xxwu commited on
Commit
47b8e3f
·
verified ·
1 Parent(s): 01be8b6

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 CHANGED
@@ -1,3 +1,61 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: Qwen/Qwen2.5-3B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: TravelPlanner_Instruct_3B_1128_1K_4Epoch
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
+ # TravelPlanner_Instruct_3B_1128_1K_4Epoch
18
+
19
+ This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) on the travelplanner_1108_5k_filter_1128_1k 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: 5e-06
39
+ - train_batch_size: 1
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 8
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 32
46
+ - total_eval_batch_size: 64
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 4.0
51
+
52
+ ### Training results
53
+
54
+
55
+
56
+ ### Framework versions
57
+
58
+ - Transformers 4.57.1
59
+ - Pytorch 2.9.0+cu128
60
+ - Datasets 4.0.0
61
+ - Tokenizers 0.22.1
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": 4.0,
3
+ "total_flos": 72384894861312.0,
4
+ "train_loss": 0.3027510484190364,
5
+ "train_runtime": 4332.047,
6
+ "train_samples_per_second": 1.106,
7
+ "train_steps_per_second": 0.035
8
+ }
chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\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>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\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" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "dtype": "bfloat16",
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 2048,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention"
49
+ ],
50
+ "max_position_embeddings": 32768,
51
+ "max_window_layers": 70,
52
+ "model_type": "qwen2",
53
+ "num_attention_heads": 16,
54
+ "num_hidden_layers": 36,
55
+ "num_key_value_heads": 2,
56
+ "pad_token_id": 151643,
57
+ "rms_norm_eps": 1e-06,
58
+ "rope_scaling": null,
59
+ "rope_theta": 1000000.0,
60
+ "sliding_window": null,
61
+ "tie_word_embeddings": true,
62
+ "transformers_version": "4.57.1",
63
+ "use_cache": false,
64
+ "use_sliding_window": false,
65
+ "vocab_size": 151936
66
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151643,
8
+ "repetition_penalty": 1.05,
9
+ "temperature": 0.7,
10
+ "top_k": 20,
11
+ "top_p": 0.8,
12
+ "transformers_version": "4.57.1"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bfbb3d8f75efcb7ca5191c8caf7114a11daea7b98fad2b3a95bdc397ea3c87a
3
+ size 4957560304
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f9f1df29fa5219796775ea3fe14f1da83a642371b2409c989731ea1728f4faa
3
+ size 1214366696
model.safetensors.index.json ADDED
@@ -0,0 +1,442 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 241664,
4
+ "total_size": 6171877376
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
261
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
262
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
263
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
264
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
265
+ "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
266
+ "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
269
+ "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
271
+ "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
273
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
274
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
275
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
276
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
277
+ "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
278
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
279
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
280
+ "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
281
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
282
+ "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
283
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
284
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
290
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
293
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
294
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
295
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
296
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
297
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
298
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
299
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
300
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
301
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
302
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
303
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
304
+ "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
305
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
306
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
307
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
308
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
309
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
310
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
311
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
312
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
313
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
314
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
315
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
316
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
317
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
318
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
319
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
320
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
321
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
322
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
323
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
324
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
325
+ "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
326
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
327
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
328
+ "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
329
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
330
+ "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
331
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
332
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
333
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
334
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
335
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
336
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
337
+ "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
338
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
339
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
340
+ "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
341
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
342
+ "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
343
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
344
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
345
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
346
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
347
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
348
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
349
+ "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
350
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
351
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
352
+ "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
353
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
354
+ "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
355
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
356
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
357
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
358
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
359
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
360
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
361
+ "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
362
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
363
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
364
+ "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
365
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
366
+ "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
367
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
368
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
369
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
370
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
371
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
372
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
373
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
374
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
375
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
376
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
377
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
378
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
379
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
380
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
382
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
383
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
384
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
385
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
386
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
387
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
388
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
389
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
390
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
391
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
392
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
394
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
396
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
398
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
399
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
400
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
401
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
402
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
403
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
404
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
405
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
406
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
407
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
408
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
409
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
410
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
411
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
412
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
413
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
414
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
415
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
416
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
417
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
418
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
419
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
420
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
421
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
422
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
423
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
424
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
425
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
426
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
427
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
428
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
429
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
430
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
432
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
433
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
434
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
435
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
436
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
437
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
438
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
439
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
440
+ "model.norm.weight": "model-00002-of-00002.safetensors"
441
+ }
442
+ }
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": "<|im_end|>",
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
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
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": 4.0,
3
+ "total_flos": 72384894861312.0,
4
+ "train_loss": 0.3027510484190364,
5
+ "train_runtime": 4332.047,
6
+ "train_samples_per_second": 1.106,
7
+ "train_steps_per_second": 0.035
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 152, "loss": 0.631, "lr": 0.0, "epoch": 0.02666666666666667, "percentage": 0.66, "elapsed_time": "0:00:48", "remaining_time": "2:01:15"}
2
+ {"current_steps": 2, "total_steps": 152, "loss": 0.6681, "lr": 3.125e-07, "epoch": 0.05333333333333334, "percentage": 1.32, "elapsed_time": "0:01:14", "remaining_time": "1:33:03"}
3
+ {"current_steps": 3, "total_steps": 152, "loss": 0.6406, "lr": 6.25e-07, "epoch": 0.08, "percentage": 1.97, "elapsed_time": "0:01:48", "remaining_time": "1:29:33"}
4
+ {"current_steps": 4, "total_steps": 152, "loss": 0.683, "lr": 9.375000000000001e-07, "epoch": 0.10666666666666667, "percentage": 2.63, "elapsed_time": "0:02:11", "remaining_time": "1:21:06"}
5
+ {"current_steps": 5, "total_steps": 152, "loss": 0.6529, "lr": 1.25e-06, "epoch": 0.13333333333333333, "percentage": 3.29, "elapsed_time": "0:02:43", "remaining_time": "1:19:53"}
6
+ {"current_steps": 6, "total_steps": 152, "loss": 0.6401, "lr": 1.5625e-06, "epoch": 0.16, "percentage": 3.95, "elapsed_time": "0:03:17", "remaining_time": "1:19:55"}
7
+ {"current_steps": 7, "total_steps": 152, "loss": 0.6234, "lr": 1.8750000000000003e-06, "epoch": 0.18666666666666668, "percentage": 4.61, "elapsed_time": "0:03:44", "remaining_time": "1:17:27"}
8
+ {"current_steps": 8, "total_steps": 152, "loss": 0.6364, "lr": 2.1875000000000002e-06, "epoch": 0.21333333333333335, "percentage": 5.26, "elapsed_time": "0:04:13", "remaining_time": "1:16:06"}
9
+ {"current_steps": 9, "total_steps": 152, "loss": 0.5939, "lr": 2.5e-06, "epoch": 0.24, "percentage": 5.92, "elapsed_time": "0:04:45", "remaining_time": "1:15:30"}
10
+ {"current_steps": 10, "total_steps": 152, "loss": 0.5808, "lr": 2.8125e-06, "epoch": 0.26666666666666666, "percentage": 6.58, "elapsed_time": "0:05:09", "remaining_time": "1:13:21"}
11
+ {"current_steps": 11, "total_steps": 152, "loss": 0.6016, "lr": 3.125e-06, "epoch": 0.29333333333333333, "percentage": 7.24, "elapsed_time": "0:05:34", "remaining_time": "1:11:28"}
12
+ {"current_steps": 12, "total_steps": 152, "loss": 0.5565, "lr": 3.4375e-06, "epoch": 0.32, "percentage": 7.89, "elapsed_time": "0:06:02", "remaining_time": "1:10:27"}
13
+ {"current_steps": 13, "total_steps": 152, "loss": 0.5212, "lr": 3.7500000000000005e-06, "epoch": 0.3466666666666667, "percentage": 8.55, "elapsed_time": "0:06:32", "remaining_time": "1:10:01"}
14
+ {"current_steps": 14, "total_steps": 152, "loss": 0.5302, "lr": 4.0625000000000005e-06, "epoch": 0.37333333333333335, "percentage": 9.21, "elapsed_time": "0:06:58", "remaining_time": "1:08:43"}
15
+ {"current_steps": 15, "total_steps": 152, "loss": 0.5141, "lr": 4.3750000000000005e-06, "epoch": 0.4, "percentage": 9.87, "elapsed_time": "0:07:28", "remaining_time": "1:08:15"}
16
+ {"current_steps": 16, "total_steps": 152, "loss": 0.4582, "lr": 4.6875000000000004e-06, "epoch": 0.4266666666666667, "percentage": 10.53, "elapsed_time": "0:07:56", "remaining_time": "1:07:31"}
17
+ {"current_steps": 17, "total_steps": 152, "loss": 0.4408, "lr": 5e-06, "epoch": 0.4533333333333333, "percentage": 11.18, "elapsed_time": "0:08:30", "remaining_time": "1:07:30"}
18
+ {"current_steps": 18, "total_steps": 152, "loss": 0.4611, "lr": 4.999333020279094e-06, "epoch": 0.48, "percentage": 11.84, "elapsed_time": "0:08:54", "remaining_time": "1:06:20"}
19
+ {"current_steps": 19, "total_steps": 152, "loss": 0.4399, "lr": 4.997332437005932e-06, "epoch": 0.5066666666666667, "percentage": 12.5, "elapsed_time": "0:09:21", "remaining_time": "1:05:28"}
20
+ {"current_steps": 20, "total_steps": 152, "loss": 0.4306, "lr": 4.993999317659293e-06, "epoch": 0.5333333333333333, "percentage": 13.16, "elapsed_time": "0:09:48", "remaining_time": "1:04:45"}
21
+ {"current_steps": 21, "total_steps": 152, "loss": 0.4238, "lr": 4.989335440737587e-06, "epoch": 0.56, "percentage": 13.82, "elapsed_time": "0:10:16", "remaining_time": "1:04:03"}
22
+ {"current_steps": 22, "total_steps": 152, "loss": 0.4202, "lr": 4.983343294809875e-06, "epoch": 0.5866666666666667, "percentage": 14.47, "elapsed_time": "0:10:41", "remaining_time": "1:03:07"}
23
+ {"current_steps": 23, "total_steps": 152, "loss": 0.386, "lr": 4.976026077188013e-06, "epoch": 0.6133333333333333, "percentage": 15.13, "elapsed_time": "0:11:11", "remaining_time": "1:02:48"}
24
+ {"current_steps": 24, "total_steps": 152, "loss": 0.3857, "lr": 4.967387692220615e-06, "epoch": 0.64, "percentage": 15.79, "elapsed_time": "0:11:36", "remaining_time": "1:01:56"}
25
+ {"current_steps": 25, "total_steps": 152, "loss": 0.3681, "lr": 4.957432749209755e-06, "epoch": 0.6666666666666666, "percentage": 16.45, "elapsed_time": "0:12:07", "remaining_time": "1:01:33"}
26
+ {"current_steps": 26, "total_steps": 152, "loss": 0.3618, "lr": 4.946166559951523e-06, "epoch": 0.6933333333333334, "percentage": 17.11, "elapsed_time": "0:12:34", "remaining_time": "1:00:56"}
27
+ {"current_steps": 27, "total_steps": 152, "loss": 0.378, "lr": 4.933595135901733e-06, "epoch": 0.72, "percentage": 17.76, "elapsed_time": "0:12:58", "remaining_time": "1:00:02"}
28
+ {"current_steps": 28, "total_steps": 152, "loss": 0.3489, "lr": 4.919725184968307e-06, "epoch": 0.7466666666666667, "percentage": 18.42, "elapsed_time": "0:13:27", "remaining_time": "0:59:35"}
29
+ {"current_steps": 29, "total_steps": 152, "loss": 0.3799, "lr": 4.904564107932048e-06, "epoch": 0.7733333333333333, "percentage": 19.08, "elapsed_time": "0:13:57", "remaining_time": "0:59:10"}
30
+ {"current_steps": 30, "total_steps": 152, "loss": 0.3482, "lr": 4.888119994497701e-06, "epoch": 0.8, "percentage": 19.74, "elapsed_time": "0:14:25", "remaining_time": "0:58:38"}
31
+ {"current_steps": 31, "total_steps": 152, "loss": 0.3634, "lr": 4.870401618977415e-06, "epoch": 0.8266666666666667, "percentage": 20.39, "elapsed_time": "0:14:51", "remaining_time": "0:58:01"}
32
+ {"current_steps": 32, "total_steps": 152, "loss": 0.3727, "lr": 4.851418435608919e-06, "epoch": 0.8533333333333334, "percentage": 21.05, "elapsed_time": "0:15:15", "remaining_time": "0:57:12"}
33
+ {"current_steps": 33, "total_steps": 152, "loss": 0.3332, "lr": 4.83118057351089e-06, "epoch": 0.88, "percentage": 21.71, "elapsed_time": "0:15:41", "remaining_time": "0:56:35"}
34
+ {"current_steps": 34, "total_steps": 152, "loss": 0.3077, "lr": 4.809698831278217e-06, "epoch": 0.9066666666666666, "percentage": 22.37, "elapsed_time": "0:16:10", "remaining_time": "0:56:07"}
35
+ {"current_steps": 35, "total_steps": 152, "loss": 0.3386, "lr": 4.786984671220053e-06, "epoch": 0.9333333333333333, "percentage": 23.03, "elapsed_time": "0:16:39", "remaining_time": "0:55:41"}
36
+ {"current_steps": 36, "total_steps": 152, "loss": 0.3282, "lr": 4.763050213243705e-06, "epoch": 0.96, "percentage": 23.68, "elapsed_time": "0:17:06", "remaining_time": "0:55:07"}
37
+ {"current_steps": 37, "total_steps": 152, "loss": 0.3321, "lr": 4.737908228387656e-06, "epoch": 0.9866666666666667, "percentage": 24.34, "elapsed_time": "0:17:38", "remaining_time": "0:54:48"}
38
+ {"current_steps": 38, "total_steps": 152, "loss": 0.3312, "lr": 4.711572132007139e-06, "epoch": 1.0, "percentage": 25.0, "elapsed_time": "0:17:51", "remaining_time": "0:53:34"}
39
+ {"current_steps": 39, "total_steps": 152, "loss": 0.3095, "lr": 4.684055976615924e-06, "epoch": 1.0266666666666666, "percentage": 25.66, "elapsed_time": "0:18:21", "remaining_time": "0:53:10"}
40
+ {"current_steps": 40, "total_steps": 152, "loss": 0.2942, "lr": 4.655374444388127e-06, "epoch": 1.0533333333333332, "percentage": 26.32, "elapsed_time": "0:18:47", "remaining_time": "0:52:37"}
41
+ {"current_steps": 41, "total_steps": 152, "loss": 0.3114, "lr": 4.625542839324036e-06, "epoch": 1.08, "percentage": 26.97, "elapsed_time": "0:19:12", "remaining_time": "0:52:00"}
42
+ {"current_steps": 42, "total_steps": 152, "loss": 0.3094, "lr": 4.594577079084146e-06, "epoch": 1.1066666666666667, "percentage": 27.63, "elapsed_time": "0:19:39", "remaining_time": "0:51:28"}
43
+ {"current_steps": 43, "total_steps": 152, "loss": 0.3156, "lr": 4.562493686495756e-06, "epoch": 1.1333333333333333, "percentage": 28.29, "elapsed_time": "0:20:08", "remaining_time": "0:51:03"}
44
+ {"current_steps": 44, "total_steps": 152, "loss": 0.2963, "lr": 4.529309780736654e-06, "epoch": 1.16, "percentage": 28.95, "elapsed_time": "0:20:38", "remaining_time": "0:50:40"}
45
+ {"current_steps": 45, "total_steps": 152, "loss": 0.2906, "lr": 4.4950430682005995e-06, "epoch": 1.1866666666666668, "percentage": 29.61, "elapsed_time": "0:21:07", "remaining_time": "0:50:13"}
46
+ {"current_steps": 46, "total_steps": 152, "loss": 0.3076, "lr": 4.459711833049485e-06, "epoch": 1.2133333333333334, "percentage": 30.26, "elapsed_time": "0:21:33", "remaining_time": "0:49:41"}
47
+ {"current_steps": 47, "total_steps": 152, "loss": 0.3027, "lr": 4.423334927457198e-06, "epoch": 1.24, "percentage": 30.92, "elapsed_time": "0:22:01", "remaining_time": "0:49:12"}
48
+ {"current_steps": 48, "total_steps": 152, "loss": 0.2892, "lr": 4.385931761550411e-06, "epoch": 1.2666666666666666, "percentage": 31.58, "elapsed_time": "0:22:27", "remaining_time": "0:48:39"}
49
+ {"current_steps": 49, "total_steps": 152, "loss": 0.2867, "lr": 4.3475222930516484e-06, "epoch": 1.2933333333333334, "percentage": 32.24, "elapsed_time": "0:22:56", "remaining_time": "0:48:12"}
50
+ {"current_steps": 50, "total_steps": 152, "loss": 0.2737, "lr": 4.308127016630176e-06, "epoch": 1.32, "percentage": 32.89, "elapsed_time": "0:23:27", "remaining_time": "0:47:51"}
51
+ {"current_steps": 51, "total_steps": 152, "loss": 0.2877, "lr": 4.267766952966369e-06, "epoch": 1.3466666666666667, "percentage": 33.55, "elapsed_time": "0:23:59", "remaining_time": "0:47:30"}
52
+ {"current_steps": 52, "total_steps": 152, "loss": 0.2848, "lr": 4.226463637535429e-06, "epoch": 1.3733333333333333, "percentage": 34.21, "elapsed_time": "0:24:24", "remaining_time": "0:46:56"}
53
+ {"current_steps": 53, "total_steps": 152, "loss": 0.292, "lr": 4.184239109116393e-06, "epoch": 1.4, "percentage": 34.87, "elapsed_time": "0:24:52", "remaining_time": "0:46:28"}
54
+ {"current_steps": 54, "total_steps": 152, "loss": 0.2625, "lr": 4.141115898032607e-06, "epoch": 1.4266666666666667, "percentage": 35.53, "elapsed_time": "0:25:22", "remaining_time": "0:46:03"}
55
+ {"current_steps": 55, "total_steps": 152, "loss": 0.2657, "lr": 4.097117014129903e-06, "epoch": 1.4533333333333334, "percentage": 36.18, "elapsed_time": "0:25:54", "remaining_time": "0:45:41"}
56
+ {"current_steps": 56, "total_steps": 152, "loss": 0.2592, "lr": 4.052265934498929e-06, "epoch": 1.48, "percentage": 36.84, "elapsed_time": "0:26:24", "remaining_time": "0:45:16"}
57
+ {"current_steps": 57, "total_steps": 152, "loss": 0.2744, "lr": 4.006586590948141e-06, "epoch": 1.5066666666666668, "percentage": 37.5, "elapsed_time": "0:26:52", "remaining_time": "0:44:47"}
58
+ {"current_steps": 58, "total_steps": 152, "loss": 0.2941, "lr": 3.960103357234192e-06, "epoch": 1.5333333333333332, "percentage": 38.16, "elapsed_time": "0:27:23", "remaining_time": "0:44:22"}
59
+ {"current_steps": 59, "total_steps": 152, "loss": 0.2763, "lr": 3.91284103605648e-06, "epoch": 1.56, "percentage": 38.82, "elapsed_time": "0:27:50", "remaining_time": "0:43:53"}
60
+ {"current_steps": 60, "total_steps": 152, "loss": 0.2737, "lr": 3.864824845822837e-06, "epoch": 1.5866666666666667, "percentage": 39.47, "elapsed_time": "0:28:18", "remaining_time": "0:43:24"}
61
+ {"current_steps": 61, "total_steps": 152, "loss": 0.268, "lr": 3.81608040719339e-06, "epoch": 1.6133333333333333, "percentage": 40.13, "elapsed_time": "0:28:45", "remaining_time": "0:42:53"}
62
+ {"current_steps": 62, "total_steps": 152, "loss": 0.2737, "lr": 3.7666337294097987e-06, "epoch": 1.6400000000000001, "percentage": 40.79, "elapsed_time": "0:29:13", "remaining_time": "0:42:24"}
63
+ {"current_steps": 63, "total_steps": 152, "loss": 0.2563, "lr": 3.7165111964171407e-06, "epoch": 1.6666666666666665, "percentage": 41.45, "elapsed_time": "0:29:40", "remaining_time": "0:41:54"}
64
+ {"current_steps": 64, "total_steps": 152, "loss": 0.2589, "lr": 3.66573955278587e-06, "epoch": 1.6933333333333334, "percentage": 42.11, "elapsed_time": "0:30:07", "remaining_time": "0:41:24"}
65
+ {"current_steps": 65, "total_steps": 152, "loss": 0.2732, "lr": 3.6143458894413463e-06, "epoch": 1.72, "percentage": 42.76, "elapsed_time": "0:30:37", "remaining_time": "0:40:58"}
66
+ {"current_steps": 66, "total_steps": 152, "loss": 0.2682, "lr": 3.5623576292085555e-06, "epoch": 1.7466666666666666, "percentage": 43.42, "elapsed_time": "0:31:02", "remaining_time": "0:40:26"}
67
+ {"current_steps": 67, "total_steps": 152, "loss": 0.2616, "lr": 3.5098025121797375e-06, "epoch": 1.7733333333333334, "percentage": 44.08, "elapsed_time": "0:31:34", "remaining_time": "0:40:04"}
68
+ {"current_steps": 68, "total_steps": 152, "loss": 0.2511, "lr": 3.4567085809127247e-06, "epoch": 1.8, "percentage": 44.74, "elapsed_time": "0:32:08", "remaining_time": "0:39:41"}
69
+ {"current_steps": 69, "total_steps": 152, "loss": 0.2554, "lr": 3.403104165467883e-06, "epoch": 1.8266666666666667, "percentage": 45.39, "elapsed_time": "0:32:40", "remaining_time": "0:39:18"}
70
+ {"current_steps": 70, "total_steps": 152, "loss": 0.2563, "lr": 3.3490178682916534e-06, "epoch": 1.8533333333333335, "percentage": 46.05, "elapsed_time": "0:33:10", "remaining_time": "0:38:51"}
71
+ {"current_steps": 71, "total_steps": 152, "loss": 0.2813, "lr": 3.2944785489547544e-06, "epoch": 1.88, "percentage": 46.71, "elapsed_time": "0:33:36", "remaining_time": "0:38:20"}
72
+ {"current_steps": 72, "total_steps": 152, "loss": 0.2629, "lr": 3.2395153087531767e-06, "epoch": 1.9066666666666667, "percentage": 47.37, "elapsed_time": "0:34:05", "remaining_time": "0:37:52"}
73
+ {"current_steps": 73, "total_steps": 152, "loss": 0.2529, "lr": 3.184157475180208e-06, "epoch": 1.9333333333333333, "percentage": 48.03, "elapsed_time": "0:34:30", "remaining_time": "0:37:21"}
74
+ {"current_steps": 74, "total_steps": 152, "loss": 0.2533, "lr": 3.1284345862777572e-06, "epoch": 1.96, "percentage": 48.68, "elapsed_time": "0:35:00", "remaining_time": "0:36:53"}
75
+ {"current_steps": 75, "total_steps": 152, "loss": 0.2447, "lr": 3.0723763748753354e-06, "epoch": 1.9866666666666668, "percentage": 49.34, "elapsed_time": "0:35:32", "remaining_time": "0:36:29"}
76
+ {"current_steps": 76, "total_steps": 152, "loss": 0.2533, "lr": 3.0160127527250993e-06, "epoch": 2.0, "percentage": 50.0, "elapsed_time": "0:35:46", "remaining_time": "0:35:46"}
77
+ {"current_steps": 77, "total_steps": 152, "loss": 0.2409, "lr": 2.9593737945414264e-06, "epoch": 2.026666666666667, "percentage": 50.66, "elapsed_time": "0:36:11", "remaining_time": "0:35:14"}
78
+ {"current_steps": 78, "total_steps": 152, "loss": 0.2304, "lr": 2.9024897219535326e-06, "epoch": 2.0533333333333332, "percentage": 51.32, "elapsed_time": "0:36:40", "remaining_time": "0:34:48"}
79
+ {"current_steps": 79, "total_steps": 152, "loss": 0.2352, "lr": 2.845390887379706e-06, "epoch": 2.08, "percentage": 51.97, "elapsed_time": "0:37:10", "remaining_time": "0:34:20"}
80
+ {"current_steps": 80, "total_steps": 152, "loss": 0.2312, "lr": 2.7881077578317445e-06, "epoch": 2.1066666666666665, "percentage": 52.63, "elapsed_time": "0:37:46", "remaining_time": "0:33:59"}
81
+ {"current_steps": 81, "total_steps": 152, "loss": 0.2518, "lr": 2.730670898658255e-06, "epoch": 2.1333333333333333, "percentage": 53.29, "elapsed_time": "0:38:13", "remaining_time": "0:33:30"}
82
+ {"current_steps": 82, "total_steps": 152, "loss": 0.2321, "lr": 2.6731109572354795e-06, "epoch": 2.16, "percentage": 53.95, "elapsed_time": "0:38:41", "remaining_time": "0:33:02"}
83
+ {"current_steps": 83, "total_steps": 152, "loss": 0.2549, "lr": 2.6154586466143495e-06, "epoch": 2.1866666666666665, "percentage": 54.61, "elapsed_time": "0:39:04", "remaining_time": "0:32:29"}
84
+ {"current_steps": 84, "total_steps": 152, "loss": 0.2542, "lr": 2.557744729132503e-06, "epoch": 2.2133333333333334, "percentage": 55.26, "elapsed_time": "0:39:31", "remaining_time": "0:32:00"}
85
+ {"current_steps": 85, "total_steps": 152, "loss": 0.2358, "lr": 2.5e-06, "epoch": 2.24, "percentage": 55.92, "elapsed_time": "0:40:02", "remaining_time": "0:31:33"}
86
+ {"current_steps": 86, "total_steps": 152, "loss": 0.2299, "lr": 2.4422552708674977e-06, "epoch": 2.2666666666666666, "percentage": 56.58, "elapsed_time": "0:40:34", "remaining_time": "0:31:08"}
87
+ {"current_steps": 87, "total_steps": 152, "loss": 0.2628, "lr": 2.3845413533856517e-06, "epoch": 2.2933333333333334, "percentage": 57.24, "elapsed_time": "0:41:02", "remaining_time": "0:30:39"}
88
+ {"current_steps": 88, "total_steps": 152, "loss": 0.2454, "lr": 2.3268890427645213e-06, "epoch": 2.32, "percentage": 57.89, "elapsed_time": "0:41:30", "remaining_time": "0:30:10"}
89
+ {"current_steps": 89, "total_steps": 152, "loss": 0.2305, "lr": 2.269329101341745e-06, "epoch": 2.3466666666666667, "percentage": 58.55, "elapsed_time": "0:42:00", "remaining_time": "0:29:43"}
90
+ {"current_steps": 90, "total_steps": 152, "loss": 0.245, "lr": 2.2118922421682563e-06, "epoch": 2.3733333333333335, "percentage": 59.21, "elapsed_time": "0:42:32", "remaining_time": "0:29:18"}
91
+ {"current_steps": 91, "total_steps": 152, "loss": 0.2429, "lr": 2.1546091126202955e-06, "epoch": 2.4, "percentage": 59.87, "elapsed_time": "0:43:00", "remaining_time": "0:28:50"}
92
+ {"current_steps": 92, "total_steps": 152, "loss": 0.2433, "lr": 2.0975102780464674e-06, "epoch": 2.4266666666666667, "percentage": 60.53, "elapsed_time": "0:43:30", "remaining_time": "0:28:22"}
93
+ {"current_steps": 93, "total_steps": 152, "loss": 0.2421, "lr": 2.040626205458574e-06, "epoch": 2.453333333333333, "percentage": 61.18, "elapsed_time": "0:43:59", "remaining_time": "0:27:54"}
94
+ {"current_steps": 94, "total_steps": 152, "loss": 0.2456, "lr": 1.9839872472749016e-06, "epoch": 2.48, "percentage": 61.84, "elapsed_time": "0:44:34", "remaining_time": "0:27:29"}
95
+ {"current_steps": 95, "total_steps": 152, "loss": 0.2497, "lr": 1.9276236251246655e-06, "epoch": 2.506666666666667, "percentage": 62.5, "elapsed_time": "0:44:59", "remaining_time": "0:26:59"}
96
+ {"current_steps": 96, "total_steps": 152, "loss": 0.2452, "lr": 1.8715654137222434e-06, "epoch": 2.533333333333333, "percentage": 63.16, "elapsed_time": "0:45:25", "remaining_time": "0:26:30"}
97
+ {"current_steps": 97, "total_steps": 152, "loss": 0.2367, "lr": 1.8158425248197931e-06, "epoch": 2.56, "percentage": 63.82, "elapsed_time": "0:45:55", "remaining_time": "0:26:02"}
98
+ {"current_steps": 98, "total_steps": 152, "loss": 0.2224, "lr": 1.7604846912468243e-06, "epoch": 2.586666666666667, "percentage": 64.47, "elapsed_time": "0:46:23", "remaining_time": "0:25:33"}
99
+ {"current_steps": 99, "total_steps": 152, "loss": 0.2342, "lr": 1.7055214510452462e-06, "epoch": 2.6133333333333333, "percentage": 65.13, "elapsed_time": "0:46:57", "remaining_time": "0:25:08"}
100
+ {"current_steps": 100, "total_steps": 152, "loss": 0.2483, "lr": 1.6509821317083466e-06, "epoch": 2.64, "percentage": 65.79, "elapsed_time": "0:47:22", "remaining_time": "0:24:38"}
101
+ {"current_steps": 101, "total_steps": 152, "loss": 0.2456, "lr": 1.5968958345321178e-06, "epoch": 2.6666666666666665, "percentage": 66.45, "elapsed_time": "0:47:55", "remaining_time": "0:24:11"}
102
+ {"current_steps": 102, "total_steps": 152, "loss": 0.2334, "lr": 1.5432914190872757e-06, "epoch": 2.6933333333333334, "percentage": 67.11, "elapsed_time": "0:48:24", "remaining_time": "0:23:43"}
103
+ {"current_steps": 103, "total_steps": 152, "loss": 0.2411, "lr": 1.490197487820263e-06, "epoch": 2.7199999999999998, "percentage": 67.76, "elapsed_time": "0:48:51", "remaining_time": "0:23:14"}
104
+ {"current_steps": 104, "total_steps": 152, "loss": 0.242, "lr": 1.4376423707914462e-06, "epoch": 2.7466666666666666, "percentage": 68.42, "elapsed_time": "0:49:20", "remaining_time": "0:22:46"}
105
+ {"current_steps": 105, "total_steps": 152, "loss": 0.2215, "lr": 1.3856541105586545e-06, "epoch": 2.7733333333333334, "percentage": 69.08, "elapsed_time": "0:49:46", "remaining_time": "0:22:17"}
106
+ {"current_steps": 106, "total_steps": 152, "loss": 0.2308, "lr": 1.3342604472141296e-06, "epoch": 2.8, "percentage": 69.74, "elapsed_time": "0:50:13", "remaining_time": "0:21:47"}
107
+ {"current_steps": 107, "total_steps": 152, "loss": 0.2364, "lr": 1.2834888035828597e-06, "epoch": 2.8266666666666667, "percentage": 70.39, "elapsed_time": "0:50:45", "remaining_time": "0:21:20"}
108
+ {"current_steps": 108, "total_steps": 152, "loss": 0.2193, "lr": 1.233366270590202e-06, "epoch": 2.8533333333333335, "percentage": 71.05, "elapsed_time": "0:51:13", "remaining_time": "0:20:52"}
109
+ {"current_steps": 109, "total_steps": 152, "loss": 0.2489, "lr": 1.1839195928066101e-06, "epoch": 2.88, "percentage": 71.71, "elapsed_time": "0:51:38", "remaining_time": "0:20:22"}
110
+ {"current_steps": 110, "total_steps": 152, "loss": 0.2452, "lr": 1.1351751541771644e-06, "epoch": 2.9066666666666667, "percentage": 72.37, "elapsed_time": "0:52:00", "remaining_time": "0:19:51"}
111
+ {"current_steps": 111, "total_steps": 152, "loss": 0.2347, "lr": 1.0871589639435204e-06, "epoch": 2.9333333333333336, "percentage": 73.03, "elapsed_time": "0:52:31", "remaining_time": "0:19:23"}
112
+ {"current_steps": 112, "total_steps": 152, "loss": 0.2283, "lr": 1.0398966427658091e-06, "epoch": 2.96, "percentage": 73.68, "elapsed_time": "0:52:55", "remaining_time": "0:18:54"}
113
+ {"current_steps": 113, "total_steps": 152, "loss": 0.2397, "lr": 9.934134090518593e-07, "epoch": 2.986666666666667, "percentage": 74.34, "elapsed_time": "0:53:25", "remaining_time": "0:18:26"}
114
+ {"current_steps": 114, "total_steps": 152, "loss": 0.2462, "lr": 9.477340655010717e-07, "epoch": 3.0, "percentage": 75.0, "elapsed_time": "0:53:39", "remaining_time": "0:17:53"}
115
+ {"current_steps": 115, "total_steps": 152, "loss": 0.2121, "lr": 9.028829858700974e-07, "epoch": 3.026666666666667, "percentage": 75.66, "elapsed_time": "0:54:13", "remaining_time": "0:17:26"}
116
+ {"current_steps": 116, "total_steps": 152, "loss": 0.2275, "lr": 8.588841019673938e-07, "epoch": 3.0533333333333332, "percentage": 76.32, "elapsed_time": "0:54:43", "remaining_time": "0:16:59"}
117
+ {"current_steps": 117, "total_steps": 152, "loss": 0.2256, "lr": 8.157608908836071e-07, "epoch": 3.08, "percentage": 76.97, "elapsed_time": "0:55:12", "remaining_time": "0:16:31"}
118
+ {"current_steps": 118, "total_steps": 152, "loss": 0.2324, "lr": 7.735363624645712e-07, "epoch": 3.1066666666666665, "percentage": 77.63, "elapsed_time": "0:55:40", "remaining_time": "0:16:02"}
119
+ {"current_steps": 119, "total_steps": 152, "loss": 0.2346, "lr": 7.322330470336314e-07, "epoch": 3.1333333333333333, "percentage": 78.29, "elapsed_time": "0:56:03", "remaining_time": "0:15:32"}
120
+ {"current_steps": 120, "total_steps": 152, "loss": 0.2174, "lr": 6.91872983369826e-07, "epoch": 3.16, "percentage": 78.95, "elapsed_time": "0:56:32", "remaining_time": "0:15:04"}
121
+ {"current_steps": 121, "total_steps": 152, "loss": 0.2195, "lr": 6.524777069483526e-07, "epoch": 3.1866666666666665, "percentage": 79.61, "elapsed_time": "0:56:58", "remaining_time": "0:14:35"}
122
+ {"current_steps": 122, "total_steps": 152, "loss": 0.2267, "lr": 6.140682384495902e-07, "epoch": 3.2133333333333334, "percentage": 80.26, "elapsed_time": "0:57:31", "remaining_time": "0:14:08"}
123
+ {"current_steps": 123, "total_steps": 152, "loss": 0.214, "lr": 5.766650725428027e-07, "epoch": 3.24, "percentage": 80.92, "elapsed_time": "0:58:02", "remaining_time": "0:13:40"}
124
+ {"current_steps": 124, "total_steps": 152, "loss": 0.2224, "lr": 5.402881669505164e-07, "epoch": 3.2666666666666666, "percentage": 81.58, "elapsed_time": "0:58:31", "remaining_time": "0:13:12"}
125
+ {"current_steps": 125, "total_steps": 152, "loss": 0.2409, "lr": 5.049569317994013e-07, "epoch": 3.2933333333333334, "percentage": 82.24, "elapsed_time": "0:59:00", "remaining_time": "0:12:44"}
126
+ {"current_steps": 126, "total_steps": 152, "loss": 0.2329, "lr": 4.70690219263347e-07, "epoch": 3.32, "percentage": 82.89, "elapsed_time": "0:59:29", "remaining_time": "0:12:16"}
127
+ {"current_steps": 127, "total_steps": 152, "loss": 0.2227, "lr": 4.3750631350424456e-07, "epoch": 3.3466666666666667, "percentage": 83.55, "elapsed_time": "0:59:58", "remaining_time": "0:11:48"}
128
+ {"current_steps": 128, "total_steps": 152, "loss": 0.2228, "lr": 4.0542292091585447e-07, "epoch": 3.3733333333333335, "percentage": 84.21, "elapsed_time": "1:00:27", "remaining_time": "0:11:20"}
129
+ {"current_steps": 129, "total_steps": 152, "loss": 0.2302, "lr": 3.7445716067596506e-07, "epoch": 3.4, "percentage": 84.87, "elapsed_time": "1:00:51", "remaining_time": "0:10:51"}
130
+ {"current_steps": 130, "total_steps": 152, "loss": 0.2314, "lr": 3.446255556118736e-07, "epoch": 3.4266666666666667, "percentage": 85.53, "elapsed_time": "1:01:25", "remaining_time": "0:10:23"}
131
+ {"current_steps": 131, "total_steps": 152, "loss": 0.2159, "lr": 3.1594402338407633e-07, "epoch": 3.453333333333333, "percentage": 86.18, "elapsed_time": "1:01:56", "remaining_time": "0:09:55"}
132
+ {"current_steps": 132, "total_steps": 152, "loss": 0.2157, "lr": 2.8842786799286204e-07, "epoch": 3.48, "percentage": 86.84, "elapsed_time": "1:02:22", "remaining_time": "0:09:27"}
133
+ {"current_steps": 133, "total_steps": 152, "loss": 0.2345, "lr": 2.620917716123444e-07, "epoch": 3.506666666666667, "percentage": 87.5, "elapsed_time": "1:02:58", "remaining_time": "0:08:59"}
134
+ {"current_steps": 134, "total_steps": 152, "loss": 0.2156, "lr": 2.3694978675629476e-07, "epoch": 3.533333333333333, "percentage": 88.16, "elapsed_time": "1:03:22", "remaining_time": "0:08:30"}
135
+ {"current_steps": 135, "total_steps": 152, "loss": 0.219, "lr": 2.1301532877994747e-07, "epoch": 3.56, "percentage": 88.82, "elapsed_time": "1:03:53", "remaining_time": "0:08:02"}
136
+ {"current_steps": 136, "total_steps": 152, "loss": 0.2347, "lr": 1.9030116872178317e-07, "epoch": 3.586666666666667, "percentage": 89.47, "elapsed_time": "1:04:18", "remaining_time": "0:07:33"}
137
+ {"current_steps": 137, "total_steps": 152, "loss": 0.2399, "lr": 1.6881942648911077e-07, "epoch": 3.6133333333333333, "percentage": 90.13, "elapsed_time": "1:04:45", "remaining_time": "0:07:05"}
138
+ {"current_steps": 138, "total_steps": 152, "loss": 0.2297, "lr": 1.4858156439108097e-07, "epoch": 3.64, "percentage": 90.79, "elapsed_time": "1:05:12", "remaining_time": "0:06:36"}
139
+ {"current_steps": 139, "total_steps": 152, "loss": 0.228, "lr": 1.2959838102258537e-07, "epoch": 3.6666666666666665, "percentage": 91.45, "elapsed_time": "1:05:40", "remaining_time": "0:06:08"}
140
+ {"current_steps": 140, "total_steps": 152, "loss": 0.2233, "lr": 1.1188000550230005e-07, "epoch": 3.6933333333333334, "percentage": 92.11, "elapsed_time": "1:06:09", "remaining_time": "0:05:40"}
141
+ {"current_steps": 141, "total_steps": 152, "loss": 0.22, "lr": 9.54358920679524e-08, "epoch": 3.7199999999999998, "percentage": 92.76, "elapsed_time": "1:06:38", "remaining_time": "0:05:11"}
142
+ {"current_steps": 142, "total_steps": 152, "loss": 0.2459, "lr": 8.027481503169371e-08, "epoch": 3.7466666666666666, "percentage": 93.42, "elapsed_time": "1:07:09", "remaining_time": "0:04:43"}
143
+ {"current_steps": 143, "total_steps": 152, "loss": 0.2222, "lr": 6.640486409826785e-08, "epoch": 3.7733333333333334, "percentage": 94.08, "elapsed_time": "1:07:36", "remaining_time": "0:04:15"}
144
+ {"current_steps": 144, "total_steps": 152, "loss": 0.2239, "lr": 5.383344004847774e-08, "epoch": 3.8, "percentage": 94.74, "elapsed_time": "1:08:07", "remaining_time": "0:03:47"}
145
+ {"current_steps": 145, "total_steps": 152, "loss": 0.2355, "lr": 4.256725079024554e-08, "epoch": 3.8266666666666667, "percentage": 95.39, "elapsed_time": "1:08:36", "remaining_time": "0:03:18"}
146
+ {"current_steps": 146, "total_steps": 152, "loss": 0.2344, "lr": 3.261230777938607e-08, "epoch": 3.8533333333333335, "percentage": 96.05, "elapsed_time": "1:09:10", "remaining_time": "0:02:50"}
147
+ {"current_steps": 147, "total_steps": 152, "loss": 0.2219, "lr": 2.3973922811987295e-08, "epoch": 3.88, "percentage": 96.71, "elapsed_time": "1:09:37", "remaining_time": "0:02:22"}
148
+ {"current_steps": 148, "total_steps": 152, "loss": 0.2346, "lr": 1.6656705190125078e-08, "epoch": 3.9066666666666667, "percentage": 97.37, "elapsed_time": "1:10:06", "remaining_time": "0:01:53"}
149
+ {"current_steps": 149, "total_steps": 152, "loss": 0.2116, "lr": 1.0664559262413831e-08, "epoch": 3.9333333333333336, "percentage": 98.03, "elapsed_time": "1:10:41", "remaining_time": "0:01:25"}
150
+ {"current_steps": 150, "total_steps": 152, "loss": 0.225, "lr": 6.00068234070772e-09, "epoch": 3.96, "percentage": 98.68, "elapsed_time": "1:11:07", "remaining_time": "0:00:56"}
151
+ {"current_steps": 151, "total_steps": 152, "loss": 0.2277, "lr": 2.6675629940689508e-09, "epoch": 3.986666666666667, "percentage": 99.34, "elapsed_time": "1:11:38", "remaining_time": "0:00:28"}
152
+ {"current_steps": 152, "total_steps": 152, "loss": 0.2014, "lr": 6.669797209069018e-10, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "1:11:51", "remaining_time": "0:00:00"}
153
+ {"current_steps": 152, "total_steps": 152, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "1:12:12", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,1107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 152,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02666666666666667,
14
+ "grad_norm": 4.878157623450739,
15
+ "learning_rate": 0.0,
16
+ "loss": 0.631,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.05333333333333334,
21
+ "grad_norm": 5.170065300315267,
22
+ "learning_rate": 3.125e-07,
23
+ "loss": 0.6681,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.08,
28
+ "grad_norm": 5.40433053963945,
29
+ "learning_rate": 6.25e-07,
30
+ "loss": 0.6406,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.10666666666666667,
35
+ "grad_norm": 4.85913880529326,
36
+ "learning_rate": 9.375000000000001e-07,
37
+ "loss": 0.683,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.13333333333333333,
42
+ "grad_norm": 4.937427693886052,
43
+ "learning_rate": 1.25e-06,
44
+ "loss": 0.6529,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.16,
49
+ "grad_norm": 4.207398221265401,
50
+ "learning_rate": 1.5625e-06,
51
+ "loss": 0.6401,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.18666666666666668,
56
+ "grad_norm": 3.319749148677077,
57
+ "learning_rate": 1.8750000000000003e-06,
58
+ "loss": 0.6234,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.21333333333333335,
63
+ "grad_norm": 3.218511281533974,
64
+ "learning_rate": 2.1875000000000002e-06,
65
+ "loss": 0.6364,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.24,
70
+ "grad_norm": 2.189582672605477,
71
+ "learning_rate": 2.5e-06,
72
+ "loss": 0.5939,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.26666666666666666,
77
+ "grad_norm": 2.0657652170400094,
78
+ "learning_rate": 2.8125e-06,
79
+ "loss": 0.5808,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.29333333333333333,
84
+ "grad_norm": 2.0442622561608177,
85
+ "learning_rate": 3.125e-06,
86
+ "loss": 0.6016,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.32,
91
+ "grad_norm": 1.546150085996069,
92
+ "learning_rate": 3.4375e-06,
93
+ "loss": 0.5565,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.3466666666666667,
98
+ "grad_norm": 1.4384263032130433,
99
+ "learning_rate": 3.7500000000000005e-06,
100
+ "loss": 0.5212,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.37333333333333335,
105
+ "grad_norm": 1.395058990926793,
106
+ "learning_rate": 4.0625000000000005e-06,
107
+ "loss": 0.5302,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.4,
112
+ "grad_norm": 1.327031867420667,
113
+ "learning_rate": 4.3750000000000005e-06,
114
+ "loss": 0.5141,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.4266666666666667,
119
+ "grad_norm": 1.1409992758726908,
120
+ "learning_rate": 4.6875000000000004e-06,
121
+ "loss": 0.4582,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.4533333333333333,
126
+ "grad_norm": 1.222665503024542,
127
+ "learning_rate": 5e-06,
128
+ "loss": 0.4408,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.48,
133
+ "grad_norm": 1.2275496249747453,
134
+ "learning_rate": 4.999333020279094e-06,
135
+ "loss": 0.4611,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.5066666666666667,
140
+ "grad_norm": 1.090224000134227,
141
+ "learning_rate": 4.997332437005932e-06,
142
+ "loss": 0.4399,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.5333333333333333,
147
+ "grad_norm": 1.027088670983558,
148
+ "learning_rate": 4.993999317659293e-06,
149
+ "loss": 0.4306,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.56,
154
+ "grad_norm": 0.9064527717256649,
155
+ "learning_rate": 4.989335440737587e-06,
156
+ "loss": 0.4238,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.5866666666666667,
161
+ "grad_norm": 0.9288966544934301,
162
+ "learning_rate": 4.983343294809875e-06,
163
+ "loss": 0.4202,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.6133333333333333,
168
+ "grad_norm": 0.9741558191339147,
169
+ "learning_rate": 4.976026077188013e-06,
170
+ "loss": 0.386,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.64,
175
+ "grad_norm": 0.9865961456076341,
176
+ "learning_rate": 4.967387692220615e-06,
177
+ "loss": 0.3857,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.6666666666666666,
182
+ "grad_norm": 0.8657767954708736,
183
+ "learning_rate": 4.957432749209755e-06,
184
+ "loss": 0.3681,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.6933333333333334,
189
+ "grad_norm": 0.8266796625020906,
190
+ "learning_rate": 4.946166559951523e-06,
191
+ "loss": 0.3618,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.72,
196
+ "grad_norm": 0.8378735258003706,
197
+ "learning_rate": 4.933595135901733e-06,
198
+ "loss": 0.378,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.7466666666666667,
203
+ "grad_norm": 0.8023453899918793,
204
+ "learning_rate": 4.919725184968307e-06,
205
+ "loss": 0.3489,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.7733333333333333,
210
+ "grad_norm": 0.8010880737255618,
211
+ "learning_rate": 4.904564107932048e-06,
212
+ "loss": 0.3799,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.8,
217
+ "grad_norm": 0.7035249640127581,
218
+ "learning_rate": 4.888119994497701e-06,
219
+ "loss": 0.3482,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.8266666666666667,
224
+ "grad_norm": 0.6932069839381024,
225
+ "learning_rate": 4.870401618977415e-06,
226
+ "loss": 0.3634,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.8533333333333334,
231
+ "grad_norm": 0.7628974273180826,
232
+ "learning_rate": 4.851418435608919e-06,
233
+ "loss": 0.3727,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.88,
238
+ "grad_norm": 0.6869681855844014,
239
+ "learning_rate": 4.83118057351089e-06,
240
+ "loss": 0.3332,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.9066666666666666,
245
+ "grad_norm": 0.6650613020220915,
246
+ "learning_rate": 4.809698831278217e-06,
247
+ "loss": 0.3077,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.9333333333333333,
252
+ "grad_norm": 0.6466272823586058,
253
+ "learning_rate": 4.786984671220053e-06,
254
+ "loss": 0.3386,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.96,
259
+ "grad_norm": 0.63358072422972,
260
+ "learning_rate": 4.763050213243705e-06,
261
+ "loss": 0.3282,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.9866666666666667,
266
+ "grad_norm": 0.6568304740183881,
267
+ "learning_rate": 4.737908228387656e-06,
268
+ "loss": 0.3321,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 1.0,
273
+ "grad_norm": 0.8135997471743929,
274
+ "learning_rate": 4.711572132007139e-06,
275
+ "loss": 0.3312,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 1.0266666666666666,
280
+ "grad_norm": 0.6202125210847353,
281
+ "learning_rate": 4.684055976615924e-06,
282
+ "loss": 0.3095,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 1.0533333333333332,
287
+ "grad_norm": 0.6368737403523828,
288
+ "learning_rate": 4.655374444388127e-06,
289
+ "loss": 0.2942,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 1.08,
294
+ "grad_norm": 0.5981092287774709,
295
+ "learning_rate": 4.625542839324036e-06,
296
+ "loss": 0.3114,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 1.1066666666666667,
301
+ "grad_norm": 0.5797424271625753,
302
+ "learning_rate": 4.594577079084146e-06,
303
+ "loss": 0.3094,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 1.1333333333333333,
308
+ "grad_norm": 0.657292657970152,
309
+ "learning_rate": 4.562493686495756e-06,
310
+ "loss": 0.3156,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 1.16,
315
+ "grad_norm": 0.5813617766296967,
316
+ "learning_rate": 4.529309780736654e-06,
317
+ "loss": 0.2963,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 1.1866666666666668,
322
+ "grad_norm": 0.6627698280340774,
323
+ "learning_rate": 4.4950430682005995e-06,
324
+ "loss": 0.2906,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 1.2133333333333334,
329
+ "grad_norm": 0.6319661573243743,
330
+ "learning_rate": 4.459711833049485e-06,
331
+ "loss": 0.3076,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 1.24,
336
+ "grad_norm": 0.6442282320374813,
337
+ "learning_rate": 4.423334927457198e-06,
338
+ "loss": 0.3027,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 1.2666666666666666,
343
+ "grad_norm": 0.5752270913424733,
344
+ "learning_rate": 4.385931761550411e-06,
345
+ "loss": 0.2892,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 1.2933333333333334,
350
+ "grad_norm": 0.596234498496008,
351
+ "learning_rate": 4.3475222930516484e-06,
352
+ "loss": 0.2867,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 1.32,
357
+ "grad_norm": 0.5988075400308576,
358
+ "learning_rate": 4.308127016630176e-06,
359
+ "loss": 0.2737,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 1.3466666666666667,
364
+ "grad_norm": 0.5679492374268279,
365
+ "learning_rate": 4.267766952966369e-06,
366
+ "loss": 0.2877,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 1.3733333333333333,
371
+ "grad_norm": 0.5843638124875605,
372
+ "learning_rate": 4.226463637535429e-06,
373
+ "loss": 0.2848,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 1.4,
378
+ "grad_norm": 0.6239858339692398,
379
+ "learning_rate": 4.184239109116393e-06,
380
+ "loss": 0.292,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 1.4266666666666667,
385
+ "grad_norm": 0.590842876175558,
386
+ "learning_rate": 4.141115898032607e-06,
387
+ "loss": 0.2625,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 1.4533333333333334,
392
+ "grad_norm": 0.5805205102067804,
393
+ "learning_rate": 4.097117014129903e-06,
394
+ "loss": 0.2657,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 1.48,
399
+ "grad_norm": 0.5446258740726869,
400
+ "learning_rate": 4.052265934498929e-06,
401
+ "loss": 0.2592,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 1.5066666666666668,
406
+ "grad_norm": 0.5872428912680386,
407
+ "learning_rate": 4.006586590948141e-06,
408
+ "loss": 0.2744,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 1.5333333333333332,
413
+ "grad_norm": 0.5959005303282,
414
+ "learning_rate": 3.960103357234192e-06,
415
+ "loss": 0.2941,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 1.56,
420
+ "grad_norm": 0.5575301840899185,
421
+ "learning_rate": 3.91284103605648e-06,
422
+ "loss": 0.2763,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 1.5866666666666667,
427
+ "grad_norm": 0.6011733484218966,
428
+ "learning_rate": 3.864824845822837e-06,
429
+ "loss": 0.2737,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 1.6133333333333333,
434
+ "grad_norm": 0.5592252944248155,
435
+ "learning_rate": 3.81608040719339e-06,
436
+ "loss": 0.268,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 1.6400000000000001,
441
+ "grad_norm": 0.5905968812158535,
442
+ "learning_rate": 3.7666337294097987e-06,
443
+ "loss": 0.2737,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 1.6666666666666665,
448
+ "grad_norm": 0.5807486706422721,
449
+ "learning_rate": 3.7165111964171407e-06,
450
+ "loss": 0.2563,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 1.6933333333333334,
455
+ "grad_norm": 0.5685076470891995,
456
+ "learning_rate": 3.66573955278587e-06,
457
+ "loss": 0.2589,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 1.72,
462
+ "grad_norm": 0.5913017391511816,
463
+ "learning_rate": 3.6143458894413463e-06,
464
+ "loss": 0.2732,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 1.7466666666666666,
469
+ "grad_norm": 0.5723987458547558,
470
+ "learning_rate": 3.5623576292085555e-06,
471
+ "loss": 0.2682,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 1.7733333333333334,
476
+ "grad_norm": 0.5647891287504915,
477
+ "learning_rate": 3.5098025121797375e-06,
478
+ "loss": 0.2616,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 1.8,
483
+ "grad_norm": 0.5411306788924399,
484
+ "learning_rate": 3.4567085809127247e-06,
485
+ "loss": 0.2511,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 1.8266666666666667,
490
+ "grad_norm": 0.5414442330245403,
491
+ "learning_rate": 3.403104165467883e-06,
492
+ "loss": 0.2554,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 1.8533333333333335,
497
+ "grad_norm": 0.5841367242867953,
498
+ "learning_rate": 3.3490178682916534e-06,
499
+ "loss": 0.2563,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 1.88,
504
+ "grad_norm": 0.593917605341576,
505
+ "learning_rate": 3.2944785489547544e-06,
506
+ "loss": 0.2813,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 1.9066666666666667,
511
+ "grad_norm": 0.6136806236288534,
512
+ "learning_rate": 3.2395153087531767e-06,
513
+ "loss": 0.2629,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 1.9333333333333333,
518
+ "grad_norm": 0.5271119497959631,
519
+ "learning_rate": 3.184157475180208e-06,
520
+ "loss": 0.2529,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 1.96,
525
+ "grad_norm": 0.5697313663850498,
526
+ "learning_rate": 3.1284345862777572e-06,
527
+ "loss": 0.2533,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 1.9866666666666668,
532
+ "grad_norm": 0.5821425842681058,
533
+ "learning_rate": 3.0723763748753354e-06,
534
+ "loss": 0.2447,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 2.0,
539
+ "grad_norm": 0.7535800017303044,
540
+ "learning_rate": 3.0160127527250993e-06,
541
+ "loss": 0.2533,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 2.026666666666667,
546
+ "grad_norm": 0.552483342107968,
547
+ "learning_rate": 2.9593737945414264e-06,
548
+ "loss": 0.2409,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 2.0533333333333332,
553
+ "grad_norm": 0.556197127799378,
554
+ "learning_rate": 2.9024897219535326e-06,
555
+ "loss": 0.2304,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 2.08,
560
+ "grad_norm": 0.5769909224218249,
561
+ "learning_rate": 2.845390887379706e-06,
562
+ "loss": 0.2352,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 2.1066666666666665,
567
+ "grad_norm": 0.5350549486190628,
568
+ "learning_rate": 2.7881077578317445e-06,
569
+ "loss": 0.2312,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 2.1333333333333333,
574
+ "grad_norm": 0.575879711705845,
575
+ "learning_rate": 2.730670898658255e-06,
576
+ "loss": 0.2518,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 2.16,
581
+ "grad_norm": 0.5624179987688637,
582
+ "learning_rate": 2.6731109572354795e-06,
583
+ "loss": 0.2321,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 2.1866666666666665,
588
+ "grad_norm": 0.5985317043095278,
589
+ "learning_rate": 2.6154586466143495e-06,
590
+ "loss": 0.2549,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 2.2133333333333334,
595
+ "grad_norm": 0.6122353052173574,
596
+ "learning_rate": 2.557744729132503e-06,
597
+ "loss": 0.2542,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 2.24,
602
+ "grad_norm": 0.5570090577421112,
603
+ "learning_rate": 2.5e-06,
604
+ "loss": 0.2358,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 2.2666666666666666,
609
+ "grad_norm": 0.5191948700167437,
610
+ "learning_rate": 2.4422552708674977e-06,
611
+ "loss": 0.2299,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 2.2933333333333334,
616
+ "grad_norm": 0.6168531258186732,
617
+ "learning_rate": 2.3845413533856517e-06,
618
+ "loss": 0.2628,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 2.32,
623
+ "grad_norm": 0.5389053132287224,
624
+ "learning_rate": 2.3268890427645213e-06,
625
+ "loss": 0.2454,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 2.3466666666666667,
630
+ "grad_norm": 0.5179374098955292,
631
+ "learning_rate": 2.269329101341745e-06,
632
+ "loss": 0.2305,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 2.3733333333333335,
637
+ "grad_norm": 0.5695776888113124,
638
+ "learning_rate": 2.2118922421682563e-06,
639
+ "loss": 0.245,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 2.4,
644
+ "grad_norm": 0.5755039229449211,
645
+ "learning_rate": 2.1546091126202955e-06,
646
+ "loss": 0.2429,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 2.4266666666666667,
651
+ "grad_norm": 0.5965665991524789,
652
+ "learning_rate": 2.0975102780464674e-06,
653
+ "loss": 0.2433,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 2.453333333333333,
658
+ "grad_norm": 0.5971610159352314,
659
+ "learning_rate": 2.040626205458574e-06,
660
+ "loss": 0.2421,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 2.48,
665
+ "grad_norm": 0.5612666487388789,
666
+ "learning_rate": 1.9839872472749016e-06,
667
+ "loss": 0.2456,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 2.506666666666667,
672
+ "grad_norm": 0.6062165663036713,
673
+ "learning_rate": 1.9276236251246655e-06,
674
+ "loss": 0.2497,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 2.533333333333333,
679
+ "grad_norm": 0.6104476309048308,
680
+ "learning_rate": 1.8715654137222434e-06,
681
+ "loss": 0.2452,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 2.56,
686
+ "grad_norm": 0.5799610488050738,
687
+ "learning_rate": 1.8158425248197931e-06,
688
+ "loss": 0.2367,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 2.586666666666667,
693
+ "grad_norm": 0.506133298921399,
694
+ "learning_rate": 1.7604846912468243e-06,
695
+ "loss": 0.2224,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 2.6133333333333333,
700
+ "grad_norm": 0.5585029123373569,
701
+ "learning_rate": 1.7055214510452462e-06,
702
+ "loss": 0.2342,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 2.64,
707
+ "grad_norm": 0.5970042964682027,
708
+ "learning_rate": 1.6509821317083466e-06,
709
+ "loss": 0.2483,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 2.6666666666666665,
714
+ "grad_norm": 0.5698789561874062,
715
+ "learning_rate": 1.5968958345321178e-06,
716
+ "loss": 0.2456,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 2.6933333333333334,
721
+ "grad_norm": 0.575481549643457,
722
+ "learning_rate": 1.5432914190872757e-06,
723
+ "loss": 0.2334,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 2.7199999999999998,
728
+ "grad_norm": 0.5730234610354396,
729
+ "learning_rate": 1.490197487820263e-06,
730
+ "loss": 0.2411,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 2.7466666666666666,
735
+ "grad_norm": 0.5746386066342895,
736
+ "learning_rate": 1.4376423707914462e-06,
737
+ "loss": 0.242,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 2.7733333333333334,
742
+ "grad_norm": 0.5828599815457075,
743
+ "learning_rate": 1.3856541105586545e-06,
744
+ "loss": 0.2215,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 2.8,
749
+ "grad_norm": 0.5293624294723653,
750
+ "learning_rate": 1.3342604472141296e-06,
751
+ "loss": 0.2308,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 2.8266666666666667,
756
+ "grad_norm": 0.5649326573487977,
757
+ "learning_rate": 1.2834888035828597e-06,
758
+ "loss": 0.2364,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 2.8533333333333335,
763
+ "grad_norm": 0.5516952435718434,
764
+ "learning_rate": 1.233366270590202e-06,
765
+ "loss": 0.2193,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 2.88,
770
+ "grad_norm": 0.6007878524036752,
771
+ "learning_rate": 1.1839195928066101e-06,
772
+ "loss": 0.2489,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 2.9066666666666667,
777
+ "grad_norm": 0.5963220503058547,
778
+ "learning_rate": 1.1351751541771644e-06,
779
+ "loss": 0.2452,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 2.9333333333333336,
784
+ "grad_norm": 0.5689392825698061,
785
+ "learning_rate": 1.0871589639435204e-06,
786
+ "loss": 0.2347,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 2.96,
791
+ "grad_norm": 0.5262629004420984,
792
+ "learning_rate": 1.0398966427658091e-06,
793
+ "loss": 0.2283,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 2.986666666666667,
798
+ "grad_norm": 0.5878912916264337,
799
+ "learning_rate": 9.934134090518593e-07,
800
+ "loss": 0.2397,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 3.0,
805
+ "grad_norm": 0.7758425321013279,
806
+ "learning_rate": 9.477340655010717e-07,
807
+ "loss": 0.2462,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 3.026666666666667,
812
+ "grad_norm": 0.5445091023055164,
813
+ "learning_rate": 9.028829858700974e-07,
814
+ "loss": 0.2121,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 3.0533333333333332,
819
+ "grad_norm": 0.5510514051591081,
820
+ "learning_rate": 8.588841019673938e-07,
821
+ "loss": 0.2275,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 3.08,
826
+ "grad_norm": 0.5202810429298531,
827
+ "learning_rate": 8.157608908836071e-07,
828
+ "loss": 0.2256,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 3.1066666666666665,
833
+ "grad_norm": 0.5379078897960086,
834
+ "learning_rate": 7.735363624645712e-07,
835
+ "loss": 0.2324,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 3.1333333333333333,
840
+ "grad_norm": 0.555391252684975,
841
+ "learning_rate": 7.322330470336314e-07,
842
+ "loss": 0.2346,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 3.16,
847
+ "grad_norm": 0.5278075406861451,
848
+ "learning_rate": 6.91872983369826e-07,
849
+ "loss": 0.2174,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 3.1866666666666665,
854
+ "grad_norm": 0.5300345672225109,
855
+ "learning_rate": 6.524777069483526e-07,
856
+ "loss": 0.2195,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 3.2133333333333334,
861
+ "grad_norm": 0.5257442851229531,
862
+ "learning_rate": 6.140682384495902e-07,
863
+ "loss": 0.2267,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 3.24,
868
+ "grad_norm": 0.5144116818126049,
869
+ "learning_rate": 5.766650725428027e-07,
870
+ "loss": 0.214,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 3.2666666666666666,
875
+ "grad_norm": 0.5232689582868187,
876
+ "learning_rate": 5.402881669505164e-07,
877
+ "loss": 0.2224,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 3.2933333333333334,
882
+ "grad_norm": 0.6470873693965277,
883
+ "learning_rate": 5.049569317994013e-07,
884
+ "loss": 0.2409,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 3.32,
889
+ "grad_norm": 0.5215129678968841,
890
+ "learning_rate": 4.70690219263347e-07,
891
+ "loss": 0.2329,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 3.3466666666666667,
896
+ "grad_norm": 0.5717396844375537,
897
+ "learning_rate": 4.3750631350424456e-07,
898
+ "loss": 0.2227,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 3.3733333333333335,
903
+ "grad_norm": 0.5391571843035108,
904
+ "learning_rate": 4.0542292091585447e-07,
905
+ "loss": 0.2228,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 3.4,
910
+ "grad_norm": 0.5898980966011218,
911
+ "learning_rate": 3.7445716067596506e-07,
912
+ "loss": 0.2302,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 3.4266666666666667,
917
+ "grad_norm": 0.6196836811494396,
918
+ "learning_rate": 3.446255556118736e-07,
919
+ "loss": 0.2314,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 3.453333333333333,
924
+ "grad_norm": 0.5347704881318596,
925
+ "learning_rate": 3.1594402338407633e-07,
926
+ "loss": 0.2159,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 3.48,
931
+ "grad_norm": 0.5400379104572814,
932
+ "learning_rate": 2.8842786799286204e-07,
933
+ "loss": 0.2157,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 3.506666666666667,
938
+ "grad_norm": 0.5365556641548208,
939
+ "learning_rate": 2.620917716123444e-07,
940
+ "loss": 0.2345,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 3.533333333333333,
945
+ "grad_norm": 0.5314050088354072,
946
+ "learning_rate": 2.3694978675629476e-07,
947
+ "loss": 0.2156,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 3.56,
952
+ "grad_norm": 0.5207638532257202,
953
+ "learning_rate": 2.1301532877994747e-07,
954
+ "loss": 0.219,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 3.586666666666667,
959
+ "grad_norm": 0.548701782465416,
960
+ "learning_rate": 1.9030116872178317e-07,
961
+ "loss": 0.2347,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 3.6133333333333333,
966
+ "grad_norm": 0.5708205943043683,
967
+ "learning_rate": 1.6881942648911077e-07,
968
+ "loss": 0.2399,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 3.64,
973
+ "grad_norm": 0.5498391265486482,
974
+ "learning_rate": 1.4858156439108097e-07,
975
+ "loss": 0.2297,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 3.6666666666666665,
980
+ "grad_norm": 0.5397111357474363,
981
+ "learning_rate": 1.2959838102258537e-07,
982
+ "loss": 0.228,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 3.6933333333333334,
987
+ "grad_norm": 0.5456438628798215,
988
+ "learning_rate": 1.1188000550230005e-07,
989
+ "loss": 0.2233,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 3.7199999999999998,
994
+ "grad_norm": 0.5189716373881338,
995
+ "learning_rate": 9.54358920679524e-08,
996
+ "loss": 0.22,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 3.7466666666666666,
1001
+ "grad_norm": 0.5610594300912937,
1002
+ "learning_rate": 8.027481503169371e-08,
1003
+ "loss": 0.2459,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 3.7733333333333334,
1008
+ "grad_norm": 0.555284297559337,
1009
+ "learning_rate": 6.640486409826785e-08,
1010
+ "loss": 0.2222,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 3.8,
1015
+ "grad_norm": 0.5299627172027022,
1016
+ "learning_rate": 5.383344004847774e-08,
1017
+ "loss": 0.2239,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 3.8266666666666667,
1022
+ "grad_norm": 0.5574148804810318,
1023
+ "learning_rate": 4.256725079024554e-08,
1024
+ "loss": 0.2355,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 3.8533333333333335,
1029
+ "grad_norm": 0.570255860154233,
1030
+ "learning_rate": 3.261230777938607e-08,
1031
+ "loss": 0.2344,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 3.88,
1036
+ "grad_norm": 0.5297061177413807,
1037
+ "learning_rate": 2.3973922811987295e-08,
1038
+ "loss": 0.2219,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 3.9066666666666667,
1043
+ "grad_norm": 0.5420940922206026,
1044
+ "learning_rate": 1.6656705190125078e-08,
1045
+ "loss": 0.2346,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 3.9333333333333336,
1050
+ "grad_norm": 0.5053476419449484,
1051
+ "learning_rate": 1.0664559262413831e-08,
1052
+ "loss": 0.2116,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 3.96,
1057
+ "grad_norm": 0.5615314464522628,
1058
+ "learning_rate": 6.00068234070772e-09,
1059
+ "loss": 0.225,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 3.986666666666667,
1064
+ "grad_norm": 0.5354216279917976,
1065
+ "learning_rate": 2.6675629940689508e-09,
1066
+ "loss": 0.2277,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 4.0,
1071
+ "grad_norm": 0.7003296689030247,
1072
+ "learning_rate": 6.669797209069018e-10,
1073
+ "loss": 0.2014,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 4.0,
1078
+ "step": 152,
1079
+ "total_flos": 72384894861312.0,
1080
+ "train_loss": 0.3027510484190364,
1081
+ "train_runtime": 4332.047,
1082
+ "train_samples_per_second": 1.106,
1083
+ "train_steps_per_second": 0.035
1084
+ }
1085
+ ],
1086
+ "logging_steps": 1,
1087
+ "max_steps": 152,
1088
+ "num_input_tokens_seen": 0,
1089
+ "num_train_epochs": 4,
1090
+ "save_steps": 200,
1091
+ "stateful_callbacks": {
1092
+ "TrainerControl": {
1093
+ "args": {
1094
+ "should_epoch_stop": false,
1095
+ "should_evaluate": false,
1096
+ "should_log": false,
1097
+ "should_save": true,
1098
+ "should_training_stop": true
1099
+ },
1100
+ "attributes": {}
1101
+ }
1102
+ },
1103
+ "total_flos": 72384894861312.0,
1104
+ "train_batch_size": 1,
1105
+ "trial_name": null,
1106
+ "trial_params": null
1107
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a6cd56a5f18706d7d80d52a1dc0020a6188e225e8a380a39be8013a37402207
3
+ size 8209
training_loss.png ADDED
vocab.json ADDED
The diff for this file is too large to render. See raw diff