333333333333, "percentage": 21.67, "elapsed_time": "0:27:07", "remaining_time": "1:38:02"}
66
+ {"current_steps": 66, "total_steps": 300, "loss": 0.8472, "lr": 7.654181830570404e-05, "epoch": 1.1, "percentage": 22.0, "elapsed_time": "0:27:27", "remaining_time": "1:37:21"}
67
+ {"current_steps": 67, "total_steps": 300, "loss": 0.599, "lr": 7.635004515894258e-05, "epoch": 1.1166666666666667, "percentage": 22.33, "elapsed_time": "0:28:18", "remaining_time": "1:38:27"}
68
+ {"current_steps": 68, "total_steps": 300, "loss": 0.5545, "lr": 7.615335079794083e-05, "epoch": 1.1333333333333333, "percentage": 22.67, "elapsed_time": "0:28:39", "remaining_time": "1:37:46"}
69
+ {"current_steps": 69, "total_steps": 300, "loss": 0.5589, "lr": 7.595176185196669e-05, "epoch": 1.15, "percentage": 23.0, "elapsed_time": "0:30:27", "remaining_time": "1:41:57"}
70
+ {"current_steps": 70, "total_steps": 300, "loss": 0.5536, "lr": 7.57453056129365e-05, "epoch": 1.1666666666666667, "percentage": 23.33, "elapsed_time": "0:30:48", "remaining_time": "1:41:12"}
71
+ {"current_steps": 71, "total_steps": 300, "loss": 0.553, "lr": 7.553401003172018e-05, "epoch": 1.1833333333333333, "percentage": 23.67, "elapsed_time": "0:31:09", "remaining_time": "1:40:30"}
72
+ {"current_steps": 72, "total_steps": 300, "loss": 0.5278, "lr": 7.531790371435709e-05, "epoch": 1.2, "percentage": 24.0, "elapsed_time": "0:31:31", "remaining_time": "1:39:48"}
73
+ {"current_steps": 73, "total_steps": 300, "loss": 0.5185, "lr": 7.509701591818328e-05, "epoch": 1.2166666666666668, "percentage": 24.33, "elapsed_time": "0:32:31", "remaining_time": "1:41:07"}
74
+ {"current_steps": 74, "total_steps": 300, "loss": 0.5235, "lr": 7.48713765478705e-05, "epoch": 1.2333333333333334, "percentage": 24.67, "elapsed_time": "0:32:51", "remaining_time": "1:40:19"}
75
+ {"current_steps": 75, "total_steps": 300, "loss": 0.5273, "lr": 7.464101615137756e-05, "epoch": 1.25, "percentage": 25.0, "elapsed_time": "0:33:12", "remaining_time": "1:39:38"}
76
+ {"current_steps": 76, "total_steps": 300, "loss": 0.5096, "lr": 7.440596591581463e-05, "epoch": 1.2666666666666666, "percentage": 25.33, "elapsed_time": "0:34:16", "remaining_time": "1:41:01"}
77
+ {"current_steps": 77, "total_steps": 300, "loss": 0.5113, "lr": 7.416625766322104e-05, "epoch": 1.2833333333333332, "percentage": 25.67, "elapsed_time": "0:34:37", "remaining_time": "1:40:15"}
78
+ {"current_steps": 78, "total_steps": 300, "loss": 0.5002, "lr": 7.392192384625704e-05, "epoch": 1.3, "percentage": 26.0, "elapsed_time": "0:34:57", "remaining_time": "1:39:30"}
79
+ {"current_steps": 79, "total_steps": 300, "loss": 0.5056, "lr": 7.36729975438103e-05, "epoch": 1.3166666666666667, "percentage": 26.33, "elapsed_time": "0:35:18", "remaining_time": "1:38:47"}
80
+ {"current_steps": 80, "total_steps": 300, "loss": 0.5052, "lr": 7.341951245651747e-05, "epoch": 1.3333333333333333, "percentage": 26.67, "elapsed_time": "0:35:40", "remaining_time": "1:38:05"}
81
+ {"current_steps": 81, "total_steps": 300, "loss": 0.4894, "lr": 7.316150290220167e-05, "epoch": 1.35, "percentage": 27.0, "elapsed_time": "0:36:00", "remaining_time": "1:37:22"}
82
+ {"current_steps": 82, "total_steps": 300, "loss": 0.4936, "lr": 7.28990038112265e-05, "epoch": 1.3666666666666667, "percentage": 27.33, "elapsed_time": "0:36:21", "remaining_time": "1:36:38"}
83
+ {"current_steps": 83, "total_steps": 300, "loss": 0.505, "lr": 7.26320507217669e-05, "epoch": 1.3833333333333333, "percentage": 27.67, "elapsed_time": "0:36:41", "remaining_time": "1:35:56"}
84
+ {"current_steps": 84, "total_steps": 300, "loss": 0.4905, "lr": 7.236067977499791e-05, "epoch": 1.4, "percentage": 28.0, "elapsed_time": "0:37:00", "remaining_time": "1:35:11"}
85
+ {"current_steps": 85, "total_steps": 300, "loss": 0.5074, "lr": 7.208492771020176e-05, "epoch": 1.4166666666666667, "percentage": 28.33, "elapsed_time": "0:37:21", "remaining_time": "1:34:30"}
86
+ {"current_steps": 86, "total_steps": 300, "loss": 0.503, "lr": 7.180483185979392e-05, "epoch": 1.4333333333333333, "percentage": 28.67, "elapsed_time": "0:37:42", "remaining_time": "1:33:50"}
87
+ {"current_steps": 87, "total_steps": 300, "loss": 0.4975, "lr": 7.152043014426888e-05, "epoch": 1.45, "percentage": 29.0, "elapsed_time": "0:38:03", "remaining_time": "1:33:11"}
88
+ {"current_steps": 88, "total_steps": 300, "loss": 0.4956, "lr": 7.123176106706638e-05, "epoch": 1.4666666666666668, "percentage": 29.33, "elapsed_time": "0:38:25", "remaining_time": "1:32:34"}
89
+ {"current_steps": 89, "total_steps": 300, "loss": 0.5099, "lr": 7.093886370935857e-05, "epoch": 1.4833333333333334, "percentage": 29.67, "elapsed_time": "0:38:46", "remaining_time": "1:31:55"}
90
+ {"current_steps": 90, "total_steps": 300, "loss": 0.4821, "lr": 7.064177772475912e-05, "epoch": 1.5, "percentage": 30.0, "elapsed_time": "0:39:07", "remaining_time": "1:31:17"}
91
+ {"current_steps": 91, "total_steps": 300, "loss": 0.5009, "lr": 7.034054333395477e-05, "epoch": 1.5166666666666666, "percentage": 30.33, "elapsed_time": "0:39:27", "remaining_time": "1:30:38"}
92
+ {"current_steps": 92, "total_steps": 300, "loss": 0.4933, "lr": 7.003520131925997e-05, "epoch": 1.5333333333333332, "percentage": 30.67, "elapsed_time": "0:39:49", "remaining_time": "1:30:01"}
93
+ {"current_steps": 93, "total_steps": 300, "loss": 0.4973, "lr": 6.972579301909577e-05, "epoch": 1.55, "percentage": 31.0, "elapsed_time": "0:40:09", "remaining_time": "1:29:23"}
94
+ {"current_steps": 94, "total_steps": 300, "loss": 0.4891, "lr": 6.941236032239316e-05, "epoch": 1.5666666666666667, "percentage": 31.33, "elapsed_time": "0:40:31", "remaining_time": "1:28:48"}
95
+ {"current_steps": 95, "total_steps": 300, "loss": 0.4906, "lr": 6.909494566292195e-05, "epoch": 1.5833333333333335, "percentage": 31.67, "elapsed_time": "0:40:52", "remaining_time": "1:28:12"}
96
+ {"current_steps": 96, "total_steps": 300, "loss": 0.4708, "lr": 6.877359201354606e-05, "epoch": 1.6, "percentage": 32.0, "elapsed_time": "0:41:14", "remaining_time": "1:27:37"}
97
+ {"current_steps": 97, "total_steps": 300, "loss": 0.48, "lr": 6.844834288040548e-05, "epoch": 1.6166666666666667, "percentage": 32.33, "elapsed_time": "0:41:34", "remaining_time": "1:27:01"}
98
+ {"current_steps": 98, "total_steps": 300, "loss": 0.4907, "lr": 6.811924229702648e-05, "epoch": 1.6333333333333333, "percentage": 32.67, "elapsed_time": "0:41:54", "remaining_time": "1:26:23"}
99
+ {"current_steps": 99, "total_steps": 300, "loss": 0.4792, "lr": 6.778633481835989e-05, "epoch": 1.65, "percentage": 33.0, "elapsed_time": "0:42:15", "remaining_time": "1:25:46"}
100
+ {"current_steps": 100, "total_steps": 300, "loss": 0.4709, "lr": 6.744966551474936e-05, "epoch": 1.6666666666666665, "percentage": 33.33, "elapsed_time": "0:42:36", "remaining_time": "1:25:13"}
101
+ {"current_steps": 101, "total_steps": 300, "loss": 0.4717, "lr": 6.71092799658293e-05, "epoch": 1.6833333333333333, "percentage": 33.67, "elapsed_time": "0:42:57", "remaining_time": "1:24:38"}
102
+ {"current_steps": 102, "total_steps": 300, "loss": 0.4726, "lr": 6.676522425435433e-05, "epoch": 1.7, "percentage": 34.0, "elapsed_time": "0:43:17", "remaining_time": "1:24:02"}
103
+ {"current_steps": 103, "total_steps": 300, "loss": 0.4732, "lr": 6.641754495996031e-05, "epoch": 1.7166666666666668, "percentage": 34.33, "elapsed_time": "0:43:38", "remaining_time": "1:23:28"}
104
+ {"current_steps": 104, "total_steps": 300, "loss": 0.475, "lr": 6.606628915285822e-05, "epoch": 1.7333333333333334, "percentage": 34.67, "elapsed_time": "0:43:58", "remaining_time": "1:22:53"}
105
+ {"current_steps": 105, "total_steps": 300, "loss": 0.476, "lr": 6.571150438746157e-05, "epoch": 1.75, "percentage": 35.0, "elapsed_time": "0:44:18", "remaining_time": "1:22:17"}
106
+ {"current_steps": 106, "total_steps": 300, "loss": 0.4804, "lr": 6.53532386959484e-05, "epoch": 1.7666666666666666, "percentage": 35.33, "elapsed_time": "0:44:39", "remaining_time": "1:21:43"}
107
+ {"current_steps": 107, "total_steps": 300, "loss": 0.4801, "lr": 6.499154058175841e-05, "epoch": 1.7833333333333332, "percentage": 35.67, "elapsed_time": "0:45:00", "remaining_time": "1:21:10"}
108
+ {"current_steps": 108, "total_steps": 300, "loss": 0.4695, "lr": 6.462645901302633e-05, "epoch": 1.8, "percentage": 36.0, "elapsed_time": "0:45:20", "remaining_time": "1:20:36"}
109
+ {"current_steps": 109, "total_steps": 300, "loss": 0.474, "lr": 6.425804341595255e-05, "epoch": 1.8166666666666667, "percentage": 36.33, "elapsed_time": "0:45:41", "remaining_time": "1:20:04"}
110
+ {"current_steps": 110, "total_steps": 300, "loss": 0.4753, "lr": 6.388634366811146e-05, "epoch": 1.8333333333333335, "percentage": 36.67, "elapsed_time": "0:46:02", "remaining_time": "1:19:31"}
111
+ {"current_steps": 111, "total_steps": 300, "loss": 0.4801, "lr": 6.351141009169893e-05, "epoch": 1.85, "percentage": 37.0, "elapsed_time": "0:46:23", "remaining_time": "1:18:58"}
112
+ {"current_steps": 112, "total_steps": 300, "loss": 0.4671, "lr": 6.313329344671946e-05, "epoch": 1.8666666666666667, "percentage": 37.33, "elapsed_time": "0:46:43", "remaining_time": "1:18:26"}
113
+ {"current_steps": 113, "total_steps": 300, "loss": 0.4742, "lr": 6.275204492411408e-05, "epoch": 1.8833333333333333, "percentage": 37.67, "elapsed_time": "0:47:04", "remaining_time": "1:17:54"}
114
+ {"current_steps": 114, "total_steps": 300, "loss": 0.4669, "lr": 6.236771613882987e-05, "epoch": 1.9, "percentage": 38.0, "elapsed_time": "0:47:25", "remaining_time": "1:17:23"}
115
+ {"current_steps": 115, "total_steps": 300, "loss": 0.4704, "lr": 6.198035912283225e-05, "epoch": 1.9166666666666665, "percentage": 38.33, "elapsed_time": "0:47:46", "remaining_time": "1:16:51"}
116
+ {"current_steps": 116, "total_steps": 300, "loss": 0.4624, "lr": 6.159002631806052e-05, "epoch": 1.9333333333333333, "percentage": 38.67, "elapsed_time": "0:48:07", "remaining_time": "1:16:19"}
117
+ {"current_steps": 117, "total_steps": 300, "loss": 0.4602, "lr": 6.11967705693282e-05, "epoch": 1.95, "percentage": 39.0, "elapsed_time": "0:48:29", "remaining_time": "1:15:50"}
118
+ {"current_steps": 118, "total_steps": 300, "loss": 0.4684, "lr": 6.0800645117168616e-05, "epoch": 1.9666666666666668, "percentage": 39.33, "elapsed_time": "0:48:50", "remaining_time": "1:15:19"}
119
+ {"current_steps": 119, "total_steps": 300, "loss": 0.4683, "lr": 6.040170359062702e-05, "epoch": 1.9833333333333334, "percentage": 39.67, "elapsed_time": "0:49:10", "remaining_time": "1:14:48"}
120
+ {"current_steps": 120, "total_steps": 300, "loss": 0.4461, "lr": 6.000000000000001e-05, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "0:49:31", "remaining_time": "1:14:17"}
121
+ {"current_steps": 121, "total_steps": 300, "loss": 0.4438, "lr": 5.959558872952349e-05, "epoch": 2.0166666666666666, "percentage": 40.33, "elapsed_time": "0:50:50", "remaining_time": "1:15:13"}
122
+ {"current_steps": 122, "total_steps": 300, "loss": 0.4412, "lr": 5.918852453000986e-05, "epoch": 2.033333333333333, "percentage": 40.67, "elapsed_time": "0:51:12", "remaining_time": "1:14:42"}
123
+ {"current_steps": 123, "total_steps": 300, "loss": 0.4383, "lr": 5.877886251143564e-05, "epoch": 2.05, "percentage": 41.0, "elapsed_time": "0:51:33", "remaining_time": "1:14:11"}
124
+ {"current_steps": 124, "total_steps": 300, "loss": 0.439, "lr": 5.836665813548047e-05, "epoch": 2.066666666666667, "percentage": 41.33, "elapsed_time": "0:51:51", "remaining_time": "1:13:36"}
125
+ {"current_steps": 125, "total_steps": 300, "loss": 0.4404, "lr": 5.79519672080185e-05, "epoch": 2.0833333333333335, "percentage": 41.67, "elapsed_time": "0:52:08", "remaining_time": "1:13:00"}
126
+ {"current_steps": 126, "total_steps": 300, "loss": 0.4446, "lr": 5.75348458715631e-05, "epoch": 2.1, "percentage": 42.0, "elapsed_time": "0:52:26", "remaining_time": "1:12:24"}
127
+ {"current_steps": 127, "total_steps": 300, "loss": 0.4328, "lr": 5.711535059766617e-05, "epoch": 2.1166666666666667, "percentage": 42.33, "elapsed_time": "0:52:47", "remaining_time": "1:11:54"}
128
+ {"current_steps": 128, "total_steps": 300, "loss": 0.4332, "lr": 5.669353817927272e-05, "epoch": 2.1333333333333333, "percentage": 42.67, "elapsed_time": "0:53:07", "remaining_time": "1:11:23"}
129
+ {"current_steps": 129, "total_steps": 300, "loss": 0.4439, "lr": 5.626946572303202e-05, "epoch": 2.15, "percentage": 43.0, "elapsed_time": "0:53:28", "remaining_time": "1:10:53"}
130
+ {"current_steps": 130, "total_steps": 300, "loss": 0.4363, "lr": 5.584319064156628e-05, "epoch": 2.1666666666666665, "percentage": 43.33, "elapsed_time": "0:53:50", "remaining_time": "1:10:24"}
131
+ {"current_steps": 131, "total_steps": 300, "loss": 0.437, "lr": 5.541477064569794e-05, "epoch": 2.183333333333333, "percentage": 43.67, "elapsed_time": "0:54:11", "remaining_time": "1:09:54"}
132
+ {"current_steps": 132, "total_steps": 300, "loss": 0.4396, "lr": 5.4984263736636494e-05, "epoch": 2.2, "percentage": 44.0, "elapsed_time": "0:54:31", "remaining_time": "1:09:24"}
133
+ {"current_steps": 133, "total_steps": 300, "loss": 0.441, "lr": 5.4551728198126066e-05, "epoch": 2.216666666666667, "percentage": 44.33, "elapsed_time": "0:54:52", "remaining_time": "1:08:54"}
134
+ {"current_steps": 134, "total_steps": 300, "loss": 0.4356, "lr": 5.4117222588554756e-05, "epoch": 2.2333333333333334, "percentage": 44.67, "elapsed_time": "0:55:15", "remaining_time": "1:08:27"}
135
+ {"current_steps": 135, "total_steps": 300, "loss": 0.4483, "lr": 5.368080573302676e-05, "epoch": 2.25, "percentage": 45.0, "elapsed_time": "0:55:35", "remaining_time": "1:07:56"}
136
+ {"current_steps": 136, "total_steps": 300, "loss": 0.4315, "lr": 5.324253671539833e-05, "epoch": 2.2666666666666666, "percentage": 45.33, "elapsed_time": "0:55:55", "remaining_time": "1:07:26"}
137
+ {"current_steps": 137, "total_steps": 300, "loss": 0.4324, "lr": 5.280247487027886e-05, "epoch": 2.283333333333333, "percentage": 45.67, "elapsed_time": "0:56:16", "remaining_time": "1:06:57"}
138
+ {"current_steps": 138, "total_steps": 300, "loss": 0.4369, "lr": 5.23606797749979e-05, "epoch": 2.3, "percentage": 46.0, "elapsed_time": "0:56:37", "remaining_time": "1:06:28"}
139
+ {"current_steps": 139, "total_steps": 300, "loss": 0.4384, "lr": 5.191721124153928e-05, "epoch": 2.3166666666666664, "percentage": 46.33, "elapsed_time": "0:56:57", "remaining_time": "1:05:58"}
140
+ {"current_steps": 140, "total_steps": 300, "loss": 0.4323, "lr": 5.1472129308443616e-05, "epoch": 2.3333333333333335, "percentage": 46.67, "elapsed_time": "0:57:18", "remaining_time": "1:05:29"}
141
+ {"current_steps": 141, "total_steps": 300, "loss": 0.4413, "lr": 5.102549423267997e-05, "epoch": 2.35, "percentage": 47.0, "elapsed_time": "0:57:39", "remaining_time": "1:05:00"}
142
+ {"current_steps": 142, "total_steps": 300, "loss": 0.4372, "lr": 5.05773664814881e-05, "epoch": 2.3666666666666667, "percentage": 47.33, "elapsed_time": "0:57:59", "remaining_time": "1:04:32"}
143
+ {"current_steps": 143, "total_steps": 300, "loss": 0.4389, "lr": 5.012780672419208e-05, "epoch": 2.3833333333333333, "percentage": 47.67, "elapsed_time": "0:58:21", "remaining_time": "1:04:04"}
144
+ {"current_steps": 144, "total_steps": 300, "loss": 0.4366, "lr": 4.967687582398671e-05, "epoch": 2.4, "percentage": 48.0, "elapsed_time": "0:58:42", "remaining_time": "1:03:36"}
145
+ {"current_steps": 145, "total_steps": 300, "loss": 0.4244, "lr": 4.922463482969761e-05, "epoch": 2.4166666666666665, "percentage": 48.33, "elapsed_time": "0:59:03", "remaining_time": "1:03:08"}
146
+ {"current_steps": 146, "total_steps": 300, "loss": 0.4263, "lr": 4.877114496751613e-05, "epoch": 2.4333333333333336, "percentage": 48.67, "elapsed_time": "0:59:24", "remaining_time": "1:02:40"}
147
+ {"current_steps": 147, "total_steps": 300, "loss": 0.4259, "lr": 4.831646763271037e-05, "epoch": 2.45, "percentage": 49.0, "elapsed_time": "0:59:45", "remaining_time": "1:02:12"}
148
+ {"current_steps": 148, "total_steps": 300, "loss": 0.4303, "lr": 4.786066438131321e-05, "epoch": 2.466666666666667, "percentage": 49.33, "elapsed_time": "1:00:05", "remaining_time": "1:01:43"}
149
+ {"current_steps": 149, "total_steps": 300, "loss": 0.4371, "lr": 4.740379692178858e-05, "epoch": 2.4833333333333334, "percentage": 49.67, "elapsed_time": "1:00:26", "remaining_time": "1:01:15"}
150
+ {"current_steps": 150, "total_steps": 300, "loss": 0.4363, "lr": 4.694592710667723e-05, "epoch": 2.5, "percentage": 50.0, "elapsed_time": "1:00:47", "remaining_time": "1:00:47"}
151
+ {"current_steps": 151, "total_steps": 300, "loss": 0.4284, "lr": 4.648711692422271e-05, "epoch": 2.5166666666666666, "percentage": 50.33, "elapsed_time": "1:01:09", "remaining_time": "1:00:20"}
152
+ {"current_steps": 152, "total_steps": 300, "loss": 0.4268, "lr": 4.602742848997933e-05, "epoch": 2.533333333333333, "percentage": 50.67, "elapsed_time": "1:01:29", "remaining_time": "0:59:52"}
153
+ {"current_steps": 153, "total_steps": 300, "loss": 0.4361, "lr": 4.556692403840262e-05, "epoch": 2.55, "percentage": 51.0, "elapsed_time": "1:01:50", "remaining_time": "0:59:25"}
154
+ {"current_steps": 154, "total_steps": 300, "loss": 0.4369, "lr": 4.51056659144238e-05, "epoch": 2.5666666666666664, "percentage": 51.33, "elapsed_time": "1:02:11", "remaining_time": "0:58:57"}
155
+ {"current_steps": 155, "total_steps": 300, "loss": 0.4288, "lr": 4.464371656500921e-05, "epoch": 2.5833333333333335, "percentage": 51.67, "elapsed_time": "1:02:33", "remaining_time": "0:58:31"}
156
+ {"current_steps": 156, "total_steps": 300, "loss": 0.4284, "lr": 4.418113853070614e-05, "epoch": 2.6, "percentage": 52.0, "elapsed_time": "1:02:53", "remaining_time": "0:58:03"}
157
+ {"current_steps": 157, "total_steps": 300, "loss": 0.4301, "lr": 4.37179944371757e-05, "epoch": 2.6166666666666667, "percentage": 52.33, "elapsed_time": "1:03:14", "remaining_time": "0:57:36"}
158
+ {"current_steps": 158, "total_steps": 300, "loss": 0.4309, "lr": 4.3254346986714334e-05, "epoch": 2.6333333333333333, "percentage": 52.67, "elapsed_time": "1:03:35", "remaining_time": "0:57:08"}
159
+ {"current_steps": 159, "total_steps": 300, "loss": 0.4383, "lr": 4.2790258949765014e-05, "epoch": 2.65, "percentage": 53.0, "elapsed_time": "1:03:56", "remaining_time": "0:56:42"}
160
+ {"current_steps": 160, "total_steps": 300, "loss": 0.4302, "lr": 4.2325793156419035e-05, "epoch": 2.6666666666666665, "percentage": 53.33, "elapsed_time": "1:04:17", "remaining_time": "0:56:15"}
161
+ {"current_steps": 161, "total_steps": 300, "loss": 0.4274, "lr": 4.186101248790988e-05, "epoch": 2.6833333333333336, "percentage": 53.67, "elapsed_time": "1:04:37", "remaining_time": "0:55:47"}
162
+ {"current_steps": 162, "total_steps": 300, "loss": 0.4283, "lr": 4.139597986810005e-05, "epoch": 2.7, "percentage": 54.0, "elapsed_time": "1:04:58", "remaining_time": "0:55:20"}
163
+ {"current_steps": 163, "total_steps": 300, "loss": 0.4262, "lr": 4.093075825496225e-05, "epoch": 2.716666666666667, "percentage": 54.33, "elapsed_time": "1:05:21", "remaining_time": "0:54:55"}
164
+ {"current_steps": 164, "total_steps": 300, "loss": 0.4267, "lr": 4.046541063205589e-05, "epoch": 2.7333333333333334, "percentage": 54.67, "elapsed_time": "1:05:42", "remaining_time": "0:54:29"}
165
+ {"current_steps": 165, "total_steps": 300, "loss": 0.431, "lr": 4e-05, "epoch": 2.75, "percentage": 55.0, "elapsed_time": "1:06:03", "remaining_time": "0:54:02"}
166
+ {"current_steps": 166, "total_steps": 300, "loss": 0.4302, "lr": 3.953458936794413e-05, "epoch": 2.7666666666666666, "percentage": 55.33, "elapsed_time": "1:06:23", "remaining_time": "0:53:35"}
167
+ {"current_steps": 167, "total_steps": 300, "loss": 0.4243, "lr": 3.9069241745037753e-05, "epoch": 2.783333333333333, "percentage": 55.67, "elapsed_time": "1:06:45", "remaining_time": "0:53:09"}
168
+ {"current_steps": 168, "total_steps": 300, "loss": 0.4282, "lr": 3.860402013189998e-05, "epoch": 2.8, "percentage": 56.0, "elapsed_time": "1:07:07", "remaining_time": "0:52:44"}
169
+ {"current_steps": 169, "total_steps": 300, "loss": 0.4267, "lr": 3.813898751209013e-05, "epoch": 2.8166666666666664, "percentage": 56.33, "elapsed_time": "1:07:26", "remaining_time": "0:52:16"}
170
+ {"current_steps": 170, "total_steps": 300, "loss": 0.4376, "lr": 3.767420684358097e-05, "epoch": 2.8333333333333335, "percentage": 56.67, "elapsed_time": "1:07:47", "remaining_time": "0:51:50"}
171
+ {"current_steps": 171, "total_steps": 300, "loss": 0.4331, "lr": 3.720974105023499e-05, "epoch": 2.85, "percentage": 57.0, "elapsed_time": "1:08:08", "remaining_time": "0:51:24"}
172
+ {"current_steps": 172, "total_steps": 300, "loss": 0.4255, "lr": 3.674565301328568e-05, "epoch": 2.8666666666666667, "percentage": 57.33, "elapsed_time": "1:08:30", "remaining_time": "0:50:58"}
173
+ {"current_steps": 173, "total_steps": 300, "loss": 0.4242, "lr": 3.628200556282432e-05, "epoch": 2.8833333333333333, "percentage": 57.67, "elapsed_time": "1:08:50", "remaining_time": "0:50:32"}
174
+ {"current_steps": 174, "total_steps": 300, "loss": 0.4329, "lr": 3.581886146929387e-05, "epoch": 2.9, "percentage": 58.0, "elapsed_time": "1:09:11", "remaining_time": "0:50:05"}
175
+ {"current_steps": 175, "total_steps": 300, "loss": 0.4338, "lr": 3.535628343499079e-05, "epoch": 2.9166666666666665, "percentage": 58.33, "elapsed_time": "1:09:31", "remaining_time": "0:49:39"}
176
+ {"current_steps": 176, "total_steps": 300, "loss": 0.4228, "lr": 3.4894334085576215e-05, "epoch": 2.9333333333333336, "percentage": 58.67, "elapsed_time": "1:09:54", "remaining_time": "0:49:14"}
177
+ {"current_steps": 177, "total_steps": 300, "loss": 0.4352, "lr": 3.44330759615974e-05, "epoch": 2.95, "percentage": 59.0, "elapsed_time": "1:10:14", "remaining_time": "0:48:48"}
178
+ {"current_steps": 178, "total_steps": 300, "loss": 0.4293, "lr": 3.397257151002068e-05, "epoch": 2.966666666666667, "percentage": 59.33, "elapsed_time": "1:10:35", "remaining_time": "0:48:23"}
179
+ {"current_steps": 179, "total_steps": 300, "loss": 0.4359, "lr": 3.351288307577731e-05, "epoch": 2.9833333333333334, "percentage": 59.67, "elapsed_time": "1:10:56", "remaining_time": "0:47:57"}
180
+ {"current_steps": 180, "total_steps": 300, "loss": 0.4174, "lr": 3.305407289332279e-05, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "1:11:18", "remaining_time": "0:47:32"}
181
+ {"current_steps": 181, "total_steps": 300, "loss": 0.4078, "lr": 3.2596203078211424e-05, "epoch": 3.0166666666666666, "percentage": 60.33, "elapsed_time": "1:14:27", "remaining_time": "0:48:57"}
182
+ {"current_steps": 182, "total_steps": 300, "loss": 0.3961, "lr": 3.213933561868679e-05, "epoch": 3.033333333333333, "percentage": 60.67, "elapsed_time": "1:14:46", "remaining_time": "0:48:29"}
183
+ {"current_steps": 183, "total_steps": 300, "loss": 0.4045, "lr": 3.168353236728964e-05, "epoch": 3.05, "percentage": 61.0, "elapsed_time": "1:15:07", "remaining_time": "0:48:01"}
184
+ {"current_steps": 184, "total_steps": 300, "loss": 0.3961, "lr": 3.122885503248386e-05, "epoch": 3.066666666666667, "percentage": 61.33, "elapsed_time": "1:15:31", "remaining_time": "0:47:36"}
185
+ {"current_steps": 185, "total_steps": 300, "loss": 0.3928, "lr": 3.07753651703024e-05, "epoch": 3.0833333333333335, "percentage": 61.67, "elapsed_time": "1:15:53", "remaining_time": "0:47:10"}
186
+ {"current_steps": 186, "total_steps": 300, "loss": 0.3967, "lr": 3.0323124176013297e-05, "epoch": 3.1, "percentage": 62.0, "elapsed_time": "1:16:13", "remaining_time": "0:46:42"}
187
+ {"current_steps": 187, "total_steps": 300, "loss": 0.3934, "lr": 2.9872193275807933e-05, "epoch": 3.1166666666666667, "percentage": 62.33, "elapsed_time": "1:16:34", "remaining_time": "0:46:16"}
188
+ {"current_steps": 188, "total_steps": 300, "loss": 0.3999, "lr": 2.9422633518511926e-05, "epoch": 3.1333333333333333, "percentage": 62.67, "elapsed_time": "1:16:56", "remaining_time": "0:45:50"}
189
+ {"current_steps": 189, "total_steps": 300, "loss": 0.3957, "lr": 2.8974505767320037e-05, "epoch": 3.15, "percentage": 63.0, "elapsed_time": "1:17:18", "remaining_time": "0:45:23"}
190
+ {"current_steps": 190, "total_steps": 300, "loss": 0.3909, "lr": 2.8527870691556404e-05, "epoch": 3.1666666666666665, "percentage": 63.33, "elapsed_time": "1:17:38", "remaining_time": "0:44:57"}
191
+ {"current_steps": 191, "total_steps": 300, "loss": 0.3979, "lr": 2.808278875846072e-05, "epoch": 3.183333333333333, "percentage": 63.67, "elapsed_time": "1:18:00", "remaining_time": "0:44:30"}
192
+ {"current_steps": 192, "total_steps": 300, "loss": 0.3878, "lr": 2.7639320225002108e-05, "epoch": 3.2, "percentage": 64.0, "elapsed_time": "1:18:22", "remaining_time": "0:44:05"}
193
+ {"current_steps": 193, "total_steps": 300, "loss": 0.4054, "lr": 2.7197525129721138e-05, "epoch": 3.216666666666667, "percentage": 64.33, "elapsed_time": "1:18:44", "remaining_time": "0:43:39"}
194
+ {"current_steps": 194, "total_steps": 300, "loss": 0.4018, "lr": 2.6757463284601682e-05, "epoch": 3.2333333333333334, "percentage": 64.67, "elapsed_time": "1:19:05", "remaining_time": "0:43:12"}
195
+ {"current_steps": 195, "total_steps": 300, "loss": 0.4003, "lr": 2.6319194266973256e-05, "epoch": 3.25, "percentage": 65.0, "elapsed_time": "1:19:26", "remaining_time": "0:42:46"}
196
+ {"current_steps": 196, "total_steps": 300, "loss": 0.3976, "lr": 2.5882777411445254e-05, "epoch": 3.2666666666666666, "percentage": 65.33, "elapsed_time": "1:19:47", "remaining_time": "0:42:20"}
197
+ {"current_steps": 197, "total_steps": 300, "loss": 0.3894, "lr": 2.5448271801873957e-05, "epoch": 3.283333333333333, "percentage": 65.67, "elapsed_time": "1:20:09", "remaining_time": "0:41:54"}
198
+ {"current_steps": 198, "total_steps": 300, "loss": 0.3937, "lr": 2.501573626336352e-05, "epoch": 3.3, "percentage": 66.0, "elapsed_time": "1:20:31", "remaining_time": "0:41:28"}
199
+ {"current_steps": 199, "total_steps": 300, "loss": 0.4047, "lr": 2.4585229354302077e-05, "epoch": 3.3166666666666664, "percentage": 66.33, "elapsed_time": "1:20:52", "remaining_time": "0:41:02"}
200
+ {"current_steps": 200, "total_steps": 300, "loss": 0.3926, "lr": 2.4156809358433728e-05, "epoch": 3.3333333333333335, "percentage": 66.67, "elapsed_time": "1:21:13", "remaining_time": "0:40:36"}
201
+ {"current_steps": 201, "total_steps": 300, "loss": 0.3996, "lr": 2.3730534276968e-05, "epoch": 3.35, "percentage": 67.0, "elapsed_time": "1:21:34", "remaining_time": "0:40:10"}
202
+ {"current_steps": 202, "total_steps": 300, "loss": 0.3988, "lr": 2.330646182072729e-05, "epoch": 3.3666666666666667, "percentage": 67.33, "elapsed_time": "1:21:55", "remaining_time": "0:39:44"}
203
+ {"current_steps": 203, "total_steps": 300, "loss": 0.3969, "lr": 2.288464940233384e-05, "epoch": 3.3833333333333333, "percentage": 67.67, "elapsed_time": "1:22:15", "remaining_time": "0:39:18"}
204
+ {"current_steps": 204, "total_steps": 300, "loss": 0.3965, "lr": 2.24651541284369e-05, "epoch": 3.4, "percentage": 68.0, "elapsed_time": "1:22:35", "remaining_time": "0:38:51"}
205
+ {"current_steps": 205, "total_steps": 300, "loss": 0.3975, "lr": 2.2048032791981515e-05, "epoch": 3.4166666666666665, "percentage": 68.33, "elapsed_time": "1:22:58", "remaining_time": "0:38:27"}
206
+ {"current_steps": 206, "total_steps": 300, "loss": 0.3867, "lr": 2.1633341864519526e-05, "epoch": 3.4333333333333336, "percentage": 68.67, "elapsed_time": "1:23:19", "remaining_time": "0:38:01"}
207
+ {"current_steps": 207, "total_steps": 300, "loss": 0.393, "lr": 2.122113748856438e-05, "epoch": 3.45, "percentage": 69.0, "elapsed_time": "1:23:39", "remaining_time": "0:37:35"}
208
+ {"current_steps": 208, "total_steps": 300, "loss": 0.4008, "lr": 2.0811475469990167e-05, "epoch": 3.466666666666667, "percentage": 69.33, "elapsed_time": "1:24:00", "remaining_time": "0:37:09"}
209
+ {"current_steps": 209, "total_steps": 300, "loss": 0.3992, "lr": 2.0404411270476527e-05, "epoch": 3.4833333333333334, "percentage": 69.67, "elapsed_time": "1:24:23", "remaining_time": "0:36:44"}
210
+ {"current_steps": 210, "total_steps": 300, "loss": 0.3951, "lr": 2.0000000000000012e-05, "epoch": 3.5, "percentage": 70.0, "elapsed_time": "1:24:45", "remaining_time": "0:36:19"}
211
+ {"current_steps": 211, "total_steps": 300, "loss": 0.3976, "lr": 1.959829640937299e-05, "epoch": 3.5166666666666666, "percentage": 70.33, "elapsed_time": "1:25:06", "remaining_time": "0:35:53"}
212
+ {"current_steps": 212, "total_steps": 300, "loss": 0.3967, "lr": 1.9199354882831387e-05, "epoch": 3.533333333333333, "percentage": 70.67, "elapsed_time": "1:25:27", "remaining_time": "0:35:28"}
213
+ {"current_steps": 213, "total_steps": 300, "loss": 0.3957, "lr": 1.880322943067181e-05, "epoch": 3.55, "percentage": 71.0, "elapsed_time": "1:25:49", "remaining_time": "0:35:03"}
214
+ {"current_steps": 214, "total_steps": 300, "loss": 0.3938, "lr": 1.8409973681939498e-05, "epoch": 3.5666666666666664, "percentage": 71.33, "elapsed_time": "1:26:12", "remaining_time": "0:34:38"}
215
+ {"current_steps": 215, "total_steps": 300, "loss": 0.4015, "lr": 1.8019640877167763e-05, "epoch": 3.5833333333333335, "percentage": 71.67, "elapsed_time": "1:26:32", "remaining_time": "0:34:12"}
216
+ {"current_steps": 216, "total_steps": 300, "loss": 0.398, "lr": 1.7632283861170135e-05, "epoch": 3.6, "percentage": 72.0, "elapsed_time": "1:26:53", "remaining_time": "0:33:47"}
217
+ {"current_steps": 217, "total_steps": 300, "loss": 0.3984, "lr": 1.7247955075885938e-05, "epoch": 3.6166666666666667, "percentage": 72.33, "elapsed_time": "1:27:15", "remaining_time": "0:33:22"}
218
+ {"current_steps": 218, "total_steps": 300, "loss": 0.4015, "lr": 1.686670655328054e-05, "epoch": 3.6333333333333333, "percentage": 72.67, "elapsed_time": "1:27:38", "remaining_time": "0:32:57"}
219
+ {"current_steps": 219, "total_steps": 300, "loss": 0.3966, "lr": 1.648858990830108e-05, "epoch": 3.65, "percentage": 73.0, "elapsed_time": "1:27:58", "remaining_time": "0:32:32"}
220
+ {"current_steps": 220, "total_steps": 300, "loss": 0.3945, "lr": 1.6113656331888563e-05, "epoch": 3.6666666666666665, "percentage": 73.33, "elapsed_time": "1:28:19", "remaining_time": "0:32:07"}
221
+ {"current_steps": 221, "total_steps": 300, "loss": 0.3958, "lr": 1.5741956584047478e-05, "epoch": 3.6833333333333336, "percentage": 73.67, "elapsed_time": "1:28:40", "remaining_time": "0:31:42"}
222
+ {"current_steps": 222, "total_steps": 300, "loss": 0.4005, "lr": 1.537354098697367e-05, "epoch": 3.7, "percentage": 74.0, "elapsed_time": "1:29:04", "remaining_time": "0:31:17"}
223
+ {"current_steps": 223, "total_steps": 300, "loss": 0.3961, "lr": 1.5008459418241601e-05, "epoch": 3.716666666666667, "percentage": 74.33, "elapsed_time": "1:29:26", "remaining_time": "0:30:52"}
224
+ {"current_steps": 224, "total_steps": 300, "loss": 0.3973, "lr": 1.4646761304051587e-05, "epoch": 3.7333333333333334, "percentage": 74.67, "elapsed_time": "1:29:46", "remaining_time": "0:30:27"}
225
+ {"current_steps": 225, "total_steps": 300, "loss": 0.3929, "lr": 1.4288495612538427e-05, "epoch": 3.75, "percentage": 75.0, "elapsed_time": "1:30:02", "remaining_time": "0:30:00"}
226
+ {"current_steps": 226, "total_steps": 300, "loss": 0.4019, "lr": 1.3933710847141795e-05, "epoch": 3.7666666666666666, "percentage": 75.33, "elapsed_time": "1:30:20", "remaining_time": "0:29:35"}
227
+ {"current_steps": 227, "total_steps": 300, "loss": 0.392, "lr": 1.3582455040039699e-05, "epoch": 3.783333333333333, "percentage": 75.67, "elapsed_time": "1:30:36", "remaining_time": "0:29:08"}
228
+ {"current_steps": 228, "total_steps": 300, "loss": 0.3891, "lr": 1.3234775745645684e-05, "epoch": 3.8, "percentage": 76.0, "elapsed_time": "1:30:51", "remaining_time": "0:28:41"}
229
+ {"current_steps": 229, "total_steps": 300, "loss": 0.3885, "lr": 1.2890720034170712e-05, "epoch": 3.8166666666666664, "percentage": 76.33, "elapsed_time": "1:31:06", "remaining_time": "0:28:14"}
230
+ {"current_steps": 230, "total_steps": 300, "loss": 0.3918, "lr": 1.2550334485250661e-05, "epoch": 3.8333333333333335, "percentage": 76.67, "elapsed_time": "1:31:24", "remaining_time": "0:27:49"}
231
+ {"current_steps": 231, "total_steps": 300, "loss": 0.394, "lr": 1.2213665181640106e-05, "epoch": 3.85, "percentage": 77.0, "elapsed_time": "1:31:43", "remaining_time": "0:27:23"}
232
+ {"current_steps": 232, "total_steps": 300, "loss": 0.3913, "lr": 1.1880757702973531e-05, "epoch": 3.8666666666666667, "percentage": 77.33, "elapsed_time": "1:32:04", "remaining_time": "0:26:59"}
233
+ {"current_steps": 233, "total_steps": 300, "loss": 0.3972, "lr": 1.1551657119594517e-05, "epoch": 3.8833333333333333, "percentage": 77.67, "elapsed_time": "1:32:25", "remaining_time": "0:26:34"}
234
+ {"current_steps": 234, "total_steps": 300, "loss": 0.3952, "lr": 1.1226407986453963e-05, "epoch": 3.9, "percentage": 78.0, "elapsed_time": "1:32:46", "remaining_time": "0:26:10"}
235
+ {"current_steps": 235, "total_steps": 300, "loss": 0.396, "lr": 1.0905054337078051e-05, "epoch": 3.9166666666666665, "percentage": 78.33, "elapsed_time": "1:33:10", "remaining_time": "0:25:46"}
236
+ {"current_steps": 236, "total_steps": 300, "loss": 0.3997, "lr": 1.0587639677606857e-05, "epoch": 3.9333333333333336, "percentage": 78.67, "elapsed_time": "1:33:31", "remaining_time": "0:25:21"}
237
+ {"current_steps": 237, "total_steps": 300, "loss": 0.3938, "lr": 1.0274206980904226e-05, "epoch": 3.95, "percentage": 79.0, "elapsed_time": "1:33:52", "remaining_time": "0:24:57"}
238
+ {"current_steps": 238, "total_steps": 300, "loss": 0.3943, "lr": 9.964798680740033e-06, "epoch": 3.966666666666667, "percentage": 79.33, "elapsed_time": "1:34:13", "remaining_time": "0:24:32"}
239
+ {"current_steps": 239, "total_steps": 300, "loss": 0.4011, "lr": 9.659456666045247e-06, "epoch": 3.9833333333333334, "percentage": 79.67, "elapsed_time": "1:34:37", "remaining_time": "0:24:09"}
240
+ {"current_steps": 240, "total_steps": 300, "loss": 0.3842, "lr": 9.358222275240884e-06, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "1:34:58", "remaining_time": "0:23:44"}
241
+ {"current_steps": 241, "total_steps": 300, "loss": 0.3761, "lr": 9.061136290641448e-06, "epoch": 4.016666666666667, "percentage": 80.33, "elapsed_time": "1:37:01", "remaining_time": "0:23:45"}
242
+ {"current_steps": 242, "total_steps": 300, "loss": 0.3796, "lr": 8.768238932933632e-06, "epoch": 4.033333333333333, "percentage": 80.67, "elapsed_time": "1:37:24", "remaining_time": "0:23:20"}
243
+ {"current_steps": 243, "total_steps": 300, "loss": 0.3792, "lr": 8.479569855731125e-06, "epoch": 4.05, "percentage": 81.0, "elapsed_time": "1:37:47", "remaining_time": "0:22:56"}
244
+ {"current_steps": 244, "total_steps": 300, "loss": 0.3702, "lr": 8.195168140206084e-06, "epoch": 4.066666666666666, "percentage": 81.33, "elapsed_time": "1:38:08", "remaining_time": "0:22:31"}
245
+ {"current_steps": 245, "total_steps": 300, "loss": 0.3648, "lr": 7.915072289798247e-06, "epoch": 4.083333333333333, "percentage": 81.67, "elapsed_time": "1:38:29", "remaining_time": "0:22:06"}
246
+ {"current_steps": 246, "total_steps": 300, "loss": 0.3873, "lr": 7.639320225002106e-06, "epoch": 4.1, "percentage": 82.0, "elapsed_time": "1:38:50", "remaining_time": "0:21:41"}
247
+ {"current_steps": 247, "total_steps": 300, "loss": 0.3802, "lr": 7.367949278233126e-06, "epoch": 4.116666666666666, "percentage": 82.33, "elapsed_time": "1:39:15", "remaining_time": "0:21:17"}
248
+ {"current_steps": 248, "total_steps": 300, "loss": 0.3812, "lr": 7.1009961887735075e-06, "epoch": 4.133333333333334, "percentage": 82.67, "elapsed_time": "1:39:35", "remaining_time": "0:20:53"}
249
+ {"current_steps": 249, "total_steps": 300, "loss": 0.3763, "lr": 6.838497097798336e-06, "epoch": 4.15, "percentage": 83.0, "elapsed_time": "1:39:56", "remaining_time": "0:20:28"}
250
+ {"current_steps": 250, "total_steps": 300, "loss": 0.3754, "lr": 6.58048754348255e-06, "epoch": 4.166666666666667, "percentage": 83.33, "elapsed_time": "1:40:17", "remaining_time": "0:20:03"}
251
+ {"current_steps": 251, "total_steps": 300, "loss": 0.3706, "lr": 6.327002456189699e-06, "epoch": 4.183333333333334, "percentage": 83.67, "elapsed_time": "1:40:40", "remaining_time": "0:19:39"}
252
+ {"current_steps": 252, "total_steps": 300, "loss": 0.3788, "lr": 6.078076153742962e-06, "epoch": 4.2, "percentage": 84.0, "elapsed_time": "1:41:02", "remaining_time": "0:19:14"}
253
+ {"current_steps": 253, "total_steps": 300, "loss": 0.372, "lr": 5.833742336778981e-06, "epoch": 4.216666666666667, "percentage": 84.33, "elapsed_time": "1:41:23", "remaining_time": "0:18:50"}
254
+ {"current_steps": 254, "total_steps": 300, "loss": 0.3683, "lr": 5.5940340841853915e-06, "epoch": 4.233333333333333, "percentage": 84.67, "elapsed_time": "1:41:44", "remaining_time": "0:18:25"}
255
+ {"current_steps": 255, "total_steps": 300, "loss": 0.3806, "lr": 5.358983848622452e-06, "epoch": 4.25, "percentage": 85.0, "elapsed_time": "1:42:03", "remaining_time": "0:18:00"}
256
+ {"current_steps": 256, "total_steps": 300, "loss": 0.3713, "lr": 5.128623452129508e-06, "epoch": 4.266666666666667, "percentage": 85.33, "elapsed_time": "1:42:20", "remaining_time": "0:17:35"}
257
+ {"current_steps": 257, "total_steps": 300, "loss": 0.3766, "lr": 4.902984081816717e-06, "epoch": 4.283333333333333, "percentage": 85.67, "elapsed_time": "1:42:35", "remaining_time": "0:17:09"}
258
+ {"current_steps": 258, "total_steps": 300, "loss": 0.3782, "lr": 4.6820962856429205e-06, "epoch": 4.3, "percentage": 86.0, "elapsed_time": "1:42:50", "remaining_time": "0:16:44"}
259
+ {"current_steps": 259, "total_steps": 300, "loss": 0.3802, "lr": 4.4659899682798446e-06, "epoch": 4.316666666666666, "percentage": 86.33, "elapsed_time": "1:43:07", "remaining_time": "0:16:19"}
260
+ {"current_steps": 260, "total_steps": 300, "loss": 0.3768, "lr": 4.254694387063514e-06, "epoch": 4.333333333333333, "percentage": 86.67, "elapsed_time": "1:43:25", "remaining_time": "0:15:54"}
261
+ {"current_steps": 261, "total_steps": 300, "loss": 0.3734, "lr": 4.048238148033328e-06, "epoch": 4.35, "percentage": 87.0, "elapsed_time": "1:43:40", "remaining_time": "0:15:29"}
262
+ {"current_steps": 262, "total_steps": 300, "loss": 0.3837, "lr": 3.846649202059181e-06, "epoch": 4.366666666666666, "percentage": 87.33, "elapsed_time": "1:43:55", "remaining_time": "0:15:04"}
263
+ {"current_steps": 263, "total_steps": 300, "loss": 0.3692, "lr": 3.6499548410574303e-06, "epoch": 4.383333333333334, "percentage": 87.67, "elapsed_time": "1:44:12", "remaining_time": "0:14:39"}
264
+ {"current_steps": 264, "total_steps": 300, "loss": 0.3677, "lr": 3.458181694295961e-06, "epoch": 4.4, "percentage": 88.0, "elapsed_time": "1:44:30", "remaining_time": "0:14:15"}
265
+ {"current_steps": 265, "total_steps": 300, "loss": 0.3855, "lr": 3.2713557247890447e-06, "epoch": 4.416666666666667, "percentage": 88.33, "elapsed_time": "1:44:45", "remaining_time": "0:13:50"}
266
+ {"current_steps": 266, "total_steps": 300, "loss": 0.372, "lr": 3.0895022257823083e-06, "epoch": 4.433333333333334, "percentage": 88.67, "elapsed_time": "1:45:00", "remaining_time": "0:13:25"}
267
+ {"current_steps": 267, "total_steps": 300, "loss": 0.381, "lr": 2.9126458173285077e-06, "epoch": 4.45, "percentage": 89.0, "elapsed_time": "1:45:18", "remaining_time": "0:13:00"}
268
+ {"current_steps": 268, "total_steps": 300, "loss": 0.3809, "lr": 2.7408104429543025e-06, "epoch": 4.466666666666667, "percentage": 89.33, "elapsed_time": "1:45:36", "remaining_time": "0:12:36"}
269
+ {"current_steps": 269, "total_steps": 300, "loss": 0.3751, "lr": 2.574019366418745e-06, "epoch": 4.483333333333333, "percentage": 89.67, "elapsed_time": "1:45:51", "remaining_time": "0:12:12"}
270
+ {"current_steps": 270, "total_steps": 300, "loss": 0.3838, "lr": 2.4122951685636674e-06, "epoch": 4.5, "percentage": 90.0, "elapsed_time": "1:46:07", "remaining_time": "0:11:47"}
271
+ {"current_steps": 271, "total_steps": 300, "loss": 0.3676, "lr": 2.25565974425666e-06, "epoch": 4.516666666666667, "percentage": 90.33, "elapsed_time": "1:46:22", "remaining_time": "0:11:23"}
272
+ {"current_steps": 272, "total_steps": 300, "loss": 0.3761, "lr": 2.104134299426832e-06, "epoch": 4.533333333333333, "percentage": 90.67, "elapsed_time": "1:46:42", "remaining_time": "0:10:59"}
273
+ {"current_steps": 273, "total_steps": 300, "loss": 0.3686, "lr": 1.957739348193859e-06, "epoch": 4.55, "percentage": 91.0, "elapsed_time": "1:46:58", "remaining_time": "0:10:34"}
274
+ {"current_steps": 274, "total_steps": 300, "loss": 0.3757, "lr": 1.8164947100907238e-06, "epoch": 4.566666666666666, "percentage": 91.33, "elapsed_time": "1:47:14", "remaining_time": "0:10:10"}
275
+ {"current_steps": 275, "total_steps": 300, "loss": 0.3739, "lr": 1.6804195073804442e-06, "epoch": 4.583333333333333, "percentage": 91.67, "elapsed_time": "1:47:30", "remaining_time": "0:09:46"}
276
+ {"current_steps": 276, "total_steps": 300, "loss": 0.3797, "lr": 1.5495321624672443e-06, "epoch": 4.6, "percentage": 92.0, "elapsed_time": "1:47:47", "remaining_time": "0:09:22"}
277
+ {"current_steps": 277, "total_steps": 300, "loss": 0.3718, "lr": 1.423850395402444e-06, "epoch": 4.616666666666667, "percentage": 92.33, "elapsed_time": "1:48:04", "remaining_time": "0:08:58"}
278
+ {"current_steps": 278, "total_steps": 300, "loss": 0.3827, "lr": 1.3033912214854482e-06, "epoch": 4.633333333333333, "percentage": 92.67, "elapsed_time": "1:48:19", "remaining_time": "0:08:34"}
279
+ {"current_steps": 279, "total_steps": 300, "loss": 0.3693, "lr": 1.1881709489601413e-06, "epoch": 4.65, "percentage": 93.0, "elapsed_time": "1:48:34", "remaining_time": "0:08:10"}
280
+ {"current_steps": 280, "total_steps": 300, "loss": 0.3772, "lr": 1.0782051768070477e-06, "epoch": 4.666666666666667, "percentage": 93.33, "elapsed_time": "1:48:52", "remaining_time": "0:07:46"}
281
+ {"current_steps": 281, "total_steps": 300, "loss": 0.3783, "lr": 9.735087926314324e-07, "epoch": 4.683333333333334, "percentage": 93.67, "elapsed_time": "1:49:10", "remaining_time": "0:07:22"}
282
+ {"current_steps": 282, "total_steps": 300, "loss": 0.3749, "lr": 8.740959706477725e-07, "epoch": 4.7, "percentage": 94.0, "elapsed_time": "1:49:25", "remaining_time": "0:06:59"}
283
+ {"current_steps": 283, "total_steps": 300, "loss": 0.381, "lr": 7.799801697608278e-07, "epoch": 4.716666666666667, "percentage": 94.33, "elapsed_time": "1:49:40", "remaining_time": "0:06:35"}
284
+ {"current_steps": 284, "total_steps": 300, "loss": 0.3718, "lr": 6.911741317434706e-07, "epoch": 4.733333333333333, "percentage": 94.67, "elapsed_time": "1:49:56", "remaining_time": "0:06:11"}
285
+ {"current_steps": 285, "total_steps": 300, "loss": 0.382, "lr": 6.076898795116792e-07, "epoch": 4.75, "percentage": 95.0, "elapsed_time": "1:50:14", "remaining_time": "0:05:48"}
286
+ {"current_steps": 286, "total_steps": 300, "loss": 0.3715, "lr": 5.295387154968312e-07, "epoch": 4.766666666666667, "percentage": 95.33, "elapsed_time": "1:50:29", "remaining_time": "0:05:24"}
287
+ {"current_steps": 287, "total_steps": 300, "loss": 0.3763, "lr": 4.5673122011553605e-07, "epoch": 4.783333333333333, "percentage": 95.67, "elapsed_time": "1:50:44", "remaining_time": "0:05:00"}
288
+ {"current_steps": 288, "total_steps": 300, "loss": 0.3808, "lr": 3.8927725033718553e-07, "epoch": 4.8, "percentage": 96.0, "elapsed_time": "1:51:02", "remaining_time": "0:04:37"}
289
+ {"current_steps": 289, "total_steps": 300, "loss": 0.3806, "lr": 3.2718593834953237e-07, "epoch": 4.816666666666666, "percentage": 96.33, "elapsed_time": "1:51:20", "remaining_time": "0:04:14"}
290
+ {"current_steps": 290, "total_steps": 300, "loss": 0.3728, "lr": 2.704656903222791e-07, "epoch": 4.833333333333333, "percentage": 96.67, "elapsed_time": "1:51:38", "remaining_time": "0:03:50"}
291
+ {"current_steps": 291, "total_steps": 300, "loss": 0.3833, "lr": 2.1912418526906841e-07, "epoch": 4.85, "percentage": 97.0, "elapsed_time": "1:51:53", "remaining_time": "0:03:27"}
292
+ {"current_steps": 292, "total_steps": 300, "loss": 0.3715, "lr": 1.7316837400782604e-07, "epoch": 4.866666666666667, "percentage": 97.33, "elapsed_time": "1:52:11", "remaining_time": "0:03:04"}
293
+ {"current_steps": 293, "total_steps": 300, "loss": 0.3786, "lr": 1.3260447821975775e-07, "epoch": 4.883333333333333, "percentage": 97.67, "elapsed_time": "1:52:29", "remaining_time": "0:02:41"}
294
+ {"current_steps": 294, "total_steps": 300, "loss": 0.3741, "lr": 9.74379896070321e-08, "epoch": 4.9, "percentage": 98.0, "elapsed_time": "1:52:44", "remaining_time": "0:02:18"}
295
+ {"current_steps": 295, "total_steps": 300, "loss": 0.3815, "lr": 6.767366914927298e-08, "epoch": 4.916666666666667, "percentage": 98.33, "elapsed_time": "1:53:00", "remaining_time": "0:01:54"}
296
+ {"current_steps": 296, "total_steps": 300, "loss": 0.371, "lr": 4.331554645901737e-08, "epoch": 4.933333333333334, "percentage": 98.67, "elapsed_time": "1:53:15", "remaining_time": "0:01:31"}
297
+ {"current_steps": 297, "total_steps": 300, "loss": 0.3762, "lr": 2.4366919236169518e-08, "epoch": 4.95, "percentage": 99.0, "elapsed_time": "1:53:35", "remaining_time": "0:01:08"}
298
+ {"current_steps": 298, "total_steps": 300, "loss": 0.3786, "lr": 1.0830352821531442e-08, "epoch": 4.966666666666667, "percentage": 99.33, "elapsed_time": "1:53:51", "remaining_time": "0:00:45"}
299
+ {"current_steps": 299, "total_steps": 300, "loss": 0.3751, "lr": 2.7076798495118127e-09, "epoch": 4.983333333333333, "percentage": 99.67, "elapsed_time": "1:54:06", "remaining_time": "0:00:22"}
300
+ {"current_steps": 300, "total_steps": 300, "loss": 0.3712, "lr": 0.0, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:54:21", "remaining_time": "0:00:00"}
301
+ {"current_steps": 300, "total_steps": 300, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:55:33", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,2142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 300,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.016666666666666666,
13
+ "grad_norm": 5.245656972900781,
14
+ "learning_rate": 2.666666666666667e-06,
15
+ "loss": 0.8776,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.03333333333333333,
20
+ "grad_norm": 5.218891393087194,
21
+ "learning_rate": 5.333333333333334e-06,
22
+ "loss": 0.8699,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.05,
27
+ "grad_norm": 4.907833071621939,
28
+ "learning_rate": 8.000000000000001e-06,
29
+ "loss": 0.8757,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.06666666666666667,
34
+ "grad_norm": 2.26627933986632,
35
+ "learning_rate": 1.0666666666666667e-05,
36
+ "loss": 0.7787,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.08333333333333333,
41
+ "grad_norm": 2.9279695049055183,
42
+ "learning_rate": 1.3333333333333333e-05,
43
+ "loss": 0.761,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.1,
48
+ "grad_norm": 3.527749490226711,
49
+ "learning_rate": 1.6000000000000003e-05,
50
+ "loss": 0.7651,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.11666666666666667,
55
+ "grad_norm": 3.605889624479288,
56
+ "learning_rate": 1.866666666666667e-05,
57
+ "loss": 0.7356,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.13333333333333333,
62
+ "grad_norm": 2.3738801725418615,
63
+ "learning_rate": 2.1333333333333335e-05,
64
+ "loss": 0.6935,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.15,
69
+ "grad_norm": 2.274725710925249,
70
+ "learning_rate": 2.4e-05,
71
+ "loss": 0.6894,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.16666666666666666,
76
+ "grad_norm": 1.9493552307289557,
77
+ "learning_rate": 2.6666666666666667e-05,
78
+ "loss": 0.6534,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.18333333333333332,
83
+ "grad_norm": 1.4315069665868227,
84
+ "learning_rate": 2.9333333333333333e-05,
85
+ "loss": 0.6564,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.2,
90
+ "grad_norm": 1.5253504226991403,
91
+ "learning_rate": 3.2000000000000005e-05,
92
+ "loss": 0.637,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.21666666666666667,
97
+ "grad_norm": 1.0362270714290227,
98
+ "learning_rate": 3.466666666666667e-05,
99
+ "loss": 0.6096,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.23333333333333334,
104
+ "grad_norm": 1.0535753199910156,
105
+ "learning_rate": 3.733333333333334e-05,
106
+ "loss": 0.6146,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.25,
111
+ "grad_norm": 0.8349010003862102,
112
+ "learning_rate": 4e-05,
113
+ "loss": 0.5966,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.26666666666666666,
118
+ "grad_norm": 1.106306463757904,
119
+ "learning_rate": 4.266666666666667e-05,
120
+ "loss": 0.5894,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.2833333333333333,
125
+ "grad_norm": 1.6404444358554484,
126
+ "learning_rate": 4.5333333333333335e-05,
127
+ "loss": 0.5883,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.3,
132
+ "grad_norm": 1.2010935784418375,
133
+ "learning_rate": 4.8e-05,
134
+ "loss": 0.5857,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.31666666666666665,
139
+ "grad_norm": 1.2437856605381512,
140
+ "learning_rate": 5.066666666666667e-05,
141
+ "loss": 0.5799,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.3333333333333333,
146
+ "grad_norm": 1.1054886271753657,
147
+ "learning_rate": 5.333333333333333e-05,
148
+ "loss": 0.5833,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.35,
153
+ "grad_norm": 1.8467836888011633,
154
+ "learning_rate": 5.6e-05,
155
+ "loss": 0.5691,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.36666666666666664,
160
+ "grad_norm": 1.3123090569088927,
161
+ "learning_rate": 5.8666666666666665e-05,
162
+ "loss": 0.5801,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.38333333333333336,
167
+ "grad_norm": 1.9040924123333776,
168
+ "learning_rate": 6.133333333333334e-05,
169
+ "loss": 0.5703,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.4,
174
+ "grad_norm": 1.519433235348848,
175
+ "learning_rate": 6.400000000000001e-05,
176
+ "loss": 0.5597,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.4166666666666667,
181
+ "grad_norm": 1.9894575780267958,
182
+ "learning_rate": 6.666666666666667e-05,
183
+ "loss": 0.5603,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.43333333333333335,
188
+ "grad_norm": 1.692437490204837,
189
+ "learning_rate": 6.933333333333334e-05,
190
+ "loss": 0.5565,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.45,
195
+ "grad_norm": 1.590883494763927,
196
+ "learning_rate": 7.2e-05,
197
+ "loss": 0.5543,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.4666666666666667,
202
+ "grad_norm": 1.7224717553042976,
203
+ "learning_rate": 7.466666666666667e-05,
204
+ "loss": 0.5545,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.48333333333333334,
209
+ "grad_norm": 1.1992732138594948,
210
+ "learning_rate": 7.733333333333333e-05,
211
+ "loss": 0.5499,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.5,
216
+ "grad_norm": 1.5597591487390383,
217
+ "learning_rate": 8e-05,
218
+ "loss": 0.5466,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.5166666666666667,
223
+ "grad_norm": 13.235144568199255,
224
+ "learning_rate": 7.99972923201505e-05,
225
+ "loss": 0.5549,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.5333333333333333,
230
+ "grad_norm": 3.874062099184836,
231
+ "learning_rate": 7.998916964717848e-05,
232
+ "loss": 0.5886,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.55,
237
+ "grad_norm": 1.4820859850590011,
238
+ "learning_rate": 7.997563308076384e-05,
239
+ "loss": 0.5638,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.5666666666666667,
244
+ "grad_norm": 2.2378343082372383,
245
+ "learning_rate": 7.9956684453541e-05,
246
+ "loss": 0.5635,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.5833333333333334,
251
+ "grad_norm": 2.0542713302674125,
252
+ "learning_rate": 7.993232633085074e-05,
253
+ "loss": 0.5569,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.6,
258
+ "grad_norm": 1.3440983509202997,
259
+ "learning_rate": 7.990256201039297e-05,
260
+ "loss": 0.5466,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.6166666666666667,
265
+ "grad_norm": 1.95814978563299,
266
+ "learning_rate": 7.986739552178024e-05,
267
+ "loss": 0.5497,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.6333333333333333,
272
+ "grad_norm": 1.4390522422057623,
273
+ "learning_rate": 7.982683162599218e-05,
274
+ "loss": 0.5501,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.65,
279
+ "grad_norm": 1.236091120549879,
280
+ "learning_rate": 7.978087581473094e-05,
281
+ "loss": 0.5319,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.6666666666666666,
286
+ "grad_norm": 1.6696941417701605,
287
+ "learning_rate": 7.972953430967773e-05,
288
+ "loss": 0.529,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.6833333333333333,
293
+ "grad_norm": 1.1511510733974055,
294
+ "learning_rate": 7.967281406165047e-05,
295
+ "loss": 0.5341,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.7,
300
+ "grad_norm": 1.5109081225827479,
301
+ "learning_rate": 7.961072274966282e-05,
302
+ "loss": 0.5422,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.7166666666666667,
307
+ "grad_norm": 1.6183268194402816,
308
+ "learning_rate": 7.954326877988446e-05,
309
+ "loss": 0.5375,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.7333333333333333,
314
+ "grad_norm": 1.2434289553277165,
315
+ "learning_rate": 7.947046128450319e-05,
316
+ "loss": 0.5354,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.75,
321
+ "grad_norm": 2.449120981246454,
322
+ "learning_rate": 7.939231012048833e-05,
323
+ "loss": 0.5368,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.7666666666666667,
328
+ "grad_norm": 1.5991953169483721,
329
+ "learning_rate": 7.930882586825653e-05,
330
+ "loss": 0.5325,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.7833333333333333,
335
+ "grad_norm": 1.9062555539894481,
336
+ "learning_rate": 7.922001983023918e-05,
337
+ "loss": 0.5263,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.8,
342
+ "grad_norm": 1.108612799462749,
343
+ "learning_rate": 7.912590402935223e-05,
344
+ "loss": 0.5198,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.8166666666666667,
349
+ "grad_norm": 2.154405805332455,
350
+ "learning_rate": 7.902649120736858e-05,
351
+ "loss": 0.5271,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.8333333333333334,
356
+ "grad_norm": 1.6242552519251434,
357
+ "learning_rate": 7.892179482319297e-05,
358
+ "loss": 0.5306,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.85,
363
+ "grad_norm": 1.8581343300186228,
364
+ "learning_rate": 7.881182905103986e-05,
365
+ "loss": 0.5304,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.8666666666666667,
370
+ "grad_norm": 1.654252376154325,
371
+ "learning_rate": 7.869660877851456e-05,
372
+ "loss": 0.5303,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.8833333333333333,
377
+ "grad_norm": 18.002108491304732,
378
+ "learning_rate": 7.857614960459756e-05,
379
+ "loss": 0.5191,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.9,
384
+ "grad_norm": 3.6384293492152766,
385
+ "learning_rate": 7.845046783753276e-05,
386
+ "loss": 0.5527,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.9166666666666666,
391
+ "grad_norm": 2.619651938582199,
392
+ "learning_rate": 7.831958049261956e-05,
393
+ "loss": 0.5317,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.9333333333333333,
398
+ "grad_norm": 1.8069739421088107,
399
+ "learning_rate": 7.818350528990929e-05,
400
+ "loss": 0.5257,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.95,
405
+ "grad_norm": 2.095214243472687,
406
+ "learning_rate": 7.804226065180615e-05,
407
+ "loss": 0.5142,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.9666666666666667,
412
+ "grad_norm": 1.388139375514743,
413
+ "learning_rate": 7.789586570057317e-05,
414
+ "loss": 0.5224,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.9833333333333333,
419
+ "grad_norm": 1.5046369746206,
420
+ "learning_rate": 7.774434025574335e-05,
421
+ "loss": 0.52,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 1.0,
426
+ "grad_norm": 1.686276016808025,
427
+ "learning_rate": 7.758770483143634e-05,
428
+ "loss": 0.5222,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 1.0166666666666666,
433
+ "grad_norm": 0.7679065511895556,
434
+ "learning_rate": 7.742598063358127e-05,
435
+ "loss": 0.4969,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 1.0333333333333334,
440
+ "grad_norm": 1.6671453143503268,
441
+ "learning_rate": 7.72591895570457e-05,
442
+ "loss": 0.5029,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 1.05,
447
+ "grad_norm": 2.220579381452646,
448
+ "learning_rate": 7.70873541826715e-05,
449
+ "loss": 0.5371,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 1.0666666666666667,
454
+ "grad_norm": 4.570845075146369,
455
+ "learning_rate": 7.69104977742177e-05,
456
+ "loss": 0.6454,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 1.0833333333333333,
461
+ "grad_norm": 95.70037821653926,
462
+ "learning_rate": 7.672864427521097e-05,
463
+ "loss": 5.1073,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 1.1,
468
+ "grad_norm": 25.51120723470009,
469
+ "learning_rate": 7.654181830570404e-05,
470
+ "loss": 0.8472,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 1.1166666666666667,
475
+ "grad_norm": 4.160165799743227,
476
+ "learning_rate": 7.635004515894258e-05,
477
+ "loss": 0.599,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 1.1333333333333333,
482
+ "grad_norm": 23.550770127615383,
483
+ "learning_rate": 7.615335079794083e-05,
484
+ "loss": 0.5545,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 1.15,
489
+ "grad_norm": 6.573080981318929,
490
+ "learning_rate": 7.595176185196669e-05,
491
+ "loss": 0.5589,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 1.1666666666666667,
496
+ "grad_norm": 2.529666305514143,
497
+ "learning_rate": 7.57453056129365e-05,
498
+ "loss": 0.5536,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 1.1833333333333333,
503
+ "grad_norm": 1.5493207967736369,
504
+ "learning_rate": 7.553401003172018e-05,
505
+ "loss": 0.553,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 1.2,
510
+ "grad_norm": 1.5353410133791279,
511
+ "learning_rate": 7.531790371435709e-05,
512
+ "loss": 0.5278,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 1.2166666666666668,
517
+ "grad_norm": 1.080718986337614,
518
+ "learning_rate": 7.509701591818328e-05,
519
+ "loss": 0.5185,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 1.2333333333333334,
524
+ "grad_norm": 1.0926454805582764,
525
+ "learning_rate": 7.48713765478705e-05,
526
+ "loss": 0.5235,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 1.25,
531
+ "grad_norm": 1.6500275732342171,
532
+ "learning_rate": 7.464101615137756e-05,
533
+ "loss": 0.5273,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 1.2666666666666666,
538
+ "grad_norm": 0.6947273168033852,
539
+ "learning_rate": 7.440596591581463e-05,
540
+ "loss": 0.5096,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 1.2833333333333332,
545
+ "grad_norm": 1.1866376155740894,
546
+ "learning_rate": 7.416625766322104e-05,
547
+ "loss": 0.5113,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 1.3,
552
+ "grad_norm": 1.364003256949255,
553
+ "learning_rate": 7.392192384625704e-05,
554
+ "loss": 0.5002,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 1.3166666666666667,
559
+ "grad_norm": 0.7699646989586344,
560
+ "learning_rate": 7.36729975438103e-05,
561
+ "loss": 0.5056,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 1.3333333333333333,
566
+ "grad_norm": 0.9387918212619166,
567
+ "learning_rate": 7.341951245651747e-05,
568
+ "loss": 0.5052,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 1.35,
573
+ "grad_norm": 0.9794384927838236,
574
+ "learning_rate": 7.316150290220167e-05,
575
+ "loss": 0.4894,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 1.3666666666666667,
580
+ "grad_norm": 1.0473737374776888,
581
+ "learning_rate": 7.28990038112265e-05,
582
+ "loss": 0.4936,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 1.3833333333333333,
587
+ "grad_norm": 1.1742291915881278,
588
+ "learning_rate": 7.26320507217669e-05,
589
+ "loss": 0.505,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 1.4,
594
+ "grad_norm": 1.6225251259818336,
595
+ "learning_rate": 7.236067977499791e-05,
596
+ "loss": 0.4905,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 1.4166666666666667,
601
+ "grad_norm": 0.8410079622378729,
602
+ "learning_rate": 7.208492771020176e-05,
603
+ "loss": 0.5074,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 1.4333333333333333,
608
+ "grad_norm": 1.8512093181988574,
609
+ "learning_rate": 7.180483185979392e-05,
610
+ "loss": 0.503,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 1.45,
615
+ "grad_norm": 1.1798570273773599,
616
+ "learning_rate": 7.152043014426888e-05,
617
+ "loss": 0.4975,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 1.4666666666666668,
622
+ "grad_norm": 2.0044106173108847,
623
+ "learning_rate": 7.123176106706638e-05,
624
+ "loss": 0.4956,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 1.4833333333333334,
629
+ "grad_norm": 1.6187294121217053,
630
+ "learning_rate": 7.093886370935857e-05,
631
+ "loss": 0.5099,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 1.5,
636
+ "grad_norm": 1.3316813459007235,
637
+ "learning_rate": 7.064177772475912e-05,
638
+ "loss": 0.4821,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 1.5166666666666666,
643
+ "grad_norm": 1.3236329742991892,
644
+ "learning_rate": 7.034054333395477e-05,
645
+ "loss": 0.5009,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 1.5333333333333332,
650
+ "grad_norm": 1.2710355585646307,
651
+ "learning_rate": 7.003520131925997e-05,
652
+ "loss": 0.4933,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 1.55,
657
+ "grad_norm": 0.8906498668488716,
658
+ "learning_rate": 6.972579301909577e-05,
659
+ "loss": 0.4973,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 1.5666666666666667,
664
+ "grad_norm": 0.9758072573672575,
665
+ "learning_rate": 6.941236032239316e-05,
666
+ "loss": 0.4891,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 1.5833333333333335,
671
+ "grad_norm": 0.8325314640236163,
672
+ "learning_rate": 6.909494566292195e-05,
673
+ "loss": 0.4906,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 1.6,
678
+ "grad_norm": 0.6862846883116868,
679
+ "learning_rate": 6.877359201354606e-05,
680
+ "loss": 0.4708,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 1.6166666666666667,
685
+ "grad_norm": 0.8114306753381507,
686
+ "learning_rate": 6.844834288040548e-05,
687
+ "loss": 0.48,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 1.6333333333333333,
692
+ "grad_norm": 0.6802406870407687,
693
+ "learning_rate": 6.811924229702648e-05,
694
+ "loss": 0.4907,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 1.65,
699
+ "grad_norm": 0.7746572186775433,
700
+ "learning_rate": 6.778633481835989e-05,
701
+ "loss": 0.4792,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 1.6666666666666665,
706
+ "grad_norm": 0.596342711723325,
707
+ "learning_rate": 6.744966551474936e-05,
708
+ "loss": 0.4709,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 1.6833333333333333,
713
+ "grad_norm": 0.5786523069395214,
714
+ "learning_rate": 6.71092799658293e-05,
715
+ "loss": 0.4717,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 1.7,
720
+ "grad_norm": 0.578720133999103,
721
+ "learning_rate": 6.676522425435433e-05,
722
+ "loss": 0.4726,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 1.7166666666666668,
727
+ "grad_norm": 0.619421135446994,
728
+ "learning_rate": 6.641754495996031e-05,
729
+ "loss": 0.4732,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 1.7333333333333334,
734
+ "grad_norm": 0.5320320618804577,
735
+ "learning_rate": 6.606628915285822e-05,
736
+ "loss": 0.475,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 1.75,
741
+ "grad_norm": 0.5935909070239521,
742
+ "learning_rate": 6.571150438746157e-05,
743
+ "loss": 0.476,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 1.7666666666666666,
748
+ "grad_norm": 0.7225146247808617,
749
+ "learning_rate": 6.53532386959484e-05,
750
+ "loss": 0.4804,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 1.7833333333333332,
755
+ "grad_norm": 0.8099377428335527,
756
+ "learning_rate": 6.499154058175841e-05,
757
+ "loss": 0.4801,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 1.8,
762
+ "grad_norm": 0.9381139587591945,
763
+ "learning_rate": 6.462645901302633e-05,
764
+ "loss": 0.4695,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 1.8166666666666667,
769
+ "grad_norm": 1.280364541057433,
770
+ "learning_rate": 6.425804341595255e-05,
771
+ "loss": 0.474,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 1.8333333333333335,
776
+ "grad_norm": 0.7258487421487859,
777
+ "learning_rate": 6.388634366811146e-05,
778
+ "loss": 0.4753,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 1.85,
783
+ "grad_norm": 0.4381708977671278,
784
+ "learning_rate": 6.351141009169893e-05,
785
+ "loss": 0.4801,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 1.8666666666666667,
790
+ "grad_norm": 0.6827208700360275,
791
+ "learning_rate": 6.313329344671946e-05,
792
+ "loss": 0.4671,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 1.8833333333333333,
797
+ "grad_norm": 1.122933541517188,
798
+ "learning_rate": 6.275204492411408e-05,
799
+ "loss": 0.4742,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 1.9,
804
+ "grad_norm": 0.8764710794281773,
805
+ "learning_rate": 6.236771613882987e-05,
806
+ "loss": 0.4669,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 1.9166666666666665,
811
+ "grad_norm": 0.6477607688780823,
812
+ "learning_rate": 6.198035912283225e-05,
813
+ "loss": 0.4704,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 1.9333333333333333,
818
+ "grad_norm": 0.5534687080744243,
819
+ "learning_rate": 6.159002631806052e-05,
820
+ "loss": 0.4624,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 1.95,
825
+ "grad_norm": 0.45096824695667637,
826
+ "learning_rate": 6.11967705693282e-05,
827
+ "loss": 0.4602,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 1.9666666666666668,
832
+ "grad_norm": 0.554357902331042,
833
+ "learning_rate": 6.0800645117168616e-05,
834
+ "loss": 0.4684,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 1.9833333333333334,
839
+ "grad_norm": 0.5221484514841085,
840
+ "learning_rate": 6.040170359062702e-05,
841
+ "loss": 0.4683,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 2.0,
846
+ "grad_norm": 0.5704263223686744,
847
+ "learning_rate": 6.000000000000001e-05,
848
+ "loss": 0.4461,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 2.0166666666666666,
853
+ "grad_norm": 0.5709278974682745,
854
+ "learning_rate": 5.959558872952349e-05,
855
+ "loss": 0.4438,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 2.033333333333333,
860
+ "grad_norm": 0.5801282027560986,
861
+ "learning_rate": 5.918852453000986e-05,
862
+ "loss": 0.4412,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 2.05,
867
+ "grad_norm": 0.6959111187765339,
868
+ "learning_rate": 5.877886251143564e-05,
869
+ "loss": 0.4383,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 2.066666666666667,
874
+ "grad_norm": 0.6383137765035167,
875
+ "learning_rate": 5.836665813548047e-05,
876
+ "loss": 0.439,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 2.0833333333333335,
881
+ "grad_norm": 0.6979472630547436,
882
+ "learning_rate": 5.79519672080185e-05,
883
+ "loss": 0.4404,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 2.1,
888
+ "grad_norm": 0.8032609331074188,
889
+ "learning_rate": 5.75348458715631e-05,
890
+ "loss": 0.4446,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 2.1166666666666667,
895
+ "grad_norm": 0.8008578170362761,
896
+ "learning_rate": 5.711535059766617e-05,
897
+ "loss": 0.4328,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 2.1333333333333333,
902
+ "grad_norm": 0.7544509359404,
903
+ "learning_rate": 5.669353817927272e-05,
904
+ "loss": 0.4332,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 2.15,
909
+ "grad_norm": 0.5277962998797086,
910
+ "learning_rate": 5.626946572303202e-05,
911
+ "loss": 0.4439,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 2.1666666666666665,
916
+ "grad_norm": 0.48832916475247207,
917
+ "learning_rate": 5.584319064156628e-05,
918
+ "loss": 0.4363,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 2.183333333333333,
923
+ "grad_norm": 0.3193641330679638,
924
+ "learning_rate": 5.541477064569794e-05,
925
+ "loss": 0.437,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 2.2,
930
+ "grad_norm": 0.43285764791873127,
931
+ "learning_rate": 5.4984263736636494e-05,
932
+ "loss": 0.4396,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 2.216666666666667,
937
+ "grad_norm": 0.506381220210278,
938
+ "learning_rate": 5.4551728198126066e-05,
939
+ "loss": 0.441,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 2.2333333333333334,
944
+ "grad_norm": 0.497473946767306,
945
+ "learning_rate": 5.4117222588554756e-05,
946
+ "loss": 0.4356,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 2.25,
951
+ "grad_norm": 0.3626547796740017,
952
+ "learning_rate": 5.368080573302676e-05,
953
+ "loss": 0.4483,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 2.2666666666666666,
958
+ "grad_norm": 0.4460556149358041,
959
+ "learning_rate": 5.324253671539833e-05,
960
+ "loss": 0.4315,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 2.283333333333333,
965
+ "grad_norm": 0.35392468089641915,
966
+ "learning_rate": 5.280247487027886e-05,
967
+ "loss": 0.4324,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 2.3,
972
+ "grad_norm": 0.477174161688509,
973
+ "learning_rate": 5.23606797749979e-05,
974
+ "loss": 0.4369,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 2.3166666666666664,
979
+ "grad_norm": 0.4332074029655615,
980
+ "learning_rate": 5.191721124153928e-05,
981
+ "loss": 0.4384,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 2.3333333333333335,
986
+ "grad_norm": 0.359337416622667,
987
+ "learning_rate": 5.1472129308443616e-05,
988
+ "loss": 0.4323,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 2.35,
993
+ "grad_norm": 0.45751469741830436,
994
+ "learning_rate": 5.102549423267997e-05,
995
+ "loss": 0.4413,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 2.3666666666666667,
1000
+ "grad_norm": 0.36273885092681685,
1001
+ "learning_rate": 5.05773664814881e-05,
1002
+ "loss": 0.4372,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 2.3833333333333333,
1007
+ "grad_norm": 0.43840182150058027,
1008
+ "learning_rate": 5.012780672419208e-05,
1009
+ "loss": 0.4389,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 2.4,
1014
+ "grad_norm": 0.5814229277766988,
1015
+ "learning_rate": 4.967687582398671e-05,
1016
+ "loss": 0.4366,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 2.4166666666666665,
1021
+ "grad_norm": 0.4648544861511475,
1022
+ "learning_rate": 4.922463482969761e-05,
1023
+ "loss": 0.4244,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 2.4333333333333336,
1028
+ "grad_norm": 0.43277324284253266,
1029
+ "learning_rate": 4.877114496751613e-05,
1030
+ "loss": 0.4263,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 2.45,
1035
+ "grad_norm": 0.3445487784949258,
1036
+ "learning_rate": 4.831646763271037e-05,
1037
+ "loss": 0.4259,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 2.466666666666667,
1042
+ "grad_norm": 0.249493804872003,
1043
+ "learning_rate": 4.786066438131321e-05,
1044
+ "loss": 0.4303,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 2.4833333333333334,
1049
+ "grad_norm": 0.35648001360715187,
1050
+ "learning_rate": 4.740379692178858e-05,
1051
+ "loss": 0.4371,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 2.5,
1056
+ "grad_norm": 0.35764410624086523,
1057
+ "learning_rate": 4.694592710667723e-05,
1058
+ "loss": 0.4363,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 2.5166666666666666,
1063
+ "grad_norm": 0.32197356996135706,
1064
+ "learning_rate": 4.648711692422271e-05,
1065
+ "loss": 0.4284,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 2.533333333333333,
1070
+ "grad_norm": 0.26813902456960564,
1071
+ "learning_rate": 4.602742848997933e-05,
1072
+ "loss": 0.4268,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 2.55,
1077
+ "grad_norm": 0.3152449367621475,
1078
+ "learning_rate": 4.556692403840262e-05,
1079
+ "loss": 0.4361,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 2.5666666666666664,
1084
+ "grad_norm": 0.3044173540598896,
1085
+ "learning_rate": 4.51056659144238e-05,
1086
+ "loss": 0.4369,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 2.5833333333333335,
1091
+ "grad_norm": 0.34156608545292216,
1092
+ "learning_rate": 4.464371656500921e-05,
1093
+ "loss": 0.4288,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 2.6,
1098
+ "grad_norm": 0.23359937356488897,
1099
+ "learning_rate": 4.418113853070614e-05,
1100
+ "loss": 0.4284,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 2.6166666666666667,
1105
+ "grad_norm": 0.2622225256652441,
1106
+ "learning_rate": 4.37179944371757e-05,
1107
+ "loss": 0.4301,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 2.6333333333333333,
1112
+ "grad_norm": 0.2666586570230336,
1113
+ "learning_rate": 4.3254346986714334e-05,
1114
+ "loss": 0.4309,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 2.65,
1119
+ "grad_norm": 0.22512452157668708,
1120
+ "learning_rate": 4.2790258949765014e-05,
1121
+ "loss": 0.4383,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 2.6666666666666665,
1126
+ "grad_norm": 0.22395685196851006,
1127
+ "learning_rate": 4.2325793156419035e-05,
1128
+ "loss": 0.4302,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 2.6833333333333336,
1133
+ "grad_norm": 0.2631712834526137,
1134
+ "learning_rate": 4.186101248790988e-05,
1135
+ "loss": 0.4274,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 2.7,
1140
+ "grad_norm": 0.18137357765826834,
1141
+ "learning_rate": 4.139597986810005e-05,
1142
+ "loss": 0.4283,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 2.716666666666667,
1147
+ "grad_norm": 0.2152319656904045,
1148
+ "learning_rate": 4.093075825496225e-05,
1149
+ "loss": 0.4262,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 2.7333333333333334,
1154
+ "grad_norm": 0.23695720587637784,
1155
+ "learning_rate": 4.046541063205589e-05,
1156
+ "loss": 0.4267,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 2.75,
1161
+ "grad_norm": 0.18535759709420013,
1162
+ "learning_rate": 4e-05,
1163
+ "loss": 0.431,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 2.7666666666666666,
1168
+ "grad_norm": 0.19512911640325292,
1169
+ "learning_rate": 3.953458936794413e-05,
1170
+ "loss": 0.4302,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 2.783333333333333,
1175
+ "grad_norm": 0.24096730339995487,
1176
+ "learning_rate": 3.9069241745037753e-05,
1177
+ "loss": 0.4243,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 2.8,
1182
+ "grad_norm": 0.252078037604114,
1183
+ "learning_rate": 3.860402013189998e-05,
1184
+ "loss": 0.4282,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 2.8166666666666664,
1189
+ "grad_norm": 0.1924034465875299,
1190
+ "learning_rate": 3.813898751209013e-05,
1191
+ "loss": 0.4267,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 2.8333333333333335,
1196
+ "grad_norm": 0.23563515928261294,
1197
+ "learning_rate": 3.767420684358097e-05,
1198
+ "loss": 0.4376,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 2.85,
1203
+ "grad_norm": 0.1634490186417809,
1204
+ "learning_rate": 3.720974105023499e-05,
1205
+ "loss": 0.4331,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 2.8666666666666667,
1210
+ "grad_norm": 0.18183833282724582,
1211
+ "learning_rate": 3.674565301328568e-05,
1212
+ "loss": 0.4255,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 2.8833333333333333,
1217
+ "grad_norm": 0.1732573714191111,
1218
+ "learning_rate": 3.628200556282432e-05,
1219
+ "loss": 0.4242,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 2.9,
1224
+ "grad_norm": 0.17815235424744558,
1225
+ "learning_rate": 3.581886146929387e-05,
1226
+ "loss": 0.4329,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 2.9166666666666665,
1231
+ "grad_norm": 0.22481501284187758,
1232
+ "learning_rate": 3.535628343499079e-05,
1233
+ "loss": 0.4338,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 2.9333333333333336,
1238
+ "grad_norm": 0.1800561213440347,
1239
+ "learning_rate": 3.4894334085576215e-05,
1240
+ "loss": 0.4228,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 2.95,
1245
+ "grad_norm": 0.19746447907155162,
1246
+ "learning_rate": 3.44330759615974e-05,
1247
+ "loss": 0.4352,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 2.966666666666667,
1252
+ "grad_norm": 0.18920195029733491,
1253
+ "learning_rate": 3.397257151002068e-05,
1254
+ "loss": 0.4293,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 2.9833333333333334,
1259
+ "grad_norm": 0.2323628846730535,
1260
+ "learning_rate": 3.351288307577731e-05,
1261
+ "loss": 0.4359,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 3.0,
1266
+ "grad_norm": 0.21748900457524406,
1267
+ "learning_rate": 3.305407289332279e-05,
1268
+ "loss": 0.4174,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 3.0166666666666666,
1273
+ "grad_norm": 0.271621511298459,
1274
+ "learning_rate": 3.2596203078211424e-05,
1275
+ "loss": 0.4078,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 3.033333333333333,
1280
+ "grad_norm": 0.2012008013431602,
1281
+ "learning_rate": 3.213933561868679e-05,
1282
+ "loss": 0.3961,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 3.05,
1287
+ "grad_norm": 0.3220604765409426,
1288
+ "learning_rate": 3.168353236728964e-05,
1289
+ "loss": 0.4045,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 3.066666666666667,
1294
+ "grad_norm": 0.19572819773614739,
1295
+ "learning_rate": 3.122885503248386e-05,
1296
+ "loss": 0.3961,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 3.0833333333333335,
1301
+ "grad_norm": 0.33244677864095823,
1302
+ "learning_rate": 3.07753651703024e-05,
1303
+ "loss": 0.3928,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 3.1,
1308
+ "grad_norm": 0.24724515409460784,
1309
+ "learning_rate": 3.0323124176013297e-05,
1310
+ "loss": 0.3967,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 3.1166666666666667,
1315
+ "grad_norm": 0.296372671702842,
1316
+ "learning_rate": 2.9872193275807933e-05,
1317
+ "loss": 0.3934,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 3.1333333333333333,
1322
+ "grad_norm": 0.23480346232564567,
1323
+ "learning_rate": 2.9422633518511926e-05,
1324
+ "loss": 0.3999,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 3.15,
1329
+ "grad_norm": 0.2299020315400507,
1330
+ "learning_rate": 2.8974505767320037e-05,
1331
+ "loss": 0.3957,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 3.1666666666666665,
1336
+ "grad_norm": 0.20438922063246678,
1337
+ "learning_rate": 2.8527870691556404e-05,
1338
+ "loss": 0.3909,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 3.183333333333333,
1343
+ "grad_norm": 0.23024242910435916,
1344
+ "learning_rate": 2.808278875846072e-05,
1345
+ "loss": 0.3979,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 3.2,
1350
+ "grad_norm": 0.19952835302247546,
1351
+ "learning_rate": 2.7639320225002108e-05,
1352
+ "loss": 0.3878,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 3.216666666666667,
1357
+ "grad_norm": 0.2433848525247375,
1358
+ "learning_rate": 2.7197525129721138e-05,
1359
+ "loss": 0.4054,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 3.2333333333333334,
1364
+ "grad_norm": 0.18781862787549544,
1365
+ "learning_rate": 2.6757463284601682e-05,
1366
+ "loss": 0.4018,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 3.25,
1371
+ "grad_norm": 0.24582760836055703,
1372
+ "learning_rate": 2.6319194266973256e-05,
1373
+ "loss": 0.4003,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 3.2666666666666666,
1378
+ "grad_norm": 0.1952833254189799,
1379
+ "learning_rate": 2.5882777411445254e-05,
1380
+ "loss": 0.3976,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 3.283333333333333,
1385
+ "grad_norm": 0.24107320758003553,
1386
+ "learning_rate": 2.5448271801873957e-05,
1387
+ "loss": 0.3894,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 3.3,
1392
+ "grad_norm": 0.20156597827284783,
1393
+ "learning_rate": 2.501573626336352e-05,
1394
+ "loss": 0.3937,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 3.3166666666666664,
1399
+ "grad_norm": 0.19144637276173257,
1400
+ "learning_rate": 2.4585229354302077e-05,
1401
+ "loss": 0.4047,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 3.3333333333333335,
1406
+ "grad_norm": 0.19465848820341938,
1407
+ "learning_rate": 2.4156809358433728e-05,
1408
+ "loss": 0.3926,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 3.35,
1413
+ "grad_norm": 0.17941943926005774,
1414
+ "learning_rate": 2.3730534276968e-05,
1415
+ "loss": 0.3996,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 3.3666666666666667,
1420
+ "grad_norm": 0.16877944368715106,
1421
+ "learning_rate": 2.330646182072729e-05,
1422
+ "loss": 0.3988,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 3.3833333333333333,
1427
+ "grad_norm": 0.15853651420700432,
1428
+ "learning_rate": 2.288464940233384e-05,
1429
+ "loss": 0.3969,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 3.4,
1434
+ "grad_norm": 0.17704756414138859,
1435
+ "learning_rate": 2.24651541284369e-05,
1436
+ "loss": 0.3965,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 3.4166666666666665,
1441
+ "grad_norm": 0.16488014130826012,
1442
+ "learning_rate": 2.2048032791981515e-05,
1443
+ "loss": 0.3975,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 3.4333333333333336,
1448
+ "grad_norm": 0.16892937284191595,
1449
+ "learning_rate": 2.1633341864519526e-05,
1450
+ "loss": 0.3867,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 3.45,
1455
+ "grad_norm": 0.1358343960156378,
1456
+ "learning_rate": 2.122113748856438e-05,
1457
+ "loss": 0.393,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 3.466666666666667,
1462
+ "grad_norm": 0.1504422610938134,
1463
+ "learning_rate": 2.0811475469990167e-05,
1464
+ "loss": 0.4008,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 3.4833333333333334,
1469
+ "grad_norm": 0.13351109545536258,
1470
+ "learning_rate": 2.0404411270476527e-05,
1471
+ "loss": 0.3992,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 3.5,
1476
+ "grad_norm": 0.14061486072290816,
1477
+ "learning_rate": 2.0000000000000012e-05,
1478
+ "loss": 0.3951,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 3.5166666666666666,
1483
+ "grad_norm": 0.13436586012369262,
1484
+ "learning_rate": 1.959829640937299e-05,
1485
+ "loss": 0.3976,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 3.533333333333333,
1490
+ "grad_norm": 0.14060275789158602,
1491
+ "learning_rate": 1.9199354882831387e-05,
1492
+ "loss": 0.3967,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 3.55,
1497
+ "grad_norm": 0.1342180419460769,
1498
+ "learning_rate": 1.880322943067181e-05,
1499
+ "loss": 0.3957,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 3.5666666666666664,
1504
+ "grad_norm": 0.1565449126623076,
1505
+ "learning_rate": 1.8409973681939498e-05,
1506
+ "loss": 0.3938,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 3.5833333333333335,
1511
+ "grad_norm": 0.13732136525737537,
1512
+ "learning_rate": 1.8019640877167763e-05,
1513
+ "loss": 0.4015,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 3.6,
1518
+ "grad_norm": 0.1528036709245904,
1519
+ "learning_rate": 1.7632283861170135e-05,
1520
+ "loss": 0.398,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 3.6166666666666667,
1525
+ "grad_norm": 0.1381840793587635,
1526
+ "learning_rate": 1.7247955075885938e-05,
1527
+ "loss": 0.3984,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 3.6333333333333333,
1532
+ "grad_norm": 0.1396644742501586,
1533
+ "learning_rate": 1.686670655328054e-05,
1534
+ "loss": 0.4015,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 3.65,
1539
+ "grad_norm": 0.13192549802922138,
1540
+ "learning_rate": 1.648858990830108e-05,
1541
+ "loss": 0.3966,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 3.6666666666666665,
1546
+ "grad_norm": 0.16349750723173231,
1547
+ "learning_rate": 1.6113656331888563e-05,
1548
+ "loss": 0.3945,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 3.6833333333333336,
1553
+ "grad_norm": 0.13224488929146622,
1554
+ "learning_rate": 1.5741956584047478e-05,
1555
+ "loss": 0.3958,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 3.7,
1560
+ "grad_norm": 0.12993749122903758,
1561
+ "learning_rate": 1.537354098697367e-05,
1562
+ "loss": 0.4005,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 3.716666666666667,
1567
+ "grad_norm": 0.14331709716651275,
1568
+ "learning_rate": 1.5008459418241601e-05,
1569
+ "loss": 0.3961,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 3.7333333333333334,
1574
+ "grad_norm": 0.12912698549430687,
1575
+ "learning_rate": 1.4646761304051587e-05,
1576
+ "loss": 0.3973,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 3.75,
1581
+ "grad_norm": 0.10960674321997634,
1582
+ "learning_rate": 1.4288495612538427e-05,
1583
+ "loss": 0.3929,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 3.7666666666666666,
1588
+ "grad_norm": 0.14116340307643566,
1589
+ "learning_rate": 1.3933710847141795e-05,
1590
+ "loss": 0.4019,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 3.783333333333333,
1595
+ "grad_norm": 0.12835976733909077,
1596
+ "learning_rate": 1.3582455040039699e-05,
1597
+ "loss": 0.392,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 3.8,
1602
+ "grad_norm": 0.128669245437869,
1603
+ "learning_rate": 1.3234775745645684e-05,
1604
+ "loss": 0.3891,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 3.8166666666666664,
1609
+ "grad_norm": 0.12765896916982683,
1610
+ "learning_rate": 1.2890720034170712e-05,
1611
+ "loss": 0.3885,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 3.8333333333333335,
1616
+ "grad_norm": 0.11261573225899339,
1617
+ "learning_rate": 1.2550334485250661e-05,
1618
+ "loss": 0.3918,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 3.85,
1623
+ "grad_norm": 0.14800903395041998,
1624
+ "learning_rate": 1.2213665181640106e-05,
1625
+ "loss": 0.394,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 3.8666666666666667,
1630
+ "grad_norm": 0.12264985697670748,
1631
+ "learning_rate": 1.1880757702973531e-05,
1632
+ "loss": 0.3913,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 3.8833333333333333,
1637
+ "grad_norm": 0.11956086317480628,
1638
+ "learning_rate": 1.1551657119594517e-05,
1639
+ "loss": 0.3972,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 3.9,
1644
+ "grad_norm": 0.12216008583272517,
1645
+ "learning_rate": 1.1226407986453963e-05,
1646
+ "loss": 0.3952,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 3.9166666666666665,
1651
+ "grad_norm": 0.10807206577145119,
1652
+ "learning_rate": 1.0905054337078051e-05,
1653
+ "loss": 0.396,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 3.9333333333333336,
1658
+ "grad_norm": 0.13607781438092512,
1659
+ "learning_rate": 1.0587639677606857e-05,
1660
+ "loss": 0.3997,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 3.95,
1665
+ "grad_norm": 0.12355453197057942,
1666
+ "learning_rate": 1.0274206980904226e-05,
1667
+ "loss": 0.3938,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 3.966666666666667,
1672
+ "grad_norm": 0.10359625686756976,
1673
+ "learning_rate": 9.964798680740033e-06,
1674
+ "loss": 0.3943,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 3.9833333333333334,
1679
+ "grad_norm": 0.10965361681764693,
1680
+ "learning_rate": 9.659456666045247e-06,
1681
+ "loss": 0.4011,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 4.0,
1686
+ "grad_norm": 0.13451240932118808,
1687
+ "learning_rate": 9.358222275240884e-06,
1688
+ "loss": 0.3842,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 4.016666666666667,
1693
+ "grad_norm": 0.16087635109826715,
1694
+ "learning_rate": 9.061136290641448e-06,
1695
+ "loss": 0.3761,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 4.033333333333333,
1700
+ "grad_norm": 0.1188504453770387,
1701
+ "learning_rate": 8.768238932933632e-06,
1702
+ "loss": 0.3796,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 4.05,
1707
+ "grad_norm": 0.11640131602293756,
1708
+ "learning_rate": 8.479569855731125e-06,
1709
+ "loss": 0.3792,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 4.066666666666666,
1714
+ "grad_norm": 0.1302923728977513,
1715
+ "learning_rate": 8.195168140206084e-06,
1716
+ "loss": 0.3702,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 4.083333333333333,
1721
+ "grad_norm": 0.13392917273999477,
1722
+ "learning_rate": 7.915072289798247e-06,
1723
+ "loss": 0.3648,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 4.1,
1728
+ "grad_norm": 0.12543716532845192,
1729
+ "learning_rate": 7.639320225002106e-06,
1730
+ "loss": 0.3873,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 4.116666666666666,
1735
+ "grad_norm": 0.127937227499042,
1736
+ "learning_rate": 7.367949278233126e-06,
1737
+ "loss": 0.3802,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 4.133333333333334,
1742
+ "grad_norm": 0.13964406384103364,
1743
+ "learning_rate": 7.1009961887735075e-06,
1744
+ "loss": 0.3812,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 4.15,
1749
+ "grad_norm": 0.11564360422872587,
1750
+ "learning_rate": 6.838497097798336e-06,
1751
+ "loss": 0.3763,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 4.166666666666667,
1756
+ "grad_norm": 0.10780983998780042,
1757
+ "learning_rate": 6.58048754348255e-06,
1758
+ "loss": 0.3754,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 4.183333333333334,
1763
+ "grad_norm": 0.11962978216910981,
1764
+ "learning_rate": 6.327002456189699e-06,
1765
+ "loss": 0.3706,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 4.2,
1770
+ "grad_norm": 0.12362296757916746,
1771
+ "learning_rate": 6.078076153742962e-06,
1772
+ "loss": 0.3788,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 4.216666666666667,
1777
+ "grad_norm": 0.11060827729490633,
1778
+ "learning_rate": 5.833742336778981e-06,
1779
+ "loss": 0.372,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 4.233333333333333,
1784
+ "grad_norm": 0.11095254927254816,
1785
+ "learning_rate": 5.5940340841853915e-06,
1786
+ "loss": 0.3683,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 4.25,
1791
+ "grad_norm": 0.10221255870180875,
1792
+ "learning_rate": 5.358983848622452e-06,
1793
+ "loss": 0.3806,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 4.266666666666667,
1798
+ "grad_norm": 0.10403266613885799,
1799
+ "learning_rate": 5.128623452129508e-06,
1800
+ "loss": 0.3713,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 4.283333333333333,
1805
+ "grad_norm": 0.11572955395038909,
1806
+ "learning_rate": 4.902984081816717e-06,
1807
+ "loss": 0.3766,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 4.3,
1812
+ "grad_norm": 0.15003311835231536,
1813
+ "learning_rate": 4.6820962856429205e-06,
1814
+ "loss": 0.3782,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 4.316666666666666,
1819
+ "grad_norm": 0.09897498567539731,
1820
+ "learning_rate": 4.4659899682798446e-06,
1821
+ "loss": 0.3802,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 4.333333333333333,
1826
+ "grad_norm": 0.09161651892999853,
1827
+ "learning_rate": 4.254694387063514e-06,
1828
+ "loss": 0.3768,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 4.35,
1833
+ "grad_norm": 0.10695851145081539,
1834
+ "learning_rate": 4.048238148033328e-06,
1835
+ "loss": 0.3734,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 4.366666666666666,
1840
+ "grad_norm": 0.11485862198811234,
1841
+ "learning_rate": 3.846649202059181e-06,
1842
+ "loss": 0.3837,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 4.383333333333334,
1847
+ "grad_norm": 0.09894255205848254,
1848
+ "learning_rate": 3.6499548410574303e-06,
1849
+ "loss": 0.3692,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 4.4,
1854
+ "grad_norm": 0.08599887026696498,
1855
+ "learning_rate": 3.458181694295961e-06,
1856
+ "loss": 0.3677,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 4.416666666666667,
1861
+ "grad_norm": 0.08698967028762236,
1862
+ "learning_rate": 3.2713557247890447e-06,
1863
+ "loss": 0.3855,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 4.433333333333334,
1868
+ "grad_norm": 0.09235513297244223,
1869
+ "learning_rate": 3.0895022257823083e-06,
1870
+ "loss": 0.372,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 4.45,
1875
+ "grad_norm": 0.10445911123787113,
1876
+ "learning_rate": 2.9126458173285077e-06,
1877
+ "loss": 0.381,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 4.466666666666667,
1882
+ "grad_norm": 0.10221496852931042,
1883
+ "learning_rate": 2.7408104429543025e-06,
1884
+ "loss": 0.3809,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 4.483333333333333,
1889
+ "grad_norm": 0.08587879304844272,
1890
+ "learning_rate": 2.574019366418745e-06,
1891
+ "loss": 0.3751,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 4.5,
1896
+ "grad_norm": 0.09015126611361238,
1897
+ "learning_rate": 2.4122951685636674e-06,
1898
+ "loss": 0.3838,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 4.516666666666667,
1903
+ "grad_norm": 0.08784996132113758,
1904
+ "learning_rate": 2.25565974425666e-06,
1905
+ "loss": 0.3676,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 4.533333333333333,
1910
+ "grad_norm": 0.0847147467848922,
1911
+ "learning_rate": 2.104134299426832e-06,
1912
+ "loss": 0.3761,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 4.55,
1917
+ "grad_norm": 0.08776259867732322,
1918
+ "learning_rate": 1.957739348193859e-06,
1919
+ "loss": 0.3686,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 4.566666666666666,
1924
+ "grad_norm": 0.08534997975862194,
1925
+ "learning_rate": 1.8164947100907238e-06,
1926
+ "loss": 0.3757,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 4.583333333333333,
1931
+ "grad_norm": 0.0837806982293435,
1932
+ "learning_rate": 1.6804195073804442e-06,
1933
+ "loss": 0.3739,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 4.6,
1938
+ "grad_norm": 0.08381875882285177,
1939
+ "learning_rate": 1.5495321624672443e-06,
1940
+ "loss": 0.3797,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 4.616666666666667,
1945
+ "grad_norm": 0.08120595617712789,
1946
+ "learning_rate": 1.423850395402444e-06,
1947
+ "loss": 0.3718,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 4.633333333333333,
1952
+ "grad_norm": 0.08481195207669447,
1953
+ "learning_rate": 1.3033912214854482e-06,
1954
+ "loss": 0.3827,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 4.65,
1959
+ "grad_norm": 0.08655723787141399,
1960
+ "learning_rate": 1.1881709489601413e-06,
1961
+ "loss": 0.3693,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 4.666666666666667,
1966
+ "grad_norm": 0.07892331394338291,
1967
+ "learning_rate": 1.0782051768070477e-06,
1968
+ "loss": 0.3772,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 4.683333333333334,
1973
+ "grad_norm": 0.08341083482611329,
1974
+ "learning_rate": 9.735087926314324e-07,
1975
+ "loss": 0.3783,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 4.7,
1980
+ "grad_norm": 0.07896510956111198,
1981
+ "learning_rate": 8.740959706477725e-07,
1982
+ "loss": 0.3749,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 4.716666666666667,
1987
+ "grad_norm": 0.08336166448673067,
1988
+ "learning_rate": 7.799801697608278e-07,
1989
+ "loss": 0.381,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 4.733333333333333,
1994
+ "grad_norm": 0.08046079736125109,
1995
+ "learning_rate": 6.911741317434706e-07,
1996
+ "loss": 0.3718,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 4.75,
2001
+ "grad_norm": 0.09024599509642792,
2002
+ "learning_rate": 6.076898795116792e-07,
2003
+ "loss": 0.382,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 4.766666666666667,
2008
+ "grad_norm": 0.08331916982861774,
2009
+ "learning_rate": 5.295387154968312e-07,
2010
+ "loss": 0.3715,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 4.783333333333333,
2015
+ "grad_norm": 0.07901763344169457,
2016
+ "learning_rate": 4.5673122011553605e-07,
2017
+ "loss": 0.3763,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 4.8,
2022
+ "grad_norm": 0.08022410821945614,
2023
+ "learning_rate": 3.8927725033718553e-07,
2024
+ "loss": 0.3808,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 4.816666666666666,
2029
+ "grad_norm": 0.07742599988645317,
2030
+ "learning_rate": 3.2718593834953237e-07,
2031
+ "loss": 0.3806,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 4.833333333333333,
2036
+ "grad_norm": 0.07882803655503354,
2037
+ "learning_rate": 2.704656903222791e-07,
2038
+ "loss": 0.3728,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 4.85,
2043
+ "grad_norm": 0.07729395855995894,
2044
+ "learning_rate": 2.1912418526906841e-07,
2045
+ "loss": 0.3833,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 4.866666666666667,
2050
+ "grad_norm": 0.07951048749391536,
2051
+ "learning_rate": 1.7316837400782604e-07,
2052
+ "loss": 0.3715,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 4.883333333333333,
2057
+ "grad_norm": 0.0760323522910653,
2058
+ "learning_rate": 1.3260447821975775e-07,
2059
+ "loss": 0.3786,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 4.9,
2064
+ "grad_norm": 0.07785411151535049,
2065
+ "learning_rate": 9.74379896070321e-08,
2066
+ "loss": 0.3741,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 4.916666666666667,
2071
+ "grad_norm": 0.07811264825931089,
2072
+ "learning_rate": 6.767366914927298e-08,
2073
+ "loss": 0.3815,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 4.933333333333334,
2078
+ "grad_norm": 0.07524369659461613,
2079
+ "learning_rate": 4.331554645901737e-08,
2080
+ "loss": 0.371,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 4.95,
2085
+ "grad_norm": 0.07719894809649144,
2086
+ "learning_rate": 2.4366919236169518e-08,
2087
+ "loss": 0.3762,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 4.966666666666667,
2092
+ "grad_norm": 0.07886340732100874,
2093
+ "learning_rate": 1.0830352821531442e-08,
2094
+ "loss": 0.3786,
2095
+ "step": 298
2096
+ },
2097
+ {
2098
+ "epoch": 4.983333333333333,
2099
+ "grad_norm": 0.07836420034802934,
2100
+ "learning_rate": 2.7076798495118127e-09,
2101
+ "loss": 0.3751,
2102
+ "step": 299
2103
+ },
2104
+ {
2105
+ "epoch": 5.0,
2106
+ "grad_norm": 0.08008746421389691,
2107
+ "learning_rate": 0.0,
2108
+ "loss": 0.3712,
2109
+ "step": 300
2110
+ },
2111
+ {
2112
+ "epoch": 5.0,
2113
+ "step": 300,
2114
+ "total_flos": 5032842677452800.0,
2115
+ "train_loss": 0.4754675631721815,
2116
+ "train_runtime": 6942.3427,
2117
+ "train_samples_per_second": 21.922,
2118
+ "train_steps_per_second": 0.043
2119
+ }
2120
+ ],
2121
+ "logging_steps": 1,
2122
+ "max_steps": 300,
2123
+ "num_input_tokens_seen": 0,
2124
+ "num_train_epochs": 5,
2125
+ "save_steps": 500,
2126
+ "stateful_callbacks": {
2127
+ "TrainerControl": {
2128
+ "args": {
2129
+ "should_epoch_stop": false,
2130
+ "should_evaluate": false,
2131
+ "should_log": false,
2132
+ "should_save": true,
2133
+ "should_training_stop": true
2134
+ },
2135
+ "attributes": {}
2136
+ }
2137
+ },
2138
+ "total_flos": 5032842677452800.0,
2139
+ "train_batch_size": 1,
2140
+ "trial_name": null,
2141
+ "trial_params": null
2142
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:629e1b61efc0f5bc65ae850a83f9a639528220ae072cb237f5b2d27617840ff8
3
+ size 7480
vocab.json ADDED
The diff for this file is too large to render. See raw diff