SeungHeeKim commited on
Commit
2692f9e
·
verified ·
1 Parent(s): 813e1f0

Upload checkpoint-3930 to mmdocteam

Browse files
README.md ADDED
@@ -0,0 +1,206 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen3-Embedding-4B
3
+ library_name: peft
4
+ tags:
5
+ - base_model:adapter:Qwen/Qwen3-Embedding-4B
6
+ - lora
7
+ - transformers
8
+ ---
9
+
10
+ # Model Card for Model ID
11
+
12
+ <!-- Provide a quick summary of what the model is/does. -->
13
+
14
+
15
+
16
+ ## Model Details
17
+
18
+ ### Model Description
19
+
20
+ <!-- Provide a longer summary of what this model is. -->
21
+
22
+
23
+
24
+ - **Developed by:** [More Information Needed]
25
+ - **Funded by [optional]:** [More Information Needed]
26
+ - **Shared by [optional]:** [More Information Needed]
27
+ - **Model type:** [More Information Needed]
28
+ - **Language(s) (NLP):** [More Information Needed]
29
+ - **License:** [More Information Needed]
30
+ - **Finetuned from model [optional]:** [More Information Needed]
31
+
32
+ ### Model Sources [optional]
33
+
34
+ <!-- Provide the basic links for the model. -->
35
+
36
+ - **Repository:** [More Information Needed]
37
+ - **Paper [optional]:** [More Information Needed]
38
+ - **Demo [optional]:** [More Information Needed]
39
+
40
+ ## Uses
41
+
42
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
43
+
44
+ ### Direct Use
45
+
46
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
47
+
48
+ [More Information Needed]
49
+
50
+ ### Downstream Use [optional]
51
+
52
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
53
+
54
+ [More Information Needed]
55
+
56
+ ### Out-of-Scope Use
57
+
58
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
59
+
60
+ [More Information Needed]
61
+
62
+ ## Bias, Risks, and Limitations
63
+
64
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
65
+
66
+ [More Information Needed]
67
+
68
+ ### Recommendations
69
+
70
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
71
+
72
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
73
+
74
+ ## How to Get Started with the Model
75
+
76
+ Use the code below to get started with the model.
77
+
78
+ [More Information Needed]
79
+
80
+ ## Training Details
81
+
82
+ ### Training Data
83
+
84
+ <!-- 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. -->
85
+
86
+ [More Information Needed]
87
+
88
+ ### Training Procedure
89
+
90
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
91
+
92
+ #### Preprocessing [optional]
93
+
94
+ [More Information Needed]
95
+
96
+
97
+ #### Training Hyperparameters
98
+
99
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
100
+
101
+ #### Speeds, Sizes, Times [optional]
102
+
103
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
104
+
105
+ [More Information Needed]
106
+
107
+ ## Evaluation
108
+
109
+ <!-- This section describes the evaluation protocols and provides the results. -->
110
+
111
+ ### Testing Data, Factors & Metrics
112
+
113
+ #### Testing Data
114
+
115
+ <!-- This should link to a Dataset Card if possible. -->
116
+
117
+ [More Information Needed]
118
+
119
+ #### Factors
120
+
121
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
122
+
123
+ [More Information Needed]
124
+
125
+ #### Metrics
126
+
127
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
128
+
129
+ [More Information Needed]
130
+
131
+ ### Results
132
+
133
+ [More Information Needed]
134
+
135
+ #### Summary
136
+
137
+
138
+
139
+ ## Model Examination [optional]
140
+
141
+ <!-- Relevant interpretability work for the model goes here -->
142
+
143
+ [More Information Needed]
144
+
145
+ ## Environmental Impact
146
+
147
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
148
+
149
+ 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).
150
+
151
+ - **Hardware Type:** [More Information Needed]
152
+ - **Hours used:** [More Information Needed]
153
+ - **Cloud Provider:** [More Information Needed]
154
+ - **Compute Region:** [More Information Needed]
155
+ - **Carbon Emitted:** [More Information Needed]
156
+
157
+ ## Technical Specifications [optional]
158
+
159
+ ### Model Architecture and Objective
160
+
161
+ [More Information Needed]
162
+
163
+ ### Compute Infrastructure
164
+
165
+ [More Information Needed]
166
+
167
+ #### Hardware
168
+
169
+ [More Information Needed]
170
+
171
+ #### Software
172
+
173
+ [More Information Needed]
174
+
175
+ ## Citation [optional]
176
+
177
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
178
+
179
+ **BibTeX:**
180
+
181
+ [More Information Needed]
182
+
183
+ **APA:**
184
+
185
+ [More Information Needed]
186
+
187
+ ## Glossary [optional]
188
+
189
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
190
+
191
+ [More Information Needed]
192
+
193
+ ## More Information [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Authors [optional]
198
+
199
+ [More Information Needed]
200
+
201
+ ## Model Card Contact
202
+
203
+ [More Information Needed]
204
+ ### Framework versions
205
+
206
+ - PEFT 0.17.1
adapter_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen3-Embedding-4B",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": "gaussian",
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 32,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "q_proj",
29
+ "o_proj",
30
+ "down_proj",
31
+ "custom_text_proj",
32
+ "v_proj",
33
+ "up_proj",
34
+ "k_proj",
35
+ "gate_proj"
36
+ ],
37
+ "target_parameters": null,
38
+ "task_type": "FEATURE_EXTRACTION",
39
+ "trainable_token_indices": null,
40
+ "use_dora": false,
41
+ "use_qalora": false,
42
+ "use_rslora": false
43
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f44300db2b482bcf62e3f18706ba898a76c210e65d8770b69ae83fe8c708a91
3
+ size 264650168
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbc2721f6a37332ad963ff3840e6bbffd3efb0b6ae4aa6e032ac152965fac4d6
3
+ size 529605265
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c77cb05c2ca6ea13f4bad55eb574a2322b2fe35ee545a06325ac494d652ddc5
3
+ size 14645
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec37826df3413179431f774a730e198cadf92dc4685ff0bf7ef8fd00f26aae9e
3
+ size 1465
trainer_state.json ADDED
@@ -0,0 +1,1908 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 2620,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.003816793893129771,
14
+ "grad_norm": 2.615494966506958,
15
+ "learning_rate": 1.7175572519083972e-06,
16
+ "loss": 0.162,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.007633587786259542,
21
+ "grad_norm": 3.7720587253570557,
22
+ "learning_rate": 3.6259541984732824e-06,
23
+ "loss": 0.1953,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.011450381679389313,
28
+ "grad_norm": 3.1540627479553223,
29
+ "learning_rate": 5.534351145038168e-06,
30
+ "loss": 0.1651,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.015267175572519083,
35
+ "grad_norm": 2.391727924346924,
36
+ "learning_rate": 7.4427480916030536e-06,
37
+ "loss": 0.0976,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.019083969465648856,
42
+ "grad_norm": 1.7957884073257446,
43
+ "learning_rate": 9.351145038167939e-06,
44
+ "loss": 0.0483,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.022900763358778626,
49
+ "grad_norm": 2.7055726051330566,
50
+ "learning_rate": 1.1259541984732823e-05,
51
+ "loss": 0.0618,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.026717557251908396,
56
+ "grad_norm": 0.7185584902763367,
57
+ "learning_rate": 1.316793893129771e-05,
58
+ "loss": 0.0452,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.030534351145038167,
63
+ "grad_norm": 0.3574228286743164,
64
+ "learning_rate": 1.5076335877862596e-05,
65
+ "loss": 0.0287,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.03435114503816794,
70
+ "grad_norm": 0.600852906703949,
71
+ "learning_rate": 1.6984732824427482e-05,
72
+ "loss": 0.0345,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.03816793893129771,
77
+ "grad_norm": 1.2814120054244995,
78
+ "learning_rate": 1.8893129770992367e-05,
79
+ "loss": 0.0375,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.04198473282442748,
84
+ "grad_norm": 0.7709506154060364,
85
+ "learning_rate": 2.0801526717557255e-05,
86
+ "loss": 0.0177,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.04580152671755725,
91
+ "grad_norm": 0.749973714351654,
92
+ "learning_rate": 2.270992366412214e-05,
93
+ "loss": 0.0219,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.04961832061068702,
98
+ "grad_norm": 0.14578384160995483,
99
+ "learning_rate": 2.4618320610687024e-05,
100
+ "loss": 0.0226,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.05343511450381679,
105
+ "grad_norm": 1.139318585395813,
106
+ "learning_rate": 2.652671755725191e-05,
107
+ "loss": 0.0247,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.05725190839694656,
112
+ "grad_norm": 1.522550344467163,
113
+ "learning_rate": 2.8435114503816796e-05,
114
+ "loss": 0.0219,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.061068702290076333,
119
+ "grad_norm": 0.010661217384040356,
120
+ "learning_rate": 3.0343511450381677e-05,
121
+ "loss": 0.0233,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.0648854961832061,
126
+ "grad_norm": 1.0627490282058716,
127
+ "learning_rate": 3.2251908396946565e-05,
128
+ "loss": 0.0143,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.06870229007633588,
133
+ "grad_norm": 0.4552942216396332,
134
+ "learning_rate": 3.416030534351145e-05,
135
+ "loss": 0.0271,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.07251908396946564,
140
+ "grad_norm": 0.6815011501312256,
141
+ "learning_rate": 3.606870229007634e-05,
142
+ "loss": 0.0185,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.07633587786259542,
147
+ "grad_norm": 0.698657751083374,
148
+ "learning_rate": 3.797709923664122e-05,
149
+ "loss": 0.0162,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.08015267175572519,
154
+ "grad_norm": 0.5514554977416992,
155
+ "learning_rate": 3.988549618320611e-05,
156
+ "loss": 0.0277,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.08396946564885496,
161
+ "grad_norm": 0.09276178479194641,
162
+ "learning_rate": 4.1793893129771e-05,
163
+ "loss": 0.0176,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.08778625954198473,
168
+ "grad_norm": 1.0245144367218018,
169
+ "learning_rate": 4.370229007633588e-05,
170
+ "loss": 0.0219,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.0916030534351145,
175
+ "grad_norm": 0.5731092095375061,
176
+ "learning_rate": 4.561068702290077e-05,
177
+ "loss": 0.0188,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.09541984732824428,
182
+ "grad_norm": 0.11703433096408844,
183
+ "learning_rate": 4.751908396946565e-05,
184
+ "loss": 0.0153,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.09923664122137404,
189
+ "grad_norm": 0.3222142159938812,
190
+ "learning_rate": 4.9427480916030536e-05,
191
+ "loss": 0.0176,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.10305343511450382,
196
+ "grad_norm": 0.6780900359153748,
197
+ "learning_rate": 4.9998912785867505e-05,
198
+ "loss": 0.0143,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.10687022900763359,
203
+ "grad_norm": 0.8537261486053467,
204
+ "learning_rate": 4.999358788306519e-05,
205
+ "loss": 0.0223,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.11068702290076336,
210
+ "grad_norm": 0.17257721722126007,
211
+ "learning_rate": 4.998382654320609e-05,
212
+ "loss": 0.0178,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.11450381679389313,
217
+ "grad_norm": 0.7881976962089539,
218
+ "learning_rate": 4.996963049895741e-05,
219
+ "loss": 0.0146,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.1183206106870229,
224
+ "grad_norm": 0.6446636915206909,
225
+ "learning_rate": 4.99510022701597e-05,
226
+ "loss": 0.0109,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.12213740458015267,
231
+ "grad_norm": 0.6660375595092773,
232
+ "learning_rate": 4.992794516337964e-05,
233
+ "loss": 0.012,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.12595419847328243,
238
+ "grad_norm": 0.47002533078193665,
239
+ "learning_rate": 4.9900463271323064e-05,
240
+ "loss": 0.0133,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.1297709923664122,
245
+ "grad_norm": 0.9555854201316833,
246
+ "learning_rate": 4.9868561472108496e-05,
247
+ "loss": 0.0173,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.13358778625954199,
252
+ "grad_norm": 0.14546959102153778,
253
+ "learning_rate": 4.9832245428401316e-05,
254
+ "loss": 0.0172,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.13740458015267176,
259
+ "grad_norm": 0.27474039793014526,
260
+ "learning_rate": 4.979152158640853e-05,
261
+ "loss": 0.0174,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.14122137404580154,
266
+ "grad_norm": 0.2749495208263397,
267
+ "learning_rate": 4.974639717473465e-05,
268
+ "loss": 0.0172,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.1450381679389313,
273
+ "grad_norm": 0.19880647957324982,
274
+ "learning_rate": 4.9696880203098525e-05,
275
+ "loss": 0.012,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.14885496183206107,
280
+ "grad_norm": 0.7163119912147522,
281
+ "learning_rate": 4.964297946091163e-05,
282
+ "loss": 0.0138,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.15267175572519084,
287
+ "grad_norm": 0.4733160436153412,
288
+ "learning_rate": 4.9584704515717884e-05,
289
+ "loss": 0.0074,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.15648854961832062,
294
+ "grad_norm": 0.5145673155784607,
295
+ "learning_rate": 4.952206571149541e-05,
296
+ "loss": 0.0178,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.16030534351145037,
301
+ "grad_norm": 0.07867272943258286,
302
+ "learning_rate": 4.945507416682046e-05,
303
+ "loss": 0.0132,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.16412213740458015,
308
+ "grad_norm": 0.023460840806365013,
309
+ "learning_rate": 4.938374177289378e-05,
310
+ "loss": 0.0085,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.16793893129770993,
315
+ "grad_norm": 0.6247947812080383,
316
+ "learning_rate": 4.930808119142993e-05,
317
+ "loss": 0.0176,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.1717557251908397,
322
+ "grad_norm": 0.49582046270370483,
323
+ "learning_rate": 4.922810585240981e-05,
324
+ "loss": 0.0188,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.17557251908396945,
329
+ "grad_norm": 1.1747221946716309,
330
+ "learning_rate": 4.914382995169673e-05,
331
+ "loss": 0.0187,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.17938931297709923,
336
+ "grad_norm": 0.9253813624382019,
337
+ "learning_rate": 4.905526844851667e-05,
338
+ "loss": 0.0125,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.183206106870229,
343
+ "grad_norm": 0.32356423139572144,
344
+ "learning_rate": 4.8962437062802924e-05,
345
+ "loss": 0.0145,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.18702290076335878,
350
+ "grad_norm": 0.16892339289188385,
351
+ "learning_rate": 4.886535227240579e-05,
352
+ "loss": 0.0132,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.19083969465648856,
357
+ "grad_norm": 0.08704151958227158,
358
+ "learning_rate": 4.8764031310167725e-05,
359
+ "loss": 0.0145,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.19083969465648856,
364
+ "eval_loss": 0.03389899432659149,
365
+ "eval_runtime": 140.2568,
366
+ "eval_samples_per_second": 56.91,
367
+ "eval_steps_per_second": 0.299,
368
+ "step": 500
369
+ },
370
+ {
371
+ "epoch": 0.1946564885496183,
372
+ "grad_norm": 0.021338067948818207,
373
+ "learning_rate": 4.865849216086438e-05,
374
+ "loss": 0.0112,
375
+ "step": 510
376
+ },
377
+ {
378
+ "epoch": 0.1984732824427481,
379
+ "grad_norm": 0.18011535704135895,
380
+ "learning_rate": 4.854875355801233e-05,
381
+ "loss": 0.0068,
382
+ "step": 520
383
+ },
384
+ {
385
+ "epoch": 0.20229007633587787,
386
+ "grad_norm": 0.6645931005477905,
387
+ "learning_rate": 4.843483498054381e-05,
388
+ "loss": 0.0182,
389
+ "step": 530
390
+ },
391
+ {
392
+ "epoch": 0.20610687022900764,
393
+ "grad_norm": 0.1481589674949646,
394
+ "learning_rate": 4.83167566493491e-05,
395
+ "loss": 0.0113,
396
+ "step": 540
397
+ },
398
+ {
399
+ "epoch": 0.2099236641221374,
400
+ "grad_norm": 0.05964776873588562,
401
+ "learning_rate": 4.819453952368731e-05,
402
+ "loss": 0.0101,
403
+ "step": 550
404
+ },
405
+ {
406
+ "epoch": 0.21374045801526717,
407
+ "grad_norm": 0.5340839624404907,
408
+ "learning_rate": 4.8068205297465986e-05,
409
+ "loss": 0.0181,
410
+ "step": 560
411
+ },
412
+ {
413
+ "epoch": 0.21755725190839695,
414
+ "grad_norm": 0.28655287623405457,
415
+ "learning_rate": 4.7937776395390434e-05,
416
+ "loss": 0.0073,
417
+ "step": 570
418
+ },
419
+ {
420
+ "epoch": 0.22137404580152673,
421
+ "grad_norm": 0.08776471763849258,
422
+ "learning_rate": 4.7803275968983244e-05,
423
+ "loss": 0.0129,
424
+ "step": 580
425
+ },
426
+ {
427
+ "epoch": 0.22519083969465647,
428
+ "grad_norm": 0.11037462204694748,
429
+ "learning_rate": 4.766472789247483e-05,
430
+ "loss": 0.0088,
431
+ "step": 590
432
+ },
433
+ {
434
+ "epoch": 0.22900763358778625,
435
+ "grad_norm": 0.21740970015525818,
436
+ "learning_rate": 4.752215675856566e-05,
437
+ "loss": 0.0115,
438
+ "step": 600
439
+ },
440
+ {
441
+ "epoch": 0.23282442748091603,
442
+ "grad_norm": 0.07760237902402878,
443
+ "learning_rate": 4.737558787406103e-05,
444
+ "loss": 0.0118,
445
+ "step": 610
446
+ },
447
+ {
448
+ "epoch": 0.2366412213740458,
449
+ "grad_norm": 0.2091819792985916,
450
+ "learning_rate": 4.722504725537896e-05,
451
+ "loss": 0.0096,
452
+ "step": 620
453
+ },
454
+ {
455
+ "epoch": 0.24045801526717558,
456
+ "grad_norm": 1.0305904150009155,
457
+ "learning_rate": 4.7070561623932265e-05,
458
+ "loss": 0.0108,
459
+ "step": 630
460
+ },
461
+ {
462
+ "epoch": 0.24427480916030533,
463
+ "grad_norm": 0.03920348733663559,
464
+ "learning_rate": 4.691215840138537e-05,
465
+ "loss": 0.0116,
466
+ "step": 640
467
+ },
468
+ {
469
+ "epoch": 0.2480916030534351,
470
+ "grad_norm": 0.02367626503109932,
471
+ "learning_rate": 4.674986570478695e-05,
472
+ "loss": 0.0133,
473
+ "step": 650
474
+ },
475
+ {
476
+ "epoch": 0.25190839694656486,
477
+ "grad_norm": 0.05315301567316055,
478
+ "learning_rate": 4.6583712341578984e-05,
479
+ "loss": 0.0087,
480
+ "step": 660
481
+ },
482
+ {
483
+ "epoch": 0.25572519083969464,
484
+ "grad_norm": 0.10831905901432037,
485
+ "learning_rate": 4.641372780448341e-05,
486
+ "loss": 0.0084,
487
+ "step": 670
488
+ },
489
+ {
490
+ "epoch": 0.2595419847328244,
491
+ "grad_norm": 0.078117236495018,
492
+ "learning_rate": 4.6239942266267056e-05,
493
+ "loss": 0.0058,
494
+ "step": 680
495
+ },
496
+ {
497
+ "epoch": 0.2633587786259542,
498
+ "grad_norm": 0.28782543540000916,
499
+ "learning_rate": 4.6062386574385886e-05,
500
+ "loss": 0.0104,
501
+ "step": 690
502
+ },
503
+ {
504
+ "epoch": 0.26717557251908397,
505
+ "grad_norm": 0.04873083531856537,
506
+ "learning_rate": 4.5881092245509506e-05,
507
+ "loss": 0.0118,
508
+ "step": 700
509
+ },
510
+ {
511
+ "epoch": 0.27099236641221375,
512
+ "grad_norm": 0.26269766688346863,
513
+ "learning_rate": 4.56960914599268e-05,
514
+ "loss": 0.0077,
515
+ "step": 710
516
+ },
517
+ {
518
+ "epoch": 0.2748091603053435,
519
+ "grad_norm": 0.3128824532032013,
520
+ "learning_rate": 4.55074170558339e-05,
521
+ "loss": 0.0107,
522
+ "step": 720
523
+ },
524
+ {
525
+ "epoch": 0.2786259541984733,
526
+ "grad_norm": 1.1486977338790894,
527
+ "learning_rate": 4.531510252350526e-05,
528
+ "loss": 0.012,
529
+ "step": 730
530
+ },
531
+ {
532
+ "epoch": 0.2824427480916031,
533
+ "grad_norm": 0.35734987258911133,
534
+ "learning_rate": 4.511918199934907e-05,
535
+ "loss": 0.0121,
536
+ "step": 740
537
+ },
538
+ {
539
+ "epoch": 0.2862595419847328,
540
+ "grad_norm": 0.2775309681892395,
541
+ "learning_rate": 4.491969025984789e-05,
542
+ "loss": 0.0139,
543
+ "step": 750
544
+ },
545
+ {
546
+ "epoch": 0.2900763358778626,
547
+ "grad_norm": 0.22545866668224335,
548
+ "learning_rate": 4.471666271538578e-05,
549
+ "loss": 0.0047,
550
+ "step": 760
551
+ },
552
+ {
553
+ "epoch": 0.29389312977099236,
554
+ "grad_norm": 0.3366382420063019,
555
+ "learning_rate": 4.451013540396281e-05,
556
+ "loss": 0.008,
557
+ "step": 770
558
+ },
559
+ {
560
+ "epoch": 0.29770992366412213,
561
+ "grad_norm": 0.645935595035553,
562
+ "learning_rate": 4.430014498479819e-05,
563
+ "loss": 0.0197,
564
+ "step": 780
565
+ },
566
+ {
567
+ "epoch": 0.3015267175572519,
568
+ "grad_norm": 0.022258713841438293,
569
+ "learning_rate": 4.408672873182322e-05,
570
+ "loss": 0.0138,
571
+ "step": 790
572
+ },
573
+ {
574
+ "epoch": 0.3053435114503817,
575
+ "grad_norm": 0.08058780431747437,
576
+ "learning_rate": 4.386992452706499e-05,
577
+ "loss": 0.01,
578
+ "step": 800
579
+ },
580
+ {
581
+ "epoch": 0.30916030534351147,
582
+ "grad_norm": 0.5103694796562195,
583
+ "learning_rate": 4.36497708539222e-05,
584
+ "loss": 0.0127,
585
+ "step": 810
586
+ },
587
+ {
588
+ "epoch": 0.31297709923664124,
589
+ "grad_norm": 0.2476615309715271,
590
+ "learning_rate": 4.342630679033432e-05,
591
+ "loss": 0.0129,
592
+ "step": 820
593
+ },
594
+ {
595
+ "epoch": 0.31679389312977096,
596
+ "grad_norm": 0.2634897530078888,
597
+ "learning_rate": 4.319957200184504e-05,
598
+ "loss": 0.0052,
599
+ "step": 830
600
+ },
601
+ {
602
+ "epoch": 0.32061068702290074,
603
+ "grad_norm": 0.31470030546188354,
604
+ "learning_rate": 4.296960673456159e-05,
605
+ "loss": 0.0165,
606
+ "step": 840
607
+ },
608
+ {
609
+ "epoch": 0.3244274809160305,
610
+ "grad_norm": 0.19848482310771942,
611
+ "learning_rate": 4.273645180801088e-05,
612
+ "loss": 0.005,
613
+ "step": 850
614
+ },
615
+ {
616
+ "epoch": 0.3282442748091603,
617
+ "grad_norm": 0.08697102218866348,
618
+ "learning_rate": 4.2500148607893965e-05,
619
+ "loss": 0.0082,
620
+ "step": 860
621
+ },
622
+ {
623
+ "epoch": 0.3320610687022901,
624
+ "grad_norm": 0.38102781772613525,
625
+ "learning_rate": 4.226073907873992e-05,
626
+ "loss": 0.0126,
627
+ "step": 870
628
+ },
629
+ {
630
+ "epoch": 0.33587786259541985,
631
+ "grad_norm": 0.14514830708503723,
632
+ "learning_rate": 4.201826571646056e-05,
633
+ "loss": 0.0058,
634
+ "step": 880
635
+ },
636
+ {
637
+ "epoch": 0.33969465648854963,
638
+ "grad_norm": 0.43940168619155884,
639
+ "learning_rate": 4.177277156080731e-05,
640
+ "loss": 0.0078,
641
+ "step": 890
642
+ },
643
+ {
644
+ "epoch": 0.3435114503816794,
645
+ "grad_norm": 0.05170935019850731,
646
+ "learning_rate": 4.152430018773153e-05,
647
+ "loss": 0.0082,
648
+ "step": 900
649
+ },
650
+ {
651
+ "epoch": 0.3473282442748092,
652
+ "grad_norm": 0.01292837131768465,
653
+ "learning_rate": 4.127289570164958e-05,
654
+ "loss": 0.0156,
655
+ "step": 910
656
+ },
657
+ {
658
+ "epoch": 0.3511450381679389,
659
+ "grad_norm": 0.21468913555145264,
660
+ "learning_rate": 4.1018602727614264e-05,
661
+ "loss": 0.0075,
662
+ "step": 920
663
+ },
664
+ {
665
+ "epoch": 0.3549618320610687,
666
+ "grad_norm": 0.7786637544631958,
667
+ "learning_rate": 4.0761466403393633e-05,
668
+ "loss": 0.0167,
669
+ "step": 930
670
+ },
671
+ {
672
+ "epoch": 0.35877862595419846,
673
+ "grad_norm": 0.06286737322807312,
674
+ "learning_rate": 4.0501532371458993e-05,
675
+ "loss": 0.0107,
676
+ "step": 940
677
+ },
678
+ {
679
+ "epoch": 0.36259541984732824,
680
+ "grad_norm": 0.19294968247413635,
681
+ "learning_rate": 4.0238846770883165e-05,
682
+ "loss": 0.0103,
683
+ "step": 950
684
+ },
685
+ {
686
+ "epoch": 0.366412213740458,
687
+ "grad_norm": 0.02884821780025959,
688
+ "learning_rate": 3.9973456229150695e-05,
689
+ "loss": 0.0133,
690
+ "step": 960
691
+ },
692
+ {
693
+ "epoch": 0.3702290076335878,
694
+ "grad_norm": 0.36911624670028687,
695
+ "learning_rate": 3.9705407853881324e-05,
696
+ "loss": 0.0072,
697
+ "step": 970
698
+ },
699
+ {
700
+ "epoch": 0.37404580152671757,
701
+ "grad_norm": 0.21048544347286224,
702
+ "learning_rate": 3.9434749224468235e-05,
703
+ "loss": 0.0047,
704
+ "step": 980
705
+ },
706
+ {
707
+ "epoch": 0.37786259541984735,
708
+ "grad_norm": 0.09334168583154678,
709
+ "learning_rate": 3.916152838363258e-05,
710
+ "loss": 0.0125,
711
+ "step": 990
712
+ },
713
+ {
714
+ "epoch": 0.3816793893129771,
715
+ "grad_norm": 0.49426600337028503,
716
+ "learning_rate": 3.8885793828895756e-05,
717
+ "loss": 0.0109,
718
+ "step": 1000
719
+ },
720
+ {
721
+ "epoch": 0.3816793893129771,
722
+ "eval_loss": 0.032893069088459015,
723
+ "eval_runtime": 140.214,
724
+ "eval_samples_per_second": 56.927,
725
+ "eval_steps_per_second": 0.3,
726
+ "step": 1000
727
+ },
728
+ {
729
+ "epoch": 0.38549618320610685,
730
+ "grad_norm": 0.19869565963745117,
731
+ "learning_rate": 3.8607594503970925e-05,
732
+ "loss": 0.0144,
733
+ "step": 1010
734
+ },
735
+ {
736
+ "epoch": 0.3893129770992366,
737
+ "grad_norm": 0.19766545295715332,
738
+ "learning_rate": 3.832697979007539e-05,
739
+ "loss": 0.0067,
740
+ "step": 1020
741
+ },
742
+ {
743
+ "epoch": 0.3931297709923664,
744
+ "grad_norm": 0.4004887044429779,
745
+ "learning_rate": 3.804399949716526e-05,
746
+ "loss": 0.0047,
747
+ "step": 1030
748
+ },
749
+ {
750
+ "epoch": 0.3969465648854962,
751
+ "grad_norm": 0.31220734119415283,
752
+ "learning_rate": 3.775870385509402e-05,
753
+ "loss": 0.0163,
754
+ "step": 1040
755
+ },
756
+ {
757
+ "epoch": 0.40076335877862596,
758
+ "grad_norm": 0.12848161160945892,
759
+ "learning_rate": 3.7471143504696625e-05,
760
+ "loss": 0.0038,
761
+ "step": 1050
762
+ },
763
+ {
764
+ "epoch": 0.40458015267175573,
765
+ "grad_norm": 0.39810845255851746,
766
+ "learning_rate": 3.718136948880056e-05,
767
+ "loss": 0.0077,
768
+ "step": 1060
769
+ },
770
+ {
771
+ "epoch": 0.4083969465648855,
772
+ "grad_norm": 0.47316208481788635,
773
+ "learning_rate": 3.6889433243165605e-05,
774
+ "loss": 0.0141,
775
+ "step": 1070
776
+ },
777
+ {
778
+ "epoch": 0.4122137404580153,
779
+ "grad_norm": 0.028033487498760223,
780
+ "learning_rate": 3.6595386587353795e-05,
781
+ "loss": 0.0049,
782
+ "step": 1080
783
+ },
784
+ {
785
+ "epoch": 0.41603053435114506,
786
+ "grad_norm": 0.036221910268068314,
787
+ "learning_rate": 3.6299281715531375e-05,
788
+ "loss": 0.0083,
789
+ "step": 1090
790
+ },
791
+ {
792
+ "epoch": 0.4198473282442748,
793
+ "grad_norm": 0.013016347773373127,
794
+ "learning_rate": 3.600117118720408e-05,
795
+ "loss": 0.0085,
796
+ "step": 1100
797
+ },
798
+ {
799
+ "epoch": 0.42366412213740456,
800
+ "grad_norm": 0.07040252536535263,
801
+ "learning_rate": 3.57011079178877e-05,
802
+ "loss": 0.0102,
803
+ "step": 1110
804
+ },
805
+ {
806
+ "epoch": 0.42748091603053434,
807
+ "grad_norm": 0.25287893414497375,
808
+ "learning_rate": 3.53991451697155e-05,
809
+ "loss": 0.0092,
810
+ "step": 1120
811
+ },
812
+ {
813
+ "epoch": 0.4312977099236641,
814
+ "grad_norm": 0.08920171856880188,
815
+ "learning_rate": 3.509533654198388e-05,
816
+ "loss": 0.0156,
817
+ "step": 1130
818
+ },
819
+ {
820
+ "epoch": 0.4351145038167939,
821
+ "grad_norm": 0.36695143580436707,
822
+ "learning_rate": 3.478973596163843e-05,
823
+ "loss": 0.0109,
824
+ "step": 1140
825
+ },
826
+ {
827
+ "epoch": 0.4389312977099237,
828
+ "grad_norm": 0.022651812061667442,
829
+ "learning_rate": 3.448239767370177e-05,
830
+ "loss": 0.0057,
831
+ "step": 1150
832
+ },
833
+ {
834
+ "epoch": 0.44274809160305345,
835
+ "grad_norm": 0.3203389644622803,
836
+ "learning_rate": 3.4173376231644797e-05,
837
+ "loss": 0.0075,
838
+ "step": 1160
839
+ },
840
+ {
841
+ "epoch": 0.44656488549618323,
842
+ "grad_norm": 0.6244869232177734,
843
+ "learning_rate": 3.386272648770333e-05,
844
+ "loss": 0.0119,
845
+ "step": 1170
846
+ },
847
+ {
848
+ "epoch": 0.45038167938931295,
849
+ "grad_norm": 0.16917894780635834,
850
+ "learning_rate": 3.355050358314172e-05,
851
+ "loss": 0.0065,
852
+ "step": 1180
853
+ },
854
+ {
855
+ "epoch": 0.4541984732824427,
856
+ "grad_norm": 0.10675910860300064,
857
+ "learning_rate": 3.323676293846501e-05,
858
+ "loss": 0.0073,
859
+ "step": 1190
860
+ },
861
+ {
862
+ "epoch": 0.4580152671755725,
863
+ "grad_norm": 0.8430480360984802,
864
+ "learning_rate": 3.2921560243581675e-05,
865
+ "loss": 0.0121,
866
+ "step": 1200
867
+ },
868
+ {
869
+ "epoch": 0.4618320610687023,
870
+ "grad_norm": 0.1763671189546585,
871
+ "learning_rate": 3.260495144791856e-05,
872
+ "loss": 0.0067,
873
+ "step": 1210
874
+ },
875
+ {
876
+ "epoch": 0.46564885496183206,
877
+ "grad_norm": 0.4134056568145752,
878
+ "learning_rate": 3.2286992750489585e-05,
879
+ "loss": 0.0115,
880
+ "step": 1220
881
+ },
882
+ {
883
+ "epoch": 0.46946564885496184,
884
+ "grad_norm": 0.02143966406583786,
885
+ "learning_rate": 3.1967740589920296e-05,
886
+ "loss": 0.0075,
887
+ "step": 1230
888
+ },
889
+ {
890
+ "epoch": 0.4732824427480916,
891
+ "grad_norm": 0.6696872115135193,
892
+ "learning_rate": 3.1647251634429856e-05,
893
+ "loss": 0.0089,
894
+ "step": 1240
895
+ },
896
+ {
897
+ "epoch": 0.4770992366412214,
898
+ "grad_norm": 0.06671352684497833,
899
+ "learning_rate": 3.1325582771772235e-05,
900
+ "loss": 0.0147,
901
+ "step": 1250
902
+ },
903
+ {
904
+ "epoch": 0.48091603053435117,
905
+ "grad_norm": 0.7138830423355103,
906
+ "learning_rate": 3.100279109913848e-05,
907
+ "loss": 0.0121,
908
+ "step": 1260
909
+ },
910
+ {
911
+ "epoch": 0.4847328244274809,
912
+ "grad_norm": 0.15019002556800842,
913
+ "learning_rate": 3.067893391302179e-05,
914
+ "loss": 0.006,
915
+ "step": 1270
916
+ },
917
+ {
918
+ "epoch": 0.48854961832061067,
919
+ "grad_norm": 0.29725247621536255,
920
+ "learning_rate": 3.035406869904721e-05,
921
+ "loss": 0.0123,
922
+ "step": 1280
923
+ },
924
+ {
925
+ "epoch": 0.49236641221374045,
926
+ "grad_norm": 0.2249823957681656,
927
+ "learning_rate": 3.0028253121767762e-05,
928
+ "loss": 0.0092,
929
+ "step": 1290
930
+ },
931
+ {
932
+ "epoch": 0.4961832061068702,
933
+ "grad_norm": 0.1760585904121399,
934
+ "learning_rate": 2.970154501442881e-05,
935
+ "loss": 0.0189,
936
+ "step": 1300
937
+ },
938
+ {
939
+ "epoch": 0.5,
940
+ "grad_norm": 0.32748275995254517,
941
+ "learning_rate": 2.9374002368702514e-05,
942
+ "loss": 0.0106,
943
+ "step": 1310
944
+ },
945
+ {
946
+ "epoch": 0.5038167938931297,
947
+ "grad_norm": 0.5537404417991638,
948
+ "learning_rate": 2.904568332439408e-05,
949
+ "loss": 0.0073,
950
+ "step": 1320
951
+ },
952
+ {
953
+ "epoch": 0.5076335877862596,
954
+ "grad_norm": 0.024763356894254684,
955
+ "learning_rate": 2.8716646159121795e-05,
956
+ "loss": 0.0039,
957
+ "step": 1330
958
+ },
959
+ {
960
+ "epoch": 0.5114503816793893,
961
+ "grad_norm": 0.3292398452758789,
962
+ "learning_rate": 2.8386949277972606e-05,
963
+ "loss": 0.0128,
964
+ "step": 1340
965
+ },
966
+ {
967
+ "epoch": 0.5152671755725191,
968
+ "grad_norm": 0.28704291582107544,
969
+ "learning_rate": 2.805665120313501e-05,
970
+ "loss": 0.0139,
971
+ "step": 1350
972
+ },
973
+ {
974
+ "epoch": 0.5190839694656488,
975
+ "grad_norm": 0.3549763560295105,
976
+ "learning_rate": 2.7725810563511157e-05,
977
+ "loss": 0.007,
978
+ "step": 1360
979
+ },
980
+ {
981
+ "epoch": 0.5229007633587787,
982
+ "grad_norm": 0.10086268186569214,
983
+ "learning_rate": 2.7394486084310128e-05,
984
+ "loss": 0.0063,
985
+ "step": 1370
986
+ },
987
+ {
988
+ "epoch": 0.5267175572519084,
989
+ "grad_norm": 0.30678582191467285,
990
+ "learning_rate": 2.7062736576623943e-05,
991
+ "loss": 0.0092,
992
+ "step": 1380
993
+ },
994
+ {
995
+ "epoch": 0.5305343511450382,
996
+ "grad_norm": 0.20195415616035461,
997
+ "learning_rate": 2.6730620926988476e-05,
998
+ "loss": 0.0094,
999
+ "step": 1390
1000
+ },
1001
+ {
1002
+ "epoch": 0.5343511450381679,
1003
+ "grad_norm": 0.7400510907173157,
1004
+ "learning_rate": 2.6398198086930915e-05,
1005
+ "loss": 0.0183,
1006
+ "step": 1400
1007
+ },
1008
+ {
1009
+ "epoch": 0.5381679389312977,
1010
+ "grad_norm": 0.10865656286478043,
1011
+ "learning_rate": 2.6065527062505634e-05,
1012
+ "loss": 0.0109,
1013
+ "step": 1410
1014
+ },
1015
+ {
1016
+ "epoch": 0.5419847328244275,
1017
+ "grad_norm": 0.1100832000374794,
1018
+ "learning_rate": 2.573266690382051e-05,
1019
+ "loss": 0.0086,
1020
+ "step": 1420
1021
+ },
1022
+ {
1023
+ "epoch": 0.5458015267175572,
1024
+ "grad_norm": 0.07376679033041,
1025
+ "learning_rate": 2.5399676694555312e-05,
1026
+ "loss": 0.0213,
1027
+ "step": 1430
1028
+ },
1029
+ {
1030
+ "epoch": 0.549618320610687,
1031
+ "grad_norm": 0.30974867939949036,
1032
+ "learning_rate": 2.506661554147417e-05,
1033
+ "loss": 0.0091,
1034
+ "step": 1440
1035
+ },
1036
+ {
1037
+ "epoch": 0.5534351145038168,
1038
+ "grad_norm": 0.4819875955581665,
1039
+ "learning_rate": 2.473354256393397e-05,
1040
+ "loss": 0.0079,
1041
+ "step": 1450
1042
+ },
1043
+ {
1044
+ "epoch": 0.5572519083969466,
1045
+ "grad_norm": 0.08225909620523453,
1046
+ "learning_rate": 2.440051688339046e-05,
1047
+ "loss": 0.0147,
1048
+ "step": 1460
1049
+ },
1050
+ {
1051
+ "epoch": 0.5610687022900763,
1052
+ "grad_norm": 0.009925187565386295,
1053
+ "learning_rate": 2.4067597612904037e-05,
1054
+ "loss": 0.0135,
1055
+ "step": 1470
1056
+ },
1057
+ {
1058
+ "epoch": 0.5648854961832062,
1059
+ "grad_norm": 0.36840465664863586,
1060
+ "learning_rate": 2.3734843846646988e-05,
1061
+ "loss": 0.0128,
1062
+ "step": 1480
1063
+ },
1064
+ {
1065
+ "epoch": 0.5687022900763359,
1066
+ "grad_norm": 0.0662972629070282,
1067
+ "learning_rate": 2.3402314649414116e-05,
1068
+ "loss": 0.0114,
1069
+ "step": 1490
1070
+ },
1071
+ {
1072
+ "epoch": 0.5725190839694656,
1073
+ "grad_norm": 0.28558099269866943,
1074
+ "learning_rate": 2.307006904613851e-05,
1075
+ "loss": 0.0113,
1076
+ "step": 1500
1077
+ },
1078
+ {
1079
+ "epoch": 0.5725190839694656,
1080
+ "eval_loss": 0.030398810282349586,
1081
+ "eval_runtime": 140.1617,
1082
+ "eval_samples_per_second": 56.949,
1083
+ "eval_steps_per_second": 0.3,
1084
+ "step": 1500
1085
+ },
1086
+ {
1087
+ "epoch": 0.5763358778625954,
1088
+ "grad_norm": 0.39870354533195496,
1089
+ "learning_rate": 2.2738166011414527e-05,
1090
+ "loss": 0.0094,
1091
+ "step": 1510
1092
+ },
1093
+ {
1094
+ "epoch": 0.5801526717557252,
1095
+ "grad_norm": 0.3758524954319,
1096
+ "learning_rate": 2.2406664459029545e-05,
1097
+ "loss": 0.0089,
1098
+ "step": 1520
1099
+ },
1100
+ {
1101
+ "epoch": 0.583969465648855,
1102
+ "grad_norm": 0.028594927862286568,
1103
+ "learning_rate": 2.207562323150662e-05,
1104
+ "loss": 0.0074,
1105
+ "step": 1530
1106
+ },
1107
+ {
1108
+ "epoch": 0.5877862595419847,
1109
+ "grad_norm": 0.23170693218708038,
1110
+ "learning_rate": 2.174510108965977e-05,
1111
+ "loss": 0.0054,
1112
+ "step": 1540
1113
+ },
1114
+ {
1115
+ "epoch": 0.5916030534351145,
1116
+ "grad_norm": 0.5391947031021118,
1117
+ "learning_rate": 2.1415156702163734e-05,
1118
+ "loss": 0.0079,
1119
+ "step": 1550
1120
+ },
1121
+ {
1122
+ "epoch": 0.5954198473282443,
1123
+ "grad_norm": 0.12324138730764389,
1124
+ "learning_rate": 2.1085848635140122e-05,
1125
+ "loss": 0.0071,
1126
+ "step": 1560
1127
+ },
1128
+ {
1129
+ "epoch": 0.5992366412213741,
1130
+ "grad_norm": 0.03993413597345352,
1131
+ "learning_rate": 2.0757235341761732e-05,
1132
+ "loss": 0.008,
1133
+ "step": 1570
1134
+ },
1135
+ {
1136
+ "epoch": 0.6030534351145038,
1137
+ "grad_norm": 0.32654133439064026,
1138
+ "learning_rate": 2.0429375151876978e-05,
1139
+ "loss": 0.0094,
1140
+ "step": 1580
1141
+ },
1142
+ {
1143
+ "epoch": 0.6068702290076335,
1144
+ "grad_norm": 0.012670164927840233,
1145
+ "learning_rate": 2.0102326261656114e-05,
1146
+ "loss": 0.0086,
1147
+ "step": 1590
1148
+ },
1149
+ {
1150
+ "epoch": 0.6106870229007634,
1151
+ "grad_norm": 0.22735942900180817,
1152
+ "learning_rate": 1.9776146723261265e-05,
1153
+ "loss": 0.0146,
1154
+ "step": 1600
1155
+ },
1156
+ {
1157
+ "epoch": 0.6145038167938931,
1158
+ "grad_norm": 0.5669217109680176,
1159
+ "learning_rate": 1.9450894434541994e-05,
1160
+ "loss": 0.0181,
1161
+ "step": 1610
1162
+ },
1163
+ {
1164
+ "epoch": 0.6183206106870229,
1165
+ "grad_norm": 0.09971689432859421,
1166
+ "learning_rate": 1.9126627128758256e-05,
1167
+ "loss": 0.0034,
1168
+ "step": 1620
1169
+ },
1170
+ {
1171
+ "epoch": 0.6221374045801527,
1172
+ "grad_norm": 0.11938827484846115,
1173
+ "learning_rate": 1.8803402364332573e-05,
1174
+ "loss": 0.0128,
1175
+ "step": 1630
1176
+ },
1177
+ {
1178
+ "epoch": 0.6259541984732825,
1179
+ "grad_norm": 0.47636914253234863,
1180
+ "learning_rate": 1.8481277514633243e-05,
1181
+ "loss": 0.0115,
1182
+ "step": 1640
1183
+ },
1184
+ {
1185
+ "epoch": 0.6297709923664122,
1186
+ "grad_norm": 0.3907536566257477,
1187
+ "learning_rate": 1.8160309757790384e-05,
1188
+ "loss": 0.0076,
1189
+ "step": 1650
1190
+ },
1191
+ {
1192
+ "epoch": 0.6335877862595419,
1193
+ "grad_norm": 0.2356630116701126,
1194
+ "learning_rate": 1.784055606654664e-05,
1195
+ "loss": 0.0131,
1196
+ "step": 1660
1197
+ },
1198
+ {
1199
+ "epoch": 0.6374045801526718,
1200
+ "grad_norm": 0.09361109882593155,
1201
+ "learning_rate": 1.752207319814438e-05,
1202
+ "loss": 0.007,
1203
+ "step": 1670
1204
+ },
1205
+ {
1206
+ "epoch": 0.6412213740458015,
1207
+ "grad_norm": 0.3632112145423889,
1208
+ "learning_rate": 1.7204917684251086e-05,
1209
+ "loss": 0.0096,
1210
+ "step": 1680
1211
+ },
1212
+ {
1213
+ "epoch": 0.6450381679389313,
1214
+ "grad_norm": 0.44978809356689453,
1215
+ "learning_rate": 1.6889145820924797e-05,
1216
+ "loss": 0.0136,
1217
+ "step": 1690
1218
+ },
1219
+ {
1220
+ "epoch": 0.648854961832061,
1221
+ "grad_norm": 0.4278349280357361,
1222
+ "learning_rate": 1.6574813658621464e-05,
1223
+ "loss": 0.0061,
1224
+ "step": 1700
1225
+ },
1226
+ {
1227
+ "epoch": 0.6526717557251909,
1228
+ "grad_norm": 0.3191720247268677,
1229
+ "learning_rate": 1.6261976992245727e-05,
1230
+ "loss": 0.0255,
1231
+ "step": 1710
1232
+ },
1233
+ {
1234
+ "epoch": 0.6564885496183206,
1235
+ "grad_norm": 0.030014334246516228,
1236
+ "learning_rate": 1.5950691351247218e-05,
1237
+ "loss": 0.0103,
1238
+ "step": 1720
1239
+ },
1240
+ {
1241
+ "epoch": 0.6603053435114504,
1242
+ "grad_norm": 0.3003236651420593,
1243
+ "learning_rate": 1.5641011989763903e-05,
1244
+ "loss": 0.0086,
1245
+ "step": 1730
1246
+ },
1247
+ {
1248
+ "epoch": 0.6641221374045801,
1249
+ "grad_norm": 0.05489334836602211,
1250
+ "learning_rate": 1.5332993876814285e-05,
1251
+ "loss": 0.0055,
1252
+ "step": 1740
1253
+ },
1254
+ {
1255
+ "epoch": 0.6679389312977099,
1256
+ "grad_norm": 0.27562958002090454,
1257
+ "learning_rate": 1.5026691686540262e-05,
1258
+ "loss": 0.0066,
1259
+ "step": 1750
1260
+ },
1261
+ {
1262
+ "epoch": 0.6717557251908397,
1263
+ "grad_norm": 0.4876582622528076,
1264
+ "learning_rate": 1.472215978850229e-05,
1265
+ "loss": 0.0088,
1266
+ "step": 1760
1267
+ },
1268
+ {
1269
+ "epoch": 0.6755725190839694,
1270
+ "grad_norm": 0.08189146220684052,
1271
+ "learning_rate": 1.4419452238028647e-05,
1272
+ "loss": 0.0087,
1273
+ "step": 1770
1274
+ },
1275
+ {
1276
+ "epoch": 0.6793893129770993,
1277
+ "grad_norm": 0.3738853633403778,
1278
+ "learning_rate": 1.4118622766620387e-05,
1279
+ "loss": 0.0091,
1280
+ "step": 1780
1281
+ },
1282
+ {
1283
+ "epoch": 0.683206106870229,
1284
+ "grad_norm": 0.2992166578769684,
1285
+ "learning_rate": 1.3819724772413929e-05,
1286
+ "loss": 0.0206,
1287
+ "step": 1790
1288
+ },
1289
+ {
1290
+ "epoch": 0.6870229007633588,
1291
+ "grad_norm": 0.6133850812911987,
1292
+ "learning_rate": 1.3522811310702634e-05,
1293
+ "loss": 0.0112,
1294
+ "step": 1800
1295
+ },
1296
+ {
1297
+ "epoch": 0.6908396946564885,
1298
+ "grad_norm": 0.25099530816078186,
1299
+ "learning_rate": 1.3227935084519385e-05,
1300
+ "loss": 0.0092,
1301
+ "step": 1810
1302
+ },
1303
+ {
1304
+ "epoch": 0.6946564885496184,
1305
+ "grad_norm": 0.4365796744823456,
1306
+ "learning_rate": 1.2935148435281643e-05,
1307
+ "loss": 0.0194,
1308
+ "step": 1820
1309
+ },
1310
+ {
1311
+ "epoch": 0.6984732824427481,
1312
+ "grad_norm": 0.5801776051521301,
1313
+ "learning_rate": 1.2644503333500673e-05,
1314
+ "loss": 0.0078,
1315
+ "step": 1830
1316
+ },
1317
+ {
1318
+ "epoch": 0.7022900763358778,
1319
+ "grad_norm": 0.0873272716999054,
1320
+ "learning_rate": 1.2356051369556593e-05,
1321
+ "loss": 0.0059,
1322
+ "step": 1840
1323
+ },
1324
+ {
1325
+ "epoch": 0.7061068702290076,
1326
+ "grad_norm": 0.03350086137652397,
1327
+ "learning_rate": 1.2069843744540999e-05,
1328
+ "loss": 0.0063,
1329
+ "step": 1850
1330
+ },
1331
+ {
1332
+ "epoch": 0.7099236641221374,
1333
+ "grad_norm": 0.33509764075279236,
1334
+ "learning_rate": 1.1785931261168537e-05,
1335
+ "loss": 0.0056,
1336
+ "step": 1860
1337
+ },
1338
+ {
1339
+ "epoch": 0.7137404580152672,
1340
+ "grad_norm": 0.12034814059734344,
1341
+ "learning_rate": 1.1504364314759311e-05,
1342
+ "loss": 0.0073,
1343
+ "step": 1870
1344
+ },
1345
+ {
1346
+ "epoch": 0.7175572519083969,
1347
+ "grad_norm": 0.5151724815368652,
1348
+ "learning_rate": 1.1225192884293578e-05,
1349
+ "loss": 0.0099,
1350
+ "step": 1880
1351
+ },
1352
+ {
1353
+ "epoch": 0.7213740458015268,
1354
+ "grad_norm": 0.32692572474479675,
1355
+ "learning_rate": 1.0948466523540296e-05,
1356
+ "loss": 0.008,
1357
+ "step": 1890
1358
+ },
1359
+ {
1360
+ "epoch": 0.7251908396946565,
1361
+ "grad_norm": 0.005217437632381916,
1362
+ "learning_rate": 1.0674234352261175e-05,
1363
+ "loss": 0.0071,
1364
+ "step": 1900
1365
+ },
1366
+ {
1367
+ "epoch": 0.7290076335877863,
1368
+ "grad_norm": 0.2179807722568512,
1369
+ "learning_rate": 1.0402545047491818e-05,
1370
+ "loss": 0.0166,
1371
+ "step": 1910
1372
+ },
1373
+ {
1374
+ "epoch": 0.732824427480916,
1375
+ "grad_norm": 0.6623926162719727,
1376
+ "learning_rate": 1.0133446834901344e-05,
1377
+ "loss": 0.0081,
1378
+ "step": 1920
1379
+ },
1380
+ {
1381
+ "epoch": 0.7366412213740458,
1382
+ "grad_norm": 0.27897024154663086,
1383
+ "learning_rate": 9.866987480232218e-06,
1384
+ "loss": 0.0109,
1385
+ "step": 1930
1386
+ },
1387
+ {
1388
+ "epoch": 0.7404580152671756,
1389
+ "grad_norm": 0.026624036952853203,
1390
+ "learning_rate": 9.603214280821707e-06,
1391
+ "loss": 0.0168,
1392
+ "step": 1940
1393
+ },
1394
+ {
1395
+ "epoch": 0.7442748091603053,
1396
+ "grad_norm": 0.505171537399292,
1397
+ "learning_rate": 9.342174057206402e-06,
1398
+ "loss": 0.0055,
1399
+ "step": 1950
1400
+ },
1401
+ {
1402
+ "epoch": 0.7480916030534351,
1403
+ "grad_norm": 0.5251939296722412,
1404
+ "learning_rate": 9.083913144811499e-06,
1405
+ "loss": 0.0067,
1406
+ "step": 1960
1407
+ },
1408
+ {
1409
+ "epoch": 0.7519083969465649,
1410
+ "grad_norm": 0.2802061438560486,
1411
+ "learning_rate": 8.828477385726055e-06,
1412
+ "loss": 0.0073,
1413
+ "step": 1970
1414
+ },
1415
+ {
1416
+ "epoch": 0.7557251908396947,
1417
+ "grad_norm": 0.4821580648422241,
1418
+ "learning_rate": 8.575912120565956e-06,
1419
+ "loss": 0.0077,
1420
+ "step": 1980
1421
+ },
1422
+ {
1423
+ "epoch": 0.7595419847328244,
1424
+ "grad_norm": 0.16226717829704285,
1425
+ "learning_rate": 8.326262180425746e-06,
1426
+ "loss": 0.0063,
1427
+ "step": 1990
1428
+ },
1429
+ {
1430
+ "epoch": 0.7633587786259542,
1431
+ "grad_norm": 0.2521667182445526,
1432
+ "learning_rate": 8.079571878921002e-06,
1433
+ "loss": 0.0058,
1434
+ "step": 2000
1435
+ },
1436
+ {
1437
+ "epoch": 0.7633587786259542,
1438
+ "eval_loss": 0.028967689722776413,
1439
+ "eval_runtime": 140.2457,
1440
+ "eval_samples_per_second": 56.914,
1441
+ "eval_steps_per_second": 0.299,
1442
+ "step": 2000
1443
+ },
1444
+ {
1445
+ "epoch": 0.767175572519084,
1446
+ "grad_norm": 0.40514904260635376,
1447
+ "learning_rate": 7.83588500432256e-06,
1448
+ "loss": 0.0112,
1449
+ "step": 2010
1450
+ },
1451
+ {
1452
+ "epoch": 0.7709923664122137,
1453
+ "grad_norm": 1.045690894126892,
1454
+ "learning_rate": 7.595244811783944e-06,
1455
+ "loss": 0.0058,
1456
+ "step": 2020
1457
+ },
1458
+ {
1459
+ "epoch": 0.7748091603053435,
1460
+ "grad_norm": 0.5543403625488281,
1461
+ "learning_rate": 7.357694015663416e-06,
1462
+ "loss": 0.0102,
1463
+ "step": 2030
1464
+ },
1465
+ {
1466
+ "epoch": 0.7786259541984732,
1467
+ "grad_norm": 0.14902685582637787,
1468
+ "learning_rate": 7.123274781942107e-06,
1469
+ "loss": 0.0041,
1470
+ "step": 2040
1471
+ },
1472
+ {
1473
+ "epoch": 0.7824427480916031,
1474
+ "grad_norm": 0.0032010909635573626,
1475
+ "learning_rate": 6.892028720739388e-06,
1476
+ "loss": 0.0159,
1477
+ "step": 2050
1478
+ },
1479
+ {
1480
+ "epoch": 0.7862595419847328,
1481
+ "grad_norm": 0.05139963701367378,
1482
+ "learning_rate": 6.663996878926943e-06,
1483
+ "loss": 0.0064,
1484
+ "step": 2060
1485
+ },
1486
+ {
1487
+ "epoch": 0.7900763358778626,
1488
+ "grad_norm": 0.3358862102031708,
1489
+ "learning_rate": 6.439219732842869e-06,
1490
+ "loss": 0.0098,
1491
+ "step": 2070
1492
+ },
1493
+ {
1494
+ "epoch": 0.7938931297709924,
1495
+ "grad_norm": 0.15072062611579895,
1496
+ "learning_rate": 6.217737181106978e-06,
1497
+ "loss": 0.0065,
1498
+ "step": 2080
1499
+ },
1500
+ {
1501
+ "epoch": 0.7977099236641222,
1502
+ "grad_norm": 0.002467066515237093,
1503
+ "learning_rate": 5.999588537538639e-06,
1504
+ "loss": 0.0037,
1505
+ "step": 2090
1506
+ },
1507
+ {
1508
+ "epoch": 0.8015267175572519,
1509
+ "grad_norm": 0.034411050379276276,
1510
+ "learning_rate": 5.784812524178529e-06,
1511
+ "loss": 0.0074,
1512
+ "step": 2100
1513
+ },
1514
+ {
1515
+ "epoch": 0.8053435114503816,
1516
+ "grad_norm": 0.08725389838218689,
1517
+ "learning_rate": 5.573447264415288e-06,
1518
+ "loss": 0.0185,
1519
+ "step": 2110
1520
+ },
1521
+ {
1522
+ "epoch": 0.8091603053435115,
1523
+ "grad_norm": 0.2480231672525406,
1524
+ "learning_rate": 5.365530276218531e-06,
1525
+ "loss": 0.0071,
1526
+ "step": 2120
1527
+ },
1528
+ {
1529
+ "epoch": 0.8129770992366412,
1530
+ "grad_norm": 0.5087897181510925,
1531
+ "learning_rate": 5.161098465479308e-06,
1532
+ "loss": 0.0243,
1533
+ "step": 2130
1534
+ },
1535
+ {
1536
+ "epoch": 0.816793893129771,
1537
+ "grad_norm": 0.3457648456096649,
1538
+ "learning_rate": 4.96018811945918e-06,
1539
+ "loss": 0.0073,
1540
+ "step": 2140
1541
+ },
1542
+ {
1543
+ "epoch": 0.8206106870229007,
1544
+ "grad_norm": 0.39516162872314453,
1545
+ "learning_rate": 4.762834900349117e-06,
1546
+ "loss": 0.0122,
1547
+ "step": 2150
1548
+ },
1549
+ {
1550
+ "epoch": 0.8244274809160306,
1551
+ "grad_norm": 0.3586041331291199,
1552
+ "learning_rate": 4.56907383893935e-06,
1553
+ "loss": 0.0073,
1554
+ "step": 2160
1555
+ },
1556
+ {
1557
+ "epoch": 0.8282442748091603,
1558
+ "grad_norm": 0.06679055839776993,
1559
+ "learning_rate": 4.378939328401338e-06,
1560
+ "loss": 0.0052,
1561
+ "step": 2170
1562
+ },
1563
+ {
1564
+ "epoch": 0.8320610687022901,
1565
+ "grad_norm": 0.40074533224105835,
1566
+ "learning_rate": 4.192465118182814e-06,
1567
+ "loss": 0.0064,
1568
+ "step": 2180
1569
+ },
1570
+ {
1571
+ "epoch": 0.8358778625954199,
1572
+ "grad_norm": 0.13426686823368073,
1573
+ "learning_rate": 4.0096843080172195e-06,
1574
+ "loss": 0.0139,
1575
+ "step": 2190
1576
+ },
1577
+ {
1578
+ "epoch": 0.8396946564885496,
1579
+ "grad_norm": 0.08818082511425018,
1580
+ "learning_rate": 3.8306293420483505e-06,
1581
+ "loss": 0.0104,
1582
+ "step": 2200
1583
+ },
1584
+ {
1585
+ "epoch": 0.8435114503816794,
1586
+ "grad_norm": 0.676325261592865,
1587
+ "learning_rate": 3.6553320030714626e-06,
1588
+ "loss": 0.0065,
1589
+ "step": 2210
1590
+ },
1591
+ {
1592
+ "epoch": 0.8473282442748091,
1593
+ "grad_norm": 0.31104177236557007,
1594
+ "learning_rate": 3.483823406891701e-06,
1595
+ "loss": 0.0074,
1596
+ "step": 2220
1597
+ },
1598
+ {
1599
+ "epoch": 0.851145038167939,
1600
+ "grad_norm": 0.358847975730896,
1601
+ "learning_rate": 3.3161339968009768e-06,
1602
+ "loss": 0.0103,
1603
+ "step": 2230
1604
+ },
1605
+ {
1606
+ "epoch": 0.8549618320610687,
1607
+ "grad_norm": 0.4074176251888275,
1608
+ "learning_rate": 3.1522935381741643e-06,
1609
+ "loss": 0.0106,
1610
+ "step": 2240
1611
+ },
1612
+ {
1613
+ "epoch": 0.8587786259541985,
1614
+ "grad_norm": 0.22954821586608887,
1615
+ "learning_rate": 2.9923311131856783e-06,
1616
+ "loss": 0.0087,
1617
+ "step": 2250
1618
+ },
1619
+ {
1620
+ "epoch": 0.8625954198473282,
1621
+ "grad_norm": 0.33302852511405945,
1622
+ "learning_rate": 2.836275115647294e-06,
1623
+ "loss": 0.013,
1624
+ "step": 2260
1625
+ },
1626
+ {
1627
+ "epoch": 0.8664122137404581,
1628
+ "grad_norm": 0.09198283404111862,
1629
+ "learning_rate": 2.6841532459681627e-06,
1630
+ "loss": 0.0067,
1631
+ "step": 2270
1632
+ },
1633
+ {
1634
+ "epoch": 0.8702290076335878,
1635
+ "grad_norm": 0.03521020710468292,
1636
+ "learning_rate": 2.5359925062378884e-06,
1637
+ "loss": 0.0092,
1638
+ "step": 2280
1639
+ },
1640
+ {
1641
+ "epoch": 0.8740458015267175,
1642
+ "grad_norm": 0.40850088000297546,
1643
+ "learning_rate": 2.3918191954336144e-06,
1644
+ "loss": 0.0064,
1645
+ "step": 2290
1646
+ },
1647
+ {
1648
+ "epoch": 0.8778625954198473,
1649
+ "grad_norm": 0.002618383150547743,
1650
+ "learning_rate": 2.2516589047518273e-06,
1651
+ "loss": 0.0069,
1652
+ "step": 2300
1653
+ },
1654
+ {
1655
+ "epoch": 0.8816793893129771,
1656
+ "grad_norm": 0.28037503361701965,
1657
+ "learning_rate": 2.1155365130658717e-06,
1658
+ "loss": 0.0063,
1659
+ "step": 2310
1660
+ },
1661
+ {
1662
+ "epoch": 0.8854961832061069,
1663
+ "grad_norm": 0.06269484013319016,
1664
+ "learning_rate": 1.9834761825098773e-06,
1665
+ "loss": 0.0043,
1666
+ "step": 2320
1667
+ },
1668
+ {
1669
+ "epoch": 0.8893129770992366,
1670
+ "grad_norm": 0.6617615222930908,
1671
+ "learning_rate": 1.8555013541899036e-06,
1672
+ "loss": 0.0148,
1673
+ "step": 2330
1674
+ },
1675
+ {
1676
+ "epoch": 0.8931297709923665,
1677
+ "grad_norm": 0.06300811469554901,
1678
+ "learning_rate": 1.7316347440230557e-06,
1679
+ "loss": 0.0116,
1680
+ "step": 2340
1681
+ },
1682
+ {
1683
+ "epoch": 0.8969465648854962,
1684
+ "grad_norm": 0.15155254304409027,
1685
+ "learning_rate": 1.61189833870537e-06,
1686
+ "loss": 0.0035,
1687
+ "step": 2350
1688
+ },
1689
+ {
1690
+ "epoch": 0.9007633587786259,
1691
+ "grad_norm": 0.7464874386787415,
1692
+ "learning_rate": 1.496313391809076e-06,
1693
+ "loss": 0.0131,
1694
+ "step": 2360
1695
+ },
1696
+ {
1697
+ "epoch": 0.9045801526717557,
1698
+ "grad_norm": 0.7433227896690369,
1699
+ "learning_rate": 1.3849004200100546e-06,
1700
+ "loss": 0.0084,
1701
+ "step": 2370
1702
+ },
1703
+ {
1704
+ "epoch": 0.9083969465648855,
1705
+ "grad_norm": 0.4609885513782501,
1706
+ "learning_rate": 1.2776791994460553e-06,
1707
+ "loss": 0.0091,
1708
+ "step": 2380
1709
+ },
1710
+ {
1711
+ "epoch": 0.9122137404580153,
1712
+ "grad_norm": 0.03363984078168869,
1713
+ "learning_rate": 1.1746687622063573e-06,
1714
+ "loss": 0.0109,
1715
+ "step": 2390
1716
+ },
1717
+ {
1718
+ "epoch": 0.916030534351145,
1719
+ "grad_norm": 0.34646764397621155,
1720
+ "learning_rate": 1.0758873929535424e-06,
1721
+ "loss": 0.0058,
1722
+ "step": 2400
1723
+ },
1724
+ {
1725
+ "epoch": 0.9198473282442748,
1726
+ "grad_norm": 0.28582972288131714,
1727
+ "learning_rate": 9.813526256778894e-07,
1728
+ "loss": 0.0054,
1729
+ "step": 2410
1730
+ },
1731
+ {
1732
+ "epoch": 0.9236641221374046,
1733
+ "grad_norm": 0.5931139588356018,
1734
+ "learning_rate": 8.910812405850566e-07,
1735
+ "loss": 0.0118,
1736
+ "step": 2420
1737
+ },
1738
+ {
1739
+ "epoch": 0.9274809160305344,
1740
+ "grad_norm": 0.44896554946899414,
1741
+ "learning_rate": 8.050892611175253e-07,
1742
+ "loss": 0.0119,
1743
+ "step": 2430
1744
+ },
1745
+ {
1746
+ "epoch": 0.9312977099236641,
1747
+ "grad_norm": 0.19585078954696655,
1748
+ "learning_rate": 7.233919511104082e-07,
1749
+ "loss": 0.0132,
1750
+ "step": 2440
1751
+ },
1752
+ {
1753
+ "epoch": 0.9351145038167938,
1754
+ "grad_norm": 0.24196402728557587,
1755
+ "learning_rate": 6.460038120820688e-07,
1756
+ "loss": 0.0051,
1757
+ "step": 2450
1758
+ },
1759
+ {
1760
+ "epoch": 0.9389312977099237,
1761
+ "grad_norm": 0.2216787487268448,
1762
+ "learning_rate": 5.729385806600484e-07,
1763
+ "loss": 0.0039,
1764
+ "step": 2460
1765
+ },
1766
+ {
1767
+ "epoch": 0.9427480916030534,
1768
+ "grad_norm": 0.008937466889619827,
1769
+ "learning_rate": 5.042092261427822e-07,
1770
+ "loss": 0.0151,
1771
+ "step": 2470
1772
+ },
1773
+ {
1774
+ "epoch": 0.9465648854961832,
1775
+ "grad_norm": 0.2098822146654129,
1776
+ "learning_rate": 4.3982794819751316e-07,
1777
+ "loss": 0.0045,
1778
+ "step": 2480
1779
+ },
1780
+ {
1781
+ "epoch": 0.950381679389313,
1782
+ "grad_norm": 0.09708132594823837,
1783
+ "learning_rate": 3.7980617469479953e-07,
1784
+ "loss": 0.0059,
1785
+ "step": 2490
1786
+ },
1787
+ {
1788
+ "epoch": 0.9541984732824428,
1789
+ "grad_norm": 0.10786189138889313,
1790
+ "learning_rate": 3.2415455968004826e-07,
1791
+ "loss": 0.0032,
1792
+ "step": 2500
1793
+ },
1794
+ {
1795
+ "epoch": 0.9541984732824428,
1796
+ "eval_loss": 0.027030499652028084,
1797
+ "eval_runtime": 140.2791,
1798
+ "eval_samples_per_second": 56.901,
1799
+ "eval_steps_per_second": 0.299,
1800
+ "step": 2500
1801
+ },
1802
+ {
1803
+ "epoch": 0.9580152671755725,
1804
+ "grad_norm": 0.5997936725616455,
1805
+ "learning_rate": 2.7288298148238913e-07,
1806
+ "loss": 0.0164,
1807
+ "step": 2510
1808
+ },
1809
+ {
1810
+ "epoch": 0.9618320610687023,
1811
+ "grad_norm": 1.1892848014831543,
1812
+ "learning_rate": 2.2600054096122703e-07,
1813
+ "loss": 0.0095,
1814
+ "step": 2520
1815
+ },
1816
+ {
1817
+ "epoch": 0.9656488549618321,
1818
+ "grad_norm": 0.014309865422546864,
1819
+ "learning_rate": 1.8351555989082892e-07,
1820
+ "loss": 0.006,
1821
+ "step": 2530
1822
+ },
1823
+ {
1824
+ "epoch": 0.9694656488549618,
1825
+ "grad_norm": 0.23357251286506653,
1826
+ "learning_rate": 1.4543557948317744e-07,
1827
+ "loss": 0.0084,
1828
+ "step": 2540
1829
+ },
1830
+ {
1831
+ "epoch": 0.9732824427480916,
1832
+ "grad_norm": 0.4700785279273987,
1833
+ "learning_rate": 1.1176735904937508e-07,
1834
+ "loss": 0.0079,
1835
+ "step": 2550
1836
+ },
1837
+ {
1838
+ "epoch": 0.9770992366412213,
1839
+ "grad_norm": 0.005513277370482683,
1840
+ "learning_rate": 8.251687479986503e-08,
1841
+ "loss": 0.0176,
1842
+ "step": 2560
1843
+ },
1844
+ {
1845
+ "epoch": 0.9809160305343512,
1846
+ "grad_norm": 0.32526788115501404,
1847
+ "learning_rate": 5.768931878361583e-08,
1848
+ "loss": 0.0091,
1849
+ "step": 2570
1850
+ },
1851
+ {
1852
+ "epoch": 0.9847328244274809,
1853
+ "grad_norm": 0.29356321692466736,
1854
+ "learning_rate": 3.728909796652525e-08,
1855
+ "loss": 0.0022,
1856
+ "step": 2580
1857
+ },
1858
+ {
1859
+ "epoch": 0.9885496183206107,
1860
+ "grad_norm": 0.03470044955611229,
1861
+ "learning_rate": 2.1319833449179317e-08,
1862
+ "loss": 0.0055,
1863
+ "step": 2590
1864
+ },
1865
+ {
1866
+ "epoch": 0.9923664122137404,
1867
+ "grad_norm": 0.004818221088498831,
1868
+ "learning_rate": 9.78435982407766e-09,
1869
+ "loss": 0.0093,
1870
+ "step": 2600
1871
+ },
1872
+ {
1873
+ "epoch": 0.9961832061068703,
1874
+ "grad_norm": 0.03156821429729462,
1875
+ "learning_rate": 2.6847246725053565e-09,
1876
+ "loss": 0.0034,
1877
+ "step": 2610
1878
+ },
1879
+ {
1880
+ "epoch": 1.0,
1881
+ "grad_norm": 0.0063484120182693005,
1882
+ "learning_rate": 2.2188201059814007e-11,
1883
+ "loss": 0.0075,
1884
+ "step": 2620
1885
+ }
1886
+ ],
1887
+ "logging_steps": 10,
1888
+ "max_steps": 2620,
1889
+ "num_input_tokens_seen": 0,
1890
+ "num_train_epochs": 1,
1891
+ "save_steps": 500,
1892
+ "stateful_callbacks": {
1893
+ "TrainerControl": {
1894
+ "args": {
1895
+ "should_epoch_stop": false,
1896
+ "should_evaluate": false,
1897
+ "should_log": false,
1898
+ "should_save": true,
1899
+ "should_training_stop": true
1900
+ },
1901
+ "attributes": {}
1902
+ }
1903
+ },
1904
+ "total_flos": 2.3731098682179103e+18,
1905
+ "train_batch_size": 192,
1906
+ "trial_name": null,
1907
+ "trial_params": null
1908
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a78901af143a5eb21598b81e77820b09f499bf50a9cc6d83e1643aeaf5af1d1d
3
+ size 5905