Doctor-Shotgun commited on
Commit
15e6f3e
1 Parent(s): 99a6a6d

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,137 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: volume/limarp-70b-qlora
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
14
+ <details><summary>See axolotl config</summary>
15
+
16
+ axolotl version: `0.4.0`
17
+ ```yaml
18
+ base_model: models/miqu-1-70b-sf
19
+ model_type: LlamaForCausalLM
20
+ tokenizer_type: LlamaTokenizer
21
+ is_llama_derived_model: true
22
+
23
+ load_in_8bit: false
24
+ load_in_4bit: true
25
+ strict: false
26
+
27
+ datasets:
28
+ - path: train-all-max-alpaca-llama.jsonl
29
+ type: completion
30
+ dataset_prepared_path:
31
+ val_set_size: 0.0
32
+ output_dir: ./volume/limarp-70b-qlora
33
+
34
+ adapter: qlora
35
+ lora_model_dir:
36
+
37
+ sequence_len: 16384
38
+ sample_packing: true
39
+ pad_to_sequence_len: true
40
+
41
+ lora_r: 32
42
+ lora_alpha: 16
43
+ lora_dropout: 0.05
44
+ lora_target_modules:
45
+ lora_target_linear: true
46
+ lora_fan_in_fan_out:
47
+
48
+ wandb_project: 70b-lora
49
+ wandb_entity:
50
+ wandb_watch:
51
+ wandb_name:
52
+ wandb_log_model:
53
+
54
+ gradient_accumulation_steps: 4
55
+ micro_batch_size: 1
56
+ num_epochs: 2
57
+ optimizer: adamw_bnb_8bit
58
+ lr_scheduler: cosine
59
+ learning_rate: 0.0001
60
+
61
+ train_on_inputs: true
62
+ group_by_length: false
63
+ bf16: true
64
+ fp16: false
65
+ tf32: true
66
+
67
+ gradient_checkpointing: true
68
+ gradient_checkpointing_kwargs:
69
+ use_reentrant: true
70
+ early_stopping_patience:
71
+ resume_from_checkpoint:
72
+ local_rank:
73
+ logging_steps: 1
74
+ xformers_attention:
75
+ flash_attention: true
76
+
77
+ warmup_steps: 10
78
+ eval_steps:
79
+ eval_table_size:
80
+ save_steps:
81
+ debug:
82
+ deepspeed:
83
+ weight_decay: 0.0
84
+ fsdp:
85
+ fsdp_config:
86
+ special_tokens:
87
+ bos_token: "<s>"
88
+ eos_token: "</s>"
89
+ unk_token: "<unk>"
90
+
91
+ ```
92
+
93
+ </details><br>
94
+
95
+ # volume/limarp-70b-qlora
96
+
97
+ This model was trained from scratch on the None dataset.
98
+
99
+ ## Model description
100
+
101
+ More information needed
102
+
103
+ ## Intended uses & limitations
104
+
105
+ More information needed
106
+
107
+ ## Training and evaluation data
108
+
109
+ More information needed
110
+
111
+ ## Training procedure
112
+
113
+ ### Training hyperparameters
114
+
115
+ The following hyperparameters were used during training:
116
+ - learning_rate: 0.0001
117
+ - train_batch_size: 1
118
+ - eval_batch_size: 1
119
+ - seed: 42
120
+ - gradient_accumulation_steps: 4
121
+ - total_train_batch_size: 4
122
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
123
+ - lr_scheduler_type: cosine
124
+ - lr_scheduler_warmup_steps: 10
125
+ - num_epochs: 2
126
+
127
+ ### Training results
128
+
129
+
130
+
131
+ ### Framework versions
132
+
133
+ - PEFT 0.7.2.dev0
134
+ - Transformers 4.37.0
135
+ - Pytorch 2.1.2+cu118
136
+ - Datasets 2.16.1
137
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "models/miqu-1-70b-sf",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 32,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "up_proj",
23
+ "v_proj",
24
+ "down_proj",
25
+ "k_proj",
26
+ "gate_proj",
27
+ "q_proj",
28
+ "o_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": false
32
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dceb80d1e7f9a1bc2c49a2be6073bb284b680f9a074f73f662a4ab7bd4cf367b
3
+ size 1657155202
checkpoint-169/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: models/miqu-1-70b-sf
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
+
201
+
202
+ ### Framework versions
203
+
204
+ - PEFT 0.7.2.dev0
checkpoint-169/adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "models/miqu-1-70b-sf",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 32,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "up_proj",
23
+ "v_proj",
24
+ "down_proj",
25
+ "k_proj",
26
+ "gate_proj",
27
+ "q_proj",
28
+ "o_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": false
32
+ }
checkpoint-169/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4033f04ee0a34017f8b1dba72e38a3e644e22c3764beb368ea077f8b1626673
3
+ size 1656902648
checkpoint-169/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d72b0e0941488683421f5371635c5ffcb035ce6099e55cf1d9fcdd290725817
3
+ size 831305300
checkpoint-169/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f92a69bdd4b0dbba88379df9544068d377fbbf9b2f7bd75ec7953d5cc0f4377
3
+ size 14244
checkpoint-169/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37ba009646cdc3da3968e4818e396351d8fd70d5c95ae79461d7c8052763d65d
3
+ size 1064
checkpoint-169/trainer_state.json ADDED
@@ -0,0 +1,1035 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.027355623100304,
5
+ "eval_steps": 500,
6
+ "global_step": 169,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 1e-05,
14
+ "loss": 1.897,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 2e-05,
20
+ "loss": 1.9202,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "learning_rate": 3e-05,
26
+ "loss": 1.9071,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 4e-05,
32
+ "loss": 1.9712,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.03,
37
+ "learning_rate": 5e-05,
38
+ "loss": 2.0125,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.04,
43
+ "learning_rate": 6e-05,
44
+ "loss": 1.8839,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.04,
49
+ "learning_rate": 7e-05,
50
+ "loss": 1.9586,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.05,
55
+ "learning_rate": 8e-05,
56
+ "loss": 1.9625,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.05,
61
+ "learning_rate": 9e-05,
62
+ "loss": 1.9269,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.06,
67
+ "learning_rate": 0.0001,
68
+ "loss": 1.9005,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.07,
73
+ "learning_rate": 9.999756004407229e-05,
74
+ "loss": 1.857,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.07,
79
+ "learning_rate": 9.999024041442456e-05,
80
+ "loss": 1.9072,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.08,
85
+ "learning_rate": 9.997804182543973e-05,
86
+ "loss": 1.7945,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.09,
91
+ "learning_rate": 9.99609654676786e-05,
92
+ "loss": 1.8496,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.09,
97
+ "learning_rate": 9.993901300776359e-05,
98
+ "loss": 1.8275,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.1,
103
+ "learning_rate": 9.991218658821608e-05,
104
+ "loss": 1.8701,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.1,
109
+ "learning_rate": 9.988048882724732e-05,
110
+ "loss": 1.8594,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.11,
115
+ "learning_rate": 9.984392281850293e-05,
116
+ "loss": 1.8669,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.12,
121
+ "learning_rate": 9.980249213076084e-05,
122
+ "loss": 1.8022,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.12,
127
+ "learning_rate": 9.97562008075832e-05,
128
+ "loss": 1.8139,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.13,
133
+ "learning_rate": 9.970505336692153e-05,
134
+ "loss": 1.8775,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.13,
139
+ "learning_rate": 9.964905480067586e-05,
140
+ "loss": 1.7862,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.14,
145
+ "learning_rate": 9.958821057420754e-05,
146
+ "loss": 1.8414,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.15,
151
+ "learning_rate": 9.952252662580579e-05,
152
+ "loss": 1.7446,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.15,
157
+ "learning_rate": 9.94520093661082e-05,
158
+ "loss": 1.8705,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.16,
163
+ "learning_rate": 9.937666567747501e-05,
164
+ "loss": 1.822,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.16,
169
+ "learning_rate": 9.92965029133174e-05,
170
+ "loss": 1.9357,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.17,
175
+ "learning_rate": 9.921152889737984e-05,
176
+ "loss": 1.7958,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.18,
181
+ "learning_rate": 9.912175192297648e-05,
182
+ "loss": 1.7557,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.18,
187
+ "learning_rate": 9.902718075218176e-05,
188
+ "loss": 1.8138,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.19,
193
+ "learning_rate": 9.89278246149752e-05,
194
+ "loss": 1.7865,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.19,
199
+ "learning_rate": 9.882369320834069e-05,
200
+ "loss": 1.7997,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.2,
205
+ "learning_rate": 9.87147966953199e-05,
206
+ "loss": 1.7534,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.21,
211
+ "learning_rate": 9.860114570402054e-05,
212
+ "loss": 1.7092,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.21,
217
+ "learning_rate": 9.848275132657903e-05,
218
+ "loss": 1.7261,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.22,
223
+ "learning_rate": 9.835962511807786e-05,
224
+ "loss": 1.7827,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.22,
229
+ "learning_rate": 9.823177909541794e-05,
230
+ "loss": 1.7948,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.23,
235
+ "learning_rate": 9.809922573614569e-05,
236
+ "loss": 1.8275,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.24,
241
+ "learning_rate": 9.796197797723532e-05,
242
+ "loss": 1.7533,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.24,
247
+ "learning_rate": 9.782004921382612e-05,
248
+ "loss": 1.7555,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.25,
253
+ "learning_rate": 9.767345329791522e-05,
254
+ "loss": 1.8018,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.26,
259
+ "learning_rate": 9.752220453700556e-05,
260
+ "loss": 1.8107,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.26,
265
+ "learning_rate": 9.736631769270957e-05,
266
+ "loss": 1.7941,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.27,
271
+ "learning_rate": 9.720580797930845e-05,
272
+ "loss": 1.8829,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.27,
277
+ "learning_rate": 9.704069106226727e-05,
278
+ "loss": 1.8041,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.28,
283
+ "learning_rate": 9.687098305670605e-05,
284
+ "loss": 1.77,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.29,
289
+ "learning_rate": 9.669670052582695e-05,
290
+ "loss": 1.7547,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.29,
295
+ "learning_rate": 9.651786047929773e-05,
296
+ "loss": 1.7594,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.3,
301
+ "learning_rate": 9.633448037159167e-05,
302
+ "loss": 1.7076,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.3,
307
+ "learning_rate": 9.614657810028402e-05,
308
+ "loss": 1.786,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.31,
313
+ "learning_rate": 9.595417200430516e-05,
314
+ "loss": 1.7076,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.32,
319
+ "learning_rate": 9.575728086215092e-05,
320
+ "loss": 1.7508,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.32,
325
+ "learning_rate": 9.555592389004966e-05,
326
+ "loss": 1.7979,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.33,
331
+ "learning_rate": 9.535012074008687e-05,
332
+ "loss": 1.7075,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.33,
337
+ "learning_rate": 9.513989149828718e-05,
338
+ "loss": 1.7828,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.34,
343
+ "learning_rate": 9.492525668265399e-05,
344
+ "loss": 1.8179,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.35,
349
+ "learning_rate": 9.470623724116692e-05,
350
+ "loss": 1.7802,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.35,
355
+ "learning_rate": 9.448285454973738e-05,
356
+ "loss": 1.7873,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.36,
361
+ "learning_rate": 9.425513041012219e-05,
362
+ "loss": 1.7315,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.36,
367
+ "learning_rate": 9.402308704779599e-05,
368
+ "loss": 1.7953,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.37,
373
+ "learning_rate": 9.378674710978185e-05,
374
+ "loss": 1.7946,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.38,
379
+ "learning_rate": 9.354613366244108e-05,
380
+ "loss": 1.7543,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.38,
385
+ "learning_rate": 9.330127018922194e-05,
386
+ "loss": 1.7302,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.39,
391
+ "learning_rate": 9.305218058836778e-05,
392
+ "loss": 1.8224,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.4,
397
+ "learning_rate": 9.279888917058452e-05,
398
+ "loss": 1.757,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.4,
403
+ "learning_rate": 9.254142065666801e-05,
404
+ "loss": 1.7506,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.41,
409
+ "learning_rate": 9.22798001750913e-05,
410
+ "loss": 1.7523,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.41,
415
+ "learning_rate": 9.201405325955221e-05,
416
+ "loss": 1.7923,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.42,
421
+ "learning_rate": 9.174420584648123e-05,
422
+ "loss": 1.7417,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.43,
427
+ "learning_rate": 9.14702842725101e-05,
428
+ "loss": 1.8008,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.43,
433
+ "learning_rate": 9.119231527190158e-05,
434
+ "loss": 1.7204,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.44,
439
+ "learning_rate": 9.091032597394012e-05,
440
+ "loss": 1.7863,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.44,
445
+ "learning_rate": 9.062434390028407e-05,
446
+ "loss": 1.7512,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.45,
451
+ "learning_rate": 9.033439696227965e-05,
452
+ "loss": 1.8159,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.46,
457
+ "learning_rate": 9.004051345823689e-05,
458
+ "loss": 1.7654,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.46,
463
+ "learning_rate": 8.974272207066767e-05,
464
+ "loss": 1.712,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.47,
469
+ "learning_rate": 8.944105186348646e-05,
470
+ "loss": 1.7975,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.47,
475
+ "learning_rate": 8.913553227917367e-05,
476
+ "loss": 1.7364,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.48,
481
+ "learning_rate": 8.882619313590212e-05,
482
+ "loss": 1.7615,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.49,
487
+ "learning_rate": 8.851306462462688e-05,
488
+ "loss": 1.6968,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.49,
493
+ "learning_rate": 8.819617730613862e-05,
494
+ "loss": 1.7455,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.5,
499
+ "learning_rate": 8.787556210808101e-05,
500
+ "loss": 1.8118,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.5,
505
+ "learning_rate": 8.755125032193214e-05,
506
+ "loss": 1.7766,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.51,
511
+ "learning_rate": 8.722327359995064e-05,
512
+ "loss": 1.7388,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.52,
517
+ "learning_rate": 8.689166395208636e-05,
518
+ "loss": 1.6951,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.52,
523
+ "learning_rate": 8.655645374285637e-05,
524
+ "loss": 1.8524,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.53,
529
+ "learning_rate": 8.621767568818613e-05,
530
+ "loss": 1.8439,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.53,
535
+ "learning_rate": 8.587536285221656e-05,
536
+ "loss": 1.7917,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.54,
541
+ "learning_rate": 8.552954864407699e-05,
542
+ "loss": 1.7381,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.55,
547
+ "learning_rate": 8.518026681462448e-05,
548
+ "loss": 1.7198,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.55,
553
+ "learning_rate": 8.482755145314986e-05,
554
+ "loss": 1.7388,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.56,
559
+ "learning_rate": 8.44714369840506e-05,
560
+ "loss": 1.7147,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.57,
565
+ "learning_rate": 8.41119581634711e-05,
566
+ "loss": 1.7247,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.57,
571
+ "learning_rate": 8.374915007591053e-05,
572
+ "loss": 1.7975,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.58,
577
+ "learning_rate": 8.338304813079865e-05,
578
+ "loss": 1.6963,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.58,
583
+ "learning_rate": 8.301368805903988e-05,
584
+ "loss": 1.7466,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.59,
589
+ "learning_rate": 8.264110590952609e-05,
590
+ "loss": 1.8162,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.6,
595
+ "learning_rate": 8.226533804561827e-05,
596
+ "loss": 1.8318,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.6,
601
+ "learning_rate": 8.188642114159747e-05,
602
+ "loss": 1.8107,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.61,
607
+ "learning_rate": 8.150439217908556e-05,
608
+ "loss": 1.7286,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.61,
613
+ "learning_rate": 8.11192884434358e-05,
614
+ "loss": 1.8096,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.62,
619
+ "learning_rate": 8.073114752009387e-05,
620
+ "loss": 1.7905,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.63,
625
+ "learning_rate": 8.034000729092968e-05,
626
+ "loss": 1.8094,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.63,
631
+ "learning_rate": 7.994590593054001e-05,
632
+ "loss": 1.7906,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.64,
637
+ "learning_rate": 7.954888190252292e-05,
638
+ "loss": 1.8019,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.64,
643
+ "learning_rate": 7.91489739557236e-05,
644
+ "loss": 1.7756,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.65,
649
+ "learning_rate": 7.874622112045269e-05,
650
+ "loss": 1.7668,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.66,
655
+ "learning_rate": 7.83406627046769e-05,
656
+ "loss": 1.7509,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.66,
661
+ "learning_rate": 7.793233829018262e-05,
662
+ "loss": 1.8472,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.67,
667
+ "learning_rate": 7.752128772871292e-05,
668
+ "loss": 1.7917,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.67,
673
+ "learning_rate": 7.710755113807794e-05,
674
+ "loss": 1.7408,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.68,
679
+ "learning_rate": 7.669116889823955e-05,
680
+ "loss": 1.6748,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.69,
685
+ "learning_rate": 7.627218164737031e-05,
686
+ "loss": 1.8016,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.69,
691
+ "learning_rate": 7.585063027788731e-05,
692
+ "loss": 1.7302,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.7,
697
+ "learning_rate": 7.542655593246103e-05,
698
+ "loss": 1.735,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.71,
703
+ "learning_rate": 7.500000000000001e-05,
704
+ "loss": 1.777,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.71,
709
+ "learning_rate": 7.457100411161128e-05,
710
+ "loss": 1.7049,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.72,
715
+ "learning_rate": 7.413961013653726e-05,
716
+ "loss": 1.826,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.72,
721
+ "learning_rate": 7.370586017806942e-05,
722
+ "loss": 1.7539,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.73,
727
+ "learning_rate": 7.326979656943906e-05,
728
+ "loss": 1.6597,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.74,
733
+ "learning_rate": 7.283146186968565e-05,
734
+ "loss": 1.7977,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.74,
739
+ "learning_rate": 7.239089885950316e-05,
740
+ "loss": 1.7501,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.75,
745
+ "learning_rate": 7.19481505370647e-05,
746
+ "loss": 1.7521,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.75,
751
+ "learning_rate": 7.150326011382604e-05,
752
+ "loss": 1.7778,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.76,
757
+ "learning_rate": 7.105627101030817e-05,
758
+ "loss": 1.7793,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.77,
763
+ "learning_rate": 7.060722685185961e-05,
764
+ "loss": 1.8148,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.77,
769
+ "learning_rate": 7.015617146439863e-05,
770
+ "loss": 1.7838,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.78,
775
+ "learning_rate": 6.970314887013584e-05,
776
+ "loss": 1.796,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.78,
781
+ "learning_rate": 6.924820328327786e-05,
782
+ "loss": 1.832,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.79,
787
+ "learning_rate": 6.879137910571191e-05,
788
+ "loss": 1.7494,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.8,
793
+ "learning_rate": 6.833272092267241e-05,
794
+ "loss": 1.7762,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.8,
799
+ "learning_rate": 6.787227349838947e-05,
800
+ "loss": 1.7136,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.81,
805
+ "learning_rate": 6.741008177171995e-05,
806
+ "loss": 1.7987,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.81,
811
+ "learning_rate": 6.694619085176159e-05,
812
+ "loss": 1.7855,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.82,
817
+ "learning_rate": 6.64806460134504e-05,
818
+ "loss": 1.801,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.83,
823
+ "learning_rate": 6.601349269314188e-05,
824
+ "loss": 1.6862,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.83,
829
+ "learning_rate": 6.554477648417657e-05,
830
+ "loss": 1.7124,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.84,
835
+ "learning_rate": 6.507454313243015e-05,
836
+ "loss": 1.7362,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.84,
841
+ "learning_rate": 6.460283853184879e-05,
842
+ "loss": 1.6903,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.85,
847
+ "learning_rate": 6.412970871996995e-05,
848
+ "loss": 1.7153,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.86,
853
+ "learning_rate": 6.365519987342917e-05,
854
+ "loss": 1.7335,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.86,
859
+ "learning_rate": 6.317935830345338e-05,
860
+ "loss": 1.7567,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.87,
865
+ "learning_rate": 6.270223045134096e-05,
866
+ "loss": 1.7885,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.88,
871
+ "learning_rate": 6.222386288392913e-05,
872
+ "loss": 1.8316,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.88,
877
+ "learning_rate": 6.174430228904919e-05,
878
+ "loss": 1.7411,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.89,
883
+ "learning_rate": 6.126359547096975e-05,
884
+ "loss": 1.7384,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.89,
889
+ "learning_rate": 6.078178934582885e-05,
890
+ "loss": 1.7717,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.9,
895
+ "learning_rate": 6.029893093705492e-05,
896
+ "loss": 1.7984,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.91,
901
+ "learning_rate": 5.981506737077744e-05,
902
+ "loss": 1.7875,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.91,
907
+ "learning_rate": 5.9330245871227454e-05,
908
+ "loss": 1.762,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.92,
913
+ "learning_rate": 5.884451375612865e-05,
914
+ "loss": 1.7517,
915
+ "step": 151
916
+ },
917
+ {
918
+