Fizzarolli commited on
Commit
2e45b8a
·
verified ·
1 Parent(s): 1609bb6

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mistral-Small-Instruct-2409
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.14.0
adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-Small-Instruct-2409",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": null,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 32,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.25,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 16,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "up_proj",
27
+ "v_proj",
28
+ "gate_proj",
29
+ "q_proj",
30
+ "down_proj",
31
+ "o_proj",
32
+ "k_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c96c82fa713ed0b990dacbb35eec8d8e3c8d7ae6f8f7bc0ebbbd80751521b1e2
3
+ size 381787464
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca42447e8385a1a5d51e994dbf975f2683154974eb443351aa9fb400cc72cc60
3
+ size 194748052
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0faa2941d3fdfa002419a3762dfa92fa368d5ad5859f4c92f1269920be6c0317
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93f9b636559f0bcd7a1ae12443a45be3d5ce7f0b4b0ea28a9d2b1845f94f5372
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
3
+ size 587583
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
trainer_state.json ADDED
@@ -0,0 +1,1643 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 230,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.004357298474945534,
13
+ "grad_norm": 0.9746105074882507,
14
+ "learning_rate": 2.4000000000000003e-06,
15
+ "loss": 1.7828,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.008714596949891068,
20
+ "grad_norm": 0.9253537654876709,
21
+ "learning_rate": 4.800000000000001e-06,
22
+ "loss": 1.8214,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.013071895424836602,
27
+ "grad_norm": 1.5627340078353882,
28
+ "learning_rate": 7.2e-06,
29
+ "loss": 1.8438,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.017429193899782137,
34
+ "grad_norm": 0.38599923253059387,
35
+ "learning_rate": 9.600000000000001e-06,
36
+ "loss": 1.7347,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.02178649237472767,
41
+ "grad_norm": 0.5854593515396118,
42
+ "learning_rate": 1.2e-05,
43
+ "loss": 1.5746,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.026143790849673203,
48
+ "grad_norm": 0.5655810236930847,
49
+ "learning_rate": 1.44e-05,
50
+ "loss": 1.6704,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.030501089324618737,
55
+ "grad_norm": 0.5204870700836182,
56
+ "learning_rate": 1.6800000000000002e-05,
57
+ "loss": 1.7218,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.034858387799564274,
62
+ "grad_norm": 0.3172350227832794,
63
+ "learning_rate": 1.9200000000000003e-05,
64
+ "loss": 1.7356,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.0392156862745098,
69
+ "grad_norm": 0.3486512005329132,
70
+ "learning_rate": 2.16e-05,
71
+ "loss": 1.6989,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.04357298474945534,
76
+ "grad_norm": 0.3535781800746918,
77
+ "learning_rate": 2.4e-05,
78
+ "loss": 1.8387,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.04793028322440087,
83
+ "grad_norm": 0.5419184565544128,
84
+ "learning_rate": 2.64e-05,
85
+ "loss": 1.6227,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.05228758169934641,
90
+ "grad_norm": 0.48862531781196594,
91
+ "learning_rate": 2.88e-05,
92
+ "loss": 1.7614,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.05664488017429194,
97
+ "grad_norm": 0.2664097547531128,
98
+ "learning_rate": 3.12e-05,
99
+ "loss": 1.6985,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.06100217864923747,
104
+ "grad_norm": 0.28547024726867676,
105
+ "learning_rate": 3.3600000000000004e-05,
106
+ "loss": 1.6369,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.06535947712418301,
111
+ "grad_norm": 0.7763476371765137,
112
+ "learning_rate": 3.6e-05,
113
+ "loss": 1.6875,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.06971677559912855,
118
+ "grad_norm": 0.40384408831596375,
119
+ "learning_rate": 3.8400000000000005e-05,
120
+ "loss": 1.5499,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.07407407407407407,
125
+ "grad_norm": 0.2866835594177246,
126
+ "learning_rate": 4.08e-05,
127
+ "loss": 1.7804,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.0784313725490196,
132
+ "grad_norm": 0.36669981479644775,
133
+ "learning_rate": 4.32e-05,
134
+ "loss": 1.6886,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.08278867102396514,
139
+ "grad_norm": 0.31070730090141296,
140
+ "learning_rate": 4.5600000000000004e-05,
141
+ "loss": 1.5843,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.08714596949891068,
146
+ "grad_norm": 0.2698839604854584,
147
+ "learning_rate": 4.8e-05,
148
+ "loss": 1.6562,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.0915032679738562,
153
+ "grad_norm": 0.3030396103858948,
154
+ "learning_rate": 5.04e-05,
155
+ "loss": 1.7683,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.09586056644880174,
160
+ "grad_norm": 0.34498634934425354,
161
+ "learning_rate": 5.28e-05,
162
+ "loss": 1.7619,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.10021786492374728,
167
+ "grad_norm": 0.315149188041687,
168
+ "learning_rate": 5.520000000000001e-05,
169
+ "loss": 1.6201,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.10457516339869281,
174
+ "grad_norm": 0.2636476159095764,
175
+ "learning_rate": 5.76e-05,
176
+ "loss": 1.6439,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.10893246187363835,
181
+ "grad_norm": 0.5684914588928223,
182
+ "learning_rate": 6e-05,
183
+ "loss": 1.823,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.11328976034858387,
188
+ "grad_norm": 0.3564894497394562,
189
+ "learning_rate": 5.9999210388787696e-05,
190
+ "loss": 1.6807,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.11764705882352941,
195
+ "grad_norm": 0.3562137186527252,
196
+ "learning_rate": 5.999684159671647e-05,
197
+ "loss": 1.7543,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.12200435729847495,
202
+ "grad_norm": 0.32931092381477356,
203
+ "learning_rate": 5.999289374848134e-05,
204
+ "loss": 1.7032,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.12636165577342048,
209
+ "grad_norm": 0.3593999743461609,
210
+ "learning_rate": 5.998736705189997e-05,
211
+ "loss": 1.5749,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.13071895424836602,
216
+ "grad_norm": 0.31765711307525635,
217
+ "learning_rate": 5.998026179790181e-05,
218
+ "loss": 1.5925,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.13507625272331156,
223
+ "grad_norm": 1.1995874643325806,
224
+ "learning_rate": 5.9971578360512726e-05,
225
+ "loss": 1.6874,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.1394335511982571,
230
+ "grad_norm": 0.3488420248031616,
231
+ "learning_rate": 5.996131719683537e-05,
232
+ "loss": 1.8334,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.1437908496732026,
237
+ "grad_norm": 1.2170417308807373,
238
+ "learning_rate": 5.994947884702506e-05,
239
+ "loss": 1.8111,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.14814814814814814,
244
+ "grad_norm": 7.140843868255615,
245
+ "learning_rate": 5.993606393426137e-05,
246
+ "loss": 1.7542,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.15250544662309368,
251
+ "grad_norm": 6.034117221832275,
252
+ "learning_rate": 5.992107316471536e-05,
253
+ "loss": 1.6763,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.1568627450980392,
258
+ "grad_norm": 24.70130729675293,
259
+ "learning_rate": 5.990450732751232e-05,
260
+ "loss": 1.7738,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.16122004357298475,
265
+ "grad_norm": 2.477736234664917,
266
+ "learning_rate": 5.988636729469032e-05,
267
+ "loss": 1.8413,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.1655773420479303,
272
+ "grad_norm": 0.5539727210998535,
273
+ "learning_rate": 5.986665402115423e-05,
274
+ "loss": 1.7711,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.16993464052287582,
279
+ "grad_norm": 0.651229739189148,
280
+ "learning_rate": 5.9845368544625516e-05,
281
+ "loss": 1.809,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.17429193899782136,
286
+ "grad_norm": 0.4992523491382599,
287
+ "learning_rate": 5.9822511985587577e-05,
288
+ "loss": 1.9164,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.1786492374727669,
293
+ "grad_norm": 0.5860515832901001,
294
+ "learning_rate": 5.979808554722675e-05,
295
+ "loss": 1.737,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.1830065359477124,
300
+ "grad_norm": 0.9775006175041199,
301
+ "learning_rate": 5.977209051536903e-05,
302
+ "loss": 1.6852,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.18736383442265794,
307
+ "grad_norm": 0.5079925656318665,
308
+ "learning_rate": 5.974452825841231e-05,
309
+ "loss": 1.6264,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.19172113289760348,
314
+ "grad_norm": 0.4939415752887726,
315
+ "learning_rate": 5.97154002272544e-05,
316
+ "loss": 1.6138,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.19607843137254902,
321
+ "grad_norm": 0.4919627606868744,
322
+ "learning_rate": 5.968470795521663e-05,
323
+ "loss": 1.6991,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.20043572984749455,
328
+ "grad_norm": 0.9349490404129028,
329
+ "learning_rate": 5.965245305796316e-05,
330
+ "loss": 1.7488,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.2047930283224401,
335
+ "grad_norm": 8.618950843811035,
336
+ "learning_rate": 5.9618637233415866e-05,
337
+ "loss": 1.7847,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.20915032679738563,
342
+ "grad_norm": 0.656200110912323,
343
+ "learning_rate": 5.958326226166505e-05,
344
+ "loss": 1.7535,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.21350762527233116,
349
+ "grad_norm": 0.49261513352394104,
350
+ "learning_rate": 5.954633000487565e-05,
351
+ "loss": 1.6509,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.2178649237472767,
356
+ "grad_norm": 0.7735104560852051,
357
+ "learning_rate": 5.950784240718929e-05,
358
+ "loss": 1.7014,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.2222222222222222,
363
+ "grad_norm": 0.5278734564781189,
364
+ "learning_rate": 5.946780149462187e-05,
365
+ "loss": 1.6646,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.22657952069716775,
370
+ "grad_norm": 10.276693344116211,
371
+ "learning_rate": 5.942620937495696e-05,
372
+ "loss": 1.9713,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.23093681917211328,
377
+ "grad_norm": 0.9025694727897644,
378
+ "learning_rate": 5.938306823763481e-05,
379
+ "loss": 1.7381,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.23529411764705882,
384
+ "grad_norm": 0.6549501419067383,
385
+ "learning_rate": 5.933838035363717e-05,
386
+ "loss": 1.5728,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.23965141612200436,
391
+ "grad_norm": 0.6484580039978027,
392
+ "learning_rate": 5.9292148075367635e-05,
393
+ "loss": 1.7029,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.2440087145969499,
398
+ "grad_norm": 0.5284441113471985,
399
+ "learning_rate": 5.924437383652789e-05,
400
+ "loss": 1.6064,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.24836601307189543,
405
+ "grad_norm": 0.4835830330848694,
406
+ "learning_rate": 5.9195060151989595e-05,
407
+ "loss": 1.6933,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.25272331154684097,
412
+ "grad_norm": 0.4144735336303711,
413
+ "learning_rate": 5.914420961766194e-05,
414
+ "loss": 1.7435,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.2570806100217865,
419
+ "grad_norm": 0.41090619564056396,
420
+ "learning_rate": 5.909182491035509e-05,
421
+ "loss": 1.6487,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.26143790849673204,
426
+ "grad_norm": 0.35188132524490356,
427
+ "learning_rate": 5.9037908787639174e-05,
428
+ "loss": 1.7431,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.2657952069716776,
433
+ "grad_norm": 0.5362684726715088,
434
+ "learning_rate": 5.898246408769921e-05,
435
+ "loss": 1.7848,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.2701525054466231,
440
+ "grad_norm": 0.37840691208839417,
441
+ "learning_rate": 5.892549372918564e-05,
442
+ "loss": 1.807,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.27450980392156865,
447
+ "grad_norm": 0.6966099143028259,
448
+ "learning_rate": 5.8867000711060704e-05,
449
+ "loss": 1.6143,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.2788671023965142,
454
+ "grad_norm": 1.4057034254074097,
455
+ "learning_rate": 5.8806988112440624e-05,
456
+ "loss": 1.5769,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.28322440087145967,
461
+ "grad_norm": 0.38457629084587097,
462
+ "learning_rate": 5.8745459092433436e-05,
463
+ "loss": 1.6125,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.2875816993464052,
468
+ "grad_norm": 0.3964170813560486,
469
+ "learning_rate": 5.868241688997275e-05,
470
+ "loss": 1.9211,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.29193899782135074,
475
+ "grad_norm": 0.4357544183731079,
476
+ "learning_rate": 5.861786482364723e-05,
477
+ "loss": 1.7145,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.2962962962962963,
482
+ "grad_norm": 0.4696052670478821,
483
+ "learning_rate": 5.8551806291525885e-05,
484
+ "loss": 1.5768,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.3006535947712418,
489
+ "grad_norm": 0.5432698130607605,
490
+ "learning_rate": 5.848424477097924e-05,
491
+ "loss": 1.7934,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.30501089324618735,
496
+ "grad_norm": 0.44644972681999207,
497
+ "learning_rate": 5.8415183818496234e-05,
498
+ "loss": 1.7114,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.3093681917211329,
503
+ "grad_norm": 0.5297689437866211,
504
+ "learning_rate": 5.8344627069497025e-05,
505
+ "loss": 1.6654,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.3137254901960784,
510
+ "grad_norm": 0.5777753591537476,
511
+ "learning_rate": 5.827257823814162e-05,
512
+ "loss": 1.7446,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.31808278867102396,
517
+ "grad_norm": 5.469757556915283,
518
+ "learning_rate": 5.819904111713436e-05,
519
+ "loss": 1.7395,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.3224400871459695,
524
+ "grad_norm": 0.5288973450660706,
525
+ "learning_rate": 5.812401957752426e-05,
526
+ "loss": 1.8596,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.32679738562091504,
531
+ "grad_norm": 1.6414694786071777,
532
+ "learning_rate": 5.804751756850124e-05,
533
+ "loss": 1.6706,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.3311546840958606,
538
+ "grad_norm": 0.9940863847732544,
539
+ "learning_rate": 5.7969539117188256e-05,
540
+ "loss": 1.7504,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.3355119825708061,
545
+ "grad_norm": 4.836872577667236,
546
+ "learning_rate": 5.789008832842924e-05,
547
+ "loss": 1.8491,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.33986928104575165,
552
+ "grad_norm": 1.7528856992721558,
553
+ "learning_rate": 5.780916938457314e-05,
554
+ "loss": 1.8635,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.3442265795206972,
559
+ "grad_norm": 1.1119537353515625,
560
+ "learning_rate": 5.772678654525362e-05,
561
+ "loss": 1.7444,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.3485838779956427,
566
+ "grad_norm": 1.9335803985595703,
567
+ "learning_rate": 5.764294414716494e-05,
568
+ "loss": 1.6888,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.35294117647058826,
573
+ "grad_norm": 2.479970932006836,
574
+ "learning_rate": 5.755764660383358e-05,
575
+ "loss": 1.5989,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.3572984749455338,
580
+ "grad_norm": 0.6857799887657166,
581
+ "learning_rate": 5.7470898405386005e-05,
582
+ "loss": 1.7211,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.3616557734204793,
587
+ "grad_norm": 0.5701134204864502,
588
+ "learning_rate": 5.738270411831222e-05,
589
+ "loss": 1.5853,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.3660130718954248,
594
+ "grad_norm": 1.7818999290466309,
595
+ "learning_rate": 5.729306838522541e-05,
596
+ "loss": 1.6756,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.37037037037037035,
601
+ "grad_norm": 0.6445415019989014,
602
+ "learning_rate": 5.720199592461757e-05,
603
+ "loss": 1.7658,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.3747276688453159,
608
+ "grad_norm": 0.7761105298995972,
609
+ "learning_rate": 5.7109491530611106e-05,
610
+ "loss": 1.6389,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.3790849673202614,
615
+ "grad_norm": 0.40940380096435547,
616
+ "learning_rate": 5.701556007270647e-05,
617
+ "loss": 1.6816,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.38344226579520696,
622
+ "grad_norm": 0.640964925289154,
623
+ "learning_rate": 5.692020649552581e-05,
624
+ "loss": 1.5405,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.3877995642701525,
629
+ "grad_norm": 0.5489770174026489,
630
+ "learning_rate": 5.6823435818552696e-05,
631
+ "loss": 1.7949,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.39215686274509803,
636
+ "grad_norm": 0.7703227400779724,
637
+ "learning_rate": 5.6725253135867915e-05,
638
+ "loss": 1.7931,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.39651416122004357,
643
+ "grad_norm": 0.5832772254943848,
644
+ "learning_rate": 5.662566361588127e-05,
645
+ "loss": 1.8679,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.4008714596949891,
650
+ "grad_norm": 0.8693870902061462,
651
+ "learning_rate": 5.652467250105952e-05,
652
+ "loss": 1.6827,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.40522875816993464,
657
+ "grad_norm": 2.1690566539764404,
658
+ "learning_rate": 5.642228510765046e-05,
659
+ "loss": 1.7037,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.4095860566448802,
664
+ "grad_norm": 1.1100988388061523,
665
+ "learning_rate": 5.6318506825403015e-05,
666
+ "loss": 1.6876,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.4139433551198257,
671
+ "grad_norm": 10.220698356628418,
672
+ "learning_rate": 5.6213343117283506e-05,
673
+ "loss": 1.8567,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.41830065359477125,
678
+ "grad_norm": 4.02601432800293,
679
+ "learning_rate": 5.610679951918817e-05,
680
+ "loss": 1.7431,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.4226579520697168,
685
+ "grad_norm": 9.665276527404785,
686
+ "learning_rate": 5.5998881639651626e-05,
687
+ "loss": 1.6413,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.42701525054466233,
692
+ "grad_norm": 16.3509578704834,
693
+ "learning_rate": 5.588959515955173e-05,
694
+ "loss": 2.2493,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.43137254901960786,
699
+ "grad_norm": 24.08732795715332,
700
+ "learning_rate": 5.577894583181048e-05,
701
+ "loss": 2.2252,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.4357298474945534,
706
+ "grad_norm": 17.57210350036621,
707
+ "learning_rate": 5.566693948109122e-05,
708
+ "loss": 1.7175,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.4400871459694989,
713
+ "grad_norm": 43.53101348876953,
714
+ "learning_rate": 5.5553582003491944e-05,
715
+ "loss": 1.9579,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.4444444444444444,
720
+ "grad_norm": 27.57504653930664,
721
+ "learning_rate": 5.543887936623503e-05,
722
+ "loss": 1.9186,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.44880174291938996,
727
+ "grad_norm": 18.363325119018555,
728
+ "learning_rate": 5.532283760735302e-05,
729
+ "loss": 1.8096,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.4531590413943355,
734
+ "grad_norm": 27.843307495117188,
735
+ "learning_rate": 5.520546283537086e-05,
736
+ "loss": 1.8707,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.45751633986928103,
741
+ "grad_norm": 11.314703941345215,
742
+ "learning_rate": 5.508676122898427e-05,
743
+ "loss": 1.5912,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.46187363834422657,
748
+ "grad_norm": 9.792496681213379,
749
+ "learning_rate": 5.496673903673455e-05,
750
+ "loss": 1.6825,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.4662309368191721,
755
+ "grad_norm": 11.959925651550293,
756
+ "learning_rate": 5.484540257667961e-05,
757
+ "loss": 1.7789,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.47058823529411764,
762
+ "grad_norm": 2.4276187419891357,
763
+ "learning_rate": 5.47227582360614e-05,
764
+ "loss": 1.6628,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.4749455337690632,
769
+ "grad_norm": 2.457439661026001,
770
+ "learning_rate": 5.459881247096969e-05,
771
+ "loss": 1.6083,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.4793028322440087,
776
+ "grad_norm": 19.251781463623047,
777
+ "learning_rate": 5.447357180600219e-05,
778
+ "loss": 1.6644,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.48366013071895425,
783
+ "grad_norm": 1.5374093055725098,
784
+ "learning_rate": 5.434704283392115e-05,
785
+ "loss": 1.6576,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.4880174291938998,
790
+ "grad_norm": 1.1958122253417969,
791
+ "learning_rate": 5.421923221530622e-05,
792
+ "loss": 1.5076,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.4923747276688453,
797
+ "grad_norm": 1.085802435874939,
798
+ "learning_rate": 5.409014667820389e-05,
799
+ "loss": 1.7292,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.49673202614379086,
804
+ "grad_norm": 1.2091395854949951,
805
+ "learning_rate": 5.395979301777334e-05,
806
+ "loss": 1.5753,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.5010893246187363,
811
+ "grad_norm": 2.773833990097046,
812
+ "learning_rate": 5.3828178095928684e-05,
813
+ "loss": 1.7763,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.5054466230936819,
818
+ "grad_norm": 0.7476174831390381,
819
+ "learning_rate": 5.369530884097779e-05,
820
+ "loss": 1.7815,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.5098039215686274,
825
+ "grad_norm": 0.7140160202980042,
826
+ "learning_rate": 5.356119224725757e-05,
827
+ "loss": 1.7438,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.514161220043573,
832
+ "grad_norm": 0.6035992503166199,
833
+ "learning_rate": 5.3425835374765745e-05,
834
+ "loss": 1.7846,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.5185185185185185,
839
+ "grad_norm": 3.483454465866089,
840
+ "learning_rate": 5.328924534878927e-05,
841
+ "loss": 1.8446,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.5228758169934641,
846
+ "grad_norm": 0.5726216435432434,
847
+ "learning_rate": 5.3151429359529226e-05,
848
+ "loss": 1.692,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.5272331154684096,
853
+ "grad_norm": 0.7607144117355347,
854
+ "learning_rate": 5.3012394661722275e-05,
855
+ "loss": 1.7304,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.5315904139433552,
860
+ "grad_norm": 0.586825966835022,
861
+ "learning_rate": 5.2872148574258864e-05,
862
+ "loss": 1.7993,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.5359477124183006,
867
+ "grad_norm": 0.4952510893344879,
868
+ "learning_rate": 5.273069847979786e-05,
869
+ "loss": 1.6976,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.5403050108932462,
874
+ "grad_norm": 0.5482230186462402,
875
+ "learning_rate": 5.258805182437795e-05,
876
+ "loss": 1.6702,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.5446623093681917,
881
+ "grad_norm": 1.4653637409210205,
882
+ "learning_rate": 5.244421611702573e-05,
883
+ "loss": 1.7064,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.5490196078431373,
888
+ "grad_norm": 0.7224717140197754,
889
+ "learning_rate": 5.229919892936033e-05,
890
+ "loss": 1.6133,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.5533769063180828,
895
+ "grad_norm": 2.9934468269348145,
896
+ "learning_rate": 5.2153007895194915e-05,
897
+ "loss": 1.8177,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.5577342047930284,
902
+ "grad_norm": 0.53426593542099,
903
+ "learning_rate": 5.2005650710134804e-05,
904
+ "loss": 1.775,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.5620915032679739,
909
+ "grad_norm": 0.5842443108558655,
910
+ "learning_rate": 5.185713513117236e-05,
911
+ "loss": 1.7364,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.5664488017429193,
916
+ "grad_norm": 0.7634817361831665,
917
+ "learning_rate": 5.1707468976278674e-05,
918
+ "loss": 1.6766,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.5708061002178649,
923
+ "grad_norm": 2.6095964908599854,
924
+ "learning_rate": 5.1556660123992014e-05,
925
+ "loss": 1.5793,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.5751633986928104,
930
+ "grad_norm": 0.6185954809188843,
931
+ "learning_rate": 5.140471651300309e-05,
932
+ "loss": 1.7295,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.579520697167756,
937
+ "grad_norm": 0.7229522466659546,
938
+ "learning_rate": 5.125164614173716e-05,
939
+ "loss": 1.6844,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.5838779956427015,
944
+ "grad_norm": 1.0191963911056519,
945
+ "learning_rate": 5.109745706793299e-05,
946
+ "loss": 1.6971,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.5882352941176471,
951
+ "grad_norm": 7.9863972663879395,
952
+ "learning_rate": 5.094215740821867e-05,
953
+ "loss": 1.6789,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.5925925925925926,
958
+ "grad_norm": 0.5257764458656311,
959
+ "learning_rate": 5.07857553376844e-05,
960
+ "loss": 1.6463,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.5969498910675382,
965
+ "grad_norm": 0.6847944855690002,
966
+ "learning_rate": 5.062825908945204e-05,
967
+ "loss": 1.7736,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.6013071895424836,
972
+ "grad_norm": 0.46256768703460693,
973
+ "learning_rate": 5.0469676954241857e-05,
974
+ "loss": 1.721,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.6056644880174292,
979
+ "grad_norm": 0.5772983431816101,
980
+ "learning_rate": 5.0310017279935964e-05,
981
+ "loss": 1.8956,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.6100217864923747,
986
+ "grad_norm": 1.1113687753677368,
987
+ "learning_rate": 5.0149288471138975e-05,
988
+ "loss": 1.8724,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.6143790849673203,
993
+ "grad_norm": 1.8465428352355957,
994
+ "learning_rate": 4.9987498988735525e-05,
995
+ "loss": 1.6231,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.6187363834422658,
1000
+ "grad_norm": 0.6225913166999817,
1001
+ "learning_rate": 4.982465734944489e-05,
1002
+ "loss": 1.7372,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.6230936819172114,
1007
+ "grad_norm": 0.6797170042991638,
1008
+ "learning_rate": 4.9660772125372715e-05,
1009
+ "loss": 1.6512,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.6274509803921569,
1014
+ "grad_norm": 0.7226108312606812,
1015
+ "learning_rate": 4.949585194355966e-05,
1016
+ "loss": 1.7288,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.6318082788671024,
1021
+ "grad_norm": 2.4343645572662354,
1022
+ "learning_rate": 4.9329905485527394e-05,
1023
+ "loss": 1.5985,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.6361655773420479,
1028
+ "grad_norm": 0.8588735461235046,
1029
+ "learning_rate": 4.916294148682151e-05,
1030
+ "loss": 1.7933,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.6405228758169934,
1035
+ "grad_norm": 0.9162130951881409,
1036
+ "learning_rate": 4.899496873655169e-05,
1037
+ "loss": 1.7511,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.644880174291939,
1042
+ "grad_norm": 1.1275595426559448,
1043
+ "learning_rate": 4.882599607692908e-05,
1044
+ "loss": 1.7821,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.6492374727668845,
1049
+ "grad_norm": 0.596320390701294,
1050
+ "learning_rate": 4.865603240280079e-05,
1051
+ "loss": 1.4973,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.6535947712418301,
1056
+ "grad_norm": 2.232231855392456,
1057
+ "learning_rate": 4.8485086661181656e-05,
1058
+ "loss": 1.6625,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.6579520697167756,
1063
+ "grad_norm": 3.6543140411376953,
1064
+ "learning_rate": 4.8313167850783304e-05,
1065
+ "loss": 1.7756,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.6623093681917211,
1070
+ "grad_norm": 32.78754425048828,
1071
+ "learning_rate": 4.8140285021540423e-05,
1072
+ "loss": 1.7519,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.6666666666666666,
1077
+ "grad_norm": 10.278705596923828,
1078
+ "learning_rate": 4.796644727413438e-05,
1079
+ "loss": 1.7621,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.6710239651416122,
1084
+ "grad_norm": 6.011966705322266,
1085
+ "learning_rate": 4.779166375951412e-05,
1086
+ "loss": 1.7506,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.6753812636165577,
1091
+ "grad_norm": 8.796587944030762,
1092
+ "learning_rate": 4.7615943678414515e-05,
1093
+ "loss": 1.8206,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.6797385620915033,
1098
+ "grad_norm": 9.715092658996582,
1099
+ "learning_rate": 4.743929628087197e-05,
1100
+ "loss": 1.736,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.6840958605664488,
1105
+ "grad_norm": 20.890012741088867,
1106
+ "learning_rate": 4.726173086573755e-05,
1107
+ "loss": 1.792,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.6884531590413944,
1112
+ "grad_norm": 6.689200401306152,
1113
+ "learning_rate": 4.708325678018744e-05,
1114
+ "loss": 1.8754,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.6928104575163399,
1119
+ "grad_norm": 10.521119117736816,
1120
+ "learning_rate": 4.6903883419230883e-05,
1121
+ "loss": 1.6421,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.6971677559912854,
1126
+ "grad_norm": 2.2947447299957275,
1127
+ "learning_rate": 4.67236202252157e-05,
1128
+ "loss": 1.7782,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.7015250544662309,
1133
+ "grad_norm": 2.0073139667510986,
1134
+ "learning_rate": 4.6542476687331165e-05,
1135
+ "loss": 1.7282,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.7058823529411765,
1140
+ "grad_norm": 2.2821898460388184,
1141
+ "learning_rate": 4.636046234110852e-05,
1142
+ "loss": 1.7421,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.710239651416122,
1147
+ "grad_norm": 0.8621974587440491,
1148
+ "learning_rate": 4.6177586767918984e-05,
1149
+ "loss": 1.7407,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.7145969498910676,
1154
+ "grad_norm": 3.2683534622192383,
1155
+ "learning_rate": 4.599385959446945e-05,
1156
+ "loss": 1.8106,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.7189542483660131,
1161
+ "grad_norm": 2.4297866821289062,
1162
+ "learning_rate": 4.5809290492295645e-05,
1163
+ "loss": 1.5172,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.7233115468409586,
1168
+ "grad_norm": 3.033637046813965,
1169
+ "learning_rate": 4.5623889177253074e-05,
1170
+ "loss": 1.7526,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.7276688453159041,
1175
+ "grad_norm": 1.2864795923233032,
1176
+ "learning_rate": 4.5437665409005564e-05,
1177
+ "loss": 1.7886,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.7320261437908496,
1182
+ "grad_norm": 2.133450984954834,
1183
+ "learning_rate": 4.525062899051145e-05,
1184
+ "loss": 1.7397,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.7363834422657952,
1189
+ "grad_norm": 0.7829226851463318,
1190
+ "learning_rate": 4.506278976750763e-05,
1191
+ "loss": 1.7315,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.7407407407407407,
1196
+ "grad_norm": 0.8621643781661987,
1197
+ "learning_rate": 4.487415762799118e-05,
1198
+ "loss": 1.7408,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.7450980392156863,
1203
+ "grad_norm": 0.6500158905982971,
1204
+ "learning_rate": 4.468474250169896e-05,
1205
+ "loss": 1.7465,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.7494553376906318,
1210
+ "grad_norm": 0.5809956192970276,
1211
+ "learning_rate": 4.4494554359584785e-05,
1212
+ "loss": 1.7293,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.7538126361655774,
1217
+ "grad_norm": 0.7333821058273315,
1218
+ "learning_rate": 4.430360321329463e-05,
1219
+ "loss": 1.727,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.7581699346405228,
1224
+ "grad_norm": 0.5068430304527283,
1225
+ "learning_rate": 4.411189911463955e-05,
1226
+ "loss": 1.7167,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.7625272331154684,
1231
+ "grad_norm": 0.6892985701560974,
1232
+ "learning_rate": 4.3919452155066614e-05,
1233
+ "loss": 1.5829,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.7668845315904139,
1238
+ "grad_norm": 1.0960310697555542,
1239
+ "learning_rate": 4.372627246512761e-05,
1240
+ "loss": 1.7752,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.7712418300653595,
1245
+ "grad_norm": 0.9808456897735596,
1246
+ "learning_rate": 4.3532370213945826e-05,
1247
+ "loss": 1.6206,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.775599128540305,
1252
+ "grad_norm": 0.9465530514717102,
1253
+ "learning_rate": 4.333775560868071e-05,
1254
+ "loss": 1.7664,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.7799564270152506,
1259
+ "grad_norm": 2.3225557804107666,
1260
+ "learning_rate": 4.3142438893990536e-05,
1261
+ "loss": 1.7564,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.7843137254901961,
1266
+ "grad_norm": 0.833987295627594,
1267
+ "learning_rate": 4.294643035149318e-05,
1268
+ "loss": 1.7599,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.7886710239651417,
1273
+ "grad_norm": 7.097892761230469,
1274
+ "learning_rate": 4.274974029922482e-05,
1275
+ "loss": 1.7297,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.7930283224400871,
1280
+ "grad_norm": 1.9574705362319946,
1281
+ "learning_rate": 4.255237909109685e-05,
1282
+ "loss": 1.6733,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.7973856209150327,
1287
+ "grad_norm": 5.98021125793457,
1288
+ "learning_rate": 4.235435711635076e-05,
1289
+ "loss": 1.7801,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.8017429193899782,
1294
+ "grad_norm": 1.4386473894119263,
1295
+ "learning_rate": 4.2155684799011346e-05,
1296
+ "loss": 1.7036,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.8061002178649237,
1301
+ "grad_norm": 1.5464740991592407,
1302
+ "learning_rate": 4.195637259733789e-05,
1303
+ "loss": 1.7301,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.8104575163398693,
1308
+ "grad_norm": 2.3751494884490967,
1309
+ "learning_rate": 4.1756431003273664e-05,
1310
+ "loss": 1.7411,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.8148148148148148,
1315
+ "grad_norm": 0.7723326086997986,
1316
+ "learning_rate": 4.155587054189365e-05,
1317
+ "loss": 1.6975,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.8191721132897604,
1322
+ "grad_norm": 0.8427643775939941,
1323
+ "learning_rate": 4.135470177085042e-05,
1324
+ "loss": 1.7452,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.8235294117647058,
1329
+ "grad_norm": 0.6999509930610657,
1330
+ "learning_rate": 4.11529352798185e-05,
1331
+ "loss": 1.8235,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.8278867102396514,
1336
+ "grad_norm": 0.6350328326225281,
1337
+ "learning_rate": 4.0950581689936744e-05,
1338
+ "loss": 1.8013,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.8322440087145969,
1343
+ "grad_norm": 0.5478256344795227,
1344
+ "learning_rate": 4.074765165324942e-05,
1345
+ "loss": 1.8239,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.8366013071895425,
1350
+ "grad_norm": 0.7619976997375488,
1351
+ "learning_rate": 4.0544155852145334e-05,
1352
+ "loss": 1.6571,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.840958605664488,
1357
+ "grad_norm": 0.6814029216766357,
1358
+ "learning_rate": 4.034010499879557e-05,
1359
+ "loss": 1.8015,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.8453159041394336,
1364
+ "grad_norm": 1.5520319938659668,
1365
+ "learning_rate": 4.0135509834589566e-05,
1366
+ "loss": 1.7239,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.8496732026143791,
1371
+ "grad_norm": 0.7724117040634155,
1372
+ "learning_rate": 3.9930381129569696e-05,
1373
+ "loss": 1.6609,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.8540305010893247,
1378
+ "grad_norm": 1.1484628915786743,
1379
+ "learning_rate": 3.972472968186434e-05,
1380
+ "loss": 1.7557,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.8583877995642701,
1385
+ "grad_norm": 1.2805622816085815,
1386
+ "learning_rate": 3.95185663171194e-05,
1387
+ "loss": 1.7035,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.8627450980392157,
1392
+ "grad_norm": 0.890356183052063,
1393
+ "learning_rate": 3.931190188792853e-05,
1394
+ "loss": 1.6805,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.8671023965141612,
1399
+ "grad_norm": 1.8623896837234497,
1400
+ "learning_rate": 3.910474727326175e-05,
1401
+ "loss": 1.6048,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.8714596949891068,
1406
+ "grad_norm": 1.6572378873825073,
1407
+ "learning_rate": 3.8897113377892805e-05,
1408
+ "loss": 1.6146,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.8758169934640523,
1413
+ "grad_norm": 0.8090646862983704,
1414
+ "learning_rate": 3.8689011131825186e-05,
1415
+ "loss": 1.6052,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 0.8801742919389978,
1420
+ "grad_norm": 1.0492998361587524,
1421
+ "learning_rate": 3.8480451489716636e-05,
1422
+ "loss": 1.8196,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 0.8845315904139434,
1427
+ "grad_norm": 0.5649470686912537,
1428
+ "learning_rate": 3.827144543030266e-05,
1429
+ "loss": 1.544,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 0.8888888888888888,
1434
+ "grad_norm": 0.9283618330955505,
1435
+ "learning_rate": 3.806200395581841e-05,
1436
+ "loss": 1.6018,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 0.8932461873638344,
1441
+ "grad_norm": 1.2240904569625854,
1442
+ "learning_rate": 3.785213809141969e-05,
1443
+ "loss": 1.8455,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 0.8976034858387799,
1448
+ "grad_norm": 1.7425321340560913,
1449
+ "learning_rate": 3.764185888460246e-05,
1450
+ "loss": 1.9087,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 0.9019607843137255,
1455
+ "grad_norm": 6.965508460998535,
1456
+ "learning_rate": 3.743117740462135e-05,
1457
+ "loss": 1.8282,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 0.906318082788671,
1462
+ "grad_norm": 1.315513253211975,
1463
+ "learning_rate": 3.722010474190695e-05,
1464
+ "loss": 1.8563,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 0.9106753812636166,
1469
+ "grad_norm": 0.5694398283958435,
1470
+ "learning_rate": 3.700865200748199e-05,
1471
+ "loss": 1.7312,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 0.9150326797385621,
1476
+ "grad_norm": 1.3388159275054932,
1477
+ "learning_rate": 3.679683033237648e-05,
1478
+ "loss": 1.7612,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 0.9193899782135077,
1483
+ "grad_norm": 1.2813358306884766,
1484
+ "learning_rate": 3.658465086704174e-05,
1485
+ "loss": 1.6871,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 0.9237472766884531,
1490
+ "grad_norm": 0.9567870497703552,
1491
+ "learning_rate": 3.6372124780763396e-05,
1492
+ "loss": 1.731,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 0.9281045751633987,
1497
+ "grad_norm": 1.2562271356582642,
1498
+ "learning_rate": 3.6159263261073515e-05,
1499
+ "loss": 1.6309,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 0.9324618736383442,
1504
+ "grad_norm": 1.0945274829864502,
1505
+ "learning_rate": 3.59460775131616e-05,
1506
+ "loss": 1.8533,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 0.9368191721132898,
1511
+ "grad_norm": 0.546955406665802,
1512
+ "learning_rate": 3.5732578759284776e-05,
1513
+ "loss": 1.6818,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 0.9411764705882353,
1518
+ "grad_norm": 0.6648678183555603,
1519
+ "learning_rate": 3.551877823817702e-05,
1520
+ "loss": 1.8012,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 0.9455337690631809,
1525
+ "grad_norm": 0.9706017374992371,
1526
+ "learning_rate": 3.53046872044576e-05,
1527
+ "loss": 1.766,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 0.9498910675381264,
1532
+ "grad_norm": 0.685961127281189,
1533
+ "learning_rate": 3.5090316928038546e-05,
1534
+ "loss": 1.735,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 0.954248366013072,
1539
+ "grad_norm": 1.0843380689620972,
1540
+ "learning_rate": 3.487567869353144e-05,
1541
+ "loss": 1.5208,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 0.9586056644880174,
1546
+ "grad_norm": 0.7091177701950073,
1547
+ "learning_rate": 3.466078379965341e-05,
1548
+ "loss": 1.8162,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 0.9629629629629629,
1553
+ "grad_norm": 0.535933792591095,
1554
+ "learning_rate": 3.4445643558632295e-05,
1555
+ "loss": 1.7281,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 0.9673202614379085,
1560
+ "grad_norm": 0.6523289680480957,
1561
+ "learning_rate": 3.423026929561117e-05,
1562
+ "loss": 1.7759,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 0.971677559912854,
1567
+ "grad_norm": 0.6564977765083313,
1568
+ "learning_rate": 3.401467234805227e-05,
1569
+ "loss": 1.5996,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 0.9760348583877996,
1574
+ "grad_norm": 0.7078843712806702,
1575
+ "learning_rate": 3.379886406514004e-05,
1576
+ "loss": 1.6532,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 0.9803921568627451,
1581
+ "grad_norm": 0.7516049742698669,
1582
+ "learning_rate": 3.358285580718383e-05,
1583
+ "loss": 1.5464,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 0.9847494553376906,
1588
+ "grad_norm": 0.7365531325340271,
1589
+ "learning_rate": 3.336665894501977e-05,
1590
+ "loss": 1.7292,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 0.9891067538126361,
1595
+ "grad_norm": 0.9807084202766418,
1596
+ "learning_rate": 3.315028485941233e-05,
1597
+ "loss": 1.4769,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 0.9934640522875817,
1602
+ "grad_norm": 0.7513118386268616,
1603
+ "learning_rate": 3.293374494045507e-05,
1604
+ "loss": 1.8098,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 0.9978213507625272,
1609
+ "grad_norm": 0.7991335988044739,
1610
+ "learning_rate": 3.271705058697122e-05,
1611
+ "loss": 1.7686,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 1.0,
1616
+ "grad_norm": 1.0507432222366333,
1617
+ "learning_rate": 3.2500213205913506e-05,
1618
+ "loss": 0.9588,
1619
+ "step": 230
1620
+ }
1621
+ ],
1622
+ "logging_steps": 1,
1623
+ "max_steps": 458,
1624
+ "num_input_tokens_seen": 0,
1625
+ "num_train_epochs": 2,
1626
+ "save_steps": 23,
1627
+ "stateful_callbacks": {
1628
+ "TrainerControl": {
1629
+ "args": {
1630
+ "should_epoch_stop": false,
1631
+ "should_evaluate": false,
1632
+ "should_log": false,
1633
+ "should_save": true,
1634
+ "should_training_stop": false
1635
+ },
1636
+ "attributes": {}
1637
+ }
1638
+ },
1639
+ "total_flos": 3.9962116695030497e+18,
1640
+ "train_batch_size": 8,
1641
+ "trial_name": null,
1642
+ "trial_params": null
1643
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b842a33b4b9b2b888314b9c7168594787bf5385c08705a9a590a7af6200a9389
3
+ size 6904