Hugging Face's logo

Dikshan1234
/
ScriptSwiftAIV2

Safetensors
Model card Files
xet
 Community
Dikshan1234 commited on
Commit
d0b06c8
·
verified ·
1 Parent(s): e3b39d2

checkpoint-3000 | step 3000 | loss 0.4153 | 7.5% complete

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. checkpoint-3000/README.md +135 -0
  3. checkpoint-3000/adapter_config.json +48 -0
  4. checkpoint-3000/adapter_model.safetensors +3 -0
  5. checkpoint-3000/chat_template.jinja +54 -0
  6. checkpoint-3000/optimizer.pt +3 -0
  7. checkpoint-3000/rng_state.pth +3 -0
  8. checkpoint-3000/scheduler.pt +3 -0
  9. checkpoint-3000/tokenizer.json +3 -0
  10. checkpoint-3000/tokenizer_config.json +30 -0
  11. checkpoint-3000/trainer_state.json +2134 -0
  12. checkpoint-3000/training_args.bin +3 -0
.gitattributes CHANGED
@@ -38,3 +38,4 @@ checkpoint-538/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
  checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
  checkpoint-1797/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
  checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
38
  checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
  checkpoint-1797/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
  checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
+ checkpoint-3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-3000/README.md ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # ScriptSwiftAI v12 (Dikshan)
2
+
3
+ > QLoRA fine-tuned full-stack code generation model by **Dikshan** (India).
4
+ > Covers Python, Django, Flask, FastAPI, React, Next.js, TypeScript, SQL, Docker.
5
+
6
+ ---
7
+
8
+ ## License
9
+
10
+ **CC BY-NC 4.0** — Non-commercial use only. Must credit Dikshan / ScriptSwiftAI.
11
+ https://creativecommons.org/licenses/by-nc/4.0/
12
+
13
+ **Copyright © 2026 Dikshan. All rights reserved.**
14
+
15
+ ---
16
+
17
+ ## Model Details
18
+
19
+ | Property | Value |
20
+ |---|---|
21
+ | **Base Model** | Qwen2.5-Coder-7B-Instruct |
22
+ | **Method** | QLoRA (4-bit, r=64) |
23
+ | **Hardware** | NVIDIA RTX 5070 Ti 16GB |
24
+ | **Target Steps** | 40,000 |
25
+ | **Dataset** | ~450-500k samples (17 datasets) |
26
+ | **Max Length** | 1536 tokens |
27
+ | **Developer** | Dikshan (India) |
28
+ | **Training Started** | June 2026 |
29
+
30
+ ---
31
+
32
+ ## Changelog / Training Timeline
33
+
34
+ *Auto-updated by train_v12.py on every checkpoint save.*
35
+ *Append-only — entries never overwritten. HuggingFace commit history provides timestamps.*
36
+
37
+
38
+ ---
39
+
40
+ ### 🔵 Checkpoint — Step 13
41
+ **Date:** June 22, 2026 at 18:44 IST
42
+ **Checkpoint:** checkpoint-13
43
+ **Step:** 13 / 40,000 (0.0% complete)
44
+ **Loss:** 0.6164
45
+ **Epoch:** 0.000
46
+ **Zone:** 📚 Learning
47
+ **Status:** Training ongoing — auto-uploaded via train_v12.py
48
+
49
+ ---
50
+
51
+ ### 🔵 Checkpoint — Step 25
52
+ **Date:** June 22, 2026 at 18:50 IST
53
+ **Checkpoint:** checkpoint-25
54
+ **Step:** 25 / 40,000 (0.1% complete)
55
+ **Loss:** 0.6057
56
+ **Epoch:** 0.001
57
+ **Zone:** 📚 Learning
58
+ **Status:** Training ongoing — auto-uploaded via train_v12.py
59
+
60
+ ---
61
+
62
+ ### 🔵 Checkpoint — Step 36
63
+ **Date:** June 22, 2026 at 18:58 IST
64
+ **Checkpoint:** checkpoint-36
65
+ **Step:** 36 / 40,000 (0.1% complete)
66
+ **Loss:** 0.5508
67
+ **Epoch:** 0.001
68
+ **Zone:** 📚 Learning
69
+ **Status:** Training ongoing — auto-uploaded via train_v12.py
70
+
71
+ ---
72
+
73
+ ### 🔵 Checkpoint — Step 42
74
+ **Date:** June 22, 2026 at 19:08 IST
75
+ **Checkpoint:** checkpoint-42
76
+ **Step:** 42 / 40,000 (0.1% complete)
77
+ **Loss:** 0.5525
78
+ **Epoch:** 0.001
79
+ **Zone:** 📚 Learning
80
+ **Status:** Training ongoing — auto-uploaded via train_v12.py
81
+
82
+ ---
83
+
84
+ ### 🔵 Checkpoint — Step 538
85
+ **Date:** June 22, 2026 at 23:38 IST
86
+ **Checkpoint:** checkpoint-538
87
+ **Step:** 538 / 40,000 (1.3% complete)
88
+ **Loss:** 0.4087
89
+ **Epoch:** 0.015
90
+ **Zone:** 📈 Good
91
+ **Status:** Training ongoing — auto-uploaded via train_v12.py
92
+
93
+ ---
94
+
95
+ ### 🔵 Checkpoint — Step 1,000
96
+ **Date:** June 23, 2026 at 03:05 IST
97
+ **Checkpoint:** checkpoint-1000
98
+ **Step:** 1,000 / 40,000 (2.5% complete)
99
+ **Loss:** 0.4174
100
+ **Epoch:** 0.029
101
+ **Zone:** 📈 Good
102
+ **Status:** Training ongoing — auto-uploaded via train_v12.py
103
+
104
+ ---
105
+
106
+ ### 🔵 Checkpoint — Step 1,797
107
+ **Date:** June 23, 2026 at 08:26 IST
108
+ **Checkpoint:** checkpoint-1797
109
+ **Step:** 1,797 / 40,000 (4.5% complete)
110
+ **Loss:** 0.3927
111
+ **Epoch:** 0.052
112
+ **Zone:** 📈 Good
113
+ **Status:** Training ongoing — auto-uploaded via train_v12.py
114
+
115
+ ---
116
+
117
+ ### 🔵 Checkpoint — Step 2,000
118
+ **Date:** June 23, 2026 at 09:52 IST
119
+ **Checkpoint:** checkpoint-2000
120
+ **Step:** 2,000 / 40,000 (5.0% complete)
121
+ **Loss:** 0.4383
122
+ **Epoch:** 0.058
123
+ **Zone:** 📈 Good
124
+ **Status:** Training ongoing — auto-uploaded via train_v12.py
125
+
126
+ ---
127
+
128
+ ### 🔵 Checkpoint — Step 3,000
129
+ **Date:** June 23, 2026 at 17:35 IST
130
+ **Checkpoint:** checkpoint-3000
131
+ **Step:** 3,000 / 40,000 (7.5% complete)
132
+ **Loss:** 0.4153
133
+ **Epoch:** 0.088
134
+ **Zone:** 📈 Good
135
+ **Status:** Training ongoing — auto-uploaded via train_v12.py
checkpoint-3000/adapter_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 128,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 64,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "gate_proj",
34
+ "down_proj",
35
+ "q_proj",
36
+ "up_proj",
37
+ "k_proj",
38
+ "v_proj",
39
+ "o_proj"
40
+ ],
41
+ "target_parameters": null,
42
+ "task_type": "CAUSAL_LM",
43
+ "trainable_token_indices": null,
44
+ "use_bdlora": null,
45
+ "use_dora": false,
46
+ "use_qalora": false,
47
+ "use_rslora": false
48
+ }
checkpoint-3000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7b9a34121c7b47d64a31e6dd015378df45f2851c378167d5914725f57136c0f
3
+ size 645975704
checkpoint-3000/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 %}
checkpoint-3000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:082c04c84bfa61f6347e4b7a5fb993fadafa79a17693ce2d7bb0353a1a2d0368
3
+ size 329492947
checkpoint-3000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff7bb38de929f646c83d92d8101a186550cbdc39c190c2b3bea243495141c038
3
+ size 14645
checkpoint-3000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:327e7bb6ae87003fe9bd850a30c17555fd21e8d3e32825d905afb7ecdf2faabf
3
+ size 1465
checkpoint-3000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
3
+ size 11421892
checkpoint-3000/tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>",
11
+ "<|object_ref_start|>",
12
+ "<|object_ref_end|>",
13
+ "<|box_start|>",
14
+ "<|box_end|>",
15
+ "<|quad_start|>",
16
+ "<|quad_end|>",
17
+ "<|vision_start|>",
18
+ "<|vision_end|>",
19
+ "<|vision_pad|>",
20
+ "<|image_pad|>",
21
+ "<|video_pad|>"
22
+ ],
23
+ "is_local": false,
24
+ "local_files_only": false,
25
+ "model_max_length": 32768,
26
+ "pad_token": "<|im_end|>",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "Qwen2Tokenizer",
29
+ "unk_token": null
30
+ }
checkpoint-3000/trainer_state.json ADDED
@@ -0,0 +1,2134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.08663167836089591,
6
+ "eval_steps": 500,
7
+ "global_step": 3000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0002922796166022129,
14
+ "grad_norm": 0.3604201674461365,
15
+ "learning_rate": 1.8e-06,
16
+ "loss": 0.6163836479187011,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.0005845592332044258,
21
+ "grad_norm": 0.307494193315506,
22
+ "learning_rate": 3.8e-06,
23
+ "loss": 0.6056640148162842,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.00014613980830110646,
28
+ "grad_norm": 0.1861964464187622,
29
+ "learning_rate": 5.8e-06,
30
+ "loss": 0.5507771968841553,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.00011691184664088517,
35
+ "grad_norm": 0.18063770234584808,
36
+ "learning_rate": 7.8e-06,
37
+ "loss": 0.5524736642837524,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.0004091914632430981,
42
+ "grad_norm": 0.1831495314836502,
43
+ "learning_rate": 9.800000000000001e-06,
44
+ "loss": 0.5550893783569336,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.000701471079845311,
49
+ "grad_norm": 0.2708336412906647,
50
+ "learning_rate": 1.18e-05,
51
+ "loss": 0.5027066707611084,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.0009937506964475238,
56
+ "grad_norm": 0.16506414115428925,
57
+ "learning_rate": 1.3800000000000002e-05,
58
+ "loss": 0.5025710105895996,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.0012860303130497368,
63
+ "grad_norm": 0.7222521305084229,
64
+ "learning_rate": 1.58e-05,
65
+ "loss": 0.44574794769287107,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.0015783099296519498,
70
+ "grad_norm": 0.3094443678855896,
71
+ "learning_rate": 1.78e-05,
72
+ "loss": 0.463105583190918,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.0018705895462541628,
77
+ "grad_norm": 0.22881925106048584,
78
+ "learning_rate": 1.9800000000000004e-05,
79
+ "loss": 0.47495498657226565,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.0021628691628563755,
84
+ "grad_norm": 0.2994537055492401,
85
+ "learning_rate": 2.18e-05,
86
+ "loss": 0.44906439781188967,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.0024551487794585887,
91
+ "grad_norm": 0.22821807861328125,
92
+ "learning_rate": 2.38e-05,
93
+ "loss": 0.4511695384979248,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.0027474283960608015,
98
+ "grad_norm": 0.23172526061534882,
99
+ "learning_rate": 2.58e-05,
100
+ "loss": 0.45236430168151853,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.003039708012663014,
105
+ "grad_norm": 0.25378280878067017,
106
+ "learning_rate": 2.7800000000000005e-05,
107
+ "loss": 0.49311389923095705,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.0033319876292652274,
112
+ "grad_norm": 0.30715328454971313,
113
+ "learning_rate": 2.98e-05,
114
+ "loss": 0.45659761428833007,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.00362426724586744,
119
+ "grad_norm": 0.2318553328514099,
120
+ "learning_rate": 3.18e-05,
121
+ "loss": 0.48353352546691897,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.003916546862469653,
126
+ "grad_norm": 0.3422481417655945,
127
+ "learning_rate": 3.38e-05,
128
+ "loss": 0.48243284225463867,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.004208826479071866,
133
+ "grad_norm": 0.2627033591270447,
134
+ "learning_rate": 3.58e-05,
135
+ "loss": 0.44968676567077637,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.004501106095674079,
140
+ "grad_norm": 0.270560622215271,
141
+ "learning_rate": 3.7800000000000004e-05,
142
+ "loss": 0.43050732612609866,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.004793385712276292,
147
+ "grad_norm": 0.29916077852249146,
148
+ "learning_rate": 3.9800000000000005e-05,
149
+ "loss": 0.38156795501708984,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.005085665328878505,
154
+ "grad_norm": 0.29618600010871887,
155
+ "learning_rate": 4.18e-05,
156
+ "loss": 0.41876654624938964,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.005377944945480718,
161
+ "grad_norm": 0.24618731439113617,
162
+ "learning_rate": 4.38e-05,
163
+ "loss": 0.4200754642486572,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.00567022456208293,
168
+ "grad_norm": 0.4028846323490143,
169
+ "learning_rate": 4.58e-05,
170
+ "loss": 0.4128837585449219,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.0059625041786851435,
175
+ "grad_norm": 0.2899196445941925,
176
+ "learning_rate": 4.78e-05,
177
+ "loss": 0.4727485656738281,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.006254783795287357,
182
+ "grad_norm": 0.372092068195343,
183
+ "learning_rate": 4.9800000000000004e-05,
184
+ "loss": 0.3837599754333496,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.00654706341188957,
189
+ "grad_norm": 0.27367591857910156,
190
+ "learning_rate": 5.1800000000000005e-05,
191
+ "loss": 0.4533690929412842,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.006839343028491782,
196
+ "grad_norm": 0.2826191782951355,
197
+ "learning_rate": 5.380000000000001e-05,
198
+ "loss": 0.5056231021881104,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.007131622645093995,
203
+ "grad_norm": 0.34035593271255493,
204
+ "learning_rate": 5.580000000000001e-05,
205
+ "loss": 0.4258269309997559,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.0074239022616962086,
210
+ "grad_norm": 0.2767459750175476,
211
+ "learning_rate": 5.7799999999999995e-05,
212
+ "loss": 0.3629124641418457,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.007716181878298421,
217
+ "grad_norm": 0.2805218994617462,
218
+ "learning_rate": 5.9800000000000003e-05,
219
+ "loss": 0.35598738193511964,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.008008461494900634,
224
+ "grad_norm": 0.32115164399147034,
225
+ "learning_rate": 6.18e-05,
226
+ "loss": 0.45623183250427246,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.008300741111502847,
231
+ "grad_norm": 0.25464335083961487,
232
+ "learning_rate": 6.38e-05,
233
+ "loss": 0.3766467809677124,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.00859302072810506,
238
+ "grad_norm": 0.240229070186615,
239
+ "learning_rate": 6.58e-05,
240
+ "loss": 0.4206503391265869,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.008885300344707274,
245
+ "grad_norm": 0.24640053510665894,
246
+ "learning_rate": 6.780000000000001e-05,
247
+ "loss": 0.42534866333007815,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.009177579961309485,
252
+ "grad_norm": 0.22595764696598053,
253
+ "learning_rate": 6.98e-05,
254
+ "loss": 0.4169299602508545,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.009469859577911698,
259
+ "grad_norm": 0.2035064995288849,
260
+ "learning_rate": 7.18e-05,
261
+ "loss": 0.36454784870147705,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.009762139194513911,
266
+ "grad_norm": 0.21908830106258392,
267
+ "learning_rate": 7.38e-05,
268
+ "loss": 0.39443838596343994,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.010054418811116125,
273
+ "grad_norm": 0.2039889395236969,
274
+ "learning_rate": 7.58e-05,
275
+ "loss": 0.4549224853515625,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.010346698427718338,
280
+ "grad_norm": 0.24606066942214966,
281
+ "learning_rate": 7.780000000000001e-05,
282
+ "loss": 0.3763291835784912,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.010638978044320551,
287
+ "grad_norm": 0.4349507689476013,
288
+ "learning_rate": 7.98e-05,
289
+ "loss": 0.42160859107971194,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.010931257660922762,
294
+ "grad_norm": 0.2086913138628006,
295
+ "learning_rate": 8.18e-05,
296
+ "loss": 0.4335451126098633,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.011223537277524976,
301
+ "grad_norm": 0.21672461926937103,
302
+ "learning_rate": 8.38e-05,
303
+ "loss": 0.39824934005737306,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.011515816894127189,
308
+ "grad_norm": 0.34380897879600525,
309
+ "learning_rate": 8.58e-05,
310
+ "loss": 0.4544211387634277,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.011808096510729402,
315
+ "grad_norm": 0.2024194449186325,
316
+ "learning_rate": 8.78e-05,
317
+ "loss": 0.4060193061828613,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.012100376127331615,
322
+ "grad_norm": 0.22563715279102325,
323
+ "learning_rate": 8.98e-05,
324
+ "loss": 0.3707286834716797,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.012392655743933828,
329
+ "grad_norm": 0.20325998961925507,
330
+ "learning_rate": 9.180000000000001e-05,
331
+ "loss": 0.37896702289581297,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.012684935360536042,
336
+ "grad_norm": 0.20927369594573975,
337
+ "learning_rate": 9.38e-05,
338
+ "loss": 0.4257774829864502,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.012977214977138253,
343
+ "grad_norm": 0.2156561017036438,
344
+ "learning_rate": 9.58e-05,
345
+ "loss": 0.33562607765197755,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.013269494593740466,
350
+ "grad_norm": 0.17501753568649292,
351
+ "learning_rate": 9.78e-05,
352
+ "loss": 0.4147501945495605,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.01356177421034268,
357
+ "grad_norm": 0.243160679936409,
358
+ "learning_rate": 9.98e-05,
359
+ "loss": 0.411363410949707,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.013854053826944893,
364
+ "grad_norm": 0.2272544652223587,
365
+ "learning_rate": 0.00010180000000000001,
366
+ "loss": 0.36809728145599363,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.014146333443547106,
371
+ "grad_norm": 0.2265583574771881,
372
+ "learning_rate": 0.0001038,
373
+ "loss": 0.352154016494751,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.014438613060149319,
378
+ "grad_norm": 0.21968695521354675,
379
+ "learning_rate": 0.00010580000000000001,
380
+ "loss": 0.40874533653259276,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.01473089267675153,
385
+ "grad_norm": 0.20146295428276062,
386
+ "learning_rate": 0.00010780000000000002,
387
+ "loss": 0.4024982452392578,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.015023172293353744,
392
+ "grad_norm": 0.22711141407489777,
393
+ "learning_rate": 0.00010980000000000001,
394
+ "loss": 0.412246561050415,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.015315451909955957,
399
+ "grad_norm": 0.2056141048669815,
400
+ "learning_rate": 0.00011180000000000002,
401
+ "loss": 0.4331079006195068,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.01560773152655817,
406
+ "grad_norm": 0.18964128196239471,
407
+ "learning_rate": 0.0001138,
408
+ "loss": 0.4245738506317139,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.01590001114316038,
413
+ "grad_norm": 0.18264859914779663,
414
+ "learning_rate": 0.0001158,
415
+ "loss": 0.3981050491333008,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.016192290759762595,
420
+ "grad_norm": 0.198320671916008,
421
+ "learning_rate": 0.0001178,
422
+ "loss": 0.44843344688415526,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.016484570376364808,
427
+ "grad_norm": 0.20583713054656982,
428
+ "learning_rate": 0.0001198,
429
+ "loss": 0.45852208137512207,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.01677684999296702,
434
+ "grad_norm": 0.18764640390872955,
435
+ "learning_rate": 0.0001218,
436
+ "loss": 0.39210479259490966,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.017069129609569234,
441
+ "grad_norm": 0.22744227945804596,
442
+ "learning_rate": 0.0001238,
443
+ "loss": 0.48337244987487793,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.017361409226171447,
448
+ "grad_norm": 0.25332197546958923,
449
+ "learning_rate": 0.0001258,
450
+ "loss": 0.47956342697143556,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.01765368884277366,
455
+ "grad_norm": 0.18094617128372192,
456
+ "learning_rate": 0.00012780000000000002,
457
+ "loss": 0.36708922386169435,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.017945968459375874,
462
+ "grad_norm": 0.2056637406349182,
463
+ "learning_rate": 0.0001298,
464
+ "loss": 0.45494647026062013,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.018238248075978087,
469
+ "grad_norm": 0.18681053817272186,
470
+ "learning_rate": 0.0001318,
471
+ "loss": 0.39863851070404055,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.0185305276925803,
476
+ "grad_norm": 0.18398210406303406,
477
+ "learning_rate": 0.00013380000000000003,
478
+ "loss": 0.42660346031188967,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.018822807309182513,
483
+ "grad_norm": 0.2018873244524002,
484
+ "learning_rate": 0.00013580000000000002,
485
+ "loss": 0.41592912673950194,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.019115086925784727,
490
+ "grad_norm": 0.20749719440937042,
491
+ "learning_rate": 0.0001378,
492
+ "loss": 0.4529616355895996,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.01940736654238694,
497
+ "grad_norm": 0.17765171825885773,
498
+ "learning_rate": 0.0001398,
499
+ "loss": 0.4367457389831543,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.01969964615898915,
504
+ "grad_norm": 0.24419377744197845,
505
+ "learning_rate": 0.0001418,
506
+ "loss": 0.4324330806732178,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.019991925775591363,
511
+ "grad_norm": 0.1319461613893509,
512
+ "learning_rate": 0.0001438,
513
+ "loss": 0.38980741500854493,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.020284205392193576,
518
+ "grad_norm": 0.18414747714996338,
519
+ "learning_rate": 0.0001458,
520
+ "loss": 0.45140395164489744,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.02057648500879579,
525
+ "grad_norm": 0.19065886735916138,
526
+ "learning_rate": 0.00014780000000000001,
527
+ "loss": 0.34149444103240967,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.020868764625398002,
532
+ "grad_norm": 0.3047577738761902,
533
+ "learning_rate": 0.0001498,
534
+ "loss": 0.39748594760894773,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.021161044242000215,
539
+ "grad_norm": 0.20547902584075928,
540
+ "learning_rate": 0.0001518,
541
+ "loss": 0.35707693099975585,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.02145332385860243,
546
+ "grad_norm": 0.1835167109966278,
547
+ "learning_rate": 0.0001538,
548
+ "loss": 0.3866844177246094,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.021745603475204642,
553
+ "grad_norm": 0.12297193706035614,
554
+ "learning_rate": 0.00015580000000000002,
555
+ "loss": 0.3809194803237915,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.022037883091806855,
560
+ "grad_norm": 0.23474228382110596,
561
+ "learning_rate": 0.00015780000000000001,
562
+ "loss": 0.40447239875793456,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.022330162708409068,
567
+ "grad_norm": 0.1950707882642746,
568
+ "learning_rate": 0.0001598,
569
+ "loss": 0.36057252883911134,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.02262244232501128,
574
+ "grad_norm": 0.19598263502120972,
575
+ "learning_rate": 0.00016180000000000003,
576
+ "loss": 0.3532793760299683,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.022914721941613495,
581
+ "grad_norm": 0.21619845926761627,
582
+ "learning_rate": 0.0001638,
583
+ "loss": 0.33423144817352296,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.023207001558215708,
588
+ "grad_norm": 0.1934775710105896,
589
+ "learning_rate": 0.0001658,
590
+ "loss": 0.4006977558135986,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.023499281174817917,
595
+ "grad_norm": 0.2345370650291443,
596
+ "learning_rate": 0.0001678,
597
+ "loss": 0.42209348678588865,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.02379156079142013,
602
+ "grad_norm": 0.2699654698371887,
603
+ "learning_rate": 0.0001698,
604
+ "loss": 0.3334143400192261,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.024083840408022344,
609
+ "grad_norm": 0.1839752197265625,
610
+ "learning_rate": 0.0001718,
611
+ "loss": 0.42084970474243166,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.024376120024624557,
616
+ "grad_norm": 0.22491669654846191,
617
+ "learning_rate": 0.0001738,
618
+ "loss": 0.420766544342041,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.02466839964122677,
623
+ "grad_norm": 0.18370424211025238,
624
+ "learning_rate": 0.00017580000000000002,
625
+ "loss": 0.3486522912979126,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.024960679257828983,
630
+ "grad_norm": 0.23166073858737946,
631
+ "learning_rate": 0.0001778,
632
+ "loss": 0.42749767303466796,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.025252958874431197,
637
+ "grad_norm": 0.22481808066368103,
638
+ "learning_rate": 0.0001798,
639
+ "loss": 0.380033016204834,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.02554523849103341,
644
+ "grad_norm": 0.24065051972866058,
645
+ "learning_rate": 0.00018180000000000003,
646
+ "loss": 0.45965576171875,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.025837518107635623,
651
+ "grad_norm": 0.190377876162529,
652
+ "learning_rate": 0.00018380000000000002,
653
+ "loss": 0.3290415287017822,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.026129797724237836,
658
+ "grad_norm": 0.2699977159500122,
659
+ "learning_rate": 0.00018580000000000002,
660
+ "loss": 0.4352889537811279,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.02642207734084005,
665
+ "grad_norm": 0.2756347060203552,
666
+ "learning_rate": 0.0001878,
667
+ "loss": 0.4288458347320557,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.026714356957442262,
672
+ "grad_norm": 0.23565548658370972,
673
+ "learning_rate": 0.0001898,
674
+ "loss": 0.29646151065826415,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.027006636574044476,
679
+ "grad_norm": 0.18665672838687897,
680
+ "learning_rate": 0.0001918,
681
+ "loss": 0.39093432426452634,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.027298916190646685,
686
+ "grad_norm": 0.24153801798820496,
687
+ "learning_rate": 0.0001938,
688
+ "loss": 0.42369751930236815,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.0275911958072489,
693
+ "grad_norm": 0.18671485781669617,
694
+ "learning_rate": 0.00019580000000000002,
695
+ "loss": 0.38338029384613037,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.027883475423851112,
700
+ "grad_norm": 0.2615300118923187,
701
+ "learning_rate": 0.0001978,
702
+ "loss": 0.36945343017578125,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.028175755040453325,
707
+ "grad_norm": 0.2992021143436432,
708
+ "learning_rate": 0.0001998,
709
+ "loss": 0.4174357891082764,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.028468034657055538,
714
+ "grad_norm": 0.27294614911079407,
715
+ "learning_rate": 0.00019999997371998945,
716
+ "loss": 0.38078644275665285,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.02876031427365775,
721
+ "grad_norm": 0.22782108187675476,
722
+ "learning_rate": 0.0001999998828755262,
723
+ "loss": 0.41697354316711427,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.029052593890259965,
728
+ "grad_norm": 0.20225366950035095,
729
+ "learning_rate": 0.00019999972714222465,
730
+ "loss": 0.38390820026397704,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.029344873506862178,
735
+ "grad_norm": 0.22823745012283325,
736
+ "learning_rate": 0.00019999950652018584,
737
+ "loss": 0.41745734214782715,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.02963715312346439,
742
+ "grad_norm": 0.2649468183517456,
743
+ "learning_rate": 0.0001999992210095529,
744
+ "loss": 0.4053181648254395,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.029929432740066604,
749
+ "grad_norm": 0.21082913875579834,
750
+ "learning_rate": 0.00019999887061051115,
751
+ "loss": 0.41599574089050295,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.030221712356668817,
756
+ "grad_norm": 0.2594168782234192,
757
+ "learning_rate": 0.00019999845532328792,
758
+ "loss": 0.4727328777313232,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.03051399197327103,
763
+ "grad_norm": 0.19130517542362213,
764
+ "learning_rate": 0.0001999979751481527,
765
+ "loss": 0.42589612007141114,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.030806271589873244,
770
+ "grad_norm": 0.2338467836380005,
771
+ "learning_rate": 0.00019999743008541709,
772
+ "loss": 0.3404257774353027,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.031098551206475453,
777
+ "grad_norm": 0.2450529932975769,
778
+ "learning_rate": 0.00019999682013543474,
779
+ "loss": 0.35564963817596434,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.03139083082307767,
784
+ "grad_norm": 0.24461933970451355,
785
+ "learning_rate": 0.00019999614529860144,
786
+ "loss": 0.39687209129333495,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.03168311043967988,
791
+ "grad_norm": 0.23187988996505737,
792
+ "learning_rate": 0.0001999954055753551,
793
+ "loss": 0.41315088272094724,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.031975390056282096,
798
+ "grad_norm": 0.22851324081420898,
799
+ "learning_rate": 0.00019999460096617572,
800
+ "loss": 0.32306632995605467,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.03226766967288431,
805
+ "grad_norm": 0.18886074423789978,
806
+ "learning_rate": 0.00019999373147158543,
807
+ "loss": 0.3556957244873047,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.03255994928948652,
812
+ "grad_norm": 0.1941390335559845,
813
+ "learning_rate": 0.00019999279709214838,
814
+ "loss": 0.42602267265319826,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.03285222890608873,
819
+ "grad_norm": 0.2191803753376007,
820
+ "learning_rate": 0.00019999179782847088,
821
+ "loss": 0.3481628656387329,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.03314450852269094,
826
+ "grad_norm": 0.27078554034233093,
827
+ "learning_rate": 0.0001999907336812014,
828
+ "loss": 0.3957390785217285,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.033436788139293155,
833
+ "grad_norm": 0.31014931201934814,
834
+ "learning_rate": 0.00019998960465103042,
835
+ "loss": 0.3879474878311157,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.03372906775589537,
840
+ "grad_norm": 0.1903751790523529,
841
+ "learning_rate": 0.00019998841073869055,
842
+ "loss": 0.42315473556518557,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.03402134737249758,
847
+ "grad_norm": 0.2546682357788086,
848
+ "learning_rate": 0.0001999871519449565,
849
+ "loss": 0.36317920684814453,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.034313626989099795,
854
+ "grad_norm": 0.1552298665046692,
855
+ "learning_rate": 0.0001999858282706451,
856
+ "loss": 0.36159753799438477,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.03460590660570201,
861
+ "grad_norm": 0.19712704420089722,
862
+ "learning_rate": 0.00019998443971661525,
863
+ "loss": 0.3884085416793823,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.03489818622230422,
868
+ "grad_norm": 0.2729942500591278,
869
+ "learning_rate": 0.000199982986283768,
870
+ "loss": 0.4681094169616699,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 0.035190465838906435,
875
+ "grad_norm": 0.1953604519367218,
876
+ "learning_rate": 0.00019998146797304642,
877
+ "loss": 0.34714839458465574,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 0.03548274545550865,
882
+ "grad_norm": 0.2132028043270111,
883
+ "learning_rate": 0.0001999798847854358,
884
+ "loss": 0.4187171936035156,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 0.03577502507211086,
889
+ "grad_norm": 0.21808749437332153,
890
+ "learning_rate": 0.0001999782367219634,
891
+ "loss": 0.4529675006866455,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 0.036067304688713074,
896
+ "grad_norm": 0.2665892541408539,
897
+ "learning_rate": 0.0001999765237836986,
898
+ "loss": 0.40354113578796386,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 0.03635958430531529,
903
+ "grad_norm": 0.18756791949272156,
904
+ "learning_rate": 0.00019997474597175302,
905
+ "loss": 0.33424665927886965,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 0.0366518639219175,
910
+ "grad_norm": 0.23514626920223236,
911
+ "learning_rate": 0.00019997290328728013,
912
+ "loss": 0.34480867385864256,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 0.036944143538519714,
917
+ "grad_norm": 0.24087919294834137,
918
+ "learning_rate": 0.0001999709957314757,
919
+ "loss": 0.40560035705566405,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 0.03723642315512193,
924
+ "grad_norm": 0.1967712640762329,
925
+ "learning_rate": 0.0001999690233055775,
926
+ "loss": 0.4166306495666504,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 0.03752870277172414,
931
+ "grad_norm": 0.22088399529457092,
932
+ "learning_rate": 0.00019996698601086545,
933
+ "loss": 0.4286780834197998,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 0.03782098238832635,
938
+ "grad_norm": 0.21077096462249756,
939
+ "learning_rate": 0.0001999648838486615,
940
+ "loss": 0.3549200534820557,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 0.038113262004928566,
945
+ "grad_norm": 0.2842172682285309,
946
+ "learning_rate": 0.0001999627168203297,
947
+ "loss": 0.4626432418823242,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 0.03840554162153078,
952
+ "grad_norm": 0.23517769575119019,
953
+ "learning_rate": 0.00019996048492727626,
954
+ "loss": 0.39797124862670896,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 0.03869782123813299,
959
+ "grad_norm": 0.22531968355178833,
960
+ "learning_rate": 0.0001999581881709494,
961
+ "loss": 0.39006221294403076,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 0.038990100854735206,
966
+ "grad_norm": 0.1859465092420578,
967
+ "learning_rate": 0.00019995582655283944,
968
+ "loss": 0.3752875804901123,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 0.03928238047133742,
973
+ "grad_norm": 0.1793965846300125,
974
+ "learning_rate": 0.00019995340007447884,
975
+ "loss": 0.3678503751754761,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 0.03957466008793963,
980
+ "grad_norm": 0.1874365508556366,
981
+ "learning_rate": 0.00019995090873744213,
982
+ "loss": 0.40687713623046873,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 0.039866939704541846,
987
+ "grad_norm": 0.22492875158786774,
988
+ "learning_rate": 0.00019994835254334592,
989
+ "loss": 0.3897545337677002,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 0.04015921932114406,
994
+ "grad_norm": 0.29545730352401733,
995
+ "learning_rate": 0.00019994573149384882,
996
+ "loss": 0.4935605049133301,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 0.040451498937746265,
1001
+ "grad_norm": 0.20854443311691284,
1002
+ "learning_rate": 0.00019994304559065168,
1003
+ "loss": 0.33220815658569336,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 0.04074377855434848,
1008
+ "grad_norm": 0.20468345284461975,
1009
+ "learning_rate": 0.0001999402948354973,
1010
+ "loss": 0.3795356035232544,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 0.04103605817095069,
1015
+ "grad_norm": 0.29992666840553284,
1016
+ "learning_rate": 0.00019993747923017065,
1017
+ "loss": 0.43836030960083006,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 0.041328337787552905,
1022
+ "grad_norm": 0.27834489941596985,
1023
+ "learning_rate": 0.0001999345987764987,
1024
+ "loss": 0.3854727029800415,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 0.04162061740415512,
1029
+ "grad_norm": 0.19028784334659576,
1030
+ "learning_rate": 0.00019993165347635062,
1031
+ "loss": 0.48855161666870117,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 0.04191289702075733,
1036
+ "grad_norm": 0.2719208002090454,
1037
+ "learning_rate": 0.00019992864333163754,
1038
+ "loss": 0.34480597972869875,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 0.042205176637359544,
1043
+ "grad_norm": 0.2201714962720871,
1044
+ "learning_rate": 0.0001999255683443127,
1045
+ "loss": 0.45578484535217284,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 0.04249745625396176,
1050
+ "grad_norm": 0.2917408049106598,
1051
+ "learning_rate": 0.00019992242851637145,
1052
+ "loss": 0.45635452270507815,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 0.04278973587056397,
1057
+ "grad_norm": 0.20707593858242035,
1058
+ "learning_rate": 0.00019991922384985115,
1059
+ "loss": 0.4358846187591553,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 0.043082015487166184,
1064
+ "grad_norm": 0.2693732976913452,
1065
+ "learning_rate": 0.00019991595434683132,
1066
+ "loss": 0.393514084815979,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 0.0433742951037684,
1071
+ "grad_norm": 0.192472904920578,
1072
+ "learning_rate": 0.0001999126200094335,
1073
+ "loss": 0.36677262783050535,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 0.04366657472037061,
1078
+ "grad_norm": 0.1903146505355835,
1079
+ "learning_rate": 0.00019990922083982127,
1080
+ "loss": 0.3809571504592896,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 0.04395885433697282,
1085
+ "grad_norm": 0.18778850138187408,
1086
+ "learning_rate": 0.00019990575684020035,
1087
+ "loss": 0.3991628885269165,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 0.044251133953575036,
1092
+ "grad_norm": 0.17295020818710327,
1093
+ "learning_rate": 0.00019990222801281844,
1094
+ "loss": 0.34786784648895264,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 0.04454341357017725,
1099
+ "grad_norm": 0.21790063381195068,
1100
+ "learning_rate": 0.00019989863435996544,
1101
+ "loss": 0.4168230533599854,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 0.04483569318677946,
1106
+ "grad_norm": 0.1902916580438614,
1107
+ "learning_rate": 0.00019989497588397318,
1108
+ "loss": 0.3928706169128418,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 0.045127972803381676,
1113
+ "grad_norm": 0.21699456870555878,
1114
+ "learning_rate": 0.0001998912525872156,
1115
+ "loss": 0.27401630878448485,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 0.04542025241998389,
1120
+ "grad_norm": 0.2811727821826935,
1121
+ "learning_rate": 0.00019988746447210872,
1122
+ "loss": 0.37927000522613524,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 0.0457125320365861,
1127
+ "grad_norm": 0.2877182364463806,
1128
+ "learning_rate": 0.0001998836115411106,
1129
+ "loss": 0.37084925174713135,
1130
+ "step": 1600
1131
+ },
1132
+ {
1133
+ "epoch": 0.046004811653188316,
1134
+ "grad_norm": 0.30798202753067017,
1135
+ "learning_rate": 0.00019987969379672138,
1136
+ "loss": 0.3814183950424194,
1137
+ "step": 1610
1138
+ },
1139
+ {
1140
+ "epoch": 0.04629709126979053,
1141
+ "grad_norm": 0.23142924904823303,
1142
+ "learning_rate": 0.00019987571124148326,
1143
+ "loss": 0.4828189849853516,
1144
+ "step": 1620
1145
+ },
1146
+ {
1147
+ "epoch": 0.04658937088639274,
1148
+ "grad_norm": 0.26372772455215454,
1149
+ "learning_rate": 0.00019987166387798043,
1150
+ "loss": 0.40070490837097167,
1151
+ "step": 1630
1152
+ },
1153
+ {
1154
+ "epoch": 0.046881650502994955,
1155
+ "grad_norm": 0.20170119404792786,
1156
+ "learning_rate": 0.00019986755170883918,
1157
+ "loss": 0.4609227657318115,
1158
+ "step": 1640
1159
+ },
1160
+ {
1161
+ "epoch": 0.04717393011959717,
1162
+ "grad_norm": 0.22828887403011322,
1163
+ "learning_rate": 0.0001998633747367279,
1164
+ "loss": 0.3876612186431885,
1165
+ "step": 1650
1166
+ },
1167
+ {
1168
+ "epoch": 0.04746620973619938,
1169
+ "grad_norm": 0.28497815132141113,
1170
+ "learning_rate": 0.00019985913296435693,
1171
+ "loss": 0.4488811016082764,
1172
+ "step": 1660
1173
+ },
1174
+ {
1175
+ "epoch": 0.047758489352801595,
1176
+ "grad_norm": 0.2250206023454666,
1177
+ "learning_rate": 0.00019985482639447874,
1178
+ "loss": 0.3711233615875244,
1179
+ "step": 1670
1180
+ },
1181
+ {
1182
+ "epoch": 0.0480507689694038,
1183
+ "grad_norm": 0.2564453184604645,
1184
+ "learning_rate": 0.00019985045502988785,
1185
+ "loss": 0.4409325122833252,
1186
+ "step": 1680
1187
+ },
1188
+ {
1189
+ "epoch": 0.048343048586006014,
1190
+ "grad_norm": 0.22390565276145935,
1191
+ "learning_rate": 0.00019984601887342073,
1192
+ "loss": 0.3880199432373047,
1193
+ "step": 1690
1194
+ },
1195
+ {
1196
+ "epoch": 0.04863532820260823,
1197
+ "grad_norm": 0.18111835420131683,
1198
+ "learning_rate": 0.00019984151792795595,
1199
+ "loss": 0.3191307783126831,
1200
+ "step": 1700
1201
+ },
1202
+ {
1203
+ "epoch": 0.04892760781921044,
1204
+ "grad_norm": 0.27317941188812256,
1205
+ "learning_rate": 0.00019983695219641417,
1206
+ "loss": 0.36649317741394044,
1207
+ "step": 1710
1208
+ },
1209
+ {
1210
+ "epoch": 0.049219887435812654,
1211
+ "grad_norm": 0.23256099224090576,
1212
+ "learning_rate": 0.000199832321681758,
1213
+ "loss": 0.4021451950073242,
1214
+ "step": 1720
1215
+ },
1216
+ {
1217
+ "epoch": 0.04951216705241487,
1218
+ "grad_norm": 0.20527933537960052,
1219
+ "learning_rate": 0.00019982762638699218,
1220
+ "loss": 0.36731953620910646,
1221
+ "step": 1730
1222
+ },
1223
+ {
1224
+ "epoch": 0.04980444666901708,
1225
+ "grad_norm": 0.2149372100830078,
1226
+ "learning_rate": 0.00019982286631516343,
1227
+ "loss": 0.38255355358123777,
1228
+ "step": 1740
1229
+ },
1230
+ {
1231
+ "epoch": 0.05009672628561929,
1232
+ "grad_norm": 0.1913089156150818,
1233
+ "learning_rate": 0.00019981804146936046,
1234
+ "loss": 0.4117907524108887,
1235
+ "step": 1750
1236
+ },
1237
+ {
1238
+ "epoch": 0.050389005902221506,
1239
+ "grad_norm": 0.2972666621208191,
1240
+ "learning_rate": 0.0001998131518527141,
1241
+ "loss": 0.39761054515838623,
1242
+ "step": 1760
1243
+ },
1244
+ {
1245
+ "epoch": 0.05068128551882372,
1246
+ "grad_norm": 0.21348360180854797,
1247
+ "learning_rate": 0.00019980819746839715,
1248
+ "loss": 0.4208479404449463,
1249
+ "step": 1770
1250
+ },
1251
+ {
1252
+ "epoch": 0.05097356513542593,
1253
+ "grad_norm": 0.21910355985164642,
1254
+ "learning_rate": 0.00019980317831962447,
1255
+ "loss": 0.45781354904174804,
1256
+ "step": 1780
1257
+ },
1258
+ {
1259
+ "epoch": 0.051265844752028146,
1260
+ "grad_norm": 0.29217293858528137,
1261
+ "learning_rate": 0.00019979809440965292,
1262
+ "loss": 0.392667555809021,
1263
+ "step": 1790
1264
+ },
1265
+ {
1266
+ "epoch": 0.05155812436863036,
1267
+ "grad_norm": 0.2685600221157074,
1268
+ "learning_rate": 0.0001997929457417814,
1269
+ "loss": 0.3381932020187378,
1270
+ "step": 1800
1271
+ },
1272
+ {
1273
+ "epoch": 0.05185040398523257,
1274
+ "grad_norm": 0.208404079079628,
1275
+ "learning_rate": 0.00019978773231935085,
1276
+ "loss": 0.3530620574951172,
1277
+ "step": 1810
1278
+ },
1279
+ {
1280
+ "epoch": 0.052142683601834786,
1281
+ "grad_norm": 0.23994538187980652,
1282
+ "learning_rate": 0.00019978245414574417,
1283
+ "loss": 0.38266212940216066,
1284
+ "step": 1820
1285
+ },
1286
+ {
1287
+ "epoch": 0.052434963218437,
1288
+ "grad_norm": 0.3314270079135895,
1289
+ "learning_rate": 0.0001997771112243863,
1290
+ "loss": 0.37249245643615725,
1291
+ "step": 1830
1292
+ },
1293
+ {
1294
+ "epoch": 0.05272724283503921,
1295
+ "grad_norm": 0.3160709738731384,
1296
+ "learning_rate": 0.0001997717035587442,
1297
+ "loss": 0.4115762233734131,
1298
+ "step": 1840
1299
+ },
1300
+ {
1301
+ "epoch": 0.053019522451641425,
1302
+ "grad_norm": 0.20398829877376556,
1303
+ "learning_rate": 0.00019976623115232692,
1304
+ "loss": 0.4115797996520996,
1305
+ "step": 1850
1306
+ },
1307
+ {
1308
+ "epoch": 0.05331180206824364,
1309
+ "grad_norm": 0.24112626910209656,
1310
+ "learning_rate": 0.00019976069400868534,
1311
+ "loss": 0.3800527811050415,
1312
+ "step": 1860
1313
+ },
1314
+ {
1315
+ "epoch": 0.05360408168484585,
1316
+ "grad_norm": 0.3240782618522644,
1317
+ "learning_rate": 0.00019975509213141255,
1318
+ "loss": 0.4142290115356445,
1319
+ "step": 1870
1320
+ },
1321
+ {
1322
+ "epoch": 0.053896361301448065,
1323
+ "grad_norm": 0.27430611848831177,
1324
+ "learning_rate": 0.0001997494255241435,
1325
+ "loss": 0.42593750953674314,
1326
+ "step": 1880
1327
+ },
1328
+ {
1329
+ "epoch": 0.05418864091805028,
1330
+ "grad_norm": 0.2675989270210266,
1331
+ "learning_rate": 0.00019974369419055514,
1332
+ "loss": 0.35791664123535155,
1333
+ "step": 1890
1334
+ },
1335
+ {
1336
+ "epoch": 0.05448092053465249,
1337
+ "grad_norm": 0.217862069606781,
1338
+ "learning_rate": 0.00019973789813436656,
1339
+ "loss": 0.42203755378723146,
1340
+ "step": 1900
1341
+ },
1342
+ {
1343
+ "epoch": 0.054773200151254704,
1344
+ "grad_norm": 0.20300687849521637,
1345
+ "learning_rate": 0.00019973203735933873,
1346
+ "loss": 0.3735295534133911,
1347
+ "step": 1910
1348
+ },
1349
+ {
1350
+ "epoch": 0.05506547976785692,
1351
+ "grad_norm": 0.24305196106433868,
1352
+ "learning_rate": 0.0001997261118692746,
1353
+ "loss": 0.3854319334030151,
1354
+ "step": 1920
1355
+ },
1356
+ {
1357
+ "epoch": 0.05535775938445913,
1358
+ "grad_norm": 0.17744389176368713,
1359
+ "learning_rate": 0.0001997201216680192,
1360
+ "loss": 0.3821631908416748,
1361
+ "step": 1930
1362
+ },
1363
+ {
1364
+ "epoch": 0.055650039001061344,
1365
+ "grad_norm": 0.28994235396385193,
1366
+ "learning_rate": 0.0001997140667594595,
1367
+ "loss": 0.36383843421936035,
1368
+ "step": 1940
1369
+ },
1370
+ {
1371
+ "epoch": 0.05594231861766355,
1372
+ "grad_norm": 0.21803227066993713,
1373
+ "learning_rate": 0.00019970794714752445,
1374
+ "loss": 0.4005745410919189,
1375
+ "step": 1950
1376
+ },
1377
+ {
1378
+ "epoch": 0.05623459823426576,
1379
+ "grad_norm": 0.22061172127723694,
1380
+ "learning_rate": 0.00019970176283618503,
1381
+ "loss": 0.42282872200012206,
1382
+ "step": 1960
1383
+ },
1384
+ {
1385
+ "epoch": 0.056526877850867976,
1386
+ "grad_norm": 0.20922382175922394,
1387
+ "learning_rate": 0.00019969551382945414,
1388
+ "loss": 0.34180996417999265,
1389
+ "step": 1970
1390
+ },
1391
+ {
1392
+ "epoch": 0.05681915746747019,
1393
+ "grad_norm": 0.21188782155513763,
1394
+ "learning_rate": 0.00019968920013138671,
1395
+ "loss": 0.3581382751464844,
1396
+ "step": 1980
1397
+ },
1398
+ {
1399
+ "epoch": 0.0571114370840724,
1400
+ "grad_norm": 0.19657376408576965,
1401
+ "learning_rate": 0.00019968282174607962,
1402
+ "loss": 0.35428762435913086,
1403
+ "step": 1990
1404
+ },
1405
+ {
1406
+ "epoch": 0.057403716700674616,
1407
+ "grad_norm": 0.20557129383087158,
1408
+ "learning_rate": 0.00019967637867767172,
1409
+ "loss": 0.4382596969604492,
1410
+ "step": 2000
1411
+ },
1412
+ {
1413
+ "epoch": 0.05769599631727683,
1414
+ "grad_norm": 0.2759098410606384,
1415
+ "learning_rate": 0.0001996698709303439,
1416
+ "loss": 0.38013901710510256,
1417
+ "step": 2010
1418
+ },
1419
+ {
1420
+ "epoch": 0.05798827593387904,
1421
+ "grad_norm": 0.2426660805940628,
1422
+ "learning_rate": 0.00019966329850831894,
1423
+ "loss": 0.4401369571685791,
1424
+ "step": 2020
1425
+ },
1426
+ {
1427
+ "epoch": 0.058280555550481256,
1428
+ "grad_norm": 0.22679618000984192,
1429
+ "learning_rate": 0.00019965666141586157,
1430
+ "loss": 0.3150460243225098,
1431
+ "step": 2030
1432
+ },
1433
+ {
1434
+ "epoch": 0.05857283516708347,
1435
+ "grad_norm": 0.29090648889541626,
1436
+ "learning_rate": 0.0001996499596572786,
1437
+ "loss": 0.3733455896377563,
1438
+ "step": 2040
1439
+ },
1440
+ {
1441
+ "epoch": 0.05886511478368568,
1442
+ "grad_norm": 0.30679851770401,
1443
+ "learning_rate": 0.00019964319323691868,
1444
+ "loss": 0.443017578125,
1445
+ "step": 2050
1446
+ },
1447
+ {
1448
+ "epoch": 0.059157394400287895,
1449
+ "grad_norm": 0.21110324561595917,
1450
+ "learning_rate": 0.00019963636215917244,
1451
+ "loss": 0.40988821983337403,
1452
+ "step": 2060
1453
+ },
1454
+ {
1455
+ "epoch": 0.05944967401689011,
1456
+ "grad_norm": 0.25294822454452515,
1457
+ "learning_rate": 0.00019962946642847258,
1458
+ "loss": 0.42485885620117186,
1459
+ "step": 2070
1460
+ },
1461
+ {
1462
+ "epoch": 0.05974195363349232,
1463
+ "grad_norm": 0.24810326099395752,
1464
+ "learning_rate": 0.0001996225060492936,
1465
+ "loss": 0.3709405422210693,
1466
+ "step": 2080
1467
+ },
1468
+ {
1469
+ "epoch": 0.060034233250094535,
1470
+ "grad_norm": 0.2301589697599411,
1471
+ "learning_rate": 0.00019961548102615204,
1472
+ "loss": 0.42913308143615725,
1473
+ "step": 2090
1474
+ },
1475
+ {
1476
+ "epoch": 0.06032651286669675,
1477
+ "grad_norm": 0.24390390515327454,
1478
+ "learning_rate": 0.00019960839136360633,
1479
+ "loss": 0.3363667011260986,
1480
+ "step": 2100
1481
+ },
1482
+ {
1483
+ "epoch": 0.06061879248329896,
1484
+ "grad_norm": 0.23716720938682556,
1485
+ "learning_rate": 0.0001996012370662569,
1486
+ "loss": 0.361738920211792,
1487
+ "step": 2110
1488
+ },
1489
+ {
1490
+ "epoch": 0.060911072099901174,
1491
+ "grad_norm": 0.20727047324180603,
1492
+ "learning_rate": 0.0001995940181387461,
1493
+ "loss": 0.38850061893463134,
1494
+ "step": 2120
1495
+ },
1496
+ {
1497
+ "epoch": 0.06120335171650339,
1498
+ "grad_norm": 0.19902947545051575,
1499
+ "learning_rate": 0.00019958673458575824,
1500
+ "loss": 0.31249237060546875,
1501
+ "step": 2130
1502
+ },
1503
+ {
1504
+ "epoch": 0.0614956313331056,
1505
+ "grad_norm": 0.24424754083156586,
1506
+ "learning_rate": 0.00019957938641201948,
1507
+ "loss": 0.41524853706359866,
1508
+ "step": 2140
1509
+ },
1510
+ {
1511
+ "epoch": 0.061787910949707814,
1512
+ "grad_norm": 0.24768763780593872,
1513
+ "learning_rate": 0.00019957197362229797,
1514
+ "loss": 0.39194750785827637,
1515
+ "step": 2150
1516
+ },
1517
+ {
1518
+ "epoch": 0.06208019056631003,
1519
+ "grad_norm": 0.3057568073272705,
1520
+ "learning_rate": 0.00019956449622140384,
1521
+ "loss": 0.31905083656311034,
1522
+ "step": 2160
1523
+ },
1524
+ {
1525
+ "epoch": 0.06237247018291224,
1526
+ "grad_norm": 0.3908090591430664,
1527
+ "learning_rate": 0.00019955695421418907,
1528
+ "loss": 0.4339137077331543,
1529
+ "step": 2170
1530
+ },
1531
+ {
1532
+ "epoch": 0.06266474979951445,
1533
+ "grad_norm": 0.21391141414642334,
1534
+ "learning_rate": 0.00019954934760554757,
1535
+ "loss": 0.3780949831008911,
1536
+ "step": 2180
1537
+ },
1538
+ {
1539
+ "epoch": 0.06295702941611667,
1540
+ "grad_norm": 0.16703805327415466,
1541
+ "learning_rate": 0.00019954167640041522,
1542
+ "loss": 0.40203108787536623,
1543
+ "step": 2190
1544
+ },
1545
+ {
1546
+ "epoch": 0.06324930903271887,
1547
+ "grad_norm": 0.2569977343082428,
1548
+ "learning_rate": 0.00019953394060376973,
1549
+ "loss": 0.42340788841247556,
1550
+ "step": 2200
1551
+ },
1552
+ {
1553
+ "epoch": 0.06354158864932109,
1554
+ "grad_norm": 0.2800414562225342,
1555
+ "learning_rate": 0.00019952614022063084,
1556
+ "loss": 0.40265374183654784,
1557
+ "step": 2210
1558
+ },
1559
+ {
1560
+ "epoch": 0.0638338682659233,
1561
+ "grad_norm": 0.21277093887329102,
1562
+ "learning_rate": 0.0001995182752560601,
1563
+ "loss": 0.3515303134918213,
1564
+ "step": 2220
1565
+ },
1566
+ {
1567
+ "epoch": 0.06412614788252552,
1568
+ "grad_norm": 0.3708363175392151,
1569
+ "learning_rate": 0.00019951034571516097,
1570
+ "loss": 0.3585836410522461,
1571
+ "step": 2230
1572
+ },
1573
+ {
1574
+ "epoch": 0.06441842749912773,
1575
+ "grad_norm": 0.21470332145690918,
1576
+ "learning_rate": 0.0001995023516030789,
1577
+ "loss": 0.35557281970977783,
1578
+ "step": 2240
1579
+ },
1580
+ {
1581
+ "epoch": 0.06471070711572995,
1582
+ "grad_norm": 0.22539454698562622,
1583
+ "learning_rate": 0.00019949429292500113,
1584
+ "loss": 0.3998990058898926,
1585
+ "step": 2250
1586
+ },
1587
+ {
1588
+ "epoch": 0.06500298673233215,
1589
+ "grad_norm": 0.19151820242404938,
1590
+ "learning_rate": 0.0001994861696861569,
1591
+ "loss": 0.3600909948348999,
1592
+ "step": 2260
1593
+ },
1594
+ {
1595
+ "epoch": 0.06529526634893437,
1596
+ "grad_norm": 0.21192649006843567,
1597
+ "learning_rate": 0.00019947798189181727,
1598
+ "loss": 0.34516177177429197,
1599
+ "step": 2270
1600
+ },
1601
+ {
1602
+ "epoch": 0.06558754596553658,
1603
+ "grad_norm": 0.2622006833553314,
1604
+ "learning_rate": 0.00019946972954729519,
1605
+ "loss": 0.3691245555877686,
1606
+ "step": 2280
1607
+ },
1608
+ {
1609
+ "epoch": 0.0658798255821388,
1610
+ "grad_norm": 0.1908690184354782,
1611
+ "learning_rate": 0.00019946141265794553,
1612
+ "loss": 0.38103673458099363,
1613
+ "step": 2290
1614
+ },
1615
+ {
1616
+ "epoch": 0.066172105198741,
1617
+ "grad_norm": 0.21785594522953033,
1618
+ "learning_rate": 0.00019945303122916505,
1619
+ "loss": 0.32585608959198,
1620
+ "step": 2300
1621
+ },
1622
+ {
1623
+ "epoch": 0.06646438481534322,
1624
+ "grad_norm": 0.31074655055999756,
1625
+ "learning_rate": 0.00019944458526639235,
1626
+ "loss": 0.4161215305328369,
1627
+ "step": 2310
1628
+ },
1629
+ {
1630
+ "epoch": 0.06675666443194543,
1631
+ "grad_norm": 0.2080898880958557,
1632
+ "learning_rate": 0.00019943607477510792,
1633
+ "loss": 0.40408644676208494,
1634
+ "step": 2320
1635
+ },
1636
+ {
1637
+ "epoch": 0.06704894404854765,
1638
+ "grad_norm": 0.20214156806468964,
1639
+ "learning_rate": 0.00019942749976083416,
1640
+ "loss": 0.373272705078125,
1641
+ "step": 2330
1642
+ },
1643
+ {
1644
+ "epoch": 0.06734122366514986,
1645
+ "grad_norm": 0.2070678323507309,
1646
+ "learning_rate": 0.00019941886022913522,
1647
+ "loss": 0.3865471363067627,
1648
+ "step": 2340
1649
+ },
1650
+ {
1651
+ "epoch": 0.06763350328175206,
1652
+ "grad_norm": 0.2521723210811615,
1653
+ "learning_rate": 0.0001994101561856173,
1654
+ "loss": 0.3574871063232422,
1655
+ "step": 2350
1656
+ },
1657
+ {
1658
+ "epoch": 0.06792578289835428,
1659
+ "grad_norm": 0.2097303718328476,
1660
+ "learning_rate": 0.00019940138763592828,
1661
+ "loss": 0.4145055770874023,
1662
+ "step": 2360
1663
+ },
1664
+ {
1665
+ "epoch": 0.06821806251495649,
1666
+ "grad_norm": 0.2956986725330353,
1667
+ "learning_rate": 0.00019939255458575802,
1668
+ "loss": 0.4034604072570801,
1669
+ "step": 2370
1670
+ },
1671
+ {
1672
+ "epoch": 0.06851034213155871,
1673
+ "grad_norm": 0.20965847373008728,
1674
+ "learning_rate": 0.00019938365704083816,
1675
+ "loss": 0.38535895347595217,
1676
+ "step": 2380
1677
+ },
1678
+ {
1679
+ "epoch": 0.06880262174816092,
1680
+ "grad_norm": 0.2410966157913208,
1681
+ "learning_rate": 0.00019937469500694226,
1682
+ "loss": 0.40244760513305666,
1683
+ "step": 2390
1684
+ },
1685
+ {
1686
+ "epoch": 0.06909490136476314,
1687
+ "grad_norm": 0.24631759524345398,
1688
+ "learning_rate": 0.00019936566848988567,
1689
+ "loss": 0.4188735008239746,
1690
+ "step": 2400
1691
+ },
1692
+ {
1693
+ "epoch": 0.06938718098136534,
1694
+ "grad_norm": 0.1852298080921173,
1695
+ "learning_rate": 0.00019935657749552558,
1696
+ "loss": 0.40854802131652834,
1697
+ "step": 2410
1698
+ },
1699
+ {
1700
+ "epoch": 0.06967946059796756,
1701
+ "grad_norm": 0.24064451456069946,
1702
+ "learning_rate": 0.00019934742202976107,
1703
+ "loss": 0.35597121715545654,
1704
+ "step": 2420
1705
+ },
1706
+ {
1707
+ "epoch": 0.06997174021456977,
1708
+ "grad_norm": 0.2895231246948242,
1709
+ "learning_rate": 0.00019933820209853297,
1710
+ "loss": 0.39232187271118163,
1711
+ "step": 2430
1712
+ },
1713
+ {
1714
+ "epoch": 0.07026401983117199,
1715
+ "grad_norm": 0.19319918751716614,
1716
+ "learning_rate": 0.00019932891770782404,
1717
+ "loss": 0.3565209150314331,
1718
+ "step": 2440
1719
+ },
1720
+ {
1721
+ "epoch": 0.0705562994477742,
1722
+ "grad_norm": 0.36313900351524353,
1723
+ "learning_rate": 0.00019931956886365884,
1724
+ "loss": 0.36571540832519533,
1725
+ "step": 2450
1726
+ },
1727
+ {
1728
+ "epoch": 0.07084857906437642,
1729
+ "grad_norm": 0.2750861346721649,
1730
+ "learning_rate": 0.0001993101555721037,
1731
+ "loss": 0.3466514587402344,
1732
+ "step": 2460
1733
+ },
1734
+ {
1735
+ "epoch": 0.07114085868097862,
1736
+ "grad_norm": 0.22644628584384918,
1737
+ "learning_rate": 0.00019930067783926675,
1738
+ "loss": 0.3429016828536987,
1739
+ "step": 2470
1740
+ },
1741
+ {
1742
+ "epoch": 0.07143313829758084,
1743
+ "grad_norm": 0.25445985794067383,
1744
+ "learning_rate": 0.0001992911356712981,
1745
+ "loss": 0.4083054542541504,
1746
+ "step": 2480
1747
+ },
1748
+ {
1749
+ "epoch": 0.07172541791418305,
1750
+ "grad_norm": 0.2863784432411194,
1751
+ "learning_rate": 0.00019928152907438946,
1752
+ "loss": 0.38512208461761477,
1753
+ "step": 2490
1754
+ },
1755
+ {
1756
+ "epoch": 0.07201769753078527,
1757
+ "grad_norm": 0.3040670156478882,
1758
+ "learning_rate": 0.0001992718580547745,
1759
+ "loss": 0.3621720552444458,
1760
+ "step": 2500
1761
+ },
1762
+ {
1763
+ "epoch": 0.07230997714738747,
1764
+ "grad_norm": 0.21406209468841553,
1765
+ "learning_rate": 0.00019926212261872866,
1766
+ "loss": 0.39595961570739746,
1767
+ "step": 2510
1768
+ },
1769
+ {
1770
+ "epoch": 0.0726022567639897,
1771
+ "grad_norm": 0.185161292552948,
1772
+ "learning_rate": 0.00019925232277256906,
1773
+ "loss": 0.38945841789245605,
1774
+ "step": 2520
1775
+ },
1776
+ {
1777
+ "epoch": 0.0728945363805919,
1778
+ "grad_norm": 0.35198086500167847,
1779
+ "learning_rate": 0.00019924245852265485,
1780
+ "loss": 0.38671183586120605,
1781
+ "step": 2530
1782
+ },
1783
+ {
1784
+ "epoch": 0.07318681599719412,
1785
+ "grad_norm": 0.2338062822818756,
1786
+ "learning_rate": 0.0001992325298753867,
1787
+ "loss": 0.40381150245666503,
1788
+ "step": 2540
1789
+ },
1790
+ {
1791
+ "epoch": 0.07347909561379633,
1792
+ "grad_norm": 0.22099274396896362,
1793
+ "learning_rate": 0.00019922253683720732,
1794
+ "loss": 0.39828627109527587,
1795
+ "step": 2550
1796
+ },
1797
+ {
1798
+ "epoch": 0.07377137523039855,
1799
+ "grad_norm": 0.2281026393175125,
1800
+ "learning_rate": 0.000199212479414601,
1801
+ "loss": 0.38828580379486083,
1802
+ "step": 2560
1803
+ },
1804
+ {
1805
+ "epoch": 0.07406365484700075,
1806
+ "grad_norm": 0.240388423204422,
1807
+ "learning_rate": 0.00019920235761409393,
1808
+ "loss": 0.3149177312850952,
1809
+ "step": 2570
1810
+ },
1811
+ {
1812
+ "epoch": 0.07435593446360297,
1813
+ "grad_norm": 0.2369592785835266,
1814
+ "learning_rate": 0.00019919217144225403,
1815
+ "loss": 0.43828372955322265,
1816
+ "step": 2580
1817
+ },
1818
+ {
1819
+ "epoch": 0.07464821408020518,
1820
+ "grad_norm": 0.2708946168422699,
1821
+ "learning_rate": 0.00019918192090569102,
1822
+ "loss": 0.3750912666320801,
1823
+ "step": 2590
1824
+ },
1825
+ {
1826
+ "epoch": 0.07494049369680739,
1827
+ "grad_norm": 0.25363683700561523,
1828
+ "learning_rate": 0.0001991716060110563,
1829
+ "loss": 0.4024306297302246,
1830
+ "step": 2600
1831
+ },
1832
+ {
1833
+ "epoch": 0.0752327733134096,
1834
+ "grad_norm": 0.25413063168525696,
1835
+ "learning_rate": 0.00019916122676504313,
1836
+ "loss": 0.4374362945556641,
1837
+ "step": 2610
1838
+ },
1839
+ {
1840
+ "epoch": 0.07552505293001181,
1841
+ "grad_norm": 0.2922676205635071,
1842
+ "learning_rate": 0.00019915078317438652,
1843
+ "loss": 0.4300537586212158,
1844
+ "step": 2620
1845
+ },
1846
+ {
1847
+ "epoch": 0.07581733254661403,
1848
+ "grad_norm": 0.23218266665935516,
1849
+ "learning_rate": 0.00019914027524586315,
1850
+ "loss": 0.30225658416748047,
1851
+ "step": 2630
1852
+ },
1853
+ {
1854
+ "epoch": 0.07610961216321624,
1855
+ "grad_norm": 0.21953946352005005,
1856
+ "learning_rate": 0.00019912970298629153,
1857
+ "loss": 0.40011258125305177,
1858
+ "step": 2640
1859
+ },
1860
+ {
1861
+ "epoch": 0.07640189177981846,
1862
+ "grad_norm": 0.2304810881614685,
1863
+ "learning_rate": 0.00019911906640253187,
1864
+ "loss": 0.39437267780303953,
1865
+ "step": 2650
1866
+ },
1867
+ {
1868
+ "epoch": 0.07669417139642067,
1869
+ "grad_norm": 0.2002577781677246,
1870
+ "learning_rate": 0.00019910836550148615,
1871
+ "loss": 0.34653146266937257,
1872
+ "step": 2660
1873
+ },
1874
+ {
1875
+ "epoch": 0.07698645101302289,
1876
+ "grad_norm": 0.26880741119384766,
1877
+ "learning_rate": 0.00019909760029009806,
1878
+ "loss": 0.38612444400787355,
1879
+ "step": 2670
1880
+ },
1881
+ {
1882
+ "epoch": 0.07727873062962509,
1883
+ "grad_norm": 0.2160756140947342,
1884
+ "learning_rate": 0.00019908677077535303,
1885
+ "loss": 0.4106006145477295,
1886
+ "step": 2680
1887
+ },
1888
+ {
1889
+ "epoch": 0.07757101024622731,
1890
+ "grad_norm": 0.2476145178079605,
1891
+ "learning_rate": 0.00019907587696427821,
1892
+ "loss": 0.4026120662689209,
1893
+ "step": 2690
1894
+ },
1895
+ {
1896
+ "epoch": 0.07786328986282952,
1897
+ "grad_norm": 0.8202416300773621,
1898
+ "learning_rate": 0.00019906491886394247,
1899
+ "loss": 0.41068472862243655,
1900
+ "step": 2700
1901
+ },
1902
+ {
1903
+ "epoch": 0.07815556947943174,
1904
+ "grad_norm": 0.25270184874534607,
1905
+ "learning_rate": 0.00019905389648145643,
1906
+ "loss": 0.388895583152771,
1907
+ "step": 2710
1908
+ },
1909
+ {
1910
+ "epoch": 0.07844784909603394,
1911
+ "grad_norm": 0.2556864619255066,
1912
+ "learning_rate": 0.00019904280982397236,
1913
+ "loss": 0.46575565338134767,
1914
+ "step": 2720
1915
+ },
1916
+ {
1917
+ "epoch": 0.07874012871263616,
1918
+ "grad_norm": 0.22981390357017517,
1919
+ "learning_rate": 0.0001990316588986843,
1920
+ "loss": 0.3884773015975952,
1921
+ "step": 2730
1922
+ },
1923
+ {
1924
+ "epoch": 0.07903240832923837,
1925
+ "grad_norm": 0.18209731578826904,
1926
+ "learning_rate": 0.00019902044371282793,
1927
+ "loss": 0.3456049680709839,
1928
+ "step": 2740
1929
+ },
1930
+ {
1931
+ "epoch": 0.07932468794584059,
1932
+ "grad_norm": 0.31520935893058777,
1933
+ "learning_rate": 0.0001990091642736807,
1934
+ "loss": 0.36254956722259524,
1935
+ "step": 2750
1936
+ },
1937
+ {
1938
+ "epoch": 0.0796169675624428,
1939
+ "grad_norm": 0.2921953797340393,
1940
+ "learning_rate": 0.00019899782058856172,
1941
+ "loss": 0.35902976989746094,
1942
+ "step": 2760
1943
+ },
1944
+ {
1945
+ "epoch": 0.07990924717904502,
1946
+ "grad_norm": 0.26231515407562256,
1947
+ "learning_rate": 0.00019898641266483173,
1948
+ "loss": 0.33397631645202636,
1949
+ "step": 2770
1950
+ },
1951
+ {
1952
+ "epoch": 0.08020152679564722,
1953
+ "grad_norm": 0.2696617543697357,
1954
+ "learning_rate": 0.00019897494050989326,
1955
+ "loss": 0.3791987657546997,
1956
+ "step": 2780
1957
+ },
1958
+ {
1959
+ "epoch": 0.08049380641224944,
1960
+ "grad_norm": 0.24650204181671143,
1961
+ "learning_rate": 0.00019896340413119043,
1962
+ "loss": 0.4233126640319824,
1963
+ "step": 2790
1964
+ },
1965
+ {
1966
+ "epoch": 0.08078608602885165,
1967
+ "grad_norm": 0.2599400281906128,
1968
+ "learning_rate": 0.00019895180353620911,
1969
+ "loss": 0.4109656810760498,
1970
+ "step": 2800
1971
+ },
1972
+ {
1973
+ "epoch": 0.08107836564545387,
1974
+ "grad_norm": 0.24897293746471405,
1975
+ "learning_rate": 0.00019894013873247678,
1976
+ "loss": 0.38447999954223633,
1977
+ "step": 2810
1978
+ },
1979
+ {
1980
+ "epoch": 0.08137064526205608,
1981
+ "grad_norm": 0.20676682889461517,
1982
+ "learning_rate": 0.0001989284097275626,
1983
+ "loss": 0.42731261253356934,
1984
+ "step": 2820
1985
+ },
1986
+ {
1987
+ "epoch": 0.0816629248786583,
1988
+ "grad_norm": 0.28797972202301025,
1989
+ "learning_rate": 0.0001989166165290774,
1990
+ "loss": 0.375295615196228,
1991
+ "step": 2830
1992
+ },
1993
+ {
1994
+ "epoch": 0.0819552044952605,
1995
+ "grad_norm": 0.24699875712394714,
1996
+ "learning_rate": 0.00019890475914467366,
1997
+ "loss": 0.37915284633636476,
1998
+ "step": 2840
1999
+ },
2000
+ {
2001
+ "epoch": 0.08224748411186272,
2002
+ "grad_norm": 0.250649631023407,
2003
+ "learning_rate": 0.0001988928375820455,
2004
+ "loss": 0.3783683776855469,
2005
+ "step": 2850
2006
+ },
2007
+ {
2008
+ "epoch": 0.08253976372846493,
2009
+ "grad_norm": 0.22644077241420746,
2010
+ "learning_rate": 0.00019888085184892868,
2011
+ "loss": 0.41778364181518557,
2012
+ "step": 2860
2013
+ },
2014
+ {
2015
+ "epoch": 0.08283204334506714,
2016
+ "grad_norm": 0.2277672290802002,
2017
+ "learning_rate": 0.00019886880195310065,
2018
+ "loss": 0.36871073246002195,
2019
+ "step": 2870
2020
+ },
2021
+ {
2022
+ "epoch": 0.08312432296166936,
2023
+ "grad_norm": 0.31684842705726624,
2024
+ "learning_rate": 0.00019885668790238043,
2025
+ "loss": 0.40143604278564454,
2026
+ "step": 2880
2027
+ },
2028
+ {
2029
+ "epoch": 0.08341660257827156,
2030
+ "grad_norm": 0.33947882056236267,
2031
+ "learning_rate": 0.0001988445097046287,
2032
+ "loss": 0.41034741401672364,
2033
+ "step": 2890
2034
+ },
2035
+ {
2036
+ "epoch": 0.08370888219487378,
2037
+ "grad_norm": 0.22324541211128235,
2038
+ "learning_rate": 0.00019883226736774776,
2039
+ "loss": 0.3964377403259277,
2040
+ "step": 2900
2041
+ },
2042
+ {
2043
+ "epoch": 0.08400116181147599,
2044
+ "grad_norm": 0.23351380228996277,
2045
+ "learning_rate": 0.00019881996089968156,
2046
+ "loss": 0.41057047843933103,
2047
+ "step": 2910
2048
+ },
2049
+ {
2050
+ "epoch": 0.08429344142807821,
2051
+ "grad_norm": 0.20214258134365082,
2052
+ "learning_rate": 0.00019880759030841558,
2053
+ "loss": 0.3924527406692505,
2054
+ "step": 2920
2055
+ },
2056
+ {
2057
+ "epoch": 0.08458572104468041,
2058
+ "grad_norm": 0.2522850036621094,
2059
+ "learning_rate": 0.00019879515560197698,
2060
+ "loss": 0.3682981252670288,
2061
+ "step": 2930
2062
+ },
2063
+ {
2064
+ "epoch": 0.08487800066128263,
2065
+ "grad_norm": 0.2607446014881134,
2066
+ "learning_rate": 0.0001987826567884345,
2067
+ "loss": 0.3693267345428467,
2068
+ "step": 2940
2069
+ },
2070
+ {
2071
+ "epoch": 0.08517028027788484,
2072
+ "grad_norm": 0.28362178802490234,
2073
+ "learning_rate": 0.00019877009387589853,
2074
+ "loss": 0.4493271350860596,
2075
+ "step": 2950
2076
+ },
2077
+ {
2078
+ "epoch": 0.08546255989448706,
2079
+ "grad_norm": 0.20476898550987244,
2080
+ "learning_rate": 0.00019875746687252096,
2081
+ "loss": 0.4254180431365967,
2082
+ "step": 2960
2083
+ },
2084
+ {
2085
+ "epoch": 0.08575483951108927,
2086
+ "grad_norm": 0.31387001276016235,
2087
+ "learning_rate": 0.00019874477578649534,
2088
+ "loss": 0.409135103225708,
2089
+ "step": 2970
2090
+ },
2091
+ {
2092
+ "epoch": 0.08604711912769149,
2093
+ "grad_norm": 0.18842676281929016,
2094
+ "learning_rate": 0.0001987320206260568,
2095
+ "loss": 0.35662786960601806,
2096
+ "step": 2980
2097
+ },
2098
+ {
2099
+ "epoch": 0.0863393987442937,
2100
+ "grad_norm": 0.28873375058174133,
2101
+ "learning_rate": 0.00019871920139948192,
2102
+ "loss": 0.34955050945281985,
2103
+ "step": 2990
2104
+ },
2105
+ {
2106
+ "epoch": 0.08663167836089591,
2107
+ "grad_norm": 0.2810521423816681,
2108
+ "learning_rate": 0.00019870631811508909,
2109
+ "loss": 0.4152508735656738,
2110
+ "step": 3000
2111
+ }
2112
+ ],
2113
+ "logging_steps": 10,
2114
+ "max_steps": 40000,
2115
+ "num_input_tokens_seen": 0,
2116
+ "num_train_epochs": 2,
2117
+ "save_steps": 1000,
2118
+ "stateful_callbacks": {
2119
+ "TrainerControl": {
2120
+ "args": {
2121
+ "should_epoch_stop": false,
2122
+ "should_evaluate": false,
2123
+ "should_log": false,
2124
+ "should_save": true,
2125
+ "should_training_stop": false
2126
+ },
2127
+ "attributes": {}
2128
+ }
2129
+ },
2130
+ "total_flos": 3.19924954202112e+18,
2131
+ "train_batch_size": 1,
2132
+ "trial_name": null,
2133
+ "trial_params": null
2134
+ }
checkpoint-3000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6ab51bd599651344f26a67a1d940a2b6432da90051bdf388dcef2423ea1342d
3
+ size 5329