ErrorAI commited on
Commit
b8ab7af
·
verified ·
1 Parent(s): 7a7c619

Training in progress, step 332, checkpoint

Browse files
last-checkpoint/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: OpenBuddy/openbuddy-llama2-13b-v8.1-fp16
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 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "OpenBuddy/openbuddy-llama2-13b-v8.1-fp16",
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": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "up_proj",
24
+ "o_proj",
25
+ "down_proj",
26
+ "gate_proj",
27
+ "q_proj",
28
+ "v_proj",
29
+ "k_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
last-checkpoint/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbe098209d1686cb8fc334b54c24397029c02c12c19bf5529ebe5c0ffeb2de4d
3
+ size 125248064
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:195fc343b97778daec912a96e8e2cd31a10bc9800e86f556c2f62ea6ed949836
3
+ size 64220436
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f27826ade17aebc5a87c4b7484b191bb18255bf804458cb979418d7b11938d1
3
+ size 14244
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edf35abeb4468756dc16f35cb005448f26edd325a42353dc5acb547729bd337c
3
+ size 1064
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f440c53d2cc6f14a7ed7124dea5f5a7402fb4fc95bccb5d8be6d0f7e74d327ed
3
+ size 568229
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "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 %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "</s>",
38
+ "sp_model_kwargs": {},
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,2357 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.2507079478950349,
5
+ "eval_steps": 500,
6
+ "global_step": 332,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0007551444213705871,
13
+ "grad_norm": 0.059659671038389206,
14
+ "learning_rate": 2e-05,
15
+ "loss": 0.4492,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0015102888427411742,
20
+ "grad_norm": 0.0642104372382164,
21
+ "learning_rate": 4e-05,
22
+ "loss": 0.4602,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.0022654332641117614,
27
+ "grad_norm": 0.06154001131653786,
28
+ "learning_rate": 6e-05,
29
+ "loss": 0.488,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.0030205776854823484,
34
+ "grad_norm": 0.07486463338136673,
35
+ "learning_rate": 8e-05,
36
+ "loss": 0.5672,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.003775722106852936,
41
+ "grad_norm": 0.08084491640329361,
42
+ "learning_rate": 0.0001,
43
+ "loss": 0.525,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.004530866528223523,
48
+ "grad_norm": 0.09173104912042618,
49
+ "learning_rate": 9.999985839072915e-05,
50
+ "loss": 0.523,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.00528601094959411,
55
+ "grad_norm": 0.10932840406894684,
56
+ "learning_rate": 9.999943356371866e-05,
57
+ "loss": 0.4872,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.006041155370964697,
62
+ "grad_norm": 0.14193305373191833,
63
+ "learning_rate": 9.999872552137497e-05,
64
+ "loss": 0.5677,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.006796299792335284,
69
+ "grad_norm": 0.15595699846744537,
70
+ "learning_rate": 9.999773426770865e-05,
71
+ "loss": 0.6329,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.007551444213705872,
76
+ "grad_norm": 0.157088503241539,
77
+ "learning_rate": 9.999645980833454e-05,
78
+ "loss": 0.5819,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.008306588635076459,
83
+ "grad_norm": 0.12618108093738556,
84
+ "learning_rate": 9.999490215047167e-05,
85
+ "loss": 0.5207,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.009061733056447046,
90
+ "grad_norm": 0.15058279037475586,
91
+ "learning_rate": 9.999306130294317e-05,
92
+ "loss": 0.5821,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.009816877477817633,
97
+ "grad_norm": 0.12929701805114746,
98
+ "learning_rate": 9.99909372761763e-05,
99
+ "loss": 0.5065,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.01057202189918822,
104
+ "grad_norm": 0.12497358024120331,
105
+ "learning_rate": 9.99885300822023e-05,
106
+ "loss": 0.524,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.011327166320558807,
111
+ "grad_norm": 0.12322711199522018,
112
+ "learning_rate": 9.998583973465646e-05,
113
+ "loss": 0.605,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.012082310741929394,
118
+ "grad_norm": 0.11271341890096664,
119
+ "learning_rate": 9.998286624877786e-05,
120
+ "loss": 0.5465,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.01283745516329998,
125
+ "grad_norm": 0.11549581587314606,
126
+ "learning_rate": 9.997960964140947e-05,
127
+ "loss": 0.5595,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.013592599584670568,
132
+ "grad_norm": 0.12339697778224945,
133
+ "learning_rate": 9.997606993099789e-05,
134
+ "loss": 0.4647,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.014347744006041155,
139
+ "grad_norm": 0.13940560817718506,
140
+ "learning_rate": 9.997224713759335e-05,
141
+ "loss": 0.5441,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.015102888427411743,
146
+ "grad_norm": 0.12651537358760834,
147
+ "learning_rate": 9.99681412828496e-05,
148
+ "loss": 0.5482,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.01585803284878233,
153
+ "grad_norm": 0.13802285492420197,
154
+ "learning_rate": 9.996375239002369e-05,
155
+ "loss": 0.4715,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.016613177270152917,
160
+ "grad_norm": 0.13440218567848206,
161
+ "learning_rate": 9.995908048397595e-05,
162
+ "loss": 0.5641,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.017368321691523504,
167
+ "grad_norm": 0.139227494597435,
168
+ "learning_rate": 9.995412559116979e-05,
169
+ "loss": 0.4398,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.01812346611289409,
174
+ "grad_norm": 0.1373261958360672,
175
+ "learning_rate": 9.994888773967157e-05,
176
+ "loss": 0.5384,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.018878610534264678,
181
+ "grad_norm": 0.14462506771087646,
182
+ "learning_rate": 9.99433669591504e-05,
183
+ "loss": 0.5708,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.019633754955635265,
188
+ "grad_norm": 0.14911501109600067,
189
+ "learning_rate": 9.993756328087805e-05,
190
+ "loss": 0.5851,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.020388899377005852,
195
+ "grad_norm": 0.13722750544548035,
196
+ "learning_rate": 9.99314767377287e-05,
197
+ "loss": 0.488,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.02114404379837644,
202
+ "grad_norm": 0.1530655175447464,
203
+ "learning_rate": 9.992510736417878e-05,
204
+ "loss": 0.5364,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.021899188219747026,
209
+ "grad_norm": 0.14158278703689575,
210
+ "learning_rate": 9.991845519630678e-05,
211
+ "loss": 0.4066,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.022654332641117613,
216
+ "grad_norm": 0.14002585411071777,
217
+ "learning_rate": 9.991152027179307e-05,
218
+ "loss": 0.4307,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.0234094770624882,
223
+ "grad_norm": 0.15578630566596985,
224
+ "learning_rate": 9.990430262991962e-05,
225
+ "loss": 0.4661,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.024164621483858787,
230
+ "grad_norm": 0.16023118793964386,
231
+ "learning_rate": 9.989680231156981e-05,
232
+ "loss": 0.4454,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.024919765905229374,
237
+ "grad_norm": 0.17581893503665924,
238
+ "learning_rate": 9.988901935922826e-05,
239
+ "loss": 0.5209,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.02567491032659996,
244
+ "grad_norm": 0.1649864912033081,
245
+ "learning_rate": 9.988095381698048e-05,
246
+ "loss": 0.5037,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.026430054747970548,
251
+ "grad_norm": 0.18106521666049957,
252
+ "learning_rate": 9.987260573051269e-05,
253
+ "loss": 0.4649,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.027185199169341135,
258
+ "grad_norm": 0.1807573437690735,
259
+ "learning_rate": 9.986397514711154e-05,
260
+ "loss": 0.4987,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.027940343590711722,
265
+ "grad_norm": 0.392092764377594,
266
+ "learning_rate": 9.985506211566388e-05,
267
+ "loss": 0.526,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.02869548801208231,
272
+ "grad_norm": 0.17764483392238617,
273
+ "learning_rate": 9.98458666866564e-05,
274
+ "loss": 0.4262,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.0294506324334529,
279
+ "grad_norm": 0.20041850209236145,
280
+ "learning_rate": 9.983638891217544e-05,
281
+ "loss": 0.5239,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.030205776854823486,
286
+ "grad_norm": 0.19753199815750122,
287
+ "learning_rate": 9.982662884590662e-05,
288
+ "loss": 0.4918,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.030960921276194073,
293
+ "grad_norm": 0.19215907156467438,
294
+ "learning_rate": 9.981658654313457e-05,
295
+ "loss": 0.4474,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.03171606569756466,
300
+ "grad_norm": 0.19931669533252716,
301
+ "learning_rate": 9.980626206074263e-05,
302
+ "loss": 0.4531,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.032471210118935244,
307
+ "grad_norm": 0.20595461130142212,
308
+ "learning_rate": 9.979565545721248e-05,
309
+ "loss": 0.4495,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.033226354540305834,
314
+ "grad_norm": 0.20857509970664978,
315
+ "learning_rate": 9.978476679262387e-05,
316
+ "loss": 0.4331,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.03398149896167642,
321
+ "grad_norm": 0.21194373071193695,
322
+ "learning_rate": 9.977359612865423e-05,
323
+ "loss": 0.3721,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.03473664338304701,
328
+ "grad_norm": 0.21357247233390808,
329
+ "learning_rate": 9.976214352857834e-05,
330
+ "loss": 0.4586,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.03549178780441759,
335
+ "grad_norm": 0.23830629885196686,
336
+ "learning_rate": 9.975040905726798e-05,
337
+ "loss": 0.4416,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.03624693222578818,
342
+ "grad_norm": 0.2576565444469452,
343
+ "learning_rate": 9.973839278119155e-05,
344
+ "loss": 0.4685,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.037002076647158766,
349
+ "grad_norm": 0.5738092660903931,
350
+ "learning_rate": 9.972609476841367e-05,
351
+ "loss": 0.3931,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.037757221068529356,
356
+ "grad_norm": 0.31976327300071716,
357
+ "learning_rate": 9.971351508859488e-05,
358
+ "loss": 0.419,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.03851236548989995,
363
+ "grad_norm": 0.11089778691530228,
364
+ "learning_rate": 9.970065381299112e-05,
365
+ "loss": 0.3417,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.03926750991127053,
370
+ "grad_norm": 0.13030797243118286,
371
+ "learning_rate": 9.968751101445343e-05,
372
+ "loss": 0.3921,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.04002265433264112,
377
+ "grad_norm": 0.12426062673330307,
378
+ "learning_rate": 9.967408676742751e-05,
379
+ "loss": 0.3519,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.040777798754011704,
384
+ "grad_norm": 0.13413658738136292,
385
+ "learning_rate": 9.966038114795328e-05,
386
+ "loss": 0.4093,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.041532943175382295,
391
+ "grad_norm": 0.1284988820552826,
392
+ "learning_rate": 9.964639423366442e-05,
393
+ "loss": 0.4002,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.04228808759675288,
398
+ "grad_norm": 0.11679685115814209,
399
+ "learning_rate": 9.963212610378803e-05,
400
+ "loss": 0.4191,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.04304323201812347,
405
+ "grad_norm": 0.12084402143955231,
406
+ "learning_rate": 9.961757683914406e-05,
407
+ "loss": 0.3768,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.04379837643949405,
412
+ "grad_norm": 0.11981435120105743,
413
+ "learning_rate": 9.960274652214496e-05,
414
+ "loss": 0.4396,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.04455352086086464,
419
+ "grad_norm": 0.1252336949110031,
420
+ "learning_rate": 9.958763523679514e-05,
421
+ "loss": 0.4526,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.045308665282235226,
426
+ "grad_norm": 0.12791119515895844,
427
+ "learning_rate": 9.957224306869053e-05,
428
+ "loss": 0.4877,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.04606380970360582,
433
+ "grad_norm": 0.12734884023666382,
434
+ "learning_rate": 9.955657010501806e-05,
435
+ "loss": 0.4608,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.0468189541249764,
440
+ "grad_norm": 0.12033625692129135,
441
+ "learning_rate": 9.954061643455523e-05,
442
+ "loss": 0.4842,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.04757409854634699,
447
+ "grad_norm": 0.11826111376285553,
448
+ "learning_rate": 9.952438214766955e-05,
449
+ "loss": 0.4132,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.048329242967717574,
454
+ "grad_norm": 0.12830643355846405,
455
+ "learning_rate": 9.950786733631801e-05,
456
+ "loss": 0.4733,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.049084387389088165,
461
+ "grad_norm": 0.13267682492733002,
462
+ "learning_rate": 9.949107209404665e-05,
463
+ "loss": 0.4303,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.04983953181045875,
468
+ "grad_norm": 0.12670353055000305,
469
+ "learning_rate": 9.947399651598993e-05,
470
+ "loss": 0.5202,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.05059467623182934,
475
+ "grad_norm": 0.15055082738399506,
476
+ "learning_rate": 9.945664069887028e-05,
477
+ "loss": 0.4475,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.05134982065319992,
482
+ "grad_norm": 0.13549265265464783,
483
+ "learning_rate": 9.943900474099748e-05,
484
+ "loss": 0.5083,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.05210496507457051,
489
+ "grad_norm": 0.12346430122852325,
490
+ "learning_rate": 9.942108874226811e-05,
491
+ "loss": 0.3601,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.052860109495941096,
496
+ "grad_norm": 0.14251157641410828,
497
+ "learning_rate": 9.940289280416508e-05,
498
+ "loss": 0.4827,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.05361525391731169,
503
+ "grad_norm": 0.13678328692913055,
504
+ "learning_rate": 9.938441702975689e-05,
505
+ "loss": 0.4081,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.05437039833868227,
510
+ "grad_norm": 0.13870520889759064,
511
+ "learning_rate": 9.93656615236972e-05,
512
+ "loss": 0.442,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.05512554276005286,
517
+ "grad_norm": 0.13190938532352448,
518
+ "learning_rate": 9.934662639222412e-05,
519
+ "loss": 0.409,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.055880687181423444,
524
+ "grad_norm": 0.1491832584142685,
525
+ "learning_rate": 9.932731174315972e-05,
526
+ "loss": 0.5432,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.056635831602794035,
531
+ "grad_norm": 0.14117342233657837,
532
+ "learning_rate": 9.930771768590933e-05,
533
+ "loss": 0.436,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.05739097602416462,
538
+ "grad_norm": 0.15490145981311798,
539
+ "learning_rate": 9.928784433146096e-05,
540
+ "loss": 0.4399,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.05814612044553521,
545
+ "grad_norm": 0.15420539677143097,
546
+ "learning_rate": 9.926769179238466e-05,
547
+ "loss": 0.4223,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.0589012648669058,
552
+ "grad_norm": 0.15358476340770721,
553
+ "learning_rate": 9.924726018283187e-05,
554
+ "loss": 0.4702,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.05965640928827638,
559
+ "grad_norm": 0.15698279440402985,
560
+ "learning_rate": 9.922654961853481e-05,
561
+ "loss": 0.4728,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.06041155370964697,
566
+ "grad_norm": 0.16668903827667236,
567
+ "learning_rate": 9.92055602168058e-05,
568
+ "loss": 0.4654,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.061166698131017556,
573
+ "grad_norm": 0.16828201711177826,
574
+ "learning_rate": 9.918429209653662e-05,
575
+ "loss": 0.4588,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.06192184255238815,
580
+ "grad_norm": 0.1675289273262024,
581
+ "learning_rate": 9.916274537819775e-05,
582
+ "loss": 0.489,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.06267698697375873,
587
+ "grad_norm": 0.19768594205379486,
588
+ "learning_rate": 9.914092018383778e-05,
589
+ "loss": 0.4707,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.06343213139512932,
594
+ "grad_norm": 0.17943724989891052,
595
+ "learning_rate": 9.911881663708275e-05,
596
+ "loss": 0.458,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.06418727581649991,
601
+ "grad_norm": 0.18578174710273743,
602
+ "learning_rate": 9.909643486313533e-05,
603
+ "loss": 0.403,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.06494242023787049,
608
+ "grad_norm": 0.1998097449541092,
609
+ "learning_rate": 9.90737749887742e-05,
610
+ "loss": 0.5154,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.06569756465924108,
615
+ "grad_norm": 0.18927428126335144,
616
+ "learning_rate": 9.905083714235326e-05,
617
+ "loss": 0.4682,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.06645270908061167,
622
+ "grad_norm": 0.18993408977985382,
623
+ "learning_rate": 9.9027621453801e-05,
624
+ "loss": 0.4373,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.06720785350198226,
629
+ "grad_norm": 0.18295501172542572,
630
+ "learning_rate": 9.900412805461967e-05,
631
+ "loss": 0.4163,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.06796299792335284,
636
+ "grad_norm": 0.20295414328575134,
637
+ "learning_rate": 9.898035707788463e-05,
638
+ "loss": 0.4816,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.06871814234472343,
643
+ "grad_norm": 0.21273529529571533,
644
+ "learning_rate": 9.895630865824347e-05,
645
+ "loss": 0.4363,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.06947328676609402,
650
+ "grad_norm": 0.21219299733638763,
651
+ "learning_rate": 9.893198293191538e-05,
652
+ "loss": 0.5055,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.07022843118746461,
657
+ "grad_norm": 0.2346925586462021,
658
+ "learning_rate": 9.890738003669029e-05,
659
+ "loss": 0.5144,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.07098357560883518,
664
+ "grad_norm": 0.2355310320854187,
665
+ "learning_rate": 9.888250011192811e-05,
666
+ "loss": 0.4826,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.07173872003020577,
671
+ "grad_norm": 0.23005840182304382,
672
+ "learning_rate": 9.885734329855798e-05,
673
+ "loss": 0.4764,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.07249386445157636,
678
+ "grad_norm": 0.2246306836605072,
679
+ "learning_rate": 9.883190973907741e-05,
680
+ "loss": 0.3891,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.07324900887294696,
685
+ "grad_norm": 0.28144529461860657,
686
+ "learning_rate": 9.880619957755151e-05,
687
+ "loss": 0.5174,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.07400415329431753,
692
+ "grad_norm": 0.27972379326820374,
693
+ "learning_rate": 9.878021295961217e-05,
694
+ "loss": 0.4433,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.07475929771568812,
699
+ "grad_norm": 0.3294559717178345,
700
+ "learning_rate": 9.875395003245724e-05,
701
+ "loss": 0.442,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.07551444213705871,
706
+ "grad_norm": 0.3774302303791046,
707
+ "learning_rate": 9.872741094484965e-05,
708
+ "loss": 0.5358,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.0762695865584293,
713
+ "grad_norm": 0.12596380710601807,
714
+ "learning_rate": 9.870059584711668e-05,
715
+ "loss": 0.3584,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.0770247309797999,
720
+ "grad_norm": 0.1355014592409134,
721
+ "learning_rate": 9.867350489114894e-05,
722
+ "loss": 0.4008,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.07777987540117047,
727
+ "grad_norm": 0.14024491608142853,
728
+ "learning_rate": 9.864613823039969e-05,
729
+ "loss": 0.3752,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.07853501982254106,
734
+ "grad_norm": 0.13403770327568054,
735
+ "learning_rate": 9.861849601988383e-05,
736
+ "loss": 0.38,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.07929016424391165,
741
+ "grad_norm": 0.1362624615430832,
742
+ "learning_rate": 9.859057841617709e-05,
743
+ "loss": 0.3889,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.08004530866528224,
748
+ "grad_norm": 0.137498140335083,
749
+ "learning_rate": 9.856238557741513e-05,
750
+ "loss": 0.4215,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.08080045308665282,
755
+ "grad_norm": 0.1259029656648636,
756
+ "learning_rate": 9.853391766329263e-05,
757
+ "loss": 0.3831,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.08155559750802341,
762
+ "grad_norm": 0.12306073307991028,
763
+ "learning_rate": 9.850517483506244e-05,
764
+ "loss": 0.3843,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.082310741929394,
769
+ "grad_norm": 0.12481655925512314,
770
+ "learning_rate": 9.847615725553456e-05,
771
+ "loss": 0.4206,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.08306588635076459,
776
+ "grad_norm": 0.11769527196884155,
777
+ "learning_rate": 9.844686508907537e-05,
778
+ "loss": 0.3633,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.08382103077213517,
783
+ "grad_norm": 0.12572641670703888,
784
+ "learning_rate": 9.841729850160652e-05,
785
+ "loss": 0.4113,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.08457617519350576,
790
+ "grad_norm": 0.12385623157024384,
791
+ "learning_rate": 9.838745766060416e-05,
792
+ "loss": 0.3894,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.08533131961487635,
797
+ "grad_norm": 0.13819383084774017,
798
+ "learning_rate": 9.835734273509786e-05,
799
+ "loss": 0.4989,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.08608646403624694,
804
+ "grad_norm": 0.13039085268974304,
805
+ "learning_rate": 9.832695389566972e-05,
806
+ "loss": 0.4502,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.08684160845761751,
811
+ "grad_norm": 0.14915941655635834,
812
+ "learning_rate": 9.829629131445342e-05,
813
+ "loss": 0.4674,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.0875967528789881,
818
+ "grad_norm": 0.13414114713668823,
819
+ "learning_rate": 9.826535516513317e-05,
820
+ "loss": 0.4914,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.0883518973003587,
825
+ "grad_norm": 0.13531801104545593,
826
+ "learning_rate": 9.82341456229428e-05,
827
+ "loss": 0.4764,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.08910704172172929,
832
+ "grad_norm": 0.1374198943376541,
833
+ "learning_rate": 9.820266286466471e-05,
834
+ "loss": 0.4299,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.08986218614309986,
839
+ "grad_norm": 0.14264227449893951,
840
+ "learning_rate": 9.817090706862895e-05,
841
+ "loss": 0.4164,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.09061733056447045,
846
+ "grad_norm": 0.14601197838783264,
847
+ "learning_rate": 9.81388784147121e-05,
848
+ "loss": 0.4273,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.09137247498584104,
853
+ "grad_norm": 0.1535925269126892,
854
+ "learning_rate": 9.810657708433637e-05,
855
+ "loss": 0.4947,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.09212761940721163,
860
+ "grad_norm": 0.1509617269039154,
861
+ "learning_rate": 9.807400326046843e-05,
862
+ "loss": 0.3626,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.09288276382858221,
867
+ "grad_norm": 0.15619726479053497,
868
+ "learning_rate": 9.804115712761851e-05,
869
+ "loss": 0.4597,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.0936379082499528,
874
+ "grad_norm": 0.1454990804195404,
875
+ "learning_rate": 9.80080388718393e-05,
876
+ "loss": 0.3858,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.09439305267132339,
881
+ "grad_norm": 0.1631968766450882,
882
+ "learning_rate": 9.797464868072488e-05,
883
+ "loss": 0.435,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.09514819709269398,
888
+ "grad_norm": 0.15620705485343933,
889
+ "learning_rate": 9.794098674340965e-05,
890
+ "loss": 0.4259,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.09590334151406457,
895
+ "grad_norm": 0.16626444458961487,
896
+ "learning_rate": 9.790705325056735e-05,
897
+ "loss": 0.4253,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.09665848593543515,
902
+ "grad_norm": 0.16531290113925934,
903
+ "learning_rate": 9.787284839440982e-05,
904
+ "loss": 0.4284,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.09741363035680574,
909
+ "grad_norm": 0.15550102293491364,
910
+ "learning_rate": 9.783837236868609e-05,
911
+ "loss": 0.3745,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.09816877477817633,
916
+ "grad_norm": 0.17284280061721802,
917
+ "learning_rate": 9.780362536868113e-05,
918
+ "loss": 0.4458,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.09892391919954692,
923
+ "grad_norm": 0.16307754814624786,
924
+ "learning_rate": 9.776860759121484e-05,
925
+ "loss": 0.4001,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.0996790636209175,
930
+ "grad_norm": 0.1765722781419754,
931
+ "learning_rate": 9.77333192346409e-05,
932
+ "loss": 0.4215,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.10043420804228809,
937
+ "grad_norm": 0.1748800426721573,
938
+ "learning_rate": 9.769776049884563e-05,
939
+ "loss": 0.4215,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.10118935246365868,
944
+ "grad_norm": 0.18451336026191711,
945
+ "learning_rate": 9.766193158524692e-05,
946
+ "loss": 0.4214,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.10194449688502927,
951
+ "grad_norm": 0.19954369962215424,
952
+ "learning_rate": 9.762583269679303e-05,
953
+ "loss": 0.4085,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.10269964130639984,
958
+ "grad_norm": 0.2019212394952774,
959
+ "learning_rate": 9.758946403796143e-05,
960
+ "loss": 0.3836,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.10345478572777043,
965
+ "grad_norm": 0.20586973428726196,
966
+ "learning_rate": 9.755282581475769e-05,
967
+ "loss": 0.4231,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.10420993014914103,
972
+ "grad_norm": 0.2090785652399063,
973
+ "learning_rate": 9.751591823471429e-05,
974
+ "loss": 0.4385,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.10496507457051162,
979
+ "grad_norm": 0.21643619239330292,
980
+ "learning_rate": 9.747874150688948e-05,
981
+ "loss": 0.4758,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.10572021899188219,
986
+ "grad_norm": 0.19914501905441284,
987
+ "learning_rate": 9.744129584186598e-05,
988
+ "loss": 0.3888,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.10647536341325278,
993
+ "grad_norm": 0.23445309698581696,
994
+ "learning_rate": 9.740358145174998e-05,
995
+ "loss": 0.4988,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.10723050783462337,
1000
+ "grad_norm": 0.21564048528671265,
1001
+ "learning_rate": 9.736559855016973e-05,
1002
+ "loss": 0.4387,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.10798565225599396,
1007
+ "grad_norm": 0.21970051527023315,
1008
+ "learning_rate": 9.73273473522745e-05,
1009
+ "loss": 0.3984,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.10874079667736454,
1014
+ "grad_norm": 0.24472594261169434,
1015
+ "learning_rate": 9.728882807473324e-05,
1016
+ "loss": 0.378,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.10949594109873513,
1021
+ "grad_norm": 0.24230483174324036,
1022
+ "learning_rate": 9.725004093573342e-05,
1023
+ "loss": 0.4024,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.11025108552010572,
1028
+ "grad_norm": 0.24002547562122345,
1029
+ "learning_rate": 9.72109861549798e-05,
1030
+ "loss": 0.3738,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.11100622994147631,
1035
+ "grad_norm": 0.2504161298274994,
1036
+ "learning_rate": 9.717166395369313e-05,
1037
+ "loss": 0.3868,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.11176137436284689,
1042
+ "grad_norm": 0.2596012055873871,
1043
+ "learning_rate": 9.713207455460894e-05,
1044
+ "loss": 0.4068,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.11251651878421748,
1049
+ "grad_norm": 0.3224775493144989,
1050
+ "learning_rate": 9.709221818197624e-05,
1051
+ "loss": 0.4875,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.11327166320558807,
1056
+ "grad_norm": 0.40476924180984497,
1057
+ "learning_rate": 9.705209506155634e-05,
1058
+ "loss": 0.4832,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.11402680762695866,
1063
+ "grad_norm": 0.11512809246778488,
1064
+ "learning_rate": 9.701170542062148e-05,
1065
+ "loss": 0.3255,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.11478195204832924,
1070
+ "grad_norm": 0.13325871527194977,
1071
+ "learning_rate": 9.697104948795352e-05,
1072
+ "loss": 0.3707,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.11553709646969983,
1077
+ "grad_norm": 0.1390884816646576,
1078
+ "learning_rate": 9.693012749384279e-05,
1079
+ "loss": 0.3659,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.11629224089107042,
1084
+ "grad_norm": 0.13481466472148895,
1085
+ "learning_rate": 9.688893967008661e-05,
1086
+ "loss": 0.3847,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.11704738531244101,
1091
+ "grad_norm": 0.14832735061645508,
1092
+ "learning_rate": 9.68474862499881e-05,
1093
+ "loss": 0.457,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.1178025297338116,
1098
+ "grad_norm": 0.13634005188941956,
1099
+ "learning_rate": 9.68057674683548e-05,
1100
+ "loss": 0.4172,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.11855767415518217,
1105
+ "grad_norm": 0.1387951821088791,
1106
+ "learning_rate": 9.676378356149734e-05,
1107
+ "loss": 0.4252,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.11931281857655276,
1112
+ "grad_norm": 0.1387217789888382,
1113
+ "learning_rate": 9.672153476722816e-05,
1114
+ "loss": 0.3928,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.12006796299792336,
1119
+ "grad_norm": 0.14391182363033295,
1120
+ "learning_rate": 9.667902132486009e-05,
1121
+ "loss": 0.4545,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.12082310741929395,
1126
+ "grad_norm": 0.1416245996952057,
1127
+ "learning_rate": 9.663624347520505e-05,
1128
+ "loss": 0.4543,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.12157825184066452,
1133
+ "grad_norm": 0.13763579726219177,
1134
+ "learning_rate": 9.659320146057262e-05,
1135
+ "loss": 0.3957,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.12233339626203511,
1140
+ "grad_norm": 0.14178583025932312,
1141
+ "learning_rate": 9.654989552476875e-05,
1142
+ "loss": 0.448,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.1230885406834057,
1147
+ "grad_norm": 0.13738113641738892,
1148
+ "learning_rate": 9.650632591309431e-05,
1149
+ "loss": 0.3954,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.1238436851047763,
1154
+ "grad_norm": 0.14869531989097595,
1155
+ "learning_rate": 9.646249287234374e-05,
1156
+ "loss": 0.4405,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.12459882952614687,
1161
+ "grad_norm": 0.14332245290279388,
1162
+ "learning_rate": 9.641839665080363e-05,
1163
+ "loss": 0.4543,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.12535397394751746,
1168
+ "grad_norm": 0.14617004990577698,
1169
+ "learning_rate": 9.637403749825135e-05,
1170
+ "loss": 0.397,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.12610911836888805,
1175
+ "grad_norm": 0.16142374277114868,
1176
+ "learning_rate": 9.632941566595357e-05,
1177
+ "loss": 0.5283,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.12686426279025864,
1182
+ "grad_norm": 0.15721464157104492,
1183
+ "learning_rate": 9.628453140666492e-05,
1184
+ "loss": 0.433,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.12761940721162923,
1189
+ "grad_norm": 0.1646830439567566,
1190
+ "learning_rate": 9.623938497462646e-05,
1191
+ "loss": 0.5024,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.12837455163299982,
1196
+ "grad_norm": 0.14574110507965088,
1197
+ "learning_rate": 9.619397662556435e-05,
1198
+ "loss": 0.4194,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.12912969605437039,
1203
+ "grad_norm": 0.15734295547008514,
1204
+ "learning_rate": 9.614830661668829e-05,
1205
+ "loss": 0.4757,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.12988484047574098,
1210
+ "grad_norm": 0.15386731922626495,
1211
+ "learning_rate": 9.610237520669016e-05,
1212
+ "loss": 0.3874,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.13063998489711157,
1217
+ "grad_norm": 0.16264206171035767,
1218
+ "learning_rate": 9.60561826557425e-05,
1219
+ "loss": 0.409,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.13139512931848216,
1224
+ "grad_norm": 0.1713552325963974,
1225
+ "learning_rate": 9.600972922549707e-05,
1226
+ "loss": 0.4799,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.13215027373985275,
1231
+ "grad_norm": 0.17139887809753418,
1232
+ "learning_rate": 9.596301517908328e-05,
1233
+ "loss": 0.3992,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.13290541816122334,
1238
+ "grad_norm": 0.16348589956760406,
1239
+ "learning_rate": 9.591604078110685e-05,
1240
+ "loss": 0.3942,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.13366056258259393,
1245
+ "grad_norm": 0.1675892323255539,
1246
+ "learning_rate": 9.586880629764817e-05,
1247
+ "loss": 0.4305,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.13441570700396452,
1252
+ "grad_norm": 0.1761837750673294,
1253
+ "learning_rate": 9.582131199626087e-05,
1254
+ "loss": 0.4386,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.1351708514253351,
1259
+ "grad_norm": 0.1876501590013504,
1260
+ "learning_rate": 9.577355814597031e-05,
1261
+ "loss": 0.4765,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.13592599584670567,
1266
+ "grad_norm": 0.18781447410583496,
1267
+ "learning_rate": 9.572554501727198e-05,
1268
+ "loss": 0.4502,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.13668114026807626,
1273
+ "grad_norm": 0.20662984251976013,
1274
+ "learning_rate": 9.567727288213005e-05,
1275
+ "loss": 0.4612,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.13743628468944685,
1280
+ "grad_norm": 0.19330036640167236,
1281
+ "learning_rate": 9.56287420139758e-05,
1282
+ "loss": 0.4344,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.13819142911081744,
1287
+ "grad_norm": 0.19399768114089966,
1288
+ "learning_rate": 9.557995268770608e-05,
1289
+ "loss": 0.4314,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.13894657353218803,
1294
+ "grad_norm": 0.200825035572052,
1295
+ "learning_rate": 9.553090517968169e-05,
1296
+ "loss": 0.4095,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.13970171795355862,
1301
+ "grad_norm": 0.21249161660671234,
1302
+ "learning_rate": 9.548159976772592e-05,
1303
+ "loss": 0.5122,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.14045686237492921,
1308
+ "grad_norm": 0.2057344764471054,
1309
+ "learning_rate": 9.543203673112293e-05,
1310
+ "loss": 0.4131,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.1412120067962998,
1315
+ "grad_norm": 0.2109992653131485,
1316
+ "learning_rate": 9.538221635061611e-05,
1317
+ "loss": 0.4596,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.14196715121767037,
1322
+ "grad_norm": 0.2060767263174057,
1323
+ "learning_rate": 9.533213890840657e-05,
1324
+ "loss": 0.4008,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.14272229563904096,
1329
+ "grad_norm": 0.22520488500595093,
1330
+ "learning_rate": 9.528180468815155e-05,
1331
+ "loss": 0.451,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.14347744006041155,
1336
+ "grad_norm": 0.23366759717464447,
1337
+ "learning_rate": 9.523121397496269e-05,
1338
+ "loss": 0.435,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.14423258448178214,
1343
+ "grad_norm": 0.23018625378608704,
1344
+ "learning_rate": 9.518036705540458e-05,
1345
+ "loss": 0.4397,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.14498772890315273,
1350
+ "grad_norm": 0.22498714923858643,
1351
+ "learning_rate": 9.512926421749304e-05,
1352
+ "loss": 0.3717,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.14574287332452332,
1357
+ "grad_norm": 0.24823418259620667,
1358
+ "learning_rate": 9.507790575069347e-05,
1359
+ "loss": 0.3805,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.1464980177458939,
1364
+ "grad_norm": 0.27361419796943665,
1365
+ "learning_rate": 9.502629194591926e-05,
1366
+ "loss": 0.5063,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.1472531621672645,
1371
+ "grad_norm": 0.27400317788124084,
1372
+ "learning_rate": 9.497442309553016e-05,
1373
+ "loss": 0.455,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.14800830658863506,
1378
+ "grad_norm": 0.30166488885879517,
1379
+ "learning_rate": 9.492229949333058e-05,
1380
+ "loss": 0.5024,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.14876345101000565,
1385
+ "grad_norm": 0.29768070578575134,
1386
+ "learning_rate": 9.486992143456792e-05,
1387
+ "loss": 0.382,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.14951859543137624,
1392
+ "grad_norm": 0.3229611814022064,
1393
+ "learning_rate": 9.481728921593093e-05,
1394
+ "loss": 0.4178,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.15027373985274683,
1399
+ "grad_norm": 0.31606340408325195,
1400
+ "learning_rate": 9.476440313554803e-05,
1401
+ "loss": 0.403,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.15102888427411743,
1406
+ "grad_norm": 0.3485797047615051,
1407
+ "learning_rate": 9.471126349298556e-05,
1408
+ "loss": 0.3898,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.15178402869548802,
1413
+ "grad_norm": 0.12325902283191681,
1414
+ "learning_rate": 9.46578705892462e-05,
1415
+ "loss": 0.3083,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 0.1525391731168586,
1420
+ "grad_norm": 0.1569177210330963,
1421
+ "learning_rate": 9.460422472676712e-05,
1422
+ "loss": 0.3685,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 0.1532943175382292,
1427
+ "grad_norm": 0.1423245519399643,
1428
+ "learning_rate": 9.45503262094184e-05,
1429
+ "loss": 0.341,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 0.1540494619595998,
1434
+ "grad_norm": 0.13771581649780273,
1435
+ "learning_rate": 9.449617534250122e-05,
1436
+ "loss": 0.3271,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 0.15480460638097035,
1441
+ "grad_norm": 0.15911588072776794,
1442
+ "learning_rate": 9.444177243274618e-05,
1443
+ "loss": 0.4001,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 0.15555975080234094,
1448
+ "grad_norm": 0.14060606062412262,
1449
+ "learning_rate": 9.438711778831152e-05,
1450
+ "loss": 0.3537,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 0.15631489522371153,
1455
+ "grad_norm": 0.1690395623445511,
1456
+ "learning_rate": 9.433221171878144e-05,
1457
+ "loss": 0.5235,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 0.15707003964508212,
1462
+ "grad_norm": 0.133980393409729,
1463
+ "learning_rate": 9.427705453516427e-05,
1464
+ "loss": 0.351,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 0.1578251840664527,
1469
+ "grad_norm": 0.1446908861398697,
1470
+ "learning_rate": 9.422164654989072e-05,
1471
+ "loss": 0.3714,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 0.1585803284878233,
1476
+ "grad_norm": 0.15370596945285797,
1477
+ "learning_rate": 9.41659880768122e-05,
1478
+ "loss": 0.4452,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 0.1593354729091939,
1483
+ "grad_norm": 0.15254907310009003,
1484
+ "learning_rate": 9.411007943119894e-05,
1485
+ "loss": 0.4388,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 0.16009061733056448,
1490
+ "grad_norm": 0.14596116542816162,
1491
+ "learning_rate": 9.405392092973823e-05,
1492
+ "loss": 0.4037,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 0.16084576175193505,
1497
+ "grad_norm": 0.14959284663200378,
1498
+ "learning_rate": 9.399751289053267e-05,
1499
+ "loss": 0.3917,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 0.16160090617330564,
1504
+ "grad_norm": 0.16624942421913147,
1505
+ "learning_rate": 9.394085563309827e-05,
1506
+ "loss": 0.4609,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 0.16235605059467623,
1511
+ "grad_norm": 0.16217663884162903,
1512
+ "learning_rate": 9.388394947836279e-05,
1513
+ "loss": 0.4446,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 0.16311119501604682,
1518
+ "grad_norm": 0.1554042100906372,
1519
+ "learning_rate": 9.382679474866376e-05,
1520
+ "loss": 0.4281,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 0.1638663394374174,
1525
+ "grad_norm": 0.16471102833747864,
1526
+ "learning_rate": 9.376939176774679e-05,
1527
+ "loss": 0.4674,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 0.164621483858788,
1532
+ "grad_norm": 0.15578734874725342,
1533
+ "learning_rate": 9.371174086076363e-05,
1534
+ "loss": 0.3938,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 0.1653766282801586,
1539
+ "grad_norm": 0.16161073744297028,
1540
+ "learning_rate": 9.365384235427042e-05,
1541
+ "loss": 0.4238,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 0.16613177270152918,
1546
+ "grad_norm": 0.16967645287513733,
1547
+ "learning_rate": 9.359569657622574e-05,
1548
+ "loss": 0.4663,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 0.16688691712289974,
1553
+ "grad_norm": 0.1597963124513626,
1554
+ "learning_rate": 9.353730385598887e-05,
1555
+ "loss": 0.4046,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 0.16764206154427033,
1560
+ "grad_norm": 0.17794618010520935,
1561
+ "learning_rate": 9.34786645243178e-05,
1562
+ "loss": 0.4111,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 0.16839720596564092,
1567
+ "grad_norm": 0.16721504926681519,
1568
+ "learning_rate": 9.341977891336749e-05,
1569
+ "loss": 0.4147,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 0.1691523503870115,
1574
+ "grad_norm": 0.1782609224319458,
1575
+ "learning_rate": 9.336064735668784e-05,
1576
+ "loss": 0.4159,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 0.1699074948083821,
1581
+ "grad_norm": 0.17892874777317047,
1582
+ "learning_rate": 9.330127018922194e-05,
1583
+ "loss": 0.4498,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 0.1706626392297527,
1588
+ "grad_norm": 0.18540053069591522,
1589
+ "learning_rate": 9.324164774730406e-05,
1590
+ "loss": 0.4727,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 0.17141778365112328,
1595
+ "grad_norm": 0.19462263584136963,
1596
+ "learning_rate": 9.318178036865785e-05,
1597
+ "loss": 0.4427,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 0.17217292807249387,
1602
+ "grad_norm": 0.19947673380374908,
1603
+ "learning_rate": 9.312166839239433e-05,
1604
+ "loss": 0.4262,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 0.17292807249386447,
1609
+ "grad_norm": 0.19704130291938782,
1610
+ "learning_rate": 9.306131215901003e-05,
1611
+ "loss": 0.4226,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 0.17368321691523503,
1616
+ "grad_norm": 0.18819350004196167,
1617
+ "learning_rate": 9.300071201038503e-05,
1618
+ "loss": 0.4082,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 0.17443836133660562,
1623
+ "grad_norm": 0.20187118649482727,
1624
+ "learning_rate": 9.293986828978106e-05,
1625
+ "loss": 0.449,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 0.1751935057579762,
1630
+ "grad_norm": 0.2177709937095642,
1631
+ "learning_rate": 9.287878134183948e-05,
1632
+ "loss": 0.4607,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 0.1759486501793468,
1637
+ "grad_norm": 0.2070026397705078,
1638
+ "learning_rate": 9.281745151257946e-05,
1639
+ "loss": 0.3923,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 0.1767037946007174,
1644
+ "grad_norm": 0.2048753798007965,
1645
+ "learning_rate": 9.275587914939586e-05,
1646
+ "loss": 0.4518,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 0.17745893902208798,
1651
+ "grad_norm": 0.20374053716659546,
1652
+ "learning_rate": 9.26940646010574e-05,
1653
+ "loss": 0.4258,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 0.17821408344345857,
1658
+ "grad_norm": 0.22188866138458252,
1659
+ "learning_rate": 9.263200821770461e-05,
1660
+ "loss": 0.3896,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 0.17896922786482916,
1665
+ "grad_norm": 0.22264693677425385,
1666
+ "learning_rate": 9.256971035084785e-05,
1667
+ "loss": 0.4189,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 0.17972437228619972,
1672
+ "grad_norm": 0.2051049768924713,
1673
+ "learning_rate": 9.250717135336534e-05,
1674
+ "loss": 0.3751,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 0.18047951670757031,
1679
+ "grad_norm": 0.24615737795829773,
1680
+ "learning_rate": 9.244439157950114e-05,
1681
+ "loss": 0.4728,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 0.1812346611289409,
1686
+ "grad_norm": 0.2331840842962265,
1687
+ "learning_rate": 9.238137138486318e-05,
1688
+ "loss": 0.4516,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 0.1819898055503115,
1693
+ "grad_norm": 0.23615127801895142,
1694
+ "learning_rate": 9.231811112642121e-05,
1695
+ "loss": 0.3788,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 0.18274494997168209,
1700
+ "grad_norm": 0.2417721003293991,
1701
+ "learning_rate": 9.225461116250483e-05,
1702
+ "loss": 0.4161,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 0.18350009439305268,
1707
+ "grad_norm": 0.26503533124923706,
1708
+ "learning_rate": 9.219087185280132e-05,
1709
+ "loss": 0.4356,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 0.18425523881442327,
1714
+ "grad_norm": 0.24484668672084808,
1715
+ "learning_rate": 9.212689355835379e-05,
1716
+ "loss": 0.3629,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 0.18501038323579386,
1721
+ "grad_norm": 0.2426530420780182,
1722
+ "learning_rate": 9.206267664155907e-05,
1723
+ "loss": 0.3427,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 0.18576552765716442,
1728
+ "grad_norm": 0.26813021302223206,
1729
+ "learning_rate": 9.199822146616552e-05,
1730
+ "loss": 0.4148,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 0.186520672078535,
1735
+ "grad_norm": 0.3065304458141327,
1736
+ "learning_rate": 9.193352839727121e-05,
1737
+ "loss": 0.4015,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 0.1872758164999056,
1742
+ "grad_norm": 0.32816389203071594,
1743
+ "learning_rate": 9.186859780132164e-05,
1744
+ "loss": 0.4233,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 0.1880309609212762,
1749
+ "grad_norm": 0.3237447738647461,
1750
+ "learning_rate": 9.18034300461078e-05,
1751
+ "loss": 0.351,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 0.18878610534264678,
1756
+ "grad_norm": 0.3921673595905304,
1757
+ "learning_rate": 9.173802550076401e-05,
1758
+ "loss": 0.4465,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 0.18954124976401737,
1763
+ "grad_norm": 0.12883761525154114,
1764
+ "learning_rate": 9.167238453576589e-05,
1765
+ "loss": 0.3514,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 0.19029639418538796,
1770
+ "grad_norm": 0.14347058534622192,
1771
+ "learning_rate": 9.160650752292819e-05,
1772
+ "loss": 0.3831,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 0.19105153860675855,
1777
+ "grad_norm": 0.1370943933725357,
1778
+ "learning_rate": 9.154039483540273e-05,
1779
+ "loss": 0.3797,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 0.19180668302812914,
1784
+ "grad_norm": 0.1585707813501358,
1785
+ "learning_rate": 9.147404684767632e-05,
1786
+ "loss": 0.4072,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 0.1925618274494997,
1791
+ "grad_norm": 0.147821843624115,
1792
+ "learning_rate": 9.140746393556854e-05,
1793
+ "loss": 0.3441,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 0.1933169718708703,
1798
+ "grad_norm": 0.1582058221101761,
1799
+ "learning_rate": 9.134064647622972e-05,
1800
+ "loss": 0.4164,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 0.1940721162922409,
1805
+ "grad_norm": 0.1520204097032547,
1806
+ "learning_rate": 9.12735948481387e-05,
1807
+ "loss": 0.3704,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 0.19482726071361148,
1812
+ "grad_norm": 0.14902523159980774,
1813
+ "learning_rate": 9.120630943110077e-05,
1814
+ "loss": 0.4204,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 0.19558240513498207,
1819
+ "grad_norm": 0.14658547937870026,
1820
+ "learning_rate": 9.113879060624553e-05,
1821
+ "loss": 0.3435,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 0.19633754955635266,
1826
+ "grad_norm": 0.14122474193572998,
1827
+ "learning_rate": 9.107103875602459e-05,
1828
+ "loss": 0.3681,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 0.19709269397772325,
1833
+ "grad_norm": 0.14616741240024567,
1834
+ "learning_rate": 9.100305426420956e-05,
1835
+ "loss": 0.3931,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 0.19784783839909384,
1840
+ "grad_norm": 0.1556493043899536,
1841
+ "learning_rate": 9.093483751588983e-05,
1842
+ "loss": 0.3966,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 0.1986029828204644,
1847
+ "grad_norm": 0.1637788712978363,
1848
+ "learning_rate": 9.086638889747035e-05,
1849
+ "loss": 0.5167,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 0.199358127241835,
1854
+ "grad_norm": 0.1598958671092987,
1855
+ "learning_rate": 9.079770879666949e-05,
1856
+ "loss": 0.4257,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 0.20011327166320558,
1861
+ "grad_norm": 0.15921838581562042,
1862
+ "learning_rate": 9.072879760251679e-05,
1863
+ "loss": 0.4247,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 0.20086841608457617,
1868
+ "grad_norm": 0.16750189661979675,
1869
+ "learning_rate": 9.065965570535082e-05,
1870
+ "loss": 0.4249,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 0.20162356050594676,
1875
+ "grad_norm": 0.18144546449184418,
1876
+ "learning_rate": 9.059028349681694e-05,
1877
+ "loss": 0.5394,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 0.20237870492731735,
1882
+ "grad_norm": 0.16736812889575958,
1883
+ "learning_rate": 9.052068136986502e-05,
1884
+ "loss": 0.5119,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 0.20313384934868794,
1889
+ "grad_norm": 0.1700868159532547,
1890
+ "learning_rate": 9.045084971874738e-05,
1891
+ "loss": 0.4552,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 0.20388899377005854,
1896
+ "grad_norm": 0.17564022541046143,
1897
+ "learning_rate": 9.038078893901634e-05,
1898
+ "loss": 0.4344,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 0.2046441381914291,
1903
+ "grad_norm": 0.18228355050086975,
1904
+ "learning_rate": 9.031049942752215e-05,
1905
+ "loss": 0.4206,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 0.2053992826127997,
1910
+ "grad_norm": 0.17782603204250336,
1911
+ "learning_rate": 9.023998158241068e-05,
1912
+ "loss": 0.4786,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 0.20615442703417028,
1917
+ "grad_norm": 0.18378295004367828,
1918
+ "learning_rate": 9.016923580312113e-05,
1919
+ "loss": 0.443,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 0.20690957145554087,
1924
+ "grad_norm": 0.17299628257751465,
1925
+ "learning_rate": 9.009826249038387e-05,
1926
+ "loss": 0.3804,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 0.20766471587691146,
1931
+ "grad_norm": 0.19087707996368408,
1932
+ "learning_rate": 9.002706204621803e-05,
1933
+ "loss": 0.4698,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 0.20841986029828205,
1938
+ "grad_norm": 0.17627054452896118,
1939
+ "learning_rate": 8.995563487392932e-05,
1940
+ "loss": 0.3927,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 0.20917500471965264,
1945
+ "grad_norm": 0.19746743142604828,
1946
+ "learning_rate": 8.988398137810777e-05,
1947
+ "loss": 0.4765,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 0.20993014914102323,
1952
+ "grad_norm": 0.19492515921592712,
1953
+ "learning_rate": 8.981210196462533e-05,
1954
+ "loss": 0.4254,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 0.21068529356239382,
1959
+ "grad_norm": 0.19054411351680756,
1960
+ "learning_rate": 8.973999704063365e-05,
1961
+ "loss": 0.398,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 0.21144043798376438,
1966
+ "grad_norm": 0.202229306101799,
1967
+ "learning_rate": 8.966766701456177e-05,
1968
+ "loss": 0.5233,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 0.21219558240513497,
1973
+ "grad_norm": 0.20624679327011108,
1974
+ "learning_rate": 8.959511229611376e-05,
1975
+ "loss": 0.4411,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 0.21295072682650557,
1980
+ "grad_norm": 0.2044438272714615,
1981
+ "learning_rate": 8.952233329626647e-05,
1982
+ "loss": 0.4102,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 0.21370587124787616,
1987
+ "grad_norm": 0.20926257967948914,
1988
+ "learning_rate": 8.944933042726714e-05,
1989
+ "loss": 0.3872,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 0.21446101566924675,
1994
+ "grad_norm": 0.2206258326768875,
1995
+ "learning_rate": 8.937610410263109e-05,
1996
+ "loss": 0.4126,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 0.21521616009061734,
2001
+ "grad_norm": 0.23429769277572632,
2002
+ "learning_rate": 8.930265473713938e-05,
2003
+ "loss": 0.4453,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 0.21597130451198793,
2008
+ "grad_norm": 0.2304621934890747,
2009
+ "learning_rate": 8.922898274683644e-05,
2010
+ "loss": 0.4429,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 0.21672644893335852,
2015
+ "grad_norm": 0.23192839324474335,
2016
+ "learning_rate": 8.915508854902778e-05,
2017
+ "loss": 0.4737,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 0.21748159335472908,
2022
+ "grad_norm": 0.23144613206386566,
2023
+ "learning_rate": 8.908097256227749e-05,
2024
+ "loss": 0.382,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 0.21823673777609967,
2029
+ "grad_norm": 0.24735011160373688,
2030
+ "learning_rate": 8.900663520640604e-05,
2031
+ "loss": 0.3929,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 0.21899188219747026,
2036
+ "grad_norm": 0.267395555973053,
2037
+ "learning_rate": 8.893207690248776e-05,
2038
+ "loss": 0.4586,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 0.21974702661884085,
2043
+ "grad_norm": 0.2836948335170746,
2044
+ "learning_rate": 8.885729807284856e-05,
2045
+ "loss": 0.5218,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 0.22050217104021144,
2050
+ "grad_norm": 0.2509090304374695,
2051
+ "learning_rate": 8.878229914106342e-05,
2052
+ "loss": 0.4114,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 0.22125731546158203,
2057
+ "grad_norm": 0.27369990944862366,
2058
+ "learning_rate": 8.870708053195413e-05,
2059
+ "loss": 0.3736,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 0.22201245988295262,
2064
+ "grad_norm": 0.279341459274292,
2065
+ "learning_rate": 8.863164267158678e-05,
2066
+ "loss": 0.3845,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 0.2227676043043232,
2071
+ "grad_norm": 0.27738478779792786,
2072
+ "learning_rate": 8.855598598726939e-05,
2073
+ "loss": 0.3331,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 0.22352274872569378,
2078
+ "grad_norm": 0.32042670249938965,
2079
+ "learning_rate": 8.848011090754947e-05,
2080
+ "loss": 0.3943,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 0.22427789314706437,
2085
+ "grad_norm": 0.2977651059627533,
2086
+ "learning_rate": 8.840401786221159e-05,
2087
+ "loss": 0.3701,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 0.22503303756843496,
2092
+ "grad_norm": 0.35676780343055725,
2093
+ "learning_rate": 8.832770728227502e-05,
2094
+ "loss": 0.4728,
2095
+ "step": 298
2096
+ },
2097
+ {
2098
+ "epoch": 0.22578818198980555,
2099
+ "grad_norm": 0.3656991720199585,
2100
+ "learning_rate": 8.825117959999116e-05,
2101
+ "loss": 0.3662,
2102
+ "step": 299
2103
+ },
2104
+ {
2105
+ "epoch": 0.22654332641117614,
2106
+ "grad_norm": 0.36816850304603577,
2107
+ "learning_rate": 8.817443524884119e-05,
2108
+ "loss": 0.3644,
2109
+ "step": 300
2110
+ },
2111
+ {
2112
+ "epoch": 0.22729847083254673,
2113
+ "grad_norm": 0.12952867150306702,
2114
+ "learning_rate": 8.809747466353356e-05,
2115
+ "loss": 0.2991,
2116
+ "step": 301
2117
+ },
2118
+ {
2119
+ "epoch": 0.22805361525391732,
2120
+ "grad_norm": 0.1346244215965271,
2121
+ "learning_rate": 8.802029828000156e-05,
2122
+ "loss": 0.3154,
2123
+ "step": 302
2124
+ },
2125
+ {
2126
+ "epoch": 0.2288087596752879,
2127
+ "grad_norm": 0.15575996041297913,
2128
+ "learning_rate": 8.794290653540084e-05,
2129
+ "loss": 0.4171,
2130
+ "step": 303
2131
+ },
2132
+ {
2133
+ "epoch": 0.22956390409665847,
2134
+ "grad_norm": 0.1542641818523407,
2135
+ "learning_rate": 8.7865299868107e-05,
2136
+ "loss": 0.3851,
2137
+ "step": 304
2138
+ },
2139
+ {
2140
+ "epoch": 0.23031904851802906,
2141
+ "grad_norm": 0.16775798797607422,
2142
+ "learning_rate": 8.778747871771292e-05,
2143
+ "loss": 0.3872,
2144
+ "step": 305
2145
+ },
2146
+ {
2147
+ "epoch": 0.23107419293939965,
2148
+ "grad_norm": 0.15936799347400665,
2149
+ "learning_rate": 8.770944352502648e-05,
2150
+ "loss": 0.3998,
2151
+ "step": 306
2152
+ },
2153
+ {
2154
+ "epoch": 0.23182933736077024,
2155
+ "grad_norm": 0.16513392329216003,
2156
+ "learning_rate": 8.763119473206794e-05,
2157
+ "loss": 0.4005,
2158
+ "step": 307
2159
+ },
2160
+ {
2161
+ "epoch": 0.23258448178214083,
2162
+ "grad_norm": 0.14965298771858215,
2163
+ "learning_rate": 8.755273278206749e-05,
2164
+ "loss": 0.3792,
2165
+ "step": 308
2166
+ },
2167
+ {
2168
+ "epoch": 0.23333962620351142,
2169
+ "grad_norm": 0.1585433930158615,
2170
+ "learning_rate": 8.74740581194627e-05,
2171
+ "loss": 0.4291,
2172
+ "step": 309
2173
+ },
2174
+ {
2175
+ "epoch": 0.23409477062488201,
2176
+ "grad_norm": 0.16825465857982635,
2177
+ "learning_rate": 8.739517118989605e-05,
2178
+ "loss": 0.4434,
2179
+ "step": 310
2180
+ },
2181
+ {
2182
+ "epoch": 0.2348499150462526,
2183
+ "grad_norm": 0.16293483972549438,
2184
+ "learning_rate": 8.731607244021236e-05,
2185
+ "loss": 0.4481,
2186
+ "step": 311
2187
+ },
2188
+ {
2189
+ "epoch": 0.2356050594676232,
2190
+ "grad_norm": 0.15974049270153046,
2191
+ "learning_rate": 8.723676231845626e-05,
2192
+ "loss": 0.4557,
2193
+ "step": 312
2194
+ },
2195
+ {
2196
+ "epoch": 0.23636020388899376,
2197
+ "grad_norm": 0.1649303436279297,
2198
+ "learning_rate": 8.715724127386972e-05,
2199
+ "loss": 0.4451,
2200
+ "step": 313
2201
+ },
2202
+ {
2203
+ "epoch": 0.23711534831036435,
2204
+ "grad_norm": 0.16639627516269684,
2205
+ "learning_rate": 8.70775097568894e-05,
2206
+ "loss": 0.4518,
2207
+ "step": 314
2208
+ },
2209
+ {
2210
+ "epoch": 0.23787049273173494,
2211
+ "grad_norm": 0.17083673179149628,
2212
+ "learning_rate": 8.69975682191442e-05,
2213
+ "loss": 0.3745,
2214
+ "step": 315
2215
+ },
2216
+ {
2217
+ "epoch": 0.23862563715310553,
2218
+ "grad_norm": 0.16381201148033142,
2219
+ "learning_rate": 8.691741711345263e-05,
2220
+ "loss": 0.3922,
2221
+ "step": 316
2222
+ },
2223
+ {
2224
+ "epoch": 0.23938078157447612,
2225
+ "grad_norm": 0.17072418332099915,
2226
+ "learning_rate": 8.683705689382024e-05,
2227
+ "loss": 0.3563,
2228
+ "step": 317
2229
+ },
2230
+ {
2231
+ "epoch": 0.2401359259958467,
2232
+ "grad_norm": 0.1824284940958023,
2233
+ "learning_rate": 8.675648801543718e-05,
2234
+ "loss": 0.432,
2235
+ "step": 318
2236
+ },
2237
+ {
2238
+ "epoch": 0.2408910704172173,
2239
+ "grad_norm": 0.17872655391693115,
2240
+ "learning_rate": 8.667571093467541e-05,
2241
+ "loss": 0.4294,
2242
+ "step": 319
2243
+ },
2244
+ {
2245
+ "epoch": 0.2416462148385879,
2246
+ "grad_norm": 0.17728659510612488,
2247
+ "learning_rate": 8.659472610908627e-05,
2248
+ "loss": 0.3963,
2249
+ "step": 320
2250
+ },
2251
+ {
2252
+ "epoch": 0.24240135925995845,
2253
+ "grad_norm": 0.18014661967754364,
2254
+ "learning_rate": 8.651353399739787e-05,
2255
+ "loss": 0.4614,
2256
+ "step": 321
2257
+ },
2258
+ {
2259
+ "epoch": 0.24315650368132904,
2260
+ "grad_norm": 0.18057285249233246,
2261
+ "learning_rate": 8.643213505951242e-05,
2262
+ "loss": 0.4134,
2263
+ "step": 322
2264
+ },
2265
+ {
2266
+ "epoch": 0.24391164810269964,
2267
+ "grad_norm": 0.19068454205989838,
2268
+ "learning_rate": 8.635052975650369e-05,
2269
+ "loss": 0.539,
2270
+ "step": 323
2271
+ },
2272
+ {
2273
+ "epoch": 0.24466679252407023,
2274
+ "grad_norm": 0.18311984837055206,
2275
+ "learning_rate": 8.626871855061438e-05,
2276
+ "loss": 0.3847,
2277
+ "step": 324
2278
+ },
2279
+ {
2280
+ "epoch": 0.24542193694544082,
2281
+ "grad_norm": 0.172931507229805,
2282
+ "learning_rate": 8.618670190525352e-05,
2283
+ "loss": 0.3835,
2284
+ "step": 325
2285
+ },
2286
+ {
2287
+ "epoch": 0.2461770813668114,
2288
+ "grad_norm": 0.18892034888267517,
2289
+ "learning_rate": 8.610448028499376e-05,
2290
+ "loss": 0.4231,
2291
+ "step": 326
2292
+ },
2293
+ {
2294
+ "epoch": 0.246932225788182,
2295
+ "grad_norm": 0.19887331128120422,
2296
+ "learning_rate": 8.602205415556889e-05,
2297
+ "loss": 0.4835,
2298
+ "step": 327
2299
+ },
2300
+ {
2301
+ "epoch": 0.2476873702095526,
2302
+ "grad_norm": 0.18918727338314056,
2303
+ "learning_rate": 8.593942398387105e-05,
2304
+ "loss": 0.4285,
2305
+ "step": 328
2306
+ },
2307
+ {
2308
+ "epoch": 0.24844251463092315,
2309
+ "grad_norm": 0.19010977447032928,
2310
+ "learning_rate": 8.585659023794818e-05,
2311
+ "loss": 0.4059,
2312
+ "step": 329
2313
+ },
2314
+ {
2315
+ "epoch": 0.24919765905229374,
2316
+ "grad_norm": 0.1906062811613083,
2317
+ "learning_rate": 8.577355338700132e-05,
2318
+ "loss": 0.423,
2319
+ "step": 330
2320
+ },
2321
+ {
2322
+ "epoch": 0.24995280347366433,
2323
+ "grad_norm": 0.1999729573726654,
2324
+ "learning_rate": 8.569031390138202e-05,
2325
+ "loss": 0.4482,
2326
+ "step": 331
2327
+ },
2328
+ {
2329
+ "epoch": 0.2507079478950349,
2330
+ "grad_norm": 0.20304431021213531,
2331
+ "learning_rate": 8.560687225258958e-05,
2332
+ "loss": 0.3917,
2333
+ "step": 332
2334
+ }
2335
+ ],
2336
+ "logging_steps": 1,
2337
+ "max_steps": 1325,
2338
+ "num_input_tokens_seen": 0,
2339
+ "num_train_epochs": 2,
2340
+ "save_steps": 332,
2341
+ "stateful_callbacks": {
2342
+ "TrainerControl": {
2343
+ "args": {
2344
+ "should_epoch_stop": false,
2345
+ "should_evaluate": false,
2346
+ "should_log": false,
2347
+ "should_save": true,
2348
+ "should_training_stop": false
2349
+ },
2350
+ "attributes": {}
2351
+ }
2352
+ },
2353
+ "total_flos": 4.277596091056128e+17,
2354
+ "train_batch_size": 4,
2355
+ "trial_name": null,
2356
+ "trial_params": null
2357
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b05f71a1575935b665b4b5a05a2d273b47d70fd6a4879aca91b7d84d7ee0a29c
3
+ size 6776