lmg-anon commited on
Commit
661d374
1 Parent(s): 63215f7

Upload folder using huggingface_hub

Browse files
checkpoint-400/.ipynb_checkpoints/adapter_config-checkpoint.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "rinna/llama-3-youko-8b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
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": 32,
14
+ "lora_dropout": 0,
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": 128,
23
+ "rank_pattern": {},
24
+ "revision": "unsloth",
25
+ "target_modules": [
26
+ "o_proj",
27
+ "k_proj",
28
+ "v_proj",
29
+ "gate_proj",
30
+ "down_proj",
31
+ "q_proj",
32
+ "up_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": true
37
+ }
checkpoint-450/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: rinna/llama-3-youko-8b
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 0.11.1
checkpoint-450/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "rinna/llama-3-youko-8b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
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": 32,
14
+ "lora_dropout": 0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": [
18
+ "lm_head",
19
+ "embed_tokens"
20
+ ],
21
+ "peft_type": "LORA",
22
+ "r": 128,
23
+ "rank_pattern": {},
24
+ "revision": "unsloth",
25
+ "target_modules": [
26
+ "gate_proj",
27
+ "q_proj",
28
+ "up_proj",
29
+ "o_proj",
30
+ "v_proj",
31
+ "k_proj",
32
+ "down_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": true
37
+ }
checkpoint-450/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0384c5c3120e71617137430ae1ad84c1f0589151e56a0a9e440bafcf19a85c39
3
+ size 11849545016
checkpoint-450/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffe5781e6fff378ec35e80d1c5d22b267e2ae1da7eeb3dcc281016542c1f6bcf
3
+ size 2779665054
checkpoint-450/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7458c20077adf99ba6aa753ec2347f8d0baf4581fe9276106300d448ed7ee413
3
+ size 14244
checkpoint-450/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfdbde9bcd4c10317c2e23e245ba40e9a4fe15085b41a95cd024379725aae288
3
+ size 1064
checkpoint-450/trainer_state.json ADDED
@@ -0,0 +1,3183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9057971014492754,
5
+ "eval_steps": 500,
6
+ "global_step": 450,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.002012882447665056,
13
+ "grad_norm": 22.921390533447266,
14
+ "learning_rate": 6.5e-06,
15
+ "loss": 1.3427,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.004025764895330112,
20
+ "grad_norm": 14.772722244262695,
21
+ "learning_rate": 1.3e-05,
22
+ "loss": 1.3647,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.006038647342995169,
27
+ "grad_norm": 11.458742141723633,
28
+ "learning_rate": 1.9499999999999996e-05,
29
+ "loss": 1.2841,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.008051529790660225,
34
+ "grad_norm": 4.747677326202393,
35
+ "learning_rate": 2.6e-05,
36
+ "loss": 1.1644,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.010064412238325281,
41
+ "grad_norm": 3.687121629714966,
42
+ "learning_rate": 3.25e-05,
43
+ "loss": 1.1084,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.012077294685990338,
48
+ "grad_norm": 3.178232431411743,
49
+ "learning_rate": 3.899999999999999e-05,
50
+ "loss": 1.0753,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.014090177133655395,
55
+ "grad_norm": 2.476033926010132,
56
+ "learning_rate": 4.5499999999999995e-05,
57
+ "loss": 1.075,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.01610305958132045,
62
+ "grad_norm": 1.9162139892578125,
63
+ "learning_rate": 5.2e-05,
64
+ "loss": 1.0195,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.018115942028985508,
69
+ "grad_norm": 1.797377109527588,
70
+ "learning_rate": 5.85e-05,
71
+ "loss": 0.9884,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.020128824476650563,
76
+ "grad_norm": 1.816100835800171,
77
+ "learning_rate": 6.5e-05,
78
+ "loss": 0.9945,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.02214170692431562,
83
+ "grad_norm": 1.843664526939392,
84
+ "learning_rate": 6.499932098548219e-05,
85
+ "loss": 0.8802,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.024154589371980676,
90
+ "grad_norm": 1.7202250957489014,
91
+ "learning_rate": 6.49972839703017e-05,
92
+ "loss": 0.9833,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.026167471819645734,
97
+ "grad_norm": 1.4981484413146973,
98
+ "learning_rate": 6.499388903957628e-05,
99
+ "loss": 0.9481,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.02818035426731079,
104
+ "grad_norm": 1.4716213941574097,
105
+ "learning_rate": 6.498913633516483e-05,
106
+ "loss": 0.8809,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.030193236714975844,
111
+ "grad_norm": 1.3817026615142822,
112
+ "learning_rate": 6.498302605566152e-05,
113
+ "loss": 0.9264,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.0322061191626409,
118
+ "grad_norm": 1.509097695350647,
119
+ "learning_rate": 6.497555845638748e-05,
120
+ "loss": 0.8829,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.03421900161030596,
125
+ "grad_norm": 1.5498337745666504,
126
+ "learning_rate": 6.496673384938014e-05,
127
+ "loss": 0.9227,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.036231884057971016,
132
+ "grad_norm": 1.527828574180603,
133
+ "learning_rate": 6.49565526033802e-05,
134
+ "loss": 0.9488,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.038244766505636074,
139
+ "grad_norm": 1.4578592777252197,
140
+ "learning_rate": 6.494501514381621e-05,
141
+ "loss": 0.8845,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.040257648953301126,
146
+ "grad_norm": 1.4198046922683716,
147
+ "learning_rate": 6.493212195278678e-05,
148
+ "loss": 0.8809,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.042270531400966184,
153
+ "grad_norm": 1.4455400705337524,
154
+ "learning_rate": 6.491787356904047e-05,
155
+ "loss": 0.8686,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.04428341384863124,
160
+ "grad_norm": 1.5711616277694702,
161
+ "learning_rate": 6.490227058795323e-05,
162
+ "loss": 0.96,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.046296296296296294,
167
+ "grad_norm": 1.4603729248046875,
168
+ "learning_rate": 6.488531366150359e-05,
169
+ "loss": 0.9026,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.04830917874396135,
174
+ "grad_norm": 1.4184608459472656,
175
+ "learning_rate": 6.48670034982453e-05,
176
+ "loss": 0.9426,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.05032206119162641,
181
+ "grad_norm": 1.4080291986465454,
182
+ "learning_rate": 6.484734086327788e-05,
183
+ "loss": 0.8857,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.05233494363929147,
188
+ "grad_norm": 1.4739091396331787,
189
+ "learning_rate": 6.482632657821454e-05,
190
+ "loss": 0.8897,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.05434782608695652,
195
+ "grad_norm": 1.320746898651123,
196
+ "learning_rate": 6.480396152114787e-05,
197
+ "loss": 0.8512,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.05636070853462158,
202
+ "grad_norm": 1.4142905473709106,
203
+ "learning_rate": 6.478024662661315e-05,
204
+ "loss": 0.9459,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.05837359098228664,
209
+ "grad_norm": 1.3830432891845703,
210
+ "learning_rate": 6.47551828855493e-05,
211
+ "loss": 0.8605,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.06038647342995169,
216
+ "grad_norm": 1.3653528690338135,
217
+ "learning_rate": 6.472877134525753e-05,
218
+ "loss": 0.8446,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.06239935587761675,
223
+ "grad_norm": 1.3041807413101196,
224
+ "learning_rate": 6.470101310935746e-05,
225
+ "loss": 0.8407,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.0644122383252818,
230
+ "grad_norm": 1.3803820610046387,
231
+ "learning_rate": 6.467190933774112e-05,
232
+ "loss": 0.8505,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.06642512077294686,
237
+ "grad_norm": 1.3407087326049805,
238
+ "learning_rate": 6.464146124652441e-05,
239
+ "loss": 0.794,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.06843800322061191,
244
+ "grad_norm": 1.4283268451690674,
245
+ "learning_rate": 6.460967010799629e-05,
246
+ "loss": 0.9139,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.07045088566827697,
251
+ "grad_norm": 1.3512784242630005,
252
+ "learning_rate": 6.457653725056568e-05,
253
+ "loss": 0.807,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.07246376811594203,
258
+ "grad_norm": 1.3088512420654297,
259
+ "learning_rate": 6.454206405870587e-05,
260
+ "loss": 0.8968,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.07447665056360708,
265
+ "grad_norm": 1.2908034324645996,
266
+ "learning_rate": 6.450625197289675e-05,
267
+ "loss": 0.8447,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.07648953301127215,
272
+ "grad_norm": 1.3444992303848267,
273
+ "learning_rate": 6.446910248956453e-05,
274
+ "loss": 0.8891,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.0785024154589372,
279
+ "grad_norm": 1.2567275762557983,
280
+ "learning_rate": 6.443061716101926e-05,
281
+ "loss": 0.8134,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.08051529790660225,
286
+ "grad_norm": 1.3401930332183838,
287
+ "learning_rate": 6.439079759539e-05,
288
+ "loss": 0.8751,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.08252818035426732,
293
+ "grad_norm": 1.3348793983459473,
294
+ "learning_rate": 6.434964545655754e-05,
295
+ "loss": 0.7942,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.08454106280193237,
300
+ "grad_norm": 1.311357021331787,
301
+ "learning_rate": 6.430716246408493e-05,
302
+ "loss": 0.8461,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.08655394524959742,
307
+ "grad_norm": 1.3319345712661743,
308
+ "learning_rate": 6.426335039314566e-05,
309
+ "loss": 0.8821,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.08856682769726248,
314
+ "grad_norm": 1.304795742034912,
315
+ "learning_rate": 6.421821107444936e-05,
316
+ "loss": 0.8655,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.09057971014492754,
321
+ "grad_norm": 1.422869086265564,
322
+ "learning_rate": 6.417174639416547e-05,
323
+ "loss": 0.9261,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.09259259259259259,
328
+ "grad_norm": 1.2931973934173584,
329
+ "learning_rate": 6.412395829384427e-05,
330
+ "loss": 0.8157,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.09460547504025765,
335
+ "grad_norm": 1.2984646558761597,
336
+ "learning_rate": 6.407484877033586e-05,
337
+ "loss": 0.7919,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.0966183574879227,
342
+ "grad_norm": 1.2596486806869507,
343
+ "learning_rate": 6.402441987570665e-05,
344
+ "loss": 0.7682,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.09863123993558776,
349
+ "grad_norm": 1.3544796705245972,
350
+ "learning_rate": 6.397267371715368e-05,
351
+ "loss": 0.9084,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.10064412238325282,
356
+ "grad_norm": 1.2623202800750732,
357
+ "learning_rate": 6.391961245691652e-05,
358
+ "loss": 0.8482,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.10265700483091787,
363
+ "grad_norm": 1.320026159286499,
364
+ "learning_rate": 6.386523831218689e-05,
365
+ "loss": 0.8436,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.10466988727858294,
370
+ "grad_norm": 1.4064967632293701,
371
+ "learning_rate": 6.38095535550161e-05,
372
+ "loss": 0.8962,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.10668276972624799,
377
+ "grad_norm": 1.3178116083145142,
378
+ "learning_rate": 6.375256051222009e-05,
379
+ "loss": 0.8064,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.10869565217391304,
384
+ "grad_norm": 1.2729371786117554,
385
+ "learning_rate": 6.369426156528213e-05,
386
+ "loss": 0.8338,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.1107085346215781,
391
+ "grad_norm": 1.2167425155639648,
392
+ "learning_rate": 6.363465915025339e-05,
393
+ "loss": 0.8078,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.11272141706924316,
398
+ "grad_norm": 1.3006845712661743,
399
+ "learning_rate": 6.357375575765108e-05,
400
+ "loss": 0.8462,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.11473429951690821,
405
+ "grad_norm": 1.245822787284851,
406
+ "learning_rate": 6.351155393235449e-05,
407
+ "loss": 0.8394,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.11674718196457327,
412
+ "grad_norm": 1.2608625888824463,
413
+ "learning_rate": 6.34480562734985e-05,
414
+ "loss": 0.8606,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.11876006441223833,
419
+ "grad_norm": 1.2614774703979492,
420
+ "learning_rate": 6.33832654343651e-05,
421
+ "loss": 0.7633,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.12077294685990338,
426
+ "grad_norm": 1.3382893800735474,
427
+ "learning_rate": 6.331718412227247e-05,
428
+ "loss": 0.8514,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.12278582930756844,
433
+ "grad_norm": 1.2239303588867188,
434
+ "learning_rate": 6.324981509846189e-05,
435
+ "loss": 0.8319,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.1247987117552335,
440
+ "grad_norm": 1.3828685283660889,
441
+ "learning_rate": 6.318116117798225e-05,
442
+ "loss": 0.8683,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.12681159420289856,
447
+ "grad_norm": 1.304027795791626,
448
+ "learning_rate": 6.311122522957255e-05,
449
+ "loss": 0.887,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.1288244766505636,
454
+ "grad_norm": 1.3097902536392212,
455
+ "learning_rate": 6.304001017554202e-05,
456
+ "loss": 0.8636,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.13083735909822866,
461
+ "grad_norm": 1.281269907951355,
462
+ "learning_rate": 6.296751899164788e-05,
463
+ "loss": 0.7537,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.13285024154589373,
468
+ "grad_norm": 1.2349010705947876,
469
+ "learning_rate": 6.289375470697116e-05,
470
+ "loss": 0.8451,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.13486312399355876,
475
+ "grad_norm": 1.2939257621765137,
476
+ "learning_rate": 6.281872040379001e-05,
477
+ "loss": 0.8249,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.13687600644122383,
482
+ "grad_norm": 1.308341145515442,
483
+ "learning_rate": 6.274241921745097e-05,
484
+ "loss": 0.8764,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.1388888888888889,
489
+ "grad_norm": 1.311805009841919,
490
+ "learning_rate": 6.266485433623794e-05,
491
+ "loss": 0.8308,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.14090177133655393,
496
+ "grad_norm": 1.6127303838729858,
497
+ "learning_rate": 6.258602900123894e-05,
498
+ "loss": 0.8069,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.142914653784219,
503
+ "grad_norm": 1.292090654373169,
504
+ "learning_rate": 6.250594650621067e-05,
505
+ "loss": 0.8174,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.14492753623188406,
510
+ "grad_norm": 1.256778359413147,
511
+ "learning_rate": 6.2424610197441e-05,
512
+ "loss": 0.7956,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.1469404186795491,
517
+ "grad_norm": 1.2579149007797241,
518
+ "learning_rate": 6.23420234736089e-05,
519
+ "loss": 0.8267,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.14895330112721417,
524
+ "grad_norm": 1.3226171731948853,
525
+ "learning_rate": 6.225818978564269e-05,
526
+ "loss": 0.9322,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.15096618357487923,
531
+ "grad_norm": 1.1891167163848877,
532
+ "learning_rate": 6.217311263657565e-05,
533
+ "loss": 0.7886,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.1529790660225443,
538
+ "grad_norm": 1.2481876611709595,
539
+ "learning_rate": 6.208679558139977e-05,
540
+ "loss": 0.7832,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.15499194847020933,
545
+ "grad_norm": 1.2592449188232422,
546
+ "learning_rate": 6.199924222691707e-05,
547
+ "loss": 0.8061,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.1570048309178744,
552
+ "grad_norm": 1.250359058380127,
553
+ "learning_rate": 6.191045623158907e-05,
554
+ "loss": 0.7942,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.15901771336553946,
559
+ "grad_norm": 1.2406524419784546,
560
+ "learning_rate": 6.182044130538373e-05,
561
+ "loss": 0.7766,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.1610305958132045,
566
+ "grad_norm": 1.2620049715042114,
567
+ "learning_rate": 6.172920120962052e-05,
568
+ "loss": 0.8445,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.16304347826086957,
573
+ "grad_norm": 1.2618622779846191,
574
+ "learning_rate": 6.16367397568133e-05,
575
+ "loss": 0.812,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.16505636070853463,
580
+ "grad_norm": 1.2560168504714966,
581
+ "learning_rate": 6.15430608105109e-05,
582
+ "loss": 0.8331,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.16706924315619967,
587
+ "grad_norm": 1.2386751174926758,
588
+ "learning_rate": 6.144816828513576e-05,
589
+ "loss": 0.7318,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.16908212560386474,
594
+ "grad_norm": 1.3558485507965088,
595
+ "learning_rate": 6.135206614582031e-05,
596
+ "loss": 0.8476,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.1710950080515298,
601
+ "grad_norm": 1.2461968660354614,
602
+ "learning_rate": 6.125475840824137e-05,
603
+ "loss": 0.8012,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.17310789049919484,
608
+ "grad_norm": 1.2398920059204102,
609
+ "learning_rate": 6.115624913845225e-05,
610
+ "loss": 0.8033,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.1751207729468599,
615
+ "grad_norm": 1.3263791799545288,
616
+ "learning_rate": 6.105654245271292e-05,
617
+ "loss": 0.8511,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.17713365539452497,
622
+ "grad_norm": 1.2072999477386475,
623
+ "learning_rate": 6.095564251731795e-05,
624
+ "loss": 0.7478,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.17914653784219,
629
+ "grad_norm": 1.287801742553711,
630
+ "learning_rate": 6.085355354842249e-05,
631
+ "loss": 0.8152,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.18115942028985507,
636
+ "grad_norm": 1.2826151847839355,
637
+ "learning_rate": 6.0750279811866046e-05,
638
+ "loss": 0.7918,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.18317230273752014,
643
+ "grad_norm": 1.276780605316162,
644
+ "learning_rate": 6.0645825622994254e-05,
645
+ "loss": 0.8774,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.18518518518518517,
650
+ "grad_norm": 1.2205020189285278,
651
+ "learning_rate": 6.0540195346478515e-05,
652
+ "loss": 0.8398,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.18719806763285024,
657
+ "grad_norm": 1.2247477769851685,
658
+ "learning_rate": 6.043339339613371e-05,
659
+ "loss": 0.8322,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.1892109500805153,
664
+ "grad_norm": 1.3282443284988403,
665
+ "learning_rate": 6.0325424234733656e-05,
666
+ "loss": 0.8003,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.19122383252818034,
671
+ "grad_norm": 1.3472024202346802,
672
+ "learning_rate": 6.0216292373824696e-05,
673
+ "loss": 0.8305,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.1932367149758454,
678
+ "grad_norm": 1.2812607288360596,
679
+ "learning_rate": 6.010600237353716e-05,
680
+ "loss": 0.7657,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.19524959742351047,
685
+ "grad_norm": 1.2958053350448608,
686
+ "learning_rate": 5.999455884239483e-05,
687
+ "loss": 0.869,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.1972624798711755,
692
+ "grad_norm": 1.2021034955978394,
693
+ "learning_rate": 5.988196643712235e-05,
694
+ "loss": 0.7798,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.19927536231884058,
699
+ "grad_norm": 1.2430065870285034,
700
+ "learning_rate": 5.976822986245067e-05,
701
+ "loss": 0.7496,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.20128824476650564,
706
+ "grad_norm": 1.2749730348587036,
707
+ "learning_rate": 5.9653353870920434e-05,
708
+ "loss": 0.831,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.20330112721417068,
713
+ "grad_norm": 1.2621365785598755,
714
+ "learning_rate": 5.953734326268337e-05,
715
+ "loss": 0.8051,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.20531400966183574,
720
+ "grad_norm": 1.1950538158416748,
721
+ "learning_rate": 5.94202028853018e-05,
722
+ "loss": 0.7866,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.2073268921095008,
727
+ "grad_norm": 1.3278518915176392,
728
+ "learning_rate": 5.930193763354597e-05,
729
+ "loss": 0.8374,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.20933977455716588,
734
+ "grad_norm": 1.281888484954834,
735
+ "learning_rate": 5.91825524491896e-05,
736
+ "loss": 0.8255,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.2113526570048309,
741
+ "grad_norm": 1.270607352256775,
742
+ "learning_rate": 5.906205232080336e-05,
743
+ "loss": 0.7782,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.21336553945249598,
748
+ "grad_norm": 1.2177718877792358,
749
+ "learning_rate": 5.894044228354644e-05,
750
+ "loss": 0.7506,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.21537842190016104,
755
+ "grad_norm": 1.247755765914917,
756
+ "learning_rate": 5.88177274189561e-05,
757
+ "loss": 0.8135,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.21739130434782608,
762
+ "grad_norm": 1.2848960161209106,
763
+ "learning_rate": 5.869391285473541e-05,
764
+ "loss": 0.8259,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.21940418679549115,
769
+ "grad_norm": 1.197343349456787,
770
+ "learning_rate": 5.856900376453892e-05,
771
+ "loss": 0.7872,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.2214170692431562,
776
+ "grad_norm": 1.2160040140151978,
777
+ "learning_rate": 5.844300536775651e-05,
778
+ "loss": 0.7725,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.22342995169082125,
783
+ "grad_norm": 1.2862228155136108,
784
+ "learning_rate": 5.831592292929532e-05,
785
+ "loss": 0.7808,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.22544283413848631,
790
+ "grad_norm": 1.2369639873504639,
791
+ "learning_rate": 5.818776175935967e-05,
792
+ "loss": 0.7898,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.22745571658615138,
797
+ "grad_norm": 1.2040680646896362,
798
+ "learning_rate": 5.805852721322927e-05,
799
+ "loss": 0.8068,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.22946859903381642,
804
+ "grad_norm": 1.28532075881958,
805
+ "learning_rate": 5.792822469103539e-05,
806
+ "loss": 0.8117,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.23148148148148148,
811
+ "grad_norm": 1.2590646743774414,
812
+ "learning_rate": 5.7796859637535194e-05,
813
+ "loss": 0.7806,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.23349436392914655,
818
+ "grad_norm": 1.223161220550537,
819
+ "learning_rate": 5.76644375418843e-05,
820
+ "loss": 0.7477,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.23550724637681159,
825
+ "grad_norm": 1.2891532182693481,
826
+ "learning_rate": 5.753096393740734e-05,
827
+ "loss": 0.8055,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.23752012882447665,
832
+ "grad_norm": 1.352499008178711,
833
+ "learning_rate": 5.739644440136678e-05,
834
+ "loss": 0.8192,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.23953301127214172,
839
+ "grad_norm": 1.2987629175186157,
840
+ "learning_rate": 5.726088455472989e-05,
841
+ "loss": 0.8279,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.24154589371980675,
846
+ "grad_norm": 1.2705352306365967,
847
+ "learning_rate": 5.7124290061933827e-05,
848
+ "loss": 0.826,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.24355877616747182,
853
+ "grad_norm": 1.3219701051712036,
854
+ "learning_rate": 5.698666663064896e-05,
855
+ "loss": 0.8321,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.24557165861513688,
860
+ "grad_norm": 1.3087178468704224,
861
+ "learning_rate": 5.6848020011540414e-05,
862
+ "loss": 0.8629,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.24758454106280192,
867
+ "grad_norm": 1.2457053661346436,
868
+ "learning_rate": 5.670835599802768e-05,
869
+ "loss": 0.8092,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.249597423510467,
874
+ "grad_norm": 1.2432583570480347,
875
+ "learning_rate": 5.656768042604265e-05,
876
+ "loss": 0.7889,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.25161030595813205,
881
+ "grad_norm": 1.3183501958847046,
882
+ "learning_rate": 5.6425999173785643e-05,
883
+ "loss": 0.8554,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.2536231884057971,
888
+ "grad_norm": 1.2189457416534424,
889
+ "learning_rate": 5.628331816147989e-05,
890
+ "loss": 0.7932,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.2556360708534622,
895
+ "grad_norm": 1.143637776374817,
896
+ "learning_rate": 5.6139643351124076e-05,
897
+ "loss": 0.7668,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.2576489533011272,
902
+ "grad_norm": 1.1862376928329468,
903
+ "learning_rate": 5.5994980746243264e-05,
904
+ "loss": 0.8165,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.25966183574879226,
909
+ "grad_norm": 1.1560195684432983,
910
+ "learning_rate": 5.5849336391637995e-05,
911
+ "loss": 0.8122,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.2616747181964573,
916
+ "grad_norm": 1.2094959020614624,
917
+ "learning_rate": 5.5702716373131716e-05,
918
+ "loss": 0.7955,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.2636876006441224,
923
+ "grad_norm": 1.2558305263519287,
924
+ "learning_rate": 5.5555126817316515e-05,
925
+ "loss": 0.8399,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.26570048309178745,
930
+ "grad_norm": 1.297591209411621,
931
+ "learning_rate": 5.540657389129707e-05,
932
+ "loss": 0.8398,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.2677133655394525,
937
+ "grad_norm": 1.3282864093780518,
938
+ "learning_rate": 5.525706380243297e-05,
939
+ "loss": 0.8156,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.26972624798711753,
944
+ "grad_norm": 1.3417863845825195,
945
+ "learning_rate": 5.510660279807935e-05,
946
+ "loss": 0.8105,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.2717391304347826,
951
+ "grad_norm": 1.2470736503601074,
952
+ "learning_rate": 5.495519716532585e-05,
953
+ "loss": 0.7849,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.27375201288244766,
958
+ "grad_norm": 1.2911748886108398,
959
+ "learning_rate": 5.480285323073384e-05,
960
+ "loss": 0.836,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.2757648953301127,
965
+ "grad_norm": 1.2390037775039673,
966
+ "learning_rate": 5.464957736007215e-05,
967
+ "loss": 0.7556,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.2777777777777778,
972
+ "grad_norm": 1.2093883752822876,
973
+ "learning_rate": 5.449537595805101e-05,
974
+ "loss": 0.8173,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.27979066022544286,
979
+ "grad_norm": 1.2018241882324219,
980
+ "learning_rate": 5.434025546805447e-05,
981
+ "loss": 0.7983,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.28180354267310787,
986
+ "grad_norm": 1.2486872673034668,
987
+ "learning_rate": 5.418422237187113e-05,
988
+ "loss": 0.813,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.28381642512077293,
993
+ "grad_norm": 1.1954402923583984,
994
+ "learning_rate": 5.4027283189423296e-05,
995
+ "loss": 0.7999,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.285829307568438,
1000
+ "grad_norm": 1.1647478342056274,
1001
+ "learning_rate": 5.386944447849457e-05,
1002
+ "loss": 0.7872,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.28784219001610306,
1007
+ "grad_norm": 1.3171889781951904,
1008
+ "learning_rate": 5.371071283445577e-05,
1009
+ "loss": 0.8074,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.2898550724637681,
1014
+ "grad_norm": 1.3020223379135132,
1015
+ "learning_rate": 5.355109488998941e-05,
1016
+ "loss": 0.8068,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.2918679549114332,
1021
+ "grad_norm": 1.1892728805541992,
1022
+ "learning_rate": 5.339059731481252e-05,
1023
+ "loss": 0.7863,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.2938808373590982,
1028
+ "grad_norm": 1.2545976638793945,
1029
+ "learning_rate": 5.322922681539793e-05,
1030
+ "loss": 0.8486,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.29589371980676327,
1035
+ "grad_norm": 1.1874210834503174,
1036
+ "learning_rate": 5.3066990134694086e-05,
1037
+ "loss": 0.7702,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.29790660225442833,
1042
+ "grad_norm": 1.2464886903762817,
1043
+ "learning_rate": 5.2903894051843204e-05,
1044
+ "loss": 0.8313,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.2999194847020934,
1049
+ "grad_norm": 1.3062876462936401,
1050
+ "learning_rate": 5.2739945381898095e-05,
1051
+ "loss": 0.8076,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.30193236714975846,
1056
+ "grad_norm": 1.2185595035552979,
1057
+ "learning_rate": 5.2575150975537353e-05,
1058
+ "loss": 0.7585,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.30394524959742353,
1063
+ "grad_norm": 1.1846880912780762,
1064
+ "learning_rate": 5.240951771877909e-05,
1065
+ "loss": 0.7762,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.3059581320450886,
1070
+ "grad_norm": 1.1666184663772583,
1071
+ "learning_rate": 5.224305253269321e-05,
1072
+ "loss": 0.7539,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.3079710144927536,
1077
+ "grad_norm": 1.2293246984481812,
1078
+ "learning_rate": 5.207576237311223e-05,
1079
+ "loss": 0.8013,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.30998389694041867,
1084
+ "grad_norm": 1.184094786643982,
1085
+ "learning_rate": 5.1907654230340546e-05,
1086
+ "loss": 0.7686,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.31199677938808373,
1091
+ "grad_norm": 1.1998686790466309,
1092
+ "learning_rate": 5.1738735128862465e-05,
1093
+ "loss": 0.7596,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.3140096618357488,
1098
+ "grad_norm": 1.1767568588256836,
1099
+ "learning_rate": 5.156901212704858e-05,
1100
+ "loss": 0.7535,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.31602254428341386,
1105
+ "grad_norm": 1.1981345415115356,
1106
+ "learning_rate": 5.139849231686086e-05,
1107
+ "loss": 0.7971,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.31803542673107893,
1112
+ "grad_norm": 1.2676053047180176,
1113
+ "learning_rate": 5.122718282355635e-05,
1114
+ "loss": 0.7575,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.32004830917874394,
1119
+ "grad_norm": 1.2075040340423584,
1120
+ "learning_rate": 5.105509080538939e-05,
1121
+ "loss": 0.8187,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.322061191626409,
1126
+ "grad_norm": 1.2567739486694336,
1127
+ "learning_rate": 5.08822234533125e-05,
1128
+ "loss": 0.7754,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.32407407407407407,
1133
+ "grad_norm": 1.1478137969970703,
1134
+ "learning_rate": 5.0708587990675954e-05,
1135
+ "loss": 0.7744,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.32608695652173914,
1140
+ "grad_norm": 1.2385374307632446,
1141
+ "learning_rate": 5.05341916729259e-05,
1142
+ "loss": 0.7852,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.3280998389694042,
1147
+ "grad_norm": 1.2898869514465332,
1148
+ "learning_rate": 5.035904178730119e-05,
1149
+ "loss": 0.8475,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.33011272141706927,
1154
+ "grad_norm": 1.2359830141067505,
1155
+ "learning_rate": 5.018314565252893e-05,
1156
+ "loss": 0.8417,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.3321256038647343,
1161
+ "grad_norm": 1.224368929862976,
1162
+ "learning_rate": 5.00065106185186e-05,
1163
+ "loss": 0.7904,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.33413848631239934,
1168
+ "grad_norm": 1.229744553565979,
1169
+ "learning_rate": 4.9829144066054964e-05,
1170
+ "loss": 0.7969,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.3361513687600644,
1175
+ "grad_norm": 1.1933088302612305,
1176
+ "learning_rate": 4.9651053406489656e-05,
1177
+ "loss": 0.7646,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.33816425120772947,
1182
+ "grad_norm": 1.2042123079299927,
1183
+ "learning_rate": 4.9472246081431494e-05,
1184
+ "loss": 0.779,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.34017713365539454,
1189
+ "grad_norm": 1.1418585777282715,
1190
+ "learning_rate": 4.9292729562435545e-05,
1191
+ "loss": 0.7586,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.3421900161030596,
1196
+ "grad_norm": 1.2688250541687012,
1197
+ "learning_rate": 4.9112511350690876e-05,
1198
+ "loss": 0.7275,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.3442028985507246,
1203
+ "grad_norm": 1.1605274677276611,
1204
+ "learning_rate": 4.893159897670716e-05,
1205
+ "loss": 0.7784,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.3462157809983897,
1210
+ "grad_norm": 1.1853288412094116,
1211
+ "learning_rate": 4.874999999999999e-05,
1212
+ "loss": 0.7872,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.34822866344605474,
1217
+ "grad_norm": 1.180342197418213,
1218
+ "learning_rate": 4.856772200877502e-05,
1219
+ "loss": 0.7877,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.3502415458937198,
1224
+ "grad_norm": 1.1545747518539429,
1225
+ "learning_rate": 4.838477261961083e-05,
1226
+ "loss": 0.7554,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.3522544283413849,
1231
+ "grad_norm": 1.4341752529144287,
1232
+ "learning_rate": 4.820115947714075e-05,
1233
+ "loss": 0.7872,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.35426731078904994,
1238
+ "grad_norm": 1.254834532737732,
1239
+ "learning_rate": 4.801689025373334e-05,
1240
+ "loss": 0.8164,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.35628019323671495,
1245
+ "grad_norm": 1.18601393699646,
1246
+ "learning_rate": 4.783197264917187e-05,
1247
+ "loss": 0.7879,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.35829307568438,
1252
+ "grad_norm": 1.2259867191314697,
1253
+ "learning_rate": 4.764641439033251e-05,
1254
+ "loss": 0.8213,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.3603059581320451,
1259
+ "grad_norm": 1.2177544832229614,
1260
+ "learning_rate": 4.746022323086153e-05,
1261
+ "loss": 0.7674,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.36231884057971014,
1266
+ "grad_norm": 1.2497576475143433,
1267
+ "learning_rate": 4.7273406950851265e-05,
1268
+ "loss": 0.7512,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.3643317230273752,
1273
+ "grad_norm": 1.192671537399292,
1274
+ "learning_rate": 4.708597335651502e-05,
1275
+ "loss": 0.7917,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.3663446054750403,
1280
+ "grad_norm": 1.2135677337646484,
1281
+ "learning_rate": 4.689793027986089e-05,
1282
+ "loss": 0.7944,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.36835748792270534,
1287
+ "grad_norm": 1.2164232730865479,
1288
+ "learning_rate": 4.670928557836452e-05,
1289
+ "loss": 0.762,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.37037037037037035,
1294
+ "grad_norm": 1.175716757774353,
1295
+ "learning_rate": 4.6520047134640736e-05,
1296
+ "loss": 0.7313,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.3723832528180354,
1301
+ "grad_norm": 1.2479422092437744,
1302
+ "learning_rate": 4.633022285611418e-05,
1303
+ "loss": 0.831,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.3743961352657005,
1308
+ "grad_norm": 1.2672486305236816,
1309
+ "learning_rate": 4.613982067468894e-05,
1310
+ "loss": 0.7899,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.37640901771336555,
1315
+ "grad_norm": 1.3110653162002563,
1316
+ "learning_rate": 4.594884854641702e-05,
1317
+ "loss": 0.7759,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.3784219001610306,
1322
+ "grad_norm": 1.2542824745178223,
1323
+ "learning_rate": 4.575731445116596e-05,
1324
+ "loss": 0.785,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.3804347826086957,
1329
+ "grad_norm": 1.144977331161499,
1330
+ "learning_rate": 4.55652263922854e-05,
1331
+ "loss": 0.7398,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.3824476650563607,
1336
+ "grad_norm": 1.1065174341201782,
1337
+ "learning_rate": 4.537259239627259e-05,
1338
+ "loss": 0.7622,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.38446054750402575,
1343
+ "grad_norm": 1.227591872215271,
1344
+ "learning_rate": 4.5179420512437075e-05,
1345
+ "loss": 0.7603,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.3864734299516908,
1350
+ "grad_norm": 1.2493457794189453,
1351
+ "learning_rate": 4.498571881256432e-05,
1352
+ "loss": 0.7863,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.3884863123993559,
1357
+ "grad_norm": 1.3239022493362427,
1358
+ "learning_rate": 4.479149539057838e-05,
1359
+ "loss": 0.849,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.39049919484702095,
1364
+ "grad_norm": 1.2450414896011353,
1365
+ "learning_rate": 4.4596758362203775e-05,
1366
+ "loss": 0.7802,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.392512077294686,
1371
+ "grad_norm": 1.3064862489700317,
1372
+ "learning_rate": 4.44015158646263e-05,
1373
+ "loss": 0.7597,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.394524959742351,
1378
+ "grad_norm": 1.2286595106124878,
1379
+ "learning_rate": 4.4205776056153084e-05,
1380
+ "loss": 0.7863,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.3965378421900161,
1385
+ "grad_norm": 1.1941579580307007,
1386
+ "learning_rate": 4.4009547115871594e-05,
1387
+ "loss": 0.7199,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.39855072463768115,
1392
+ "grad_norm": 1.2539899349212646,
1393
+ "learning_rate": 4.3812837243307933e-05,
1394
+ "loss": 0.7807,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.4005636070853462,
1399
+ "grad_norm": 1.2592153549194336,
1400
+ "learning_rate": 4.3615654658084234e-05,
1401
+ "loss": 0.7657,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.4025764895330113,
1406
+ "grad_norm": 1.1356335878372192,
1407
+ "learning_rate": 4.341800759957512e-05,
1408
+ "loss": 0.6915,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.40458937198067635,
1413
+ "grad_norm": 1.1767053604125977,
1414
+ "learning_rate": 4.32199043265635e-05,
1415
+ "loss": 0.781,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 0.40660225442834136,
1420
+ "grad_norm": 1.3261032104492188,
1421
+ "learning_rate": 4.302135311689543e-05,
1422
+ "loss": 0.7527,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 0.4086151368760064,
1427
+ "grad_norm": 1.2210772037506104,
1428
+ "learning_rate": 4.282236226713422e-05,
1429
+ "loss": 0.7815,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 0.4106280193236715,
1434
+ "grad_norm": 1.2168560028076172,
1435
+ "learning_rate": 4.26229400922138e-05,
1436
+ "loss": 0.7397,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 0.41264090177133655,
1441
+ "grad_norm": 1.24334716796875,
1442
+ "learning_rate": 4.2423094925091174e-05,
1443
+ "loss": 0.8202,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 0.4146537842190016,
1448
+ "grad_norm": 1.22861647605896,
1449
+ "learning_rate": 4.2222835116398354e-05,
1450
+ "loss": 0.7951,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 0.4166666666666667,
1455
+ "grad_norm": 1.2528316974639893,
1456
+ "learning_rate": 4.2022169034093314e-05,
1457
+ "loss": 0.7412,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 0.41867954911433175,
1462
+ "grad_norm": 1.259413242340088,
1463
+ "learning_rate": 4.182110506311043e-05,
1464
+ "loss": 0.8283,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 0.42069243156199676,
1469
+ "grad_norm": 1.1932429075241089,
1470
+ "learning_rate": 4.161965160501001e-05,
1471
+ "loss": 0.7777,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 0.4227053140096618,
1476
+ "grad_norm": 1.2518868446350098,
1477
+ "learning_rate": 4.14178170776273e-05,
1478
+ "loss": 0.8084,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 0.4247181964573269,
1483
+ "grad_norm": 1.1913188695907593,
1484
+ "learning_rate": 4.1215609914720716e-05,
1485
+ "loss": 0.7893,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 0.42673107890499196,
1490
+ "grad_norm": 1.174193024635315,
1491
+ "learning_rate": 4.1013038565619436e-05,
1492
+ "loss": 0.75,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 0.428743961352657,
1497
+ "grad_norm": 1.2024927139282227,
1498
+ "learning_rate": 4.081011149487037e-05,
1499
+ "loss": 0.7476,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 0.4307568438003221,
1504
+ "grad_norm": 1.2005985975265503,
1505
+ "learning_rate": 4.060683718188439e-05,
1506
+ "loss": 0.7445,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 0.4327697262479871,
1511
+ "grad_norm": 1.2409402132034302,
1512
+ "learning_rate": 4.0403224120582105e-05,
1513
+ "loss": 0.754,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 0.43478260869565216,
1518
+ "grad_norm": 1.1732304096221924,
1519
+ "learning_rate": 4.0199280819038866e-05,
1520
+ "loss": 0.7627,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 0.4367954911433172,
1525
+ "grad_norm": 1.1297844648361206,
1526
+ "learning_rate": 3.9995015799129304e-05,
1527
+ "loss": 0.7363,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 0.4388083735909823,
1532
+ "grad_norm": 1.1647371053695679,
1533
+ "learning_rate": 3.9790437596171196e-05,
1534
+ "loss": 0.7578,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 0.44082125603864736,
1539
+ "grad_norm": 1.2122061252593994,
1540
+ "learning_rate": 3.9585554758568836e-05,
1541
+ "loss": 0.7232,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 0.4428341384863124,
1546
+ "grad_norm": 1.1666353940963745,
1547
+ "learning_rate": 3.938037584745585e-05,
1548
+ "loss": 0.7585,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 0.44484702093397743,
1553
+ "grad_norm": 1.1572037935256958,
1554
+ "learning_rate": 3.917490943633741e-05,
1555
+ "loss": 0.7167,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 0.4468599033816425,
1560
+ "grad_norm": 1.1842679977416992,
1561
+ "learning_rate": 3.896916411073206e-05,
1562
+ "loss": 0.7835,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 0.44887278582930756,
1567
+ "grad_norm": 1.2700228691101074,
1568
+ "learning_rate": 3.8763148467812915e-05,
1569
+ "loss": 0.7771,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 0.45088566827697263,
1574
+ "grad_norm": 1.2174429893493652,
1575
+ "learning_rate": 3.8556871116048424e-05,
1576
+ "loss": 0.7462,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 0.4528985507246377,
1581
+ "grad_norm": 1.2977925539016724,
1582
+ "learning_rate": 3.835034067484267e-05,
1583
+ "loss": 0.7824,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 0.45491143317230276,
1588
+ "grad_norm": 1.2482331991195679,
1589
+ "learning_rate": 3.814356577417524e-05,
1590
+ "loss": 0.7877,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 0.45692431561996777,
1595
+ "grad_norm": 1.1702152490615845,
1596
+ "learning_rate": 3.793655505424054e-05,
1597
+ "loss": 0.7245,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 0.45893719806763283,
1602
+ "grad_norm": 1.1979886293411255,
1603
+ "learning_rate": 3.772931716508686e-05,
1604
+ "loss": 0.7637,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 0.4609500805152979,
1609
+ "grad_norm": 1.202635407447815,
1610
+ "learning_rate": 3.752186076625482e-05,
1611
+ "loss": 0.8038,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 0.46296296296296297,
1616
+ "grad_norm": 1.2843554019927979,
1617
+ "learning_rate": 3.731419452641559e-05,
1618
+ "loss": 0.7628,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 0.46497584541062803,
1623
+ "grad_norm": 1.2422301769256592,
1624
+ "learning_rate": 3.710632712300867e-05,
1625
+ "loss": 0.7793,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 0.4669887278582931,
1630
+ "grad_norm": 1.229872465133667,
1631
+ "learning_rate": 3.6898267241879266e-05,
1632
+ "loss": 0.787,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 0.4690016103059581,
1637
+ "grad_norm": 1.1803100109100342,
1638
+ "learning_rate": 3.669002357691536e-05,
1639
+ "loss": 0.7118,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 0.47101449275362317,
1644
+ "grad_norm": 1.2324291467666626,
1645
+ "learning_rate": 3.648160482968447e-05,
1646
+ "loss": 0.7781,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 0.47302737520128824,
1651
+ "grad_norm": 1.2399364709854126,
1652
+ "learning_rate": 3.627301970906998e-05,
1653
+ "loss": 0.8275,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 0.4750402576489533,
1658
+ "grad_norm": 1.167107343673706,
1659
+ "learning_rate": 3.6064276930907275e-05,
1660
+ "loss": 0.8124,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 0.47705314009661837,
1665
+ "grad_norm": 1.1939244270324707,
1666
+ "learning_rate": 3.585538521761956e-05,
1667
+ "loss": 0.7746,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 0.47906602254428343,
1672
+ "grad_norm": 1.151248574256897,
1673
+ "learning_rate": 3.564635329785332e-05,
1674
+ "loss": 0.7189,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 0.4810789049919485,
1679
+ "grad_norm": 1.225353479385376,
1680
+ "learning_rate": 3.543718990611371e-05,
1681
+ "loss": 0.7178,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 0.4830917874396135,
1686
+ "grad_norm": 1.1944713592529297,
1687
+ "learning_rate": 3.5227903782399465e-05,
1688
+ "loss": 0.7887,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 0.4851046698872786,
1693
+ "grad_norm": 1.2270437479019165,
1694
+ "learning_rate": 3.501850367183775e-05,
1695
+ "loss": 0.7748,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 0.48711755233494364,
1700
+ "grad_norm": 1.2102910280227661,
1701
+ "learning_rate": 3.4808998324318723e-05,
1702
+ "loss": 0.7739,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 0.4891304347826087,
1707
+ "grad_norm": 1.2025328874588013,
1708
+ "learning_rate": 3.459939649412993e-05,
1709
+ "loss": 0.7636,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 0.49114331723027377,
1714
+ "grad_norm": 1.2945396900177002,
1715
+ "learning_rate": 3.438970693959046e-05,
1716
+ "loss": 0.801,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 0.49315619967793883,
1721
+ "grad_norm": 1.1986439228057861,
1722
+ "learning_rate": 3.417993842268507e-05,
1723
+ "loss": 0.7242,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 0.49516908212560384,
1728
+ "grad_norm": 1.2383544445037842,
1729
+ "learning_rate": 3.397009970869796e-05,
1730
+ "loss": 0.7916,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 0.4971819645732689,
1735
+ "grad_norm": 1.2588520050048828,
1736
+ "learning_rate": 3.376019956584654e-05,
1737
+ "loss": 0.7865,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 0.499194847020934,
1742
+ "grad_norm": 1.2207812070846558,
1743
+ "learning_rate": 3.35502467649151e-05,
1744
+ "loss": 0.7671,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 0.501207729468599,
1749
+ "grad_norm": 1.1526901721954346,
1750
+ "learning_rate": 3.334025007888823e-05,
1751
+ "loss": 0.7068,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 0.5032206119162641,
1756
+ "grad_norm": 1.2134076356887817,
1757
+ "learning_rate": 3.313021828258429e-05,
1758
+ "loss": 0.7811,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 0.5052334943639292,
1763
+ "grad_norm": 1.1232891082763672,
1764
+ "learning_rate": 3.292016015228877e-05,
1765
+ "loss": 0.7456,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 0.5072463768115942,
1770
+ "grad_norm": 1.1962013244628906,
1771
+ "learning_rate": 3.271008446538752e-05,
1772
+ "loss": 0.7699,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 0.5092592592592593,
1777
+ "grad_norm": 1.2679433822631836,
1778
+ "learning_rate": 3.25e-05,
1779
+ "loss": 0.7838,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 0.5112721417069244,
1784
+ "grad_norm": 1.1369578838348389,
1785
+ "learning_rate": 3.2289915534612466e-05,
1786
+ "loss": 0.7326,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 0.5132850241545893,
1791
+ "grad_norm": 1.20002281665802,
1792
+ "learning_rate": 3.207983984771123e-05,
1793
+ "loss": 0.7554,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 0.5152979066022544,
1798
+ "grad_norm": 1.1573915481567383,
1799
+ "learning_rate": 3.186978171741571e-05,
1800
+ "loss": 0.682,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 0.5173107890499195,
1805
+ "grad_norm": 1.1725130081176758,
1806
+ "learning_rate": 3.165974992111178e-05,
1807
+ "loss": 0.7674,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 0.5193236714975845,
1812
+ "grad_norm": 1.2105400562286377,
1813
+ "learning_rate": 3.1449753235084904e-05,
1814
+ "loss": 0.7425,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 0.5213365539452496,
1819
+ "grad_norm": 1.1620723009109497,
1820
+ "learning_rate": 3.123980043415345e-05,
1821
+ "loss": 0.7396,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 0.5233494363929146,
1826
+ "grad_norm": 1.163138508796692,
1827
+ "learning_rate": 3.102990029130204e-05,
1828
+ "loss": 0.7131,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 0.5253623188405797,
1833
+ "grad_norm": 1.2142436504364014,
1834
+ "learning_rate": 3.082006157731492e-05,
1835
+ "loss": 0.724,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 0.5273752012882448,
1840
+ "grad_norm": 1.1541523933410645,
1841
+ "learning_rate": 3.061029306040954e-05,
1842
+ "loss": 0.7305,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 0.5293880837359098,
1847
+ "grad_norm": 1.208058476448059,
1848
+ "learning_rate": 3.040060350587007e-05,
1849
+ "loss": 0.7625,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 0.5314009661835749,
1854
+ "grad_norm": 1.1648660898208618,
1855
+ "learning_rate": 3.0191001675681278e-05,
1856
+ "loss": 0.7422,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 0.53341384863124,
1861
+ "grad_norm": 1.175646424293518,
1862
+ "learning_rate": 2.9981496328162244e-05,
1863
+ "loss": 0.7202,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 0.535426731078905,
1868
+ "grad_norm": 1.1440715789794922,
1869
+ "learning_rate": 2.9772096217600523e-05,
1870
+ "loss": 0.6784,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 0.5374396135265701,
1875
+ "grad_norm": 1.2752009630203247,
1876
+ "learning_rate": 2.956281009388629e-05,
1877
+ "loss": 0.7446,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 0.5394524959742351,
1882
+ "grad_norm": 1.2139878273010254,
1883
+ "learning_rate": 2.9353646702146676e-05,
1884
+ "loss": 0.7583,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 0.5414653784219001,
1889
+ "grad_norm": 1.2297486066818237,
1890
+ "learning_rate": 2.9144614782380454e-05,
1891
+ "loss": 0.7103,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 0.5434782608695652,
1896
+ "grad_norm": 1.1957374811172485,
1897
+ "learning_rate": 2.893572306909272e-05,
1898
+ "loss": 0.763,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 0.5454911433172303,
1903
+ "grad_norm": 1.1861435174942017,
1904
+ "learning_rate": 2.872698029093001e-05,
1905
+ "loss": 0.8011,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 0.5475040257648953,
1910
+ "grad_norm": 1.232905626296997,
1911
+ "learning_rate": 2.8518395170315524e-05,
1912
+ "loss": 0.8291,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 0.5495169082125604,
1917
+ "grad_norm": 1.2735815048217773,
1918
+ "learning_rate": 2.830997642308463e-05,
1919
+ "loss": 0.7339,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 0.5515297906602254,
1924
+ "grad_norm": 1.256100058555603,
1925
+ "learning_rate": 2.8101732758120746e-05,
1926
+ "loss": 0.8017,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 0.5535426731078905,
1931
+ "grad_norm": 1.228579044342041,
1932
+ "learning_rate": 2.7893672876991337e-05,
1933
+ "loss": 0.7774,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 0.5555555555555556,
1938
+ "grad_norm": 1.1710914373397827,
1939
+ "learning_rate": 2.768580547358442e-05,
1940
+ "loss": 0.7252,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 0.5575684380032206,
1945
+ "grad_norm": 1.1470144987106323,
1946
+ "learning_rate": 2.7478139233745183e-05,
1947
+ "loss": 0.7662,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 0.5595813204508857,
1952
+ "grad_norm": 1.1679579019546509,
1953
+ "learning_rate": 2.7270682834913133e-05,
1954
+ "loss": 0.7748,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 0.5615942028985508,
1959
+ "grad_norm": 1.1878283023834229,
1960
+ "learning_rate": 2.7063444945759455e-05,
1961
+ "loss": 0.7375,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 0.5636070853462157,
1966
+ "grad_norm": 1.1710705757141113,
1967
+ "learning_rate": 2.6856434225824763e-05,
1968
+ "loss": 0.757,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 0.5656199677938808,
1973
+ "grad_norm": 1.1414003372192383,
1974
+ "learning_rate": 2.6649659325157332e-05,
1975
+ "loss": 0.7062,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 0.5676328502415459,
1980
+ "grad_norm": 1.189766764640808,
1981
+ "learning_rate": 2.644312888395158e-05,
1982
+ "loss": 0.7539,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 0.5696457326892109,
1987
+ "grad_norm": 1.2260947227478027,
1988
+ "learning_rate": 2.6236851532187076e-05,
1989
+ "loss": 0.7388,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 0.571658615136876,
1994
+ "grad_norm": 1.328162431716919,
1995
+ "learning_rate": 2.6030835889267932e-05,
1996
+ "loss": 0.7612,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 0.5736714975845411,
2001
+ "grad_norm": 1.1704083681106567,
2002
+ "learning_rate": 2.582509056366258e-05,
2003
+ "loss": 0.7511,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 0.5756843800322061,
2008
+ "grad_norm": 1.1261523962020874,
2009
+ "learning_rate": 2.561962415254416e-05,
2010
+ "loss": 0.7225,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 0.5776972624798712,
2015
+ "grad_norm": 1.2048742771148682,
2016
+ "learning_rate": 2.541444524143116e-05,
2017
+ "loss": 0.7864,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 0.5797101449275363,
2022
+ "grad_norm": 1.2203797101974487,
2023
+ "learning_rate": 2.5209562403828805e-05,
2024
+ "loss": 0.7114,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 0.5817230273752013,
2029
+ "grad_norm": 1.2502771615982056,
2030
+ "learning_rate": 2.5004984200870694e-05,
2031
+ "loss": 0.8076,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 0.5837359098228664,
2036
+ "grad_norm": 1.1746399402618408,
2037
+ "learning_rate": 2.480071918096112e-05,
2038
+ "loss": 0.7951,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 0.5857487922705314,
2043
+ "grad_norm": 1.1511627435684204,
2044
+ "learning_rate": 2.45967758794179e-05,
2045
+ "loss": 0.7189,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 0.5877616747181964,
2050
+ "grad_norm": 1.1979589462280273,
2051
+ "learning_rate": 2.4393162818115607e-05,
2052
+ "loss": 0.7739,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 0.5897745571658615,
2057
+ "grad_norm": 1.1766811609268188,
2058
+ "learning_rate": 2.4189888505129634e-05,
2059
+ "loss": 0.7609,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 0.5917874396135265,
2064
+ "grad_norm": 1.177783727645874,
2065
+ "learning_rate": 2.3986961434380555e-05,
2066
+ "loss": 0.7161,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 0.5938003220611916,
2071
+ "grad_norm": 1.1824970245361328,
2072
+ "learning_rate": 2.378439008527928e-05,
2073
+ "loss": 0.7752,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 0.5958132045088567,
2078
+ "grad_norm": 1.1629244089126587,
2079
+ "learning_rate": 2.3582182922372703e-05,
2080
+ "loss": 0.7514,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 0.5978260869565217,
2085
+ "grad_norm": 1.193488359451294,
2086
+ "learning_rate": 2.3380348394989985e-05,
2087
+ "loss": 0.7257,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 0.5998389694041868,
2092
+ "grad_norm": 1.2829092741012573,
2093
+ "learning_rate": 2.3178894936889573e-05,
2094
+ "loss": 0.8165,
2095
+ "step": 298
2096
+ },
2097
+ {
2098
+ "epoch": 0.6018518518518519,
2099
+ "grad_norm": 1.1431480646133423,
2100
+ "learning_rate": 2.2977830965906677e-05,
2101
+ "loss": 0.7237,
2102
+ "step": 299
2103
+ },
2104
+ {
2105
+ "epoch": 0.6038647342995169,
2106
+ "grad_norm": 1.1849764585494995,
2107
+ "learning_rate": 2.277716488360165e-05,
2108
+ "loss": 0.7758,
2109
+ "step": 300
2110
+ },
2111
+ {
2112
+ "epoch": 0.605877616747182,
2113
+ "grad_norm": 1.1299766302108765,
2114
+ "learning_rate": 2.2576905074908823e-05,
2115
+ "loss": 0.7272,
2116
+ "step": 301
2117
+ },
2118
+ {
2119
+ "epoch": 0.6078904991948471,
2120
+ "grad_norm": 1.1116759777069092,
2121
+ "learning_rate": 2.2377059907786196e-05,
2122
+ "loss": 0.7152,
2123
+ "step": 302
2124
+ },
2125
+ {
2126
+ "epoch": 0.6099033816425121,
2127
+ "grad_norm": 1.1651757955551147,
2128
+ "learning_rate": 2.217763773286577e-05,
2129
+ "loss": 0.7587,
2130
+ "step": 303
2131
+ },
2132
+ {
2133
+ "epoch": 0.6119162640901772,
2134
+ "grad_norm": 1.1139724254608154,
2135
+ "learning_rate": 2.1978646883104566e-05,
2136
+ "loss": 0.7187,
2137
+ "step": 304
2138
+ },
2139
+ {
2140
+ "epoch": 0.6139291465378421,
2141
+ "grad_norm": 1.1941097974777222,
2142
+ "learning_rate": 2.1780095673436497e-05,
2143
+ "loss": 0.7337,
2144
+ "step": 305
2145
+ },
2146
+ {
2147
+ "epoch": 0.6159420289855072,
2148
+ "grad_norm": 1.1893556118011475,
2149
+ "learning_rate": 2.1581992400424884e-05,
2150
+ "loss": 0.7453,
2151
+ "step": 306
2152
+ },
2153
+ {
2154
+ "epoch": 0.6179549114331723,
2155
+ "grad_norm": 1.2010302543640137,
2156
+ "learning_rate": 2.1384345341915767e-05,
2157
+ "loss": 0.7541,
2158
+ "step": 307
2159
+ },
2160
+ {
2161
+ "epoch": 0.6199677938808373,
2162
+ "grad_norm": 1.0827986001968384,
2163
+ "learning_rate": 2.1187162756692057e-05,
2164
+ "loss": 0.7393,
2165
+ "step": 308
2166
+ },
2167
+ {
2168
+ "epoch": 0.6219806763285024,
2169
+ "grad_norm": 1.2004282474517822,
2170
+ "learning_rate": 2.09904528841284e-05,
2171
+ "loss": 0.7522,
2172
+ "step": 309
2173
+ },
2174
+ {
2175
+ "epoch": 0.6239935587761675,
2176
+ "grad_norm": 1.1190348863601685,
2177
+ "learning_rate": 2.0794223943846917e-05,
2178
+ "loss": 0.7141,
2179
+ "step": 310
2180
+ },
2181
+ {
2182
+ "epoch": 0.6260064412238325,
2183
+ "grad_norm": 1.2460802793502808,
2184
+ "learning_rate": 2.059848413537369e-05,
2185
+ "loss": 0.818,
2186
+ "step": 311
2187
+ },
2188
+ {
2189
+ "epoch": 0.6280193236714976,
2190
+ "grad_norm": 1.1238231658935547,
2191
+ "learning_rate": 2.040324163779623e-05,
2192
+ "loss": 0.7505,
2193
+ "step": 312
2194
+ },
2195
+ {
2196
+ "epoch": 0.6300322061191627,
2197
+ "grad_norm": 1.264402985572815,
2198
+ "learning_rate": 2.020850460942162e-05,
2199
+ "loss": 0.7544,
2200
+ "step": 313
2201
+ },
2202
+ {
2203
+ "epoch": 0.6320450885668277,
2204
+ "grad_norm": 1.197068214416504,
2205
+ "learning_rate": 2.0014281187435673e-05,
2206
+ "loss": 0.751,
2207
+ "step": 314
2208
+ },
2209
+ {
2210
+ "epoch": 0.6340579710144928,
2211
+ "grad_norm": 1.1713694334030151,
2212
+ "learning_rate": 1.9820579487562915e-05,
2213
+ "loss": 0.7245,
2214
+ "step": 315
2215
+ },
2216
+ {
2217
+ "epoch": 0.6360708534621579,
2218
+ "grad_norm": 1.2123608589172363,
2219
+ "learning_rate": 1.9627407603727402e-05,
2220
+ "loss": 0.7627,
2221
+ "step": 316
2222
+ },
2223
+ {
2224
+ "epoch": 0.6380837359098228,
2225
+ "grad_norm": 1.1857858896255493,
2226
+ "learning_rate": 1.9434773607714608e-05,
2227
+ "loss": 0.7352,
2228
+ "step": 317
2229
+ },
2230
+ {
2231
+ "epoch": 0.6400966183574879,
2232
+ "grad_norm": 1.1570547819137573,
2233
+ "learning_rate": 1.9242685548834033e-05,
2234
+ "loss": 0.7537,
2235
+ "step": 318
2236
+ },
2237
+ {
2238
+ "epoch": 0.6421095008051529,
2239
+ "grad_norm": 1.2034544944763184,
2240
+ "learning_rate": 1.9051151453582976e-05,
2241
+ "loss": 0.7414,
2242
+ "step": 319
2243
+ },
2244
+ {
2245
+ "epoch": 0.644122383252818,
2246
+ "grad_norm": 1.1642334461212158,
2247
+ "learning_rate": 1.8860179325311052e-05,
2248
+ "loss": 0.7448,
2249
+ "step": 320
2250
+ },
2251
+ {
2252
+ "epoch": 0.6461352657004831,
2253
+ "grad_norm": 1.235265851020813,
2254
+ "learning_rate": 1.866977714388581e-05,
2255
+ "loss": 0.773,
2256
+ "step": 321
2257
+ },
2258
+ {
2259
+ "epoch": 0.6481481481481481,
2260
+ "grad_norm": 1.2570306062698364,
2261
+ "learning_rate": 1.847995286535927e-05,
2262
+ "loss": 0.7205,
2263
+ "step": 322
2264
+ },
2265
+ {
2266
+ "epoch": 0.6501610305958132,
2267
+ "grad_norm": 1.201730489730835,
2268
+ "learning_rate": 1.829071442163547e-05,
2269
+ "loss": 0.7353,
2270
+ "step": 323
2271
+ },
2272
+ {
2273
+ "epoch": 0.6521739130434783,
2274
+ "grad_norm": 1.1657803058624268,
2275
+ "learning_rate": 1.8102069720139113e-05,
2276
+ "loss": 0.7206,
2277
+ "step": 324
2278
+ },
2279
+ {
2280
+ "epoch": 0.6541867954911433,
2281
+ "grad_norm": 1.0922691822052002,
2282
+ "learning_rate": 1.7914026643484976e-05,
2283
+ "loss": 0.7105,
2284
+ "step": 325
2285
+ },
2286
+ {
2287
+ "epoch": 0.6561996779388084,
2288
+ "grad_norm": 1.1522175073623657,
2289
+ "learning_rate": 1.772659304914873e-05,
2290
+ "loss": 0.7529,
2291
+ "step": 326
2292
+ },
2293
+ {
2294
+ "epoch": 0.6582125603864735,
2295
+ "grad_norm": 1.1323693990707397,
2296
+ "learning_rate": 1.7539776769138468e-05,
2297
+ "loss": 0.728,
2298
+ "step": 327
2299
+ },
2300
+ {
2301
+ "epoch": 0.6602254428341385,
2302
+ "grad_norm": 1.229993224143982,
2303
+ "learning_rate": 1.7353585609667497e-05,
2304
+ "loss": 0.7535,
2305
+ "step": 328
2306
+ },
2307
+ {
2308
+ "epoch": 0.6622383252818036,
2309
+ "grad_norm": 1.1816473007202148,
2310
+ "learning_rate": 1.7168027350828144e-05,
2311
+ "loss": 0.7336,
2312
+ "step": 329
2313
+ },
2314
+ {
2315
+ "epoch": 0.6642512077294686,
2316
+ "grad_norm": 1.2471328973770142,
2317
+ "learning_rate": 1.6983109746266657e-05,
2318
+ "loss": 0.7856,
2319
+ "step": 330
2320
+ },
2321
+ {
2322
+ "epoch": 0.6662640901771336,
2323
+ "grad_norm": 1.1073960065841675,
2324
+ "learning_rate": 1.6798840522859247e-05,
2325
+ "loss": 0.6935,
2326
+ "step": 331
2327
+ },
2328
+ {
2329
+ "epoch": 0.6682769726247987,
2330
+ "grad_norm": 1.2102614641189575,
2331
+ "learning_rate": 1.6615227380389165e-05,
2332
+ "loss": 0.7561,
2333
+ "step": 332
2334
+ },
2335
+ {
2336
+ "epoch": 0.6702898550724637,
2337
+ "grad_norm": 1.3027081489562988,
2338
+ "learning_rate": 1.6432277991224978e-05,
2339
+ "loss": 0.7802,
2340
+ "step": 333
2341
+ },
2342
+ {
2343
+ "epoch": 0.6723027375201288,
2344
+ "grad_norm": 1.2084347009658813,
2345
+ "learning_rate": 1.6250000000000005e-05,
2346
+ "loss": 0.8191,
2347
+ "step": 334
2348
+ },
2349
+ {
2350
+ "epoch": 0.6743156199677939,
2351
+ "grad_norm": 1.2484228610992432,
2352
+ "learning_rate": 1.6068401023292833e-05,
2353
+ "loss": 0.7389,
2354
+ "step": 335
2355
+ },
2356
+ {
2357
+ "epoch": 0.6763285024154589,
2358
+ "grad_norm": 1.2207857370376587,
2359
+ "learning_rate": 1.5887488649309122e-05,
2360
+ "loss": 0.7465,
2361
+ "step": 336
2362
+ },
2363
+ {
2364
+ "epoch": 0.678341384863124,
2365
+ "grad_norm": 1.1802961826324463,
2366
+ "learning_rate": 1.5707270437564453e-05,
2367
+ "loss": 0.7105,
2368
+ "step": 337
2369
+ },
2370
+ {
2371
+ "epoch": 0.6803542673107891,
2372
+ "grad_norm": 1.1720234155654907,
2373
+ "learning_rate": 1.5527753918568504e-05,
2374
+ "loss": 0.6955,
2375
+ "step": 338
2376
+ },
2377
+ {
2378
+ "epoch": 0.6823671497584541,
2379
+ "grad_norm": 1.0980851650238037,
2380
+ "learning_rate": 1.5348946593510345e-05,
2381
+ "loss": 0.7273,
2382
+ "step": 339
2383
+ },
2384
+ {
2385
+ "epoch": 0.6843800322061192,
2386
+ "grad_norm": 1.2615996599197388,
2387
+ "learning_rate": 1.5170855933945039e-05,
2388
+ "loss": 0.7734,
2389
+ "step": 340
2390
+ },
2391
+ {
2392
+ "epoch": 0.6863929146537843,
2393
+ "grad_norm": 1.1403189897537231,
2394
+ "learning_rate": 1.4993489381481403e-05,
2395
+ "loss": 0.7184,
2396
+ "step": 341
2397
+ },
2398
+ {
2399
+ "epoch": 0.6884057971014492,
2400
+ "grad_norm": 1.2819575071334839,
2401
+ "learning_rate": 1.481685434747106e-05,
2402
+ "loss": 0.832,
2403
+ "step": 342
2404
+ },
2405
+ {
2406
+ "epoch": 0.6904186795491143,
2407
+ "grad_norm": 1.1605795621871948,
2408
+ "learning_rate": 1.4640958212698804e-05,
2409
+ "loss": 0.7517,
2410
+ "step": 343
2411
+ },
2412
+ {
2413
+ "epoch": 0.6924315619967794,
2414
+ "grad_norm": 1.1168081760406494,
2415
+ "learning_rate": 1.4465808327074102e-05,
2416
+ "loss": 0.6931,
2417
+ "step": 344
2418
+ },
2419
+ {
2420
+ "epoch": 0.6944444444444444,
2421
+ "grad_norm": 1.167962670326233,
2422
+ "learning_rate": 1.4291412009324043e-05,
2423
+ "loss": 0.6917,
2424
+ "step": 345
2425
+ },
2426
+ {
2427
+ "epoch": 0.6964573268921095,
2428
+ "grad_norm": 1.1960166692733765,
2429
+ "learning_rate": 1.41177765466875e-05,
2430
+ "loss": 0.7653,
2431
+ "step": 346
2432
+ },
2433
+ {
2434
+ "epoch": 0.6984702093397746,
2435
+ "grad_norm": 1.1906245946884155,
2436
+ "learning_rate": 1.3944909194610604e-05,
2437
+ "loss": 0.7477,
2438
+ "step": 347
2439
+ },
2440
+ {
2441
+ "epoch": 0.7004830917874396,
2442
+ "grad_norm": 1.2501006126403809,
2443
+ "learning_rate": 1.3772817176443637e-05,
2444
+ "loss": 0.8167,
2445
+ "step": 348
2446
+ },
2447
+ {
2448
+ "epoch": 0.7024959742351047,
2449
+ "grad_norm": 1.1363681554794312,
2450
+ "learning_rate": 1.360150768313913e-05,
2451
+ "loss": 0.7148,
2452
+ "step": 349
2453
+ },
2454
+ {
2455
+ "epoch": 0.7045088566827697,
2456
+ "grad_norm": 1.164594292640686,
2457
+ "learning_rate": 1.343098787295142e-05,
2458
+ "loss": 0.761,
2459
+ "step": 350
2460
+ },
2461
+ {
2462
+ "epoch": 0.7065217391304348,
2463
+ "grad_norm": 1.1728458404541016,
2464
+ "learning_rate": 1.3261264871137532e-05,
2465
+ "loss": 0.759,
2466
+ "step": 351
2467
+ },
2468
+ {
2469
+ "epoch": 0.7085346215780999,
2470
+ "grad_norm": 1.1953744888305664,
2471
+ "learning_rate": 1.3092345769659455e-05,
2472
+ "loss": 0.7295,
2473
+ "step": 352
2474
+ },
2475
+ {
2476
+ "epoch": 0.7105475040257649,
2477
+ "grad_norm": 1.18873131275177,
2478
+ "learning_rate": 1.2924237626887782e-05,
2479
+ "loss": 0.7068,
2480
+ "step": 353
2481
+ },
2482
+ {
2483
+ "epoch": 0.7125603864734299,
2484
+ "grad_norm": 1.201655626296997,
2485
+ "learning_rate": 1.2756947467306781e-05,
2486
+ "loss": 0.8004,
2487
+ "step": 354
2488
+ },
2489
+ {
2490
+ "epoch": 0.714573268921095,
2491
+ "grad_norm": 1.2549744844436646,
2492
+ "learning_rate": 1.2590482281220907e-05,
2493
+ "loss": 0.7748,
2494
+ "step": 355
2495
+ },
2496
+ {
2497
+ "epoch": 0.71658615136876,
2498
+ "grad_norm": 1.1518903970718384,
2499
+ "learning_rate": 1.2424849024462648e-05,
2500
+ "loss": 0.7148,
2501
+ "step": 356
2502
+ },
2503
+ {
2504
+ "epoch": 0.7185990338164251,
2505
+ "grad_norm": 1.2530384063720703,
2506
+ "learning_rate": 1.2260054618101907e-05,
2507
+ "loss": 0.7865,
2508
+ "step": 357
2509
+ },
2510
+ {
2511
+ "epoch": 0.7206119162640902,
2512
+ "grad_norm": 1.1757794618606567,
2513
+ "learning_rate": 1.2096105948156802e-05,
2514
+ "loss": 0.7733,
2515
+ "step": 358
2516
+ },
2517
+ {
2518
+ "epoch": 0.7226247987117552,
2519
+ "grad_norm": 1.0709518194198608,
2520
+ "learning_rate": 1.1933009865305918e-05,
2521
+ "loss": 0.6824,
2522
+ "step": 359
2523
+ },
2524
+ {
2525
+ "epoch": 0.7246376811594203,
2526
+ "grad_norm": 1.3024777173995972,
2527
+ "learning_rate": 1.1770773184602051e-05,
2528
+ "loss": 0.8065,
2529
+ "step": 360
2530
+ },
2531
+ {
2532
+ "epoch": 0.7266505636070854,
2533
+ "grad_norm": 1.153552532196045,
2534
+ "learning_rate": 1.160940268518747e-05,
2535
+ "loss": 0.7283,
2536
+ "step": 361
2537
+ },
2538
+ {
2539
+ "epoch": 0.7286634460547504,
2540
+ "grad_norm": 1.239566445350647,
2541
+ "learning_rate": 1.1448905110010584e-05,
2542
+ "loss": 0.753,
2543
+ "step": 362
2544
+ },
2545
+ {
2546
+ "epoch": 0.7306763285024155,
2547
+ "grad_norm": 1.223362684249878,
2548
+ "learning_rate": 1.1289287165544234e-05,
2549
+ "loss": 0.7867,
2550
+ "step": 363
2551
+ },
2552
+ {
2553
+ "epoch": 0.7326892109500805,
2554
+ "grad_norm": 1.1192233562469482,
2555
+ "learning_rate": 1.1130555521505434e-05,
2556
+ "loss": 0.7062,
2557
+ "step": 364
2558
+ },
2559
+ {
2560
+ "epoch": 0.7347020933977456,
2561
+ "grad_norm": 1.172276496887207,
2562
+ "learning_rate": 1.09727168105767e-05,
2563
+ "loss": 0.726,
2564
+ "step": 365
2565
+ },
2566
+ {
2567
+ "epoch": 0.7367149758454107,
2568
+ "grad_norm": 1.3750008344650269,
2569
+ "learning_rate": 1.0815777628128859e-05,
2570
+ "loss": 0.7472,
2571
+ "step": 366
2572
+ },
2573
+ {
2574
+ "epoch": 0.7387278582930756,
2575
+ "grad_norm": 1.0873605012893677,
2576
+ "learning_rate": 1.065974453194552e-05,
2577
+ "loss": 0.7121,
2578
+ "step": 367
2579
+ },
2580
+ {
2581
+ "epoch": 0.7407407407407407,
2582
+ "grad_norm": 1.194230318069458,
2583
+ "learning_rate": 1.0504624041948988e-05,
2584
+ "loss": 0.7557,
2585
+ "step": 368
2586
+ },
2587
+ {
2588
+ "epoch": 0.7427536231884058,
2589
+ "grad_norm": 1.1566953659057617,
2590
+ "learning_rate": 1.0350422639927854e-05,
2591
+ "loss": 0.7104,
2592
+ "step": 369
2593
+ },
2594
+ {
2595
+ "epoch": 0.7447665056360708,
2596
+ "grad_norm": 1.1560354232788086,
2597
+ "learning_rate": 1.0197146769266161e-05,
2598
+ "loss": 0.7252,
2599
+ "step": 370
2600
+ },
2601
+ {
2602
+ "epoch": 0.7467793880837359,
2603
+ "grad_norm": 1.144019365310669,
2604
+ "learning_rate": 1.0044802834674153e-05,
2605
+ "loss": 0.7066,
2606
+ "step": 371
2607
+ },
2608
+ {
2609
+ "epoch": 0.748792270531401,
2610
+ "grad_norm": 1.1338632106781006,
2611
+ "learning_rate": 9.893397201920635e-06,
2612
+ "loss": 0.7272,
2613
+ "step": 372
2614
+ },
2615
+ {
2616
+ "epoch": 0.750805152979066,
2617
+ "grad_norm": 1.0915791988372803,
2618
+ "learning_rate": 9.742936197567023e-06,
2619
+ "loss": 0.6837,
2620
+ "step": 373
2621
+ },
2622
+ {
2623
+ "epoch": 0.7528180354267311,
2624
+ "grad_norm": 1.2796902656555176,
2625
+ "learning_rate": 9.593426108702926e-06,
2626
+ "loss": 0.7793,
2627
+ "step": 374
2628
+ },
2629
+ {
2630
+ "epoch": 0.7548309178743962,
2631
+ "grad_norm": 1.248378038406372,
2632
+ "learning_rate": 9.444873182683483e-06,
2633
+ "loss": 0.7716,
2634
+ "step": 375
2635
+ },
2636
+ {
2637
+ "epoch": 0.7568438003220612,
2638
+ "grad_norm": 1.1415481567382812,
2639
+ "learning_rate": 9.297283626868286e-06,
2640
+ "loss": 0.7048,
2641
+ "step": 376
2642
+ },
2643
+ {
2644
+ "epoch": 0.7588566827697263,
2645
+ "grad_norm": 1.2144063711166382,
2646
+ "learning_rate": 9.150663608362011e-06,
2647
+ "loss": 0.7534,
2648
+ "step": 377
2649
+ },
2650
+ {
2651
+ "epoch": 0.7608695652173914,
2652
+ "grad_norm": 1.1962350606918335,
2653
+ "learning_rate": 9.00501925375673e-06,
2654
+ "loss": 0.7506,
2655
+ "step": 378
2656
+ },
2657
+ {
2658
+ "epoch": 0.7628824476650563,
2659
+ "grad_norm": 1.2141233682632446,
2660
+ "learning_rate": 8.860356648875915e-06,
2661
+ "loss": 0.7769,
2662
+ "step": 379
2663
+ },
2664
+ {
2665
+ "epoch": 0.7648953301127214,
2666
+ "grad_norm": 1.1662864685058594,
2667
+ "learning_rate": 8.716681838520107e-06,
2668
+ "loss": 0.7564,
2669
+ "step": 380
2670
+ },
2671
+ {
2672
+ "epoch": 0.7669082125603864,
2673
+ "grad_norm": 1.1819028854370117,
2674
+ "learning_rate": 8.574000826214358e-06,
2675
+ "loss": 0.707,
2676
+ "step": 381
2677
+ },
2678
+ {
2679
+ "epoch": 0.7689210950080515,
2680
+ "grad_norm": 1.2373204231262207,
2681
+ "learning_rate": 8.432319573957356e-06,
2682
+ "loss": 0.7568,
2683
+ "step": 382
2684
+ },
2685
+ {
2686
+ "epoch": 0.7709339774557166,
2687
+ "grad_norm": 1.1681913137435913,
2688
+ "learning_rate": 8.291644001972314e-06,
2689
+ "loss": 0.715,
2690
+ "step": 383
2691
+ },
2692
+ {
2693
+ "epoch": 0.7729468599033816,
2694
+ "grad_norm": 1.113655924797058,
2695
+ "learning_rate": 8.151979988459579e-06,
2696
+ "loss": 0.7002,
2697
+ "step": 384
2698
+ },
2699
+ {
2700
+ "epoch": 0.7749597423510467,
2701
+ "grad_norm": 1.2017922401428223,
2702
+ "learning_rate": 8.013333369351026e-06,
2703
+ "loss": 0.7705,
2704
+ "step": 385
2705
+ },
2706
+ {
2707
+ "epoch": 0.7769726247987118,
2708
+ "grad_norm": 1.1531996726989746,
2709
+ "learning_rate": 7.875709938066166e-06,
2710
+ "loss": 0.7342,
2711
+ "step": 386
2712
+ },
2713
+ {
2714
+ "epoch": 0.7789855072463768,
2715
+ "grad_norm": 1.152120590209961,
2716
+ "learning_rate": 7.739115445270107e-06,
2717
+ "loss": 0.6955,
2718
+ "step": 387
2719
+ },
2720
+ {
2721
+ "epoch": 0.7809983896940419,
2722
+ "grad_norm": 1.2263264656066895,
2723
+ "learning_rate": 7.603555598633218e-06,
2724
+ "loss": 0.7702,
2725
+ "step": 388
2726
+ },
2727
+ {
2728
+ "epoch": 0.783011272141707,
2729
+ "grad_norm": 1.1699055433273315,
2730
+ "learning_rate": 7.469036062592665e-06,
2731
+ "loss": 0.7221,
2732
+ "step": 389
2733
+ },
2734
+ {
2735
+ "epoch": 0.785024154589372,
2736
+ "grad_norm": 1.18465256690979,
2737
+ "learning_rate": 7.335562458115694e-06,
2738
+ "loss": 0.7551,
2739
+ "step": 390
2740
+ },
2741
+ {
2742
+ "epoch": 0.7870370370370371,
2743
+ "grad_norm": 1.1775195598602295,
2744
+ "learning_rate": 7.2031403624647985e-06,
2745
+ "loss": 0.7137,
2746
+ "step": 391
2747
+ },
2748
+ {
2749
+ "epoch": 0.789049919484702,
2750
+ "grad_norm": 1.1562498807907104,
2751
+ "learning_rate": 7.071775308964607e-06,
2752
+ "loss": 0.7103,
2753
+ "step": 392
2754
+ },
2755
+ {
2756
+ "epoch": 0.7910628019323671,
2757
+ "grad_norm": 1.146081566810608,
2758
+ "learning_rate": 6.9414727867707234e-06,
2759
+ "loss": 0.7525,
2760
+ "step": 393
2761
+ },
2762
+ {
2763
+ "epoch": 0.7930756843800322,
2764
+ "grad_norm": 1.1677244901657104,
2765
+ "learning_rate": 6.812238240640326e-06,
2766
+ "loss": 0.7529,
2767
+ "step": 394
2768
+ },
2769
+ {
2770
+ "epoch": 0.7950885668276972,
2771
+ "grad_norm": 1.1934747695922852,
2772
+ "learning_rate": 6.684077070704684e-06,
2773
+ "loss": 0.7735,
2774
+ "step": 395
2775
+ },
2776
+ {
2777
+ "epoch": 0.7971014492753623,
2778
+ "grad_norm": 1.1619067192077637,
2779
+ "learning_rate": 6.556994632243477e-06,
2780
+ "loss": 0.7394,
2781
+ "step": 396
2782
+ },
2783
+ {
2784
+ "epoch": 0.7991143317230274,
2785
+ "grad_norm": 1.155696988105774,
2786
+ "learning_rate": 6.430996235461075e-06,
2787
+ "loss": 0.6981,
2788
+ "step": 397
2789
+ },
2790
+ {
2791
+ "epoch": 0.8011272141706924,
2792
+ "grad_norm": 1.0751657485961914,
2793
+ "learning_rate": 6.306087145264586e-06,
2794
+ "loss": 0.654,
2795
+ "step": 398
2796
+ },
2797
+ {
2798
+ "epoch": 0.8031400966183575,
2799
+ "grad_norm": 1.186436414718628,
2800
+ "learning_rate": 6.182272581043894e-06,
2801
+ "loss": 0.7745,
2802
+ "step": 399
2803
+ },
2804
+ {
2805
+ "epoch": 0.8051529790660226,
2806
+ "grad_norm": 1.1653515100479126,
2807
+ "learning_rate": 6.0595577164535555e-06,
2808
+ "loss": 0.7119,
2809
+ "step": 400
2810
+ },
2811
+ {
2812
+ "epoch": 0.8071658615136876,
2813
+ "grad_norm": 1.1874843835830688,
2814
+ "learning_rate": 5.937947679196634e-06,
2815
+ "loss": 0.7271,
2816
+ "step": 401
2817
+ },
2818
+ {
2819
+ "epoch": 0.8091787439613527,
2820
+ "grad_norm": 1.1206715106964111,
2821
+ "learning_rate": 5.817447550810402e-06,
2822
+ "loss": 0.7106,
2823
+ "step": 402
2824
+ },
2825
+ {
2826
+ "epoch": 0.8111916264090178,
2827
+ "grad_norm": 1.1597195863723755,
2828
+ "learning_rate": 5.69806236645403e-06,
2829
+ "loss": 0.7278,
2830
+ "step": 403
2831
+ },
2832
+ {
2833
+ "epoch": 0.8132045088566827,
2834
+ "grad_norm": 1.1792165040969849,
2835
+ "learning_rate": 5.579797114698201e-06,
2836
+ "loss": 0.7158,
2837
+ "step": 404
2838
+ },
2839
+ {
2840
+ "epoch": 0.8152173913043478,
2841
+ "grad_norm": 1.1763123273849487,
2842
+ "learning_rate": 5.462656737316625e-06,
2843
+ "loss": 0.7111,
2844
+ "step": 405
2845
+ },
2846
+ {
2847
+ "epoch": 0.8172302737520128,
2848
+ "grad_norm": 1.1549781560897827,
2849
+ "learning_rate": 5.346646129079571e-06,
2850
+ "loss": 0.7139,
2851
+ "step": 406
2852
+ },
2853
+ {
2854
+ "epoch": 0.8192431561996779,
2855
+ "grad_norm": 1.0576976537704468,
2856
+ "learning_rate": 5.231770137549324e-06,
2857
+ "loss": 0.6884,
2858
+ "step": 407
2859
+ },
2860
+ {
2861
+ "epoch": 0.821256038647343,
2862
+ "grad_norm": 1.2329165935516357,
2863
+ "learning_rate": 5.118033562877639e-06,
2864
+ "loss": 0.7629,
2865
+ "step": 408
2866
+ },
2867
+ {
2868
+ "epoch": 0.823268921095008,
2869
+ "grad_norm": 1.217031717300415,
2870
+ "learning_rate": 5.005441157605165e-06,
2871
+ "loss": 0.7645,
2872
+ "step": 409
2873
+ },
2874
+ {
2875
+ "epoch": 0.8252818035426731,
2876
+ "grad_norm": 1.2384543418884277,
2877
+ "learning_rate": 4.893997626462837e-06,
2878
+ "loss": 0.803,
2879
+ "step": 410
2880
+ },
2881
+ {
2882
+ "epoch": 0.8272946859903382,
2883
+ "grad_norm": 1.2117931842803955,
2884
+ "learning_rate": 4.783707626175302e-06,
2885
+ "loss": 0.7443,
2886
+ "step": 411
2887
+ },
2888
+ {
2889
+ "epoch": 0.8293075684380032,
2890
+ "grad_norm": 1.192091703414917,
2891
+ "learning_rate": 4.674575765266343e-06,
2892
+ "loss": 0.7897,
2893
+ "step": 412
2894
+ },
2895
+ {
2896
+ "epoch": 0.8313204508856683,
2897
+ "grad_norm": 1.1320070028305054,
2898
+ "learning_rate": 4.566606603866287e-06,
2899
+ "loss": 0.7322,
2900
+ "step": 413
2901
+ },
2902
+ {
2903
+ "epoch": 0.8333333333333334,
2904
+ "grad_norm": 1.1446431875228882,
2905
+ "learning_rate": 4.459804653521476e-06,
2906
+ "loss": 0.7131,
2907
+ "step": 414
2908
+ },
2909
+ {
2910
+ "epoch": 0.8353462157809984,
2911
+ "grad_norm": 1.159525990486145,
2912
+ "learning_rate": 4.3541743770057415e-06,
2913
+ "loss": 0.6985,
2914
+ "step": 415
2915
+ },
2916
+ {
2917
+ "epoch": 0.8373590982286635,
2918
+ "grad_norm": 1.15835702419281,
2919
+ "learning_rate": 4.249720188133946e-06,
2920
+ "loss": 0.7334,
2921
+ "step": 416
2922
+ },
2923
+ {
2924
+ "epoch": 0.8393719806763285,
2925
+ "grad_norm": 1.1312042474746704,
2926
+ "learning_rate": 4.146446451577505e-06,
2927
+ "loss": 0.7053,
2928
+ "step": 417
2929
+ },
2930
+ {
2931
+ "epoch": 0.8413848631239935,
2932
+ "grad_norm": 1.2126394510269165,
2933
+ "learning_rate": 4.04435748268205e-06,
2934
+ "loss": 0.7575,
2935
+ "step": 418
2936
+ },
2937
+ {
2938
+ "epoch": 0.8433977455716586,
2939
+ "grad_norm": 1.138115644454956,
2940
+ "learning_rate": 3.943457547287085e-06,
2941
+ "loss": 0.713,
2942
+ "step": 419
2943
+ },
2944
+ {
2945
+ "epoch": 0.8454106280193237,
2946
+ "grad_norm": 1.15996515750885,
2947
+ "learning_rate": 3.84375086154774e-06,
2948
+ "loss": 0.6766,
2949
+ "step": 420
2950
+ },
2951
+ {
2952
+ "epoch": 0.8474235104669887,
2953
+ "grad_norm": 1.1611663103103638,
2954
+ "learning_rate": 3.745241591758621e-06,
2955
+ "loss": 0.7414,
2956
+ "step": 421
2957
+ },
2958
+ {
2959
+ "epoch": 0.8494363929146538,
2960
+ "grad_norm": 1.2409067153930664,
2961
+ "learning_rate": 3.647933854179685e-06,
2962
+ "loss": 0.6949,
2963
+ "step": 422
2964
+ },
2965
+ {
2966
+ "epoch": 0.8514492753623188,
2967
+ "grad_norm": 1.1697113513946533,
2968
+ "learning_rate": 3.5518317148642477e-06,
2969
+ "loss": 0.7303,
2970
+ "step": 423
2971
+ },
2972
+ {
2973
+ "epoch": 0.8534621578099839,
2974
+ "grad_norm": 1.1085422039031982,
2975
+ "learning_rate": 3.4569391894891044e-06,
2976
+ "loss": 0.7416,
2977
+ "step": 424
2978
+ },
2979
+ {
2980
+ "epoch": 0.855475040257649,
2981
+ "grad_norm": 1.0984251499176025,
2982
+ "learning_rate": 3.363260243186695e-06,
2983
+ "loss": 0.7174,
2984
+ "step": 425
2985
+ },
2986
+ {
2987
+ "epoch": 0.857487922705314,
2988
+ "grad_norm": 1.1758277416229248,
2989
+ "learning_rate": 3.270798790379478e-06,
2990
+ "loss": 0.7143,
2991
+ "step": 426
2992
+ },
2993
+ {
2994
+ "epoch": 0.8595008051529791,
2995
+ "grad_norm": 1.1498491764068604,
2996
+ "learning_rate": 3.1795586946162735e-06,
2997
+ "loss": 0.6948,
2998
+ "step": 427
2999
+ },
3000
+ {
3001
+ "epoch": 0.8615136876006442,
3002
+ "grad_norm": 1.141033411026001,
3003
+ "learning_rate": 3.0895437684109264e-06,
3004
+ "loss": 0.6885,
3005
+ "step": 428
3006
+ },
3007
+ {
3008
+ "epoch": 0.8635265700483091,
3009
+ "grad_norm": 1.22016179561615,
3010
+ "learning_rate": 3.000757773082916e-06,
3011
+ "loss": 0.7343,
3012
+ "step": 429
3013
+ },
3014
+ {
3015
+ "epoch": 0.8655394524959742,
3016
+ "grad_norm": 1.1663223505020142,
3017
+ "learning_rate": 2.9132044186002364e-06,
3018
+ "loss": 0.72,
3019
+ "step": 430
3020
+ },
3021
+ {
3022
+ "epoch": 0.8675523349436393,
3023
+ "grad_norm": 1.105422019958496,
3024
+ "learning_rate": 2.826887363424344e-06,
3025
+ "loss": 0.6861,
3026
+ "step": 431
3027
+ },
3028
+ {
3029
+ "epoch": 0.8695652173913043,
3030
+ "grad_norm": 1.2099831104278564,
3031
+ "learning_rate": 2.7418102143573087e-06,
3032
+ "loss": 0.7634,
3033
+ "step": 432
3034
+ },
3035
+ {
3036
+ "epoch": 0.8715780998389694,
3037
+ "grad_norm": 1.2633130550384521,
3038
+ "learning_rate": 2.6579765263910984e-06,
3039
+ "loss": 0.7891,
3040
+ "step": 433
3041
+ },
3042
+ {
3043
+ "epoch": 0.8735909822866345,
3044
+ "grad_norm": 1.1842279434204102,
3045
+ "learning_rate": 2.575389802559005e-06,
3046
+ "loss": 0.7129,
3047
+ "step": 434
3048
+ },
3049
+ {
3050
+ "epoch": 0.8756038647342995,
3051
+ "grad_norm": 1.1939607858657837,
3052
+ "learning_rate": 2.494053493789313e-06,
3053
+ "loss": 0.7441,
3054
+ "step": 435
3055
+ },
3056
+ {
3057
+ "epoch": 0.8776167471819646,
3058
+ "grad_norm": 1.1123054027557373,
3059
+ "learning_rate": 2.413970998761064e-06,
3060
+ "loss": 0.7262,
3061
+ "step": 436
3062
+ },
3063
+ {
3064
+ "epoch": 0.8796296296296297,
3065
+ "grad_norm": 1.1603885889053345,
3066
+ "learning_rate": 2.3351456637620527e-06,
3067
+ "loss": 0.7358,
3068
+ "step": 437
3069
+ },
3070
+ {
3071
+ "epoch": 0.8816425120772947,
3072
+ "grad_norm": 1.2573004961013794,
3073
+ "learning_rate": 2.2575807825490253e-06,
3074
+ "loss": 0.7212,
3075
+ "step": 438
3076
+ },
3077
+ {
3078
+ "epoch": 0.8836553945249598,
3079
+ "grad_norm": 1.1583482027053833,
3080
+ "learning_rate": 2.181279596209982e-06,
3081
+ "loss": 0.7326,
3082
+ "step": 439
3083
+ },
3084
+ {
3085
+ "epoch": 0.8856682769726248,
3086
+ "grad_norm": 1.1847565174102783,
3087
+ "learning_rate": 2.106245293028837e-06,
3088
+ "loss": 0.7113,
3089
+ "step": 440
3090
+ },
3091
+ {
3092
+ "epoch": 0.8876811594202898,
3093
+ "grad_norm": 1.1204357147216797,
3094
+ "learning_rate": 2.0324810083521118e-06,
3095
+ "loss": 0.7036,
3096
+ "step": 441
3097
+ },
3098
+ {
3099
+ "epoch": 0.8896940418679549,
3100
+ "grad_norm": 1.151846170425415,
3101
+ "learning_rate": 1.9599898244579795e-06,
3102
+ "loss": 0.6821,
3103
+ "step": 442
3104
+ },
3105
+ {
3106
+ "epoch": 0.8917069243156199,
3107
+ "grad_norm": 1.183159589767456,
3108
+ "learning_rate": 1.8887747704274393e-06,
3109
+ "loss": 0.7567,
3110
+ "step": 443
3111
+ },
3112
+ {
3113
+ "epoch": 0.893719806763285,
3114
+ "grad_norm": 1.1199069023132324,
3115
+ "learning_rate": 1.8188388220177505e-06,
3116
+ "loss": 0.7097,
3117
+ "step": 444
3118
+ },
3119
+ {
3120
+ "epoch": 0.8957326892109501,
3121
+ "grad_norm": 1.135633945465088,
3122
+ "learning_rate": 1.7501849015381162e-06,
3123
+ "loss": 0.6987,
3124
+ "step": 445
3125
+ },
3126
+ {
3127
+ "epoch": 0.8977455716586151,
3128
+ "grad_norm": 1.1989564895629883,
3129
+ "learning_rate": 1.6828158777275144e-06,
3130
+ "loss": 0.7762,
3131
+ "step": 446
3132
+ },
3133
+ {
3134
+ "epoch": 0.8997584541062802,
3135
+ "grad_norm": 1.143509030342102,
3136
+ "learning_rate": 1.6167345656348955e-06,
3137
+ "loss": 0.7116,
3138
+ "step": 447
3139
+ },
3140
+ {
3141
+ "epoch": 0.9017713365539453,
3142
+ "grad_norm": 1.1980332136154175,
3143
+ "learning_rate": 1.5519437265015023e-06,
3144
+ "loss": 0.7295,
3145
+ "step": 448
3146
+ },
3147
+ {
3148
+ "epoch": 0.9037842190016103,
3149
+ "grad_norm": 1.184076189994812,
3150
+ "learning_rate": 1.4884460676455125e-06,
3151
+ "loss": 0.7432,
3152
+ "step": 449
3153
+ },
3154
+ {
3155
+ "epoch": 0.9057971014492754,
3156
+ "grad_norm": 1.1753592491149902,
3157
+ "learning_rate": 1.4262442423489138e-06,
3158
+ "loss": 0.7106,
3159
+ "step": 450
3160
+ }
3161
+ ],
3162
+ "logging_steps": 1,
3163
+ "max_steps": 496,
3164
+ "num_input_tokens_seen": 0,
3165
+ "num_train_epochs": 1,
3166
+ "save_steps": 50,
3167
+ "stateful_callbacks": {
3168
+ "TrainerControl": {
3169
+ "args": {
3170
+ "should_epoch_stop": false,
3171
+ "should_evaluate": false,
3172
+ "should_log": false,
3173
+ "should_save": true,
3174
+ "should_training_stop": false
3175
+ },
3176
+ "attributes": {}
3177
+ }
3178
+ },
3179
+ "total_flos": 5.282660945579213e+17,
3180
+ "train_batch_size": 6,
3181
+ "trial_name": null,
3182
+ "trial_params": null
3183
+ }
checkpoint-450/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fcacbd424439d9c4fe73a007c2520ea74f14d61c1b4e5cead1430854c05a21d
3
+ size 5112