diaenra commited on
Commit
5453d31
·
verified ·
1 Parent(s): 5dcad98

Training in progress, step 239, checkpoint

Browse files
last-checkpoint/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-3B
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.2
last-checkpoint/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-3B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": [
18
+ "embed_tokens",
19
+ "lm_head"
20
+ ],
21
+ "peft_type": "LORA",
22
+ "r": 32,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "gate_proj",
27
+ "k_proj",
28
+ "o_proj",
29
+ "down_proj",
30
+ "up_proj",
31
+ "v_proj",
32
+ "q_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
last-checkpoint/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3305692d35b74b4005d38dcd6bd52131ab98072dcd251e4840ccb14462988419
3
+ size 1484196216
last-checkpoint/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
+ }
last-checkpoint/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e00b34523a67b3bfe28f1c0874e7d90b2a372e85cc94c15b5e33bb1923c29df
3
+ size 2968683840
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:664cf91330e3a233afde7b7c1f1a019063aac8c1a125dbd6950c74fb90893118
3
+ size 14244
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63c2fbe0dd778bed0f6058f5bb7c39f95ac01aa2b0a9c287de935e25b97fbedf
3
+ size 1064
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
last-checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|endoftext|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,1706 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.01198791177097571,
5
+ "eval_steps": 500,
6
+ "global_step": 239,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 5.0158626656802136e-05,
13
+ "grad_norm": 3.5492336750030518,
14
+ "learning_rate": 1.0000000000000002e-06,
15
+ "loss": 2.1967,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.00010031725331360427,
20
+ "grad_norm": 4.093388080596924,
21
+ "learning_rate": 2.0000000000000003e-06,
22
+ "loss": 2.074,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.00015047587997040642,
27
+ "grad_norm": 5.221968650817871,
28
+ "learning_rate": 3e-06,
29
+ "loss": 1.8972,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.00020063450662720855,
34
+ "grad_norm": 5.642177104949951,
35
+ "learning_rate": 4.000000000000001e-06,
36
+ "loss": 1.8401,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.0002507931332840107,
41
+ "grad_norm": 5.066410541534424,
42
+ "learning_rate": 5e-06,
43
+ "loss": 1.8184,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.00030095175994081285,
48
+ "grad_norm": 6.9239301681518555,
49
+ "learning_rate": 6e-06,
50
+ "loss": 1.8774,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.00035111038659761494,
55
+ "grad_norm": 4.572519302368164,
56
+ "learning_rate": 7.000000000000001e-06,
57
+ "loss": 1.7552,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.0004012690132544171,
62
+ "grad_norm": 5.454565525054932,
63
+ "learning_rate": 8.000000000000001e-06,
64
+ "loss": 1.6517,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.00045142763991121924,
69
+ "grad_norm": 3.9561901092529297,
70
+ "learning_rate": 9e-06,
71
+ "loss": 1.937,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.0005015862665680214,
76
+ "grad_norm": 4.928288459777832,
77
+ "learning_rate": 1e-05,
78
+ "loss": 1.8208,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.0005517448932248235,
83
+ "grad_norm": 5.23153018951416,
84
+ "learning_rate": 1.1000000000000001e-05,
85
+ "loss": 1.8182,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.0006019035198816257,
90
+ "grad_norm": 5.184555530548096,
91
+ "learning_rate": 1.2e-05,
92
+ "loss": 1.6997,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.0006520621465384278,
97
+ "grad_norm": 4.049405574798584,
98
+ "learning_rate": 1.3000000000000001e-05,
99
+ "loss": 1.7283,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.0007022207731952299,
104
+ "grad_norm": 5.253482818603516,
105
+ "learning_rate": 1.4000000000000001e-05,
106
+ "loss": 1.7556,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.0007523793998520321,
111
+ "grad_norm": 7.162256717681885,
112
+ "learning_rate": 1.5e-05,
113
+ "loss": 1.7063,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.0008025380265088342,
118
+ "grad_norm": 6.176828384399414,
119
+ "learning_rate": 1.6000000000000003e-05,
120
+ "loss": 1.9373,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.0008526966531656363,
125
+ "grad_norm": 5.38509464263916,
126
+ "learning_rate": 1.7000000000000003e-05,
127
+ "loss": 1.8507,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.0009028552798224385,
132
+ "grad_norm": 5.271251678466797,
133
+ "learning_rate": 1.8e-05,
134
+ "loss": 1.7382,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.0009530139064792406,
139
+ "grad_norm": 4.529239654541016,
140
+ "learning_rate": 1.9e-05,
141
+ "loss": 1.7572,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.0010031725331360428,
146
+ "grad_norm": 6.6834940910339355,
147
+ "learning_rate": 2e-05,
148
+ "loss": 1.6145,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.0010533311597928448,
153
+ "grad_norm": 5.881002902984619,
154
+ "learning_rate": 2.1e-05,
155
+ "loss": 1.8464,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.001103489786449647,
160
+ "grad_norm": 4.667331695556641,
161
+ "learning_rate": 2.2000000000000003e-05,
162
+ "loss": 1.9726,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.0011536484131064492,
167
+ "grad_norm": 4.439915180206299,
168
+ "learning_rate": 2.3000000000000003e-05,
169
+ "loss": 1.9501,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.0012038070397632514,
174
+ "grad_norm": 4.341642379760742,
175
+ "learning_rate": 2.4e-05,
176
+ "loss": 1.6347,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.0012539656664200534,
181
+ "grad_norm": 5.318514823913574,
182
+ "learning_rate": 2.5e-05,
183
+ "loss": 2.0127,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.0013041242930768556,
188
+ "grad_norm": 4.649798393249512,
189
+ "learning_rate": 2.6000000000000002e-05,
190
+ "loss": 1.533,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.0013542829197336578,
195
+ "grad_norm": 5.03102970123291,
196
+ "learning_rate": 2.7000000000000002e-05,
197
+ "loss": 1.6971,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.0014044415463904598,
202
+ "grad_norm": 6.526177406311035,
203
+ "learning_rate": 2.8000000000000003e-05,
204
+ "loss": 1.4764,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.001454600173047262,
209
+ "grad_norm": 4.814057350158691,
210
+ "learning_rate": 2.9e-05,
211
+ "loss": 1.8919,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.0015047587997040642,
216
+ "grad_norm": 5.465883255004883,
217
+ "learning_rate": 3e-05,
218
+ "loss": 1.8328,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.0015549174263608662,
223
+ "grad_norm": 5.6578264236450195,
224
+ "learning_rate": 3.1e-05,
225
+ "loss": 1.6715,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.0016050760530176684,
230
+ "grad_norm": 5.566780090332031,
231
+ "learning_rate": 3.2000000000000005e-05,
232
+ "loss": 1.8483,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.0016552346796744706,
237
+ "grad_norm": 5.120264053344727,
238
+ "learning_rate": 3.3e-05,
239
+ "loss": 1.8823,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.0017053933063312726,
244
+ "grad_norm": 5.753010272979736,
245
+ "learning_rate": 3.4000000000000007e-05,
246
+ "loss": 1.6993,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.0017555519329880748,
251
+ "grad_norm": 6.242431640625,
252
+ "learning_rate": 3.5e-05,
253
+ "loss": 1.8161,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.001805710559644877,
258
+ "grad_norm": 5.681616306304932,
259
+ "learning_rate": 3.6e-05,
260
+ "loss": 1.8614,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.001855869186301679,
265
+ "grad_norm": 6.1227569580078125,
266
+ "learning_rate": 3.7e-05,
267
+ "loss": 1.7892,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.0019060278129584812,
272
+ "grad_norm": 5.99332332611084,
273
+ "learning_rate": 3.8e-05,
274
+ "loss": 1.4083,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.0019561864396152834,
279
+ "grad_norm": 5.745953559875488,
280
+ "learning_rate": 3.9000000000000006e-05,
281
+ "loss": 1.4741,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.0020063450662720856,
286
+ "grad_norm": 5.3738837242126465,
287
+ "learning_rate": 4e-05,
288
+ "loss": 1.8169,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.0020565036929288878,
293
+ "grad_norm": 5.091897010803223,
294
+ "learning_rate": 4.1e-05,
295
+ "loss": 1.67,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.0021066623195856895,
300
+ "grad_norm": 5.49876070022583,
301
+ "learning_rate": 4.2e-05,
302
+ "loss": 1.4768,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.0021568209462424917,
307
+ "grad_norm": 8.60002613067627,
308
+ "learning_rate": 4.3e-05,
309
+ "loss": 1.6741,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.002206979572899294,
314
+ "grad_norm": 5.658391952514648,
315
+ "learning_rate": 4.4000000000000006e-05,
316
+ "loss": 1.7292,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.002257138199556096,
321
+ "grad_norm": 6.834291934967041,
322
+ "learning_rate": 4.5e-05,
323
+ "loss": 1.7368,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.0023072968262128984,
328
+ "grad_norm": 9.042109489440918,
329
+ "learning_rate": 4.600000000000001e-05,
330
+ "loss": 1.5894,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.0023574554528697006,
335
+ "grad_norm": 8.759542465209961,
336
+ "learning_rate": 4.7e-05,
337
+ "loss": 1.5485,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.0024076140795265028,
342
+ "grad_norm": 8.1019868850708,
343
+ "learning_rate": 4.8e-05,
344
+ "loss": 1.3596,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.0024577727061833045,
349
+ "grad_norm": 10.25011157989502,
350
+ "learning_rate": 4.9e-05,
351
+ "loss": 1.2274,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.0025079313328401067,
356
+ "grad_norm": 10.12292194366455,
357
+ "learning_rate": 5e-05,
358
+ "loss": 1.1246,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.002558089959496909,
363
+ "grad_norm": 3.036353349685669,
364
+ "learning_rate": 5.1000000000000006e-05,
365
+ "loss": 1.9104,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.002608248586153711,
370
+ "grad_norm": 3.3351845741271973,
371
+ "learning_rate": 5.2000000000000004e-05,
372
+ "loss": 1.6544,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.0026584072128105134,
377
+ "grad_norm": 4.553438186645508,
378
+ "learning_rate": 5.300000000000001e-05,
379
+ "loss": 1.777,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.0027085658394673156,
384
+ "grad_norm": 5.190873622894287,
385
+ "learning_rate": 5.4000000000000005e-05,
386
+ "loss": 1.7235,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.0027587244661241173,
391
+ "grad_norm": 4.517773628234863,
392
+ "learning_rate": 5.500000000000001e-05,
393
+ "loss": 1.515,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.0028088830927809195,
398
+ "grad_norm": 4.626497268676758,
399
+ "learning_rate": 5.6000000000000006e-05,
400
+ "loss": 1.7808,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.0028590417194377217,
405
+ "grad_norm": 6.360121250152588,
406
+ "learning_rate": 5.6999999999999996e-05,
407
+ "loss": 1.8502,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.002909200346094524,
412
+ "grad_norm": 6.034987926483154,
413
+ "learning_rate": 5.8e-05,
414
+ "loss": 1.8749,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.002959358972751326,
419
+ "grad_norm": 5.864983558654785,
420
+ "learning_rate": 5.9e-05,
421
+ "loss": 1.6335,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.0030095175994081283,
426
+ "grad_norm": 5.735439300537109,
427
+ "learning_rate": 6e-05,
428
+ "loss": 1.7521,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.0030596762260649306,
433
+ "grad_norm": 4.080763816833496,
434
+ "learning_rate": 6.1e-05,
435
+ "loss": 1.3012,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.0031098348527217323,
440
+ "grad_norm": 4.825160026550293,
441
+ "learning_rate": 6.2e-05,
442
+ "loss": 1.6357,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.0031599934793785345,
447
+ "grad_norm": 4.864975929260254,
448
+ "learning_rate": 6.3e-05,
449
+ "loss": 1.8173,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.0032101521060353367,
454
+ "grad_norm": 5.236722946166992,
455
+ "learning_rate": 6.400000000000001e-05,
456
+ "loss": 1.6182,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.003260310732692139,
461
+ "grad_norm": 5.208855628967285,
462
+ "learning_rate": 6.500000000000001e-05,
463
+ "loss": 1.6164,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.003310469359348941,
468
+ "grad_norm": 4.640886306762695,
469
+ "learning_rate": 6.6e-05,
470
+ "loss": 1.4392,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.0033606279860057433,
475
+ "grad_norm": 6.360536575317383,
476
+ "learning_rate": 6.7e-05,
477
+ "loss": 1.555,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.003410786612662545,
482
+ "grad_norm": 5.957921028137207,
483
+ "learning_rate": 6.800000000000001e-05,
484
+ "loss": 1.7957,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.0034609452393193473,
489
+ "grad_norm": 4.701836109161377,
490
+ "learning_rate": 6.9e-05,
491
+ "loss": 1.6242,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.0035111038659761495,
496
+ "grad_norm": 5.555307388305664,
497
+ "learning_rate": 7e-05,
498
+ "loss": 1.2819,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.0035612624926329517,
503
+ "grad_norm": 5.1163177490234375,
504
+ "learning_rate": 7.1e-05,
505
+ "loss": 1.4986,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.003611421119289754,
510
+ "grad_norm": 6.242301940917969,
511
+ "learning_rate": 7.2e-05,
512
+ "loss": 1.9205,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.003661579745946556,
517
+ "grad_norm": 3.3643064498901367,
518
+ "learning_rate": 7.3e-05,
519
+ "loss": 1.6765,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.003711738372603358,
524
+ "grad_norm": 6.956996917724609,
525
+ "learning_rate": 7.4e-05,
526
+ "loss": 1.7204,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.00376189699926016,
531
+ "grad_norm": 4.798349380493164,
532
+ "learning_rate": 7.500000000000001e-05,
533
+ "loss": 1.8442,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.0038120556259169623,
538
+ "grad_norm": 3.9241135120391846,
539
+ "learning_rate": 7.6e-05,
540
+ "loss": 1.6925,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.0038622142525737645,
545
+ "grad_norm": 7.881755828857422,
546
+ "learning_rate": 7.7e-05,
547
+ "loss": 1.7764,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.003912372879230567,
552
+ "grad_norm": 6.434783458709717,
553
+ "learning_rate": 7.800000000000001e-05,
554
+ "loss": 1.5407,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.0039625315058873685,
559
+ "grad_norm": 4.235235691070557,
560
+ "learning_rate": 7.900000000000001e-05,
561
+ "loss": 1.9038,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.004012690132544171,
566
+ "grad_norm": 6.253316879272461,
567
+ "learning_rate": 8e-05,
568
+ "loss": 1.6845,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.004062848759200973,
573
+ "grad_norm": 4.719666957855225,
574
+ "learning_rate": 8.1e-05,
575
+ "loss": 1.8441,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.0041130073858577755,
580
+ "grad_norm": 4.454250335693359,
581
+ "learning_rate": 8.2e-05,
582
+ "loss": 1.9411,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.004163166012514577,
587
+ "grad_norm": 5.313316345214844,
588
+ "learning_rate": 8.3e-05,
589
+ "loss": 1.5968,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.004213324639171379,
594
+ "grad_norm": 4.927578449249268,
595
+ "learning_rate": 8.4e-05,
596
+ "loss": 1.5322,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.004263483265828182,
601
+ "grad_norm": 4.616065979003906,
602
+ "learning_rate": 8.5e-05,
603
+ "loss": 1.748,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.0043136418924849835,
608
+ "grad_norm": 6.438388347625732,
609
+ "learning_rate": 8.6e-05,
610
+ "loss": 1.7049,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.004363800519141786,
615
+ "grad_norm": 4.77520751953125,
616
+ "learning_rate": 8.7e-05,
617
+ "loss": 1.6878,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.004413959145798588,
622
+ "grad_norm": 5.103641033172607,
623
+ "learning_rate": 8.800000000000001e-05,
624
+ "loss": 1.4719,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.0044641177724553905,
629
+ "grad_norm": 4.581231594085693,
630
+ "learning_rate": 8.900000000000001e-05,
631
+ "loss": 1.7409,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.004514276399112192,
636
+ "grad_norm": 5.612283706665039,
637
+ "learning_rate": 9e-05,
638
+ "loss": 1.7616,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.004564435025768994,
643
+ "grad_norm": 6.311402320861816,
644
+ "learning_rate": 9.1e-05,
645
+ "loss": 1.4114,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.004614593652425797,
650
+ "grad_norm": 9.486177444458008,
651
+ "learning_rate": 9.200000000000001e-05,
652
+ "loss": 1.1956,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.0046647522790825985,
657
+ "grad_norm": 7.196384906768799,
658
+ "learning_rate": 9.300000000000001e-05,
659
+ "loss": 1.706,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.004714910905739401,
664
+ "grad_norm": 5.772494316101074,
665
+ "learning_rate": 9.4e-05,
666
+ "loss": 1.5761,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.004765069532396203,
671
+ "grad_norm": 7.097485542297363,
672
+ "learning_rate": 9.5e-05,
673
+ "loss": 1.4743,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.0048152281590530055,
678
+ "grad_norm": 7.195338249206543,
679
+ "learning_rate": 9.6e-05,
680
+ "loss": 1.4798,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.004865386785709807,
685
+ "grad_norm": 7.066890239715576,
686
+ "learning_rate": 9.7e-05,
687
+ "loss": 1.1984,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.004915545412366609,
692
+ "grad_norm": 8.48562240600586,
693
+ "learning_rate": 9.8e-05,
694
+ "loss": 1.3506,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.004965704039023412,
699
+ "grad_norm": 8.873973846435547,
700
+ "learning_rate": 9.900000000000001e-05,
701
+ "loss": 1.1898,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.0050158626656802135,
706
+ "grad_norm": 9.311749458312988,
707
+ "learning_rate": 0.0001,
708
+ "loss": 0.9361,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.005066021292337016,
713
+ "grad_norm": 3.371002674102783,
714
+ "learning_rate": 9.999999993078908e-05,
715
+ "loss": 1.8373,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.005116179918993818,
720
+ "grad_norm": 3.5822818279266357,
721
+ "learning_rate": 9.999999972315628e-05,
722
+ "loss": 1.6158,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.00516633854565062,
727
+ "grad_norm": 3.606417179107666,
728
+ "learning_rate": 9.999999937710161e-05,
729
+ "loss": 1.6813,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.005216497172307422,
734
+ "grad_norm": 5.331118583679199,
735
+ "learning_rate": 9.999999889262508e-05,
736
+ "loss": 1.7903,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.005266655798964224,
741
+ "grad_norm": 4.608427047729492,
742
+ "learning_rate": 9.999999826972668e-05,
743
+ "loss": 1.7265,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.005316814425621027,
748
+ "grad_norm": 5.363006114959717,
749
+ "learning_rate": 9.999999750840643e-05,
750
+ "loss": 1.8263,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.0053669730522778285,
755
+ "grad_norm": 4.672063827514648,
756
+ "learning_rate": 9.99999966086643e-05,
757
+ "loss": 1.7855,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.005417131678934631,
762
+ "grad_norm": 5.497429370880127,
763
+ "learning_rate": 9.999999557050034e-05,
764
+ "loss": 1.4177,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.005467290305591433,
769
+ "grad_norm": 6.637028694152832,
770
+ "learning_rate": 9.99999943939145e-05,
771
+ "loss": 1.7589,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.005517448932248235,
776
+ "grad_norm": 3.890974998474121,
777
+ "learning_rate": 9.999999307890684e-05,
778
+ "loss": 1.498,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.005567607558905037,
783
+ "grad_norm": 3.6080667972564697,
784
+ "learning_rate": 9.99999916254773e-05,
785
+ "loss": 1.3389,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.005617766185561839,
790
+ "grad_norm": 3.9386773109436035,
791
+ "learning_rate": 9.999999003362595e-05,
792
+ "loss": 1.5423,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.005667924812218642,
797
+ "grad_norm": 3.796339511871338,
798
+ "learning_rate": 9.999998830335273e-05,
799
+ "loss": 1.6022,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.0057180834388754435,
804
+ "grad_norm": 5.058220386505127,
805
+ "learning_rate": 9.999998643465769e-05,
806
+ "loss": 1.6884,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.005768242065532246,
811
+ "grad_norm": 4.7729692459106445,
812
+ "learning_rate": 9.999998442754082e-05,
813
+ "loss": 1.2262,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.005818400692189048,
818
+ "grad_norm": 5.240146160125732,
819
+ "learning_rate": 9.999998228200212e-05,
820
+ "loss": 1.569,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.00586855931884585,
825
+ "grad_norm": 5.360896110534668,
826
+ "learning_rate": 9.999997999804161e-05,
827
+ "loss": 1.7018,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.005918717945502652,
832
+ "grad_norm": 6.045897483825684,
833
+ "learning_rate": 9.999997757565929e-05,
834
+ "loss": 1.5096,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.005968876572159454,
839
+ "grad_norm": 5.264241695404053,
840
+ "learning_rate": 9.999997501485517e-05,
841
+ "loss": 1.6213,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.006019035198816257,
846
+ "grad_norm": 3.9072487354278564,
847
+ "learning_rate": 9.999997231562923e-05,
848
+ "loss": 1.6774,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.0060691938254730585,
853
+ "grad_norm": 4.171389579772949,
854
+ "learning_rate": 9.999996947798151e-05,
855
+ "loss": 1.5459,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.006119352452129861,
860
+ "grad_norm": 5.671729564666748,
861
+ "learning_rate": 9.999996650191202e-05,
862
+ "loss": 1.8808,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.006169511078786663,
867
+ "grad_norm": 4.9551239013671875,
868
+ "learning_rate": 9.999996338742074e-05,
869
+ "loss": 1.7071,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.006219669705443465,
874
+ "grad_norm": 4.296231746673584,
875
+ "learning_rate": 9.999996013450772e-05,
876
+ "loss": 1.7096,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.006269828332100267,
881
+ "grad_norm": 4.7311272621154785,
882
+ "learning_rate": 9.999995674317293e-05,
883
+ "loss": 1.7114,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.006319986958757069,
888
+ "grad_norm": 5.266380310058594,
889
+ "learning_rate": 9.999995321341638e-05,
890
+ "loss": 1.5675,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.006370145585413872,
895
+ "grad_norm": 5.088979721069336,
896
+ "learning_rate": 9.999994954523811e-05,
897
+ "loss": 1.7762,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.0064203042120706735,
902
+ "grad_norm": 5.097537994384766,
903
+ "learning_rate": 9.99999457386381e-05,
904
+ "loss": 1.6353,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.006470462838727475,
909
+ "grad_norm": 5.021105766296387,
910
+ "learning_rate": 9.999994179361638e-05,
911
+ "loss": 1.635,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.006520621465384278,
916
+ "grad_norm": 4.90013313293457,
917
+ "learning_rate": 9.999993771017295e-05,
918
+ "loss": 1.8159,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.00657078009204108,
923
+ "grad_norm": 6.177980422973633,
924
+ "learning_rate": 9.999993348830783e-05,
925
+ "loss": 1.6693,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.006620938718697882,
930
+ "grad_norm": 4.298121929168701,
931
+ "learning_rate": 9.999992912802102e-05,
932
+ "loss": 1.5833,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.006671097345354684,
937
+ "grad_norm": 5.9864349365234375,
938
+ "learning_rate": 9.999992462931256e-05,
939
+ "loss": 1.5427,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.006721255972011487,
944
+ "grad_norm": 4.874154090881348,
945
+ "learning_rate": 9.999991999218243e-05,
946
+ "loss": 1.8125,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.0067714145986682885,
951
+ "grad_norm": 4.420952320098877,
952
+ "learning_rate": 9.999991521663066e-05,
953
+ "loss": 1.6948,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.00682157322532509,
958
+ "grad_norm": 7.217179775238037,
959
+ "learning_rate": 9.999991030265726e-05,
960
+ "loss": 1.3042,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.006871731851981893,
965
+ "grad_norm": 5.299327373504639,
966
+ "learning_rate": 9.999990525026222e-05,
967
+ "loss": 1.5594,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.006921890478638695,
972
+ "grad_norm": 4.912446975708008,
973
+ "learning_rate": 9.99999000594456e-05,
974
+ "loss": 1.673,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.006972049105295497,
979
+ "grad_norm": 4.7740654945373535,
980
+ "learning_rate": 9.999989473020737e-05,
981
+ "loss": 1.6493,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.007022207731952299,
986
+ "grad_norm": 5.836091041564941,
987
+ "learning_rate": 9.999988926254758e-05,
988
+ "loss": 1.296,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.007072366358609102,
993
+ "grad_norm": 5.817897796630859,
994
+ "learning_rate": 9.999988365646623e-05,
995
+ "loss": 1.6388,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.0071225249852659035,
1000
+ "grad_norm": 5.8604278564453125,
1001
+ "learning_rate": 9.999987791196333e-05,
1002
+ "loss": 1.9454,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.007172683611922705,
1007
+ "grad_norm": 6.577927112579346,
1008
+ "learning_rate": 9.999987202903889e-05,
1009
+ "loss": 1.6439,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.007222842238579508,
1014
+ "grad_norm": 5.996036052703857,
1015
+ "learning_rate": 9.999986600769295e-05,
1016
+ "loss": 1.5554,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.00727300086523631,
1021
+ "grad_norm": 5.742420196533203,
1022
+ "learning_rate": 9.999985984792553e-05,
1023
+ "loss": 1.6343,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.007323159491893112,
1028
+ "grad_norm": 6.655057907104492,
1029
+ "learning_rate": 9.99998535497366e-05,
1030
+ "loss": 1.541,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.007373318118549914,
1035
+ "grad_norm": 5.933575630187988,
1036
+ "learning_rate": 9.999984711312622e-05,
1037
+ "loss": 1.204,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.007423476745206716,
1042
+ "grad_norm": 8.165215492248535,
1043
+ "learning_rate": 9.999984053809441e-05,
1044
+ "loss": 1.4714,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.0074736353718635185,
1049
+ "grad_norm": 8.663423538208008,
1050
+ "learning_rate": 9.999983382464116e-05,
1051
+ "loss": 1.3971,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.00752379399852032,
1056
+ "grad_norm": 7.599918365478516,
1057
+ "learning_rate": 9.999982697276651e-05,
1058
+ "loss": 0.9067,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.007573952625177123,
1063
+ "grad_norm": 3.1658380031585693,
1064
+ "learning_rate": 9.999981998247048e-05,
1065
+ "loss": 1.9463,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.007624111251833925,
1070
+ "grad_norm": 3.542314052581787,
1071
+ "learning_rate": 9.999981285375307e-05,
1072
+ "loss": 1.742,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.007674269878490727,
1077
+ "grad_norm": 4.111073970794678,
1078
+ "learning_rate": 9.999980558661432e-05,
1079
+ "loss": 1.7274,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.007724428505147529,
1084
+ "grad_norm": 5.310257911682129,
1085
+ "learning_rate": 9.999979818105423e-05,
1086
+ "loss": 1.9207,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.007774587131804331,
1091
+ "grad_norm": 4.864629745483398,
1092
+ "learning_rate": 9.999979063707284e-05,
1093
+ "loss": 1.7775,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.007824745758461133,
1098
+ "grad_norm": 4.800562381744385,
1099
+ "learning_rate": 9.999978295467016e-05,
1100
+ "loss": 1.6394,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.007874904385117936,
1105
+ "grad_norm": 5.542998790740967,
1106
+ "learning_rate": 9.999977513384622e-05,
1107
+ "loss": 1.9211,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.007925063011774737,
1112
+ "grad_norm": 4.554020881652832,
1113
+ "learning_rate": 9.999976717460102e-05,
1114
+ "loss": 1.7228,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.00797522163843154,
1119
+ "grad_norm": 5.0133056640625,
1120
+ "learning_rate": 9.999975907693461e-05,
1121
+ "loss": 1.6986,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.008025380265088342,
1126
+ "grad_norm": 3.597456932067871,
1127
+ "learning_rate": 9.9999750840847e-05,
1128
+ "loss": 1.618,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.008075538891745143,
1133
+ "grad_norm": 3.8272383213043213,
1134
+ "learning_rate": 9.999974246633824e-05,
1135
+ "loss": 1.5303,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.008125697518401946,
1140
+ "grad_norm": 4.668627738952637,
1141
+ "learning_rate": 9.999973395340828e-05,
1142
+ "loss": 1.715,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.008175856145058748,
1147
+ "grad_norm": 3.4355103969573975,
1148
+ "learning_rate": 9.999972530205721e-05,
1149
+ "loss": 1.5708,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.008226014771715551,
1154
+ "grad_norm": 4.077895641326904,
1155
+ "learning_rate": 9.999971651228504e-05,
1156
+ "loss": 2.0105,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.008276173398372352,
1161
+ "grad_norm": 5.014714241027832,
1162
+ "learning_rate": 9.999970758409179e-05,
1163
+ "loss": 1.8614,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.008326332025029155,
1168
+ "grad_norm": 5.244025707244873,
1169
+ "learning_rate": 9.999969851747746e-05,
1170
+ "loss": 1.7,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.008376490651685957,
1175
+ "grad_norm": 5.047165393829346,
1176
+ "learning_rate": 9.999968931244212e-05,
1177
+ "loss": 1.6595,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.008426649278342758,
1182
+ "grad_norm": 4.581408500671387,
1183
+ "learning_rate": 9.999967996898576e-05,
1184
+ "loss": 1.8837,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.00847680790499956,
1189
+ "grad_norm": 5.111804962158203,
1190
+ "learning_rate": 9.999967048710844e-05,
1191
+ "loss": 1.2134,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.008526966531656363,
1196
+ "grad_norm": 4.815063953399658,
1197
+ "learning_rate": 9.999966086681014e-05,
1198
+ "loss": 1.8506,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.008577125158313166,
1203
+ "grad_norm": 4.20850944519043,
1204
+ "learning_rate": 9.999965110809093e-05,
1205
+ "loss": 1.1193,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.008627283784969967,
1210
+ "grad_norm": 7.372136116027832,
1211
+ "learning_rate": 9.999964121095081e-05,
1212
+ "loss": 1.4076,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.00867744241162677,
1217
+ "grad_norm": 4.237338066101074,
1218
+ "learning_rate": 9.999963117538982e-05,
1219
+ "loss": 1.7532,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.008727601038283572,
1224
+ "grad_norm": 4.2047905921936035,
1225
+ "learning_rate": 9.999962100140799e-05,
1226
+ "loss": 1.7366,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.008777759664940373,
1231
+ "grad_norm": 4.078057765960693,
1232
+ "learning_rate": 9.999961068900532e-05,
1233
+ "loss": 1.696,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.008827918291597176,
1238
+ "grad_norm": 3.925241231918335,
1239
+ "learning_rate": 9.999960023818189e-05,
1240
+ "loss": 1.8851,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.008878076918253978,
1245
+ "grad_norm": 4.202706813812256,
1246
+ "learning_rate": 9.999958964893767e-05,
1247
+ "loss": 1.6194,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.008928235544910781,
1252
+ "grad_norm": 5.677591800689697,
1253
+ "learning_rate": 9.999957892127275e-05,
1254
+ "loss": 1.8302,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.008978394171567582,
1259
+ "grad_norm": 4.774147987365723,
1260
+ "learning_rate": 9.99995680551871e-05,
1261
+ "loss": 1.9582,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.009028552798224385,
1266
+ "grad_norm": 4.708377361297607,
1267
+ "learning_rate": 9.999955705068081e-05,
1268
+ "loss": 1.5443,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.009078711424881187,
1273
+ "grad_norm": 6.373831748962402,
1274
+ "learning_rate": 9.999954590775387e-05,
1275
+ "loss": 1.4237,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.009128870051537988,
1280
+ "grad_norm": 4.654812812805176,
1281
+ "learning_rate": 9.999953462640633e-05,
1282
+ "loss": 2.0366,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.00917902867819479,
1287
+ "grad_norm": 5.303413391113281,
1288
+ "learning_rate": 9.999952320663817e-05,
1289
+ "loss": 1.5228,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.009229187304851593,
1294
+ "grad_norm": 4.800450801849365,
1295
+ "learning_rate": 9.99995116484495e-05,
1296
+ "loss": 1.6961,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.009279345931508396,
1301
+ "grad_norm": 4.739235877990723,
1302
+ "learning_rate": 9.99994999518403e-05,
1303
+ "loss": 1.8077,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.009329504558165197,
1308
+ "grad_norm": 4.644327163696289,
1309
+ "learning_rate": 9.999948811681063e-05,
1310
+ "loss": 1.6023,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.009379663184822,
1315
+ "grad_norm": 4.27376127243042,
1316
+ "learning_rate": 9.999947614336051e-05,
1317
+ "loss": 1.6617,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.009429821811478802,
1322
+ "grad_norm": 3.941235065460205,
1323
+ "learning_rate": 9.999946403148997e-05,
1324
+ "loss": 1.5798,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.009479980438135603,
1329
+ "grad_norm": 4.801257610321045,
1330
+ "learning_rate": 9.999945178119906e-05,
1331
+ "loss": 1.5509,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.009530139064792406,
1336
+ "grad_norm": 4.117572784423828,
1337
+ "learning_rate": 9.999943939248777e-05,
1338
+ "loss": 1.655,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.009580297691449208,
1343
+ "grad_norm": 4.655939102172852,
1344
+ "learning_rate": 9.999942686535619e-05,
1345
+ "loss": 1.5012,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.009630456318106011,
1350
+ "grad_norm": 4.619282245635986,
1351
+ "learning_rate": 9.999941419980431e-05,
1352
+ "loss": 1.3436,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.009680614944762812,
1357
+ "grad_norm": 5.15116548538208,
1358
+ "learning_rate": 9.99994013958322e-05,
1359
+ "loss": 1.8281,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.009730773571419615,
1364
+ "grad_norm": 5.120091915130615,
1365
+ "learning_rate": 9.999938845343988e-05,
1366
+ "loss": 1.7552,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.009780932198076417,
1371
+ "grad_norm": 5.901042938232422,
1372
+ "learning_rate": 9.999937537262738e-05,
1373
+ "loss": 1.5446,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.009831090824733218,
1378
+ "grad_norm": 6.0915846824646,
1379
+ "learning_rate": 9.999936215339475e-05,
1380
+ "loss": 1.4559,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.00988124945139002,
1385
+ "grad_norm": 6.821080207824707,
1386
+ "learning_rate": 9.999934879574202e-05,
1387
+ "loss": 1.6452,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.009931408078046823,
1392
+ "grad_norm": 6.907961845397949,
1393
+ "learning_rate": 9.999933529966923e-05,
1394
+ "loss": 1.4225,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.009981566704703626,
1399
+ "grad_norm": 6.944931983947754,
1400
+ "learning_rate": 9.99993216651764e-05,
1401
+ "loss": 1.1927,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.010031725331360427,
1406
+ "grad_norm": 7.315927505493164,
1407
+ "learning_rate": 9.999930789226358e-05,
1408
+ "loss": 0.863,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.01008188395801723,
1413
+ "grad_norm": 2.1428048610687256,
1414
+ "learning_rate": 9.999929398093082e-05,
1415
+ "loss": 1.7098,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 0.010132042584674032,
1420
+ "grad_norm": 3.6517727375030518,
1421
+ "learning_rate": 9.999927993117815e-05,
1422
+ "loss": 1.6545,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 0.010182201211330833,
1427
+ "grad_norm": 4.238412380218506,
1428
+ "learning_rate": 9.999926574300559e-05,
1429
+ "loss": 1.9832,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 0.010232359837987636,
1434
+ "grad_norm": 4.278627395629883,
1435
+ "learning_rate": 9.999925141641322e-05,
1436
+ "loss": 1.825,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 0.010282518464644438,
1441
+ "grad_norm": 4.463462829589844,
1442
+ "learning_rate": 9.999923695140103e-05,
1443
+ "loss": 1.6986,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 0.01033267709130124,
1448
+ "grad_norm": 5.852229118347168,
1449
+ "learning_rate": 9.99992223479691e-05,
1450
+ "loss": 1.9561,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 0.010382835717958042,
1455
+ "grad_norm": 5.828834533691406,
1456
+ "learning_rate": 9.999920760611747e-05,
1457
+ "loss": 1.5839,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 0.010432994344614845,
1462
+ "grad_norm": 4.150822639465332,
1463
+ "learning_rate": 9.999919272584615e-05,
1464
+ "loss": 1.7085,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 0.010483152971271647,
1469
+ "grad_norm": 3.853485107421875,
1470
+ "learning_rate": 9.99991777071552e-05,
1471
+ "loss": 1.7434,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 0.010533311597928448,
1476
+ "grad_norm": 3.409013509750366,
1477
+ "learning_rate": 9.999916255004466e-05,
1478
+ "loss": 1.4738,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 0.01058347022458525,
1483
+ "grad_norm": 4.30065393447876,
1484
+ "learning_rate": 9.999914725451457e-05,
1485
+ "loss": 1.6132,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 0.010633628851242053,
1490
+ "grad_norm": 4.496330261230469,
1491
+ "learning_rate": 9.999913182056498e-05,
1492
+ "loss": 1.6567,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 0.010683787477898854,
1497
+ "grad_norm": 3.97495698928833,
1498
+ "learning_rate": 9.999911624819593e-05,
1499
+ "loss": 1.6223,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 0.010733946104555657,
1504
+ "grad_norm": 3.9297423362731934,
1505
+ "learning_rate": 9.999910053740744e-05,
1506
+ "loss": 1.9551,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 0.01078410473121246,
1511
+ "grad_norm": 4.655943393707275,
1512
+ "learning_rate": 9.99990846881996e-05,
1513
+ "loss": 1.3605,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 0.010834263357869262,
1518
+ "grad_norm": 3.850569248199463,
1519
+ "learning_rate": 9.99990687005724e-05,
1520
+ "loss": 1.4915,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 0.010884421984526063,
1525
+ "grad_norm": 3.8779959678649902,
1526
+ "learning_rate": 9.999905257452593e-05,
1527
+ "loss": 1.697,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 0.010934580611182866,
1532
+ "grad_norm": 3.9161744117736816,
1533
+ "learning_rate": 9.999903631006023e-05,
1534
+ "loss": 1.472,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 0.010984739237839668,
1539
+ "grad_norm": 3.332963705062866,
1540
+ "learning_rate": 9.99990199071753e-05,
1541
+ "loss": 1.8336,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 0.01103489786449647,
1546
+ "grad_norm": 3.0808727741241455,
1547
+ "learning_rate": 9.999900336587124e-05,
1548
+ "loss": 1.8147,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 0.011085056491153272,
1553
+ "grad_norm": 3.166036605834961,
1554
+ "learning_rate": 9.999898668614807e-05,
1555
+ "loss": 1.5529,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 0.011135215117810075,
1560
+ "grad_norm": 4.316058158874512,
1561
+ "learning_rate": 9.999896986800583e-05,
1562
+ "loss": 1.8339,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 0.011185373744466877,
1567
+ "grad_norm": 3.5491528511047363,
1568
+ "learning_rate": 9.999895291144456e-05,
1569
+ "loss": 1.457,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 0.011235532371123678,
1574
+ "grad_norm": 4.302348613739014,
1575
+ "learning_rate": 9.999893581646436e-05,
1576
+ "loss": 1.8205,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 0.01128569099778048,
1581
+ "grad_norm": 4.645691871643066,
1582
+ "learning_rate": 9.99989185830652e-05,
1583
+ "loss": 1.6126,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 0.011335849624437283,
1588
+ "grad_norm": 3.585592746734619,
1589
+ "learning_rate": 9.99989012112472e-05,
1590
+ "loss": 1.6233,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 0.011386008251094084,
1595
+ "grad_norm": 4.083550930023193,
1596
+ "learning_rate": 9.999888370101036e-05,
1597
+ "loss": 1.6479,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 0.011436166877750887,
1602
+ "grad_norm": 4.8738274574279785,
1603
+ "learning_rate": 9.999886605235475e-05,
1604
+ "loss": 1.544,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 0.01148632550440769,
1609
+ "grad_norm": 4.471858978271484,
1610
+ "learning_rate": 9.999884826528039e-05,
1611
+ "loss": 1.7492,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 0.011536484131064492,
1616
+ "grad_norm": 4.995892524719238,
1617
+ "learning_rate": 9.999883033978738e-05,
1618
+ "loss": 1.4996,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 0.011586642757721293,
1623
+ "grad_norm": 3.729520320892334,
1624
+ "learning_rate": 9.999881227587573e-05,
1625
+ "loss": 1.2047,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 0.011636801384378096,
1630
+ "grad_norm": 3.6157472133636475,
1631
+ "learning_rate": 9.999879407354551e-05,
1632
+ "loss": 1.8276,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 0.011686960011034898,
1637
+ "grad_norm": 3.605586528778076,
1638
+ "learning_rate": 9.999877573279675e-05,
1639
+ "loss": 1.6217,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 0.0117371186376917,
1644
+ "grad_norm": 3.8058934211730957,
1645
+ "learning_rate": 9.999875725362953e-05,
1646
+ "loss": 1.602,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 0.011787277264348502,
1651
+ "grad_norm": 4.18014669418335,
1652
+ "learning_rate": 9.999873863604385e-05,
1653
+ "loss": 1.572,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 0.011837435891005305,
1658
+ "grad_norm": 3.300985336303711,
1659
+ "learning_rate": 9.999871988003983e-05,
1660
+ "loss": 1.3266,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 0.011887594517662107,
1665
+ "grad_norm": 4.596490383148193,
1666
+ "learning_rate": 9.999870098561748e-05,
1667
+ "loss": 1.5166,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 0.011937753144318908,
1672
+ "grad_norm": 3.664485216140747,
1673
+ "learning_rate": 9.999868195277684e-05,
1674
+ "loss": 1.6468,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 0.01198791177097571,
1679
+ "grad_norm": 4.02537202835083,
1680
+ "learning_rate": 9.999866278151801e-05,
1681
+ "loss": 1.7261,
1682
+ "step": 239
1683
+ }
1684
+ ],
1685
+ "logging_steps": 1,
1686
+ "max_steps": 59808,
1687
+ "num_input_tokens_seen": 0,
1688
+ "num_train_epochs": 3,
1689
+ "save_steps": 239,
1690
+ "stateful_callbacks": {
1691
+ "TrainerControl": {
1692
+ "args": {
1693
+ "should_epoch_stop": false,
1694
+ "should_evaluate": false,
1695
+ "should_log": false,
1696
+ "should_save": true,
1697
+ "should_training_stop": false
1698
+ },
1699
+ "attributes": {}
1700
+ }
1701
+ },
1702
+ "total_flos": 2.164717070057472e+16,
1703
+ "train_batch_size": 2,
1704
+ "trial_name": null,
1705
+ "trial_params": null
1706
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6ee56cf3ad6533b74f45eeb6d4801c4c9cf0152917a29fc04e29b3924e5e760
3
+ size 6840
last-checkpoint/vocab.json ADDED
The diff for this file is too large to render. See raw diff