stringtron commited on
Commit
5825b71
1 Parent(s): 41d5770

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: bigcode-openrail-m
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: aurora-m/aurora-m-v0.1
7
+ model-index:
8
+ - name: lora-out
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ [<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)
16
+ <details><summary>See axolotl config</summary>
17
+
18
+ axolotl version: `0.4.0`
19
+ ```yaml
20
+ base_model: aurora-m/aurora-m-v0.1 # this can be swapped for mdel model when the model is released
21
+ model_type: AutoModelForCausalLM
22
+ tokenizer_type: AutoTokenizer
23
+ is_llama_derived_model: false
24
+
25
+ load_in_8bit: false # when this is true inference quality is terrible
26
+ load_in_4bit: false
27
+ strict: false
28
+
29
+ datasets:
30
+ - path: /workspace/axolotl-mdel/mtg.txt # change this to where your dataset is
31
+ type: completion # change this to 'alpaca' if you are using alpaca formatting
32
+
33
+ lora_modules_to_save:
34
+ - embed_tokens
35
+ - lm_head
36
+
37
+ dataset_prepared_path:
38
+ val_set_size: 0.05
39
+ output_dir: ./lora-out
40
+
41
+ sequence_len: 4096 # this can be tweaked for efficiency
42
+ sample_packing: true
43
+ pad_to_sequence_len: true
44
+
45
+ adapter: lora
46
+ lora_model_dir:
47
+ lora_r: 32
48
+ lora_alpha: 16
49
+ lora_dropout: 0.05
50
+ lora_target_linear: true
51
+ lora_fan_in_fan_out:
52
+
53
+ wandb_project: mtg-aurora-test-Mike # give this a name
54
+ wandb_entity:
55
+ wandb_watch:
56
+ wandb_name:
57
+ wandb_log_model:
58
+
59
+ gradient_accumulation_steps: 2 # this can be tweaked for efficiency
60
+ micro_batch_size: 1 # this can be tweaked for efficiency
61
+ num_epochs: 1 # this can be experimented with
62
+ optimizer: adamw_bnb_8bit
63
+ lr_scheduler: cosine
64
+ learning_rate: 0.0002
65
+
66
+ train_on_inputs: true
67
+ group_by_length: false
68
+ bf16: true
69
+ fp16: false
70
+ tf32: false
71
+
72
+ gradient_checkpointing: true
73
+ early_stopping_patience:
74
+ resume_from_checkpoint:
75
+ local_rank:
76
+ logging_steps: 1
77
+ xformers_attention:
78
+ flash_attention: false # when this is true, inference quality is terrible
79
+ s2_attention:
80
+
81
+ warmup_steps: 10 # this can be tweaked for efficiency
82
+ evals_per_epoch: 10 # this can be tweaked for efficiency
83
+ eval_table_size:
84
+ eval_table_max_new_tokens: 128
85
+ saves_per_epoch: 1
86
+ debug:
87
+ deepspeed:
88
+ weight_decay: 0.0
89
+ fsdp:
90
+ fsdp_config:
91
+ special_tokens:
92
+ pad_token: "<|endoftext|>"
93
+ eos_token: "<|endoftext|>"
94
+
95
+ ```
96
+
97
+ </details><br>
98
+
99
+ # lora-out
100
+
101
+ This model is a fine-tuned version of [aurora-m/aurora-m-v0.1](https://huggingface.co/aurora-m/aurora-m-v0.1) on the None dataset.
102
+ It achieves the following results on the evaluation set:
103
+ - Loss: 0.7942
104
+
105
+ ## Model description
106
+
107
+ More information needed
108
+
109
+ ## Intended uses & limitations
110
+
111
+ More information needed
112
+
113
+ ## Training and evaluation data
114
+
115
+ More information needed
116
+
117
+ ## Training procedure
118
+
119
+ ### Training hyperparameters
120
+
121
+ The following hyperparameters were used during training:
122
+ - learning_rate: 0.0002
123
+ - train_batch_size: 1
124
+ - eval_batch_size: 1
125
+ - seed: 42
126
+ - gradient_accumulation_steps: 2
127
+ - total_train_batch_size: 2
128
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
129
+ - lr_scheduler_type: cosine
130
+ - lr_scheduler_warmup_steps: 10
131
+ - num_epochs: 1
132
+
133
+ ### Training results
134
+
135
+ | Training Loss | Epoch | Step | Validation Loss |
136
+ |:-------------:|:-----:|:----:|:---------------:|
137
+ | 4.2833 | 0.0 | 1 | 4.0842 |
138
+ | 2.1913 | 0.1 | 25 | 1.9823 |
139
+ | 1.2729 | 0.21 | 50 | 1.2218 |
140
+ | 1.0634 | 0.31 | 75 | 1.0093 |
141
+ | 0.9576 | 0.41 | 100 | 0.9341 |
142
+ | 0.9326 | 0.52 | 125 | 0.8691 |
143
+ | 0.8558 | 0.62 | 150 | 0.8325 |
144
+ | 0.8218 | 0.73 | 175 | 0.8047 |
145
+ | 0.8579 | 0.83 | 200 | 0.7980 |
146
+ | 0.9001 | 0.93 | 225 | 0.7942 |
147
+
148
+
149
+ ### Framework versions
150
+
151
+ - PEFT 0.8.2
152
+ - Transformers 4.38.0.dev0
153
+ - Pytorch 2.1.2+cu118
154
+ - Datasets 2.16.1
155
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "aurora-m/aurora-m-v0.1",
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": [
17
+ "embed_tokens",
18
+ "lm_head"
19
+ ],
20
+ "peft_type": "LORA",
21
+ "r": 32,
22
+ "rank_pattern": {},
23
+ "revision": null,
24
+ "target_modules": [
25
+ "c_proj",
26
+ "c_fc",
27
+ "c_attn"
28
+ ],
29
+ "task_type": "CAUSAL_LM",
30
+ "use_rslora": false
31
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0632dcaf9a9592c4f7e57c76254e946e9b46f40d5452c3bb18fd921ffc62c4d3
3
+ size 1429029714
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<filename>": 49152,
3
+ "<gh_stars>": 49153,
4
+ "<issue_comment>": 49155,
5
+ "<issue_start>": 49154
6
+ }
checkpoint-241/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: aurora-m/aurora-m-v0.1
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 0.8.2
checkpoint-241/adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "aurora-m/aurora-m-v0.1",
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": [
17
+ "embed_tokens",
18
+ "lm_head"
19
+ ],
20
+ "peft_type": "LORA",
21
+ "r": 32,
22
+ "rank_pattern": {},
23
+ "revision": null,
24
+ "target_modules": [
25
+ "c_proj",
26
+ "c_fc",
27
+ "c_attn"
28
+ ],
29
+ "task_type": "CAUSAL_LM",
30
+ "use_rslora": false
31
+ }
checkpoint-241/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42886f2edbedc24c7086096790354d5cf5f7d47174b83a69e73664aaaf496f24
3
+ size 2637015752
checkpoint-241/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c04fadc43d9bcc0ca03b98c73cfbd6d9cb32802e5c019bc715566a20cb50b61
3
+ size 826871704
checkpoint-241/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f24e00645cc08087bf206cfd932ba5f0fece885d758b0fc1e9060d777e7eebef
3
+ size 14244
checkpoint-241/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5939dffaffa27516a665d7288c4418204f16cc2c1fee3d39b441522b0b2ae897
3
+ size 1064
checkpoint-241/trainer_state.json ADDED
@@ -0,0 +1,1547 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 25,
6
+ "global_step": 241,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 2e-05,
14
+ "loss": 4.2833,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "eval_loss": 4.084170341491699,
20
+ "eval_runtime": 31.753,
21
+ "eval_samples_per_second": 42.484,
22
+ "eval_steps_per_second": 42.484,
23
+ "step": 1
24
+ },
25
+ {
26
+ "epoch": 0.01,
27
+ "learning_rate": 4e-05,
28
+ "loss": 4.1902,
29
+ "step": 2
30
+ },
31
+ {
32
+ "epoch": 0.01,
33
+ "learning_rate": 6e-05,
34
+ "loss": 4.1948,
35
+ "step": 3
36
+ },
37
+ {
38
+ "epoch": 0.02,
39
+ "learning_rate": 8e-05,
40
+ "loss": 4.1128,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.02,
45
+ "learning_rate": 0.0001,
46
+ "loss": 3.8583,
47
+ "step": 5
48
+ },
49
+ {
50
+ "epoch": 0.02,
51
+ "learning_rate": 0.00012,
52
+ "loss": 3.5261,
53
+ "step": 6
54
+ },
55
+ {
56
+ "epoch": 0.03,
57
+ "learning_rate": 0.00014,
58
+ "loss": 3.3442,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.03,
63
+ "learning_rate": 0.00016,
64
+ "loss": 3.2207,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.04,
69
+ "learning_rate": 0.00018,
70
+ "loss": 3.1737,
71
+ "step": 9
72
+ },
73
+ {
74
+ "epoch": 0.04,
75
+ "learning_rate": 0.0002,
76
+ "loss": 2.9994,
77
+ "step": 10
78
+ },
79
+ {
80
+ "epoch": 0.05,
81
+ "learning_rate": 0.00019999075218579183,
82
+ "loss": 2.8883,
83
+ "step": 11
84
+ },
85
+ {
86
+ "epoch": 0.05,
87
+ "learning_rate": 0.00019996301045360873,
88
+ "loss": 2.7732,
89
+ "step": 12
90
+ },
91
+ {
92
+ "epoch": 0.05,
93
+ "learning_rate": 0.0001999167799344583,
94
+ "loss": 2.7801,
95
+ "step": 13
96
+ },
97
+ {
98
+ "epoch": 0.06,
99
+ "learning_rate": 0.00019985206917896563,
100
+ "loss": 2.6675,
101
+ "step": 14
102
+ },
103
+ {
104
+ "epoch": 0.06,
105
+ "learning_rate": 0.00019976889015579165,
106
+ "loss": 2.5948,
107
+ "step": 15
108
+ },
109
+ {
110
+ "epoch": 0.07,
111
+ "learning_rate": 0.00019966725824941932,
112
+ "loss": 2.4837,
113
+ "step": 16
114
+ },
115
+ {
116
+ "epoch": 0.07,
117
+ "learning_rate": 0.00019954719225730847,
118
+ "loss": 2.4834,
119
+ "step": 17
120
+ },
121
+ {
122
+ "epoch": 0.07,
123
+ "learning_rate": 0.00019940871438641882,
124
+ "loss": 2.4078,
125
+ "step": 18
126
+ },
127
+ {
128
+ "epoch": 0.08,
129
+ "learning_rate": 0.00019925185024910277,
130
+ "loss": 2.4653,
131
+ "step": 19
132
+ },
133
+ {
134
+ "epoch": 0.08,
135
+ "learning_rate": 0.00019907662885836836,
136
+ "loss": 2.4306,
137
+ "step": 20
138
+ },
139
+ {
140
+ "epoch": 0.09,
141
+ "learning_rate": 0.00019888308262251285,
142
+ "loss": 2.3513,
143
+ "step": 21
144
+ },
145
+ {
146
+ "epoch": 0.09,
147
+ "learning_rate": 0.0001986712473391289,
148
+ "loss": 2.3479,
149
+ "step": 22
150
+ },
151
+ {
152
+ "epoch": 0.1,
153
+ "learning_rate": 0.00019844116218848334,
154
+ "loss": 2.2955,
155
+ "step": 23
156
+ },
157
+ {
158
+ "epoch": 0.1,
159
+ "learning_rate": 0.00019819286972627066,
160
+ "loss": 2.1092,
161
+ "step": 24
162
+ },
163
+ {
164
+ "epoch": 0.1,
165
+ "learning_rate": 0.00019792641587574212,
166
+ "loss": 2.1913,
167
+ "step": 25
168
+ },
169
+ {
170
+ "epoch": 0.1,
171
+ "eval_loss": 1.9823017120361328,
172
+ "eval_runtime": 32.6562,
173
+ "eval_samples_per_second": 41.309,
174
+ "eval_steps_per_second": 41.309,
175
+ "step": 25
176
+ },
177
+ {
178
+ "epoch": 0.11,
179
+ "learning_rate": 0.00019764184991921178,
180
+ "loss": 2.1422,
181
+ "step": 26
182
+ },
183
+ {
184
+ "epoch": 0.11,
185
+ "learning_rate": 0.0001973392244889415,
186
+ "loss": 2.0439,
187
+ "step": 27
188
+ },
189
+ {
190
+ "epoch": 0.12,
191
+ "learning_rate": 0.00019701859555740648,
192
+ "loss": 2.0627,
193
+ "step": 28
194
+ },
195
+ {
196
+ "epoch": 0.12,
197
+ "learning_rate": 0.00019668002242694238,
198
+ "loss": 2.0766,
199
+ "step": 29
200
+ },
201
+ {
202
+ "epoch": 0.12,
203
+ "learning_rate": 0.00019632356771877735,
204
+ "loss": 1.888,
205
+ "step": 30
206
+ },
207
+ {
208
+ "epoch": 0.13,
209
+ "learning_rate": 0.00019594929736144976,
210
+ "loss": 1.8309,
211
+ "step": 31
212
+ },
213
+ {
214
+ "epoch": 0.13,
215
+ "learning_rate": 0.0001955572805786141,
216
+ "loss": 1.8954,
217
+ "step": 32
218
+ },
219
+ {
220
+ "epoch": 0.14,
221
+ "learning_rate": 0.00019514758987623784,
222
+ "loss": 1.7275,
223
+ "step": 33
224
+ },
225
+ {
226
+ "epoch": 0.14,
227
+ "learning_rate": 0.000194720301029191,
228
+ "loss": 1.7485,
229
+ "step": 34
230
+ },
231
+ {
232
+ "epoch": 0.15,
233
+ "learning_rate": 0.00019427549306723097,
234
+ "loss": 1.715,
235
+ "step": 35
236
+ },
237
+ {
238
+ "epoch": 0.15,
239
+ "learning_rate": 0.0001938132482603856,
240
+ "loss": 1.6701,
241
+ "step": 36
242
+ },
243
+ {
244
+ "epoch": 0.15,
245
+ "learning_rate": 0.0001933336521037367,
246
+ "loss": 1.625,
247
+ "step": 37
248
+ },
249
+ {
250
+ "epoch": 0.16,
251
+ "learning_rate": 0.00019283679330160726,
252
+ "loss": 1.6836,
253
+ "step": 38
254
+ },
255
+ {
256
+ "epoch": 0.16,
257
+ "learning_rate": 0.00019232276375115515,
258
+ "loss": 1.5382,
259
+ "step": 39
260
+ },
261
+ {
262
+ "epoch": 0.17,
263
+ "learning_rate": 0.00019179165852537596,
264
+ "loss": 1.6118,
265
+ "step": 40
266
+ },
267
+ {
268
+ "epoch": 0.17,
269
+ "learning_rate": 0.00019124357585551872,
270
+ "loss": 1.463,
271
+ "step": 41
272
+ },
273
+ {
274
+ "epoch": 0.17,
275
+ "learning_rate": 0.00019067861711291744,
276
+ "loss": 1.4755,
277
+ "step": 42
278
+ },
279
+ {
280
+ "epoch": 0.18,
281
+ "learning_rate": 0.0001900968867902419,
282
+ "loss": 1.4729,
283
+ "step": 43
284
+ },
285
+ {
286
+ "epoch": 0.18,
287
+ "learning_rate": 0.000189498492482171,
288
+ "loss": 1.4846,
289
+ "step": 44
290
+ },
291
+ {
292
+ "epoch": 0.19,
293
+ "learning_rate": 0.00018888354486549237,
294
+ "loss": 1.3988,
295
+ "step": 45
296
+ },
297
+ {
298
+ "epoch": 0.19,
299
+ "learning_rate": 0.00018825215767863214,
300
+ "loss": 1.4139,
301
+ "step": 46
302
+ },
303
+ {
304
+ "epoch": 0.2,
305
+ "learning_rate": 0.0001876044477006183,
306
+ "loss": 1.3069,
307
+ "step": 47
308
+ },
309
+ {
310
+ "epoch": 0.2,
311
+ "learning_rate": 0.00018694053472948156,
312
+ "loss": 1.3292,
313
+ "step": 48
314
+ },
315
+ {
316
+ "epoch": 0.2,
317
+ "learning_rate": 0.00018626054156009806,
318
+ "loss": 1.327,
319
+ "step": 49
320
+ },
321
+ {
322
+ "epoch": 0.21,
323
+ "learning_rate": 0.00018556459396147775,
324
+ "loss": 1.2729,
325
+ "step": 50
326
+ },
327
+ {
328
+ "epoch": 0.21,
329
+ "eval_loss": 1.2218066453933716,
330
+ "eval_runtime": 32.6642,
331
+ "eval_samples_per_second": 41.299,
332
+ "eval_steps_per_second": 41.299,
333
+ "step": 50
334
+ },
335
+ {
336
+ "epoch": 0.21,
337
+ "learning_rate": 0.00018485282065350235,
338
+ "loss": 1.2795,
339
+ "step": 51
340
+ },
341
+ {
342
+ "epoch": 0.22,
343
+ "learning_rate": 0.00018412535328311814,
344
+ "loss": 1.2314,
345
+ "step": 52
346
+ },
347
+ {
348
+ "epoch": 0.22,
349
+ "learning_rate": 0.0001833823263999867,
350
+ "loss": 1.2671,
351
+ "step": 53
352
+ },
353
+ {
354
+ "epoch": 0.22,
355
+ "learning_rate": 0.0001826238774315995,
356
+ "loss": 1.2724,
357
+ "step": 54
358
+ },
359
+ {
360
+ "epoch": 0.23,
361
+ "learning_rate": 0.00018185014665785936,
362
+ "loss": 1.2788,
363
+ "step": 55
364
+ },
365
+ {
366
+ "epoch": 0.23,
367
+ "learning_rate": 0.00018106127718513516,
368
+ "loss": 1.245,
369
+ "step": 56
370
+ },
371
+ {
372
+ "epoch": 0.24,
373
+ "learning_rate": 0.00018025741491979326,
374
+ "loss": 1.1788,
375
+ "step": 57
376
+ },
377
+ {
378
+ "epoch": 0.24,
379
+ "learning_rate": 0.00017943870854121124,
380
+ "loss": 1.2128,
381
+ "step": 58
382
+ },
383
+ {
384
+ "epoch": 0.24,
385
+ "learning_rate": 0.00017860530947427875,
386
+ "loss": 1.1785,
387
+ "step": 59
388
+ },
389
+ {
390
+ "epoch": 0.25,
391
+ "learning_rate": 0.00017775737186139038,
392
+ "loss": 1.2401,
393
+ "step": 60
394
+ },
395
+ {
396
+ "epoch": 0.25,
397
+ "learning_rate": 0.0001768950525339362,
398
+ "loss": 1.1508,
399
+ "step": 61
400
+ },
401
+ {
402
+ "epoch": 0.26,
403
+ "learning_rate": 0.00017601851098329483,
404
+ "loss": 1.1936,
405
+ "step": 62
406
+ },
407
+ {
408
+ "epoch": 0.26,
409
+ "learning_rate": 0.00017512790933133437,
410
+ "loss": 1.0948,
411
+ "step": 63
412
+ },
413
+ {
414
+ "epoch": 0.27,
415
+ "learning_rate": 0.000174223412300427,
416
+ "loss": 1.2041,
417
+ "step": 64
418
+ },
419
+ {
420
+ "epoch": 0.27,
421
+ "learning_rate": 0.00017330518718298264,
422
+ "loss": 1.1611,
423
+ "step": 65
424
+ },
425
+ {
426
+ "epoch": 0.27,
427
+ "learning_rate": 0.00017237340381050703,
428
+ "loss": 1.1415,
429
+ "step": 66
430
+ },
431
+ {
432
+ "epoch": 0.28,
433
+ "learning_rate": 0.00017142823452219038,
434
+ "loss": 1.058,
435
+ "step": 67
436
+ },
437
+ {
438
+ "epoch": 0.28,
439
+ "learning_rate": 0.00017046985413303215,
440
+ "loss": 1.141,
441
+ "step": 68
442
+ },
443
+ {
444
+ "epoch": 0.29,
445
+ "learning_rate": 0.00016949843990150796,
446
+ "loss": 1.1613,
447
+ "step": 69
448
+ },
449
+ {
450
+ "epoch": 0.29,
451
+ "learning_rate": 0.00016851417149678444,
452
+ "loss": 1.1096,
453
+ "step": 70
454
+ },
455
+ {
456
+ "epoch": 0.29,
457
+ "learning_rate": 0.00016751723096548835,
458
+ "loss": 1.1144,
459
+ "step": 71
460
+ },
461
+ {
462
+ "epoch": 0.3,
463
+ "learning_rate": 0.00016650780269803587,
464
+ "loss": 1.0665,
465
+ "step": 72
466
+ },
467
+ {
468
+ "epoch": 0.3,
469
+ "learning_rate": 0.00016548607339452853,
470
+ "loss": 1.1126,
471
+ "step": 73
472
+ },
473
+ {
474
+ "epoch": 0.31,
475
+ "learning_rate": 0.00016445223203022166,
476
+ "loss": 1.0365,
477
+ "step": 74
478
+ },
479
+ {
480
+ "epoch": 0.31,
481
+ "learning_rate": 0.00016340646982057247,
482
+ "loss": 1.0634,
483
+ "step": 75
484
+ },
485
+ {
486
+ "epoch": 0.31,
487
+ "eval_loss": 1.0092816352844238,
488
+ "eval_runtime": 32.6429,
489
+ "eval_samples_per_second": 41.326,
490
+ "eval_steps_per_second": 41.326,
491
+ "step": 75
492
+ },
493
+ {
494
+ "epoch": 0.32,
495
+ "learning_rate": 0.00016234898018587337,
496
+ "loss": 1.0822,
497
+ "step": 76
498
+ },
499
+ {
500
+ "epoch": 0.32,
501
+ "learning_rate": 0.0001612799587154777,
502
+ "loss": 1.0586,
503
+ "step": 77
504
+ },
505
+ {
506
+ "epoch": 0.32,
507
+ "learning_rate": 0.00016019960313162434,
508
+ "loss": 1.0547,
509
+ "step": 78
510
+ },
511
+ {
512
+ "epoch": 0.33,
513
+ "learning_rate": 0.00015910811325286768,
514
+ "loss": 1.0551,
515
+ "step": 79
516
+ },
517
+ {
518
+ "epoch": 0.33,
519
+ "learning_rate": 0.00015800569095711982,
520
+ "loss": 1.1206,
521
+ "step": 80
522
+ },
523
+ {
524
+ "epoch": 0.34,
525
+ "learning_rate": 0.00015689254014431225,
526
+ "loss": 1.0909,
527
+ "step": 81
528
+ },
529
+ {
530
+ "epoch": 0.34,
531
+ "learning_rate": 0.00015576886669868296,
532
+ "loss": 1.0764,
533
+ "step": 82
534
+ },
535
+ {
536
+ "epoch": 0.34,
537
+ "learning_rate": 0.00015463487845069707,
538
+ "loss": 1.0442,
539
+ "step": 83
540
+ },
541
+ {
542
+ "epoch": 0.35,
543
+ "learning_rate": 0.00015349078513860726,
544
+ "loss": 4.5754,
545
+ "step": 84
546
+ },
547
+ {
548
+ "epoch": 0.35,
549
+ "learning_rate": 0.00015233679836966122,
550
+ "loss": 1.0489,
551
+ "step": 85
552
+ },
553
+ {
554
+ "epoch": 0.36,
555
+ "learning_rate": 0.0001511731315809637,
556
+ "loss": 1.0664,
557
+ "step": 86
558
+ },
559
+ {
560
+ "epoch": 0.36,
561
+ "learning_rate": 0.00015000000000000001,
562
+ "loss": 1.0965,
563
+ "step": 87
564
+ },
565
+ {
566
+ "epoch": 0.37,
567
+ "learning_rate": 0.00014881762060482814,
568
+ "loss": 1.0181,
569
+ "step": 88
570
+ },
571
+ {
572
+ "epoch": 0.37,
573
+ "learning_rate": 0.0001476262120839475,
574
+ "loss": 1.0609,
575
+ "step": 89
576
+ },
577
+ {
578
+ "epoch": 0.37,
579
+ "learning_rate": 0.00014642599479585105,
580
+ "loss": 1.0165,
581
+ "step": 90
582
+ },
583
+ {
584
+ "epoch": 0.38,
585
+ "learning_rate": 0.00014521719072826858,
586
+ "loss": 1.0059,
587
+ "step": 91
588
+ },
589
+ {
590
+ "epoch": 0.38,
591
+ "learning_rate": 0.0001440000234571087,
592
+ "loss": 0.9537,
593
+ "step": 92
594
+ },
595
+ {
596
+ "epoch": 0.39,
597
+ "learning_rate": 0.0001427747181051071,
598
+ "loss": 1.0747,
599
+ "step": 93
600
+ },
601
+ {
602
+ "epoch": 0.39,
603
+ "learning_rate": 0.00014154150130018866,
604
+ "loss": 1.0587,
605
+ "step": 94
606
+ },
607
+ {
608
+ "epoch": 0.39,
609
+ "learning_rate": 0.00014030060113355116,
610
+ "loss": 0.9952,
611
+ "step": 95
612
+ },
613
+ {
614
+ "epoch": 0.4,
615
+ "learning_rate": 0.00013905224711747844,
616
+ "loss": 1.0379,
617
+ "step": 96
618
+ },
619
+ {
620
+ "epoch": 0.4,
621
+ "learning_rate": 0.00013779667014289065,
622
+ "loss": 1.0189,
623
+ "step": 97
624
+ },
625
+ {
626
+ "epoch": 0.41,
627
+ "learning_rate": 0.00013653410243663952,
628
+ "loss": 0.9906,
629
+ "step": 98
630
+ },
631
+ {
632
+ "epoch": 0.41,
633
+ "learning_rate": 0.00013526477751855644,
634
+ "loss": 0.9633,
635
+ "step": 99
636
+ },
637
+ {
638
+ "epoch": 0.41,
639
+ "learning_rate": 0.00013398893015826167,
640
+ "loss": 0.9576,
641
+ "step": 100
642
+ },
643
+ {
644
+ "epoch": 0.41,
645
+ "eval_loss": 0.9341132640838623,
646
+ "eval_runtime": 32.6516,
647
+ "eval_samples_per_second": 41.315,
648
+ "eval_steps_per_second": 41.315,
649
+ "step": 100
650
+ },
651
+ {
652
+ "epoch": 0.42,
653
+ "learning_rate": 0.00013270679633174218,
654
+ "loss": 1.0156,
655
+ "step": 101
656
+ },
657
+ {
658
+ "epoch": 0.42,
659
+ "learning_rate": 0.00013141861317770626,
660
+ "loss": 1.0206,
661
+ "step": 102
662
+ },
663
+ {
664
+ "epoch": 0.43,
665
+ "learning_rate": 0.00013012461895372344,
666
+ "loss": 0.9947,
667
+ "step": 103
668
+ },
669
+ {
670
+ "epoch": 0.43,
671
+ "learning_rate": 0.0001288250529921571,
672
+ "loss": 0.9504,
673
+ "step": 104
674
+ },
675
+ {
676
+ "epoch": 0.44,
677
+ "learning_rate": 0.00012752015565589852,
678
+ "loss": 0.9726,
679
+ "step": 105
680
+ },
681
+ {
682
+ "epoch": 0.44,
683
+ "learning_rate": 0.00012621016829391022,
684
+ "loss": 0.9701,
685
+ "step": 106
686
+ },
687
+ {
688
+ "epoch": 0.44,
689
+ "learning_rate": 0.00012489533319658702,
690
+ "loss": 0.9525,
691
+ "step": 107
692
+ },
693
+ {
694
+ "epoch": 0.45,
695
+ "learning_rate": 0.00012357589355094275,
696
+ "loss": 0.957,
697
+ "step": 108
698
+ },
699
+ {
700
+ "epoch": 0.45,
701
+ "learning_rate": 0.00012225209339563145,
702
+ "loss": 1.0044,
703
+ "step": 109
704
+ },
705
+ {
706
+ "epoch": 0.46,
707
+ "learning_rate": 0.00012092417757581085,
708
+ "loss": 0.9591,
709
+ "step": 110
710
+ },
711
+ {
712
+ "epoch": 0.46,
713
+ "learning_rate": 0.00011959239169785667,
714
+ "loss": 0.9566,
715
+ "step": 111
716
+ },
717
+ {
718
+ "epoch": 0.46,
719
+ "learning_rate": 0.00011825698208393619,
720
+ "loss": 0.9558,
721
+ "step": 112
722
+ },
723
+ {
724
+ "epoch": 0.47,
725
+ "learning_rate": 0.00011691819572644939,
726
+ "loss": 0.9966,
727
+ "step": 113
728
+ },
729
+ {
730
+ "epoch": 0.47,
731
+ "learning_rate": 0.0001155762802423463,
732
+ "loss": 0.9135,
733
+ "step": 114
734
+ },
735
+ {
736
+ "epoch": 0.48,
737
+ "learning_rate": 0.00011423148382732853,
738
+ "loss": 0.9496,
739
+ "step": 115
740
+ },
741
+ {
742
+ "epoch": 0.48,
743
+ "learning_rate": 0.0001128840552099439,
744
+ "loss": 0.9863,
745
+ "step": 116
746
+ },
747
+ {
748
+ "epoch": 0.49,
749
+ "learning_rate": 0.00011153424360558267,
750
+ "loss": 0.9535,
751
+ "step": 117
752
+ },
753
+ {
754
+ "epoch": 0.49,
755
+ "learning_rate": 0.00011018229867038356,
756
+ "loss": 0.9271,
757
+ "step": 118
758
+ },
759
+ {
760
+ "epoch": 0.49,
761
+ "learning_rate": 0.00010882847045505808,
762
+ "loss": 0.9278,
763
+ "step": 119
764
+ },
765
+ {
766
+ "epoch": 0.5,
767
+ "learning_rate": 0.00010747300935864243,
768
+ "loss": 0.9571,
769
+ "step": 120
770
+ },
771
+ {
772
+ "epoch": 0.5,
773
+ "learning_rate": 0.00010611616608218429,
774
+ "loss": 0.9439,
775
+ "step": 121
776
+ },
777
+ {
778
+ "epoch": 0.51,
779
+ "learning_rate": 0.00010475819158237425,
780
+ "loss": 0.9159,
781
+ "step": 122
782
+ },
783
+ {
784
+ "epoch": 0.51,
785
+ "learning_rate": 0.00010339933702512979,
786
+ "loss": 0.9311,
787
+ "step": 123
788
+ },
789
+ {
790
+ "epoch": 0.51,
791
+ "learning_rate": 0.00010203985373914056,
792
+ "loss": 0.9363,
793
+ "step": 124
794
+ },
795
+ {
796
+ "epoch": 0.52,
797
+ "learning_rate": 0.00010067999316938347,
798
+ "loss": 0.9326,
799
+ "step": 125
800
+ },
801
+ {
802
+ "epoch": 0.52,
803
+ "eval_loss": 0.8691431879997253,
804
+ "eval_runtime": 32.6582,
805
+ "eval_samples_per_second": 41.307,
806
+ "eval_steps_per_second": 41.307,
807
+ "step": 125
808
+ },
809
+ {
810
+ "epoch": 0.52,
811
+ "learning_rate": 9.932000683061653e-05,
812
+ "loss": 0.9236,
813
+ "step": 126
814
+ },
815
+ {
816
+ "epoch": 0.53,
817
+ "learning_rate": 9.79601462608595e-05,
818
+ "loss": 0.8996,
819
+ "step": 127
820
+ },
821
+ {
822
+ "epoch": 0.53,
823
+ "learning_rate": 9.660066297487022e-05,
824
+ "loss": 0.9336,
825
+ "step": 128
826
+ },
827
+ {
828
+ "epoch": 0.54,
829
+ "learning_rate": 9.524180841762577e-05,
830
+ "loss": 0.9034,
831
+ "step": 129
832
+ },
833
+ {
834
+ "epoch": 0.54,
835
+ "learning_rate": 9.388383391781575e-05,
836
+ "loss": 0.9279,
837
+ "step": 130
838
+ },
839
+ {
840
+ "epoch": 0.54,
841
+ "learning_rate": 9.252699064135758e-05,
842
+ "loss": 0.8601,
843
+ "step": 131
844
+ },
845
+ {
846
+ "epoch": 0.55,
847
+ "learning_rate": 9.117152954494194e-05,
848
+ "loss": 0.9478,
849
+ "step": 132
850
+ },
851
+ {
852
+ "epoch": 0.55,
853
+ "learning_rate": 8.981770132961649e-05,
854
+ "loss": 0.9073,
855
+ "step": 133
856
+ },
857
+ {
858
+ "epoch": 0.56,
859
+ "learning_rate": 8.846575639441732e-05,
860
+ "loss": 0.9208,
861
+ "step": 134
862
+ },
863
+ {
864
+ "epoch": 0.56,
865
+ "learning_rate": 8.711594479005614e-05,
866
+ "loss": 0.8884,
867
+ "step": 135
868
+ },
869
+ {
870
+ "epoch": 0.56,
871
+ "learning_rate": 8.57685161726715e-05,
872
+ "loss": 0.9422,
873
+ "step": 136
874
+ },
875
+ {
876
+ "epoch": 0.57,
877
+ "learning_rate": 8.442371975765368e-05,
878
+ "loss": 0.953,
879
+ "step": 137
880
+ },
881
+ {
882
+ "epoch": 0.57,
883
+ "learning_rate": 8.308180427355062e-05,
884
+ "loss": 0.8997,
885
+ "step": 138
886
+ },
887
+ {
888
+ "epoch": 0.58,
889
+ "learning_rate": 8.174301791606385e-05,
890
+ "loss": 0.8609,
891
+ "step": 139
892
+ },
893
+ {
894
+ "epoch": 0.58,
895
+ "learning_rate": 8.040760830214333e-05,
896
+ "loss": 0.9007,
897
+ "step": 140
898
+ },
899
+ {
900
+ "epoch": 0.59,
901
+ "learning_rate": 7.907582242418916e-05,
902
+ "loss": 0.8916,
903
+ "step": 141
904
+ },
905
+ {
906
+ "epoch": 0.59,
907
+ "learning_rate": 7.774790660436858e-05,
908
+ "loss": 0.9183,
909
+ "step": 142
910
+ },
911
+ {
912
+ "epoch": 0.59,
913
+ "learning_rate": 7.642410644905726e-05,
914
+ "loss": 0.9534,
915
+ "step": 143
916
+ },
917
+ {
918
+ "epoch": 0.6,
919
+ "learning_rate": 7.510466680341301e-05,
920
+ "loss": 0.8849,
921
+ "step": 144
922
+ },
923
+ {
924
+ "epoch": 0.6,
925
+ "learning_rate": 7.378983170608982e-05,
926
+ "loss": 0.8619,
927
+ "step": 145
928
+ },
929
+ {
930
+ "epoch": 0.61,
931
+ "learning_rate": 7.24798443441015e-05,
932
+ "loss": 0.9094,
933
+ "step": 146
934
+ },
935
+ {
936
+ "epoch": 0.61,
937
+ "learning_rate": 7.117494700784292e-05,
938
+ "loss": 0.8986,
939
+ "step": 147
940
+ },
941
+ {
942
+ "epoch": 0.61,
943
+ "learning_rate": 6.98753810462766e-05,
944
+ "loss": 0.8789,
945
+ "step": 148
946
+ },
947
+ {
948
+ "epoch": 0.62,
949
+ "learning_rate": 6.858138682229376e-05,
950
+ "loss": 0.8993,
951
+ "step": 149
952
+ },
953
+ {
954
+ "epoch": 0.62,
955
+ "learning_rate": 6.729320366825784e-05,
956
+ "loss": 0.8558,
957
+ "step": 150
958
+ },
959
+ {
960
+ "epoch": 0.62,
961
+ "eval_loss": 0.8324622511863708,
962
+ "eval_runtime": 32.6563,
963
+ "eval_samples_per_second": 41.309,
964
+ "eval_steps_per_second": 41.309,
965
+ "step": 150
966
+ },
967
+ {
968
+ "epoch": 0.63,
969
+ "learning_rate": 6.601106984173835e-05,
970
+ "loss": 0.9118,
971
+ "step": 151
972
+ },
973
+ {
974
+ "epoch": 0.63,
975
+ "learning_rate": 6.47352224814436e-05,
976
+ "loss": 0.8773,
977
+ "step": 152
978
+ },
979
+ {
980
+ "epoch": 0.63,
981
+ "learning_rate": 6.34658975633605e-05,
982
+ "loss": 0.8344,
983
+ "step": 153
984
+ },
985
+ {
986
+ "epoch": 0.64,
987
+ "learning_rate": 6.220332985710936e-05,
988
+ "loss": 0.8663,
989
+ "step": 154
990
+ },
991
+ {
992
+ "epoch": 0.64,
993
+ "learning_rate": 6.094775288252157e-05,
994
+ "loss": 0.8629,
995
+ "step": 155
996
+ },
997
+ {
998
+ "epoch": 0.65,
999
+ "learning_rate": 5.969939886644884e-05,
1000
+ "loss": 0.845,
1001
+ "step": 156
1002
+ },
1003
+ {
1004
+ "epoch": 0.65,
1005
+ "learning_rate": 5.845849869981137e-05,
1006
+ "loss": 0.8738,
1007
+ "step": 157
1008
+ },
1009
+ {
1010
+ "epoch": 0.66,
1011
+ "learning_rate": 5.7225281894892935e-05,
1012
+ "loss": 0.8875,
1013
+ "step": 158
1014
+ },
1015
+ {
1016
+ "epoch": 0.66,
1017
+ "learning_rate": 5.599997654289129e-05,
1018
+ "loss": 0.9275,
1019
+ "step": 159
1020
+ },
1021
+ {
1022
+ "epoch": 0.66,
1023
+ "learning_rate": 5.478280927173145e-05,
1024
+ "loss": 0.8762,
1025
+ "step": 160
1026
+ },
1027
+ {
1028
+ "epoch": 0.67,
1029
+ "learning_rate": 5.357400520414898e-05,
1030
+ "loss": 0.8882,
1031
+ "step": 161
1032
+ },
1033
+ {
1034
+ "epoch": 0.67,
1035
+ "learning_rate": 5.2373787916052486e-05,
1036
+ "loss": 0.8783,
1037
+ "step": 162
1038
+ },
1039
+ {
1040
+ "epoch": 0.68,
1041
+ "learning_rate": 5.11823793951719e-05,
1042
+ "loss": 0.8861,
1043
+ "step": 163
1044
+ },
1045
+ {
1046
+ "epoch": 0.68,
1047
+ "learning_rate": 5.000000000000002e-05,
1048
+ "loss": 0.8866,
1049
+ "step": 164
1050
+ },
1051
+ {
1052
+ "epoch": 0.68,
1053
+ "learning_rate": 4.882686841903628e-05,
1054
+ "loss": 0.8969,
1055
+ "step": 165
1056
+ },
1057
+ {
1058
+ "epoch": 0.69,
1059
+ "learning_rate": 4.7663201630338816e-05,
1060
+ "loss": 0.8631,
1061
+ "step": 166
1062
+ },
1063
+ {
1064
+ "epoch": 0.69,
1065
+ "learning_rate": 4.650921486139278e-05,
1066
+ "loss": 0.8231,
1067
+ "step": 167
1068
+ },
1069
+ {
1070
+ "epoch": 0.7,
1071
+ "learning_rate": 4.5365121549302914e-05,
1072
+ "loss": 0.8565,
1073
+ "step": 168
1074
+ },
1075
+ {
1076
+ "epoch": 0.7,
1077
+ "learning_rate": 4.423113330131707e-05,
1078
+ "loss": 0.8911,
1079
+ "step": 169
1080
+ },
1081
+ {
1082
+ "epoch": 0.71,
1083
+ "learning_rate": 4.310745985568778e-05,
1084
+ "loss": 0.8266,
1085
+ "step": 170
1086
+ },
1087
+ {
1088
+ "epoch": 0.71,
1089
+ "learning_rate": 4.19943090428802e-05,
1090
+ "loss": 0.8191,
1091
+ "step": 171
1092
+ },
1093
+ {
1094
+ "epoch": 0.71,
1095
+ "learning_rate": 4.089188674713236e-05,
1096
+ "loss": 0.8744,
1097
+ "step": 172
1098
+ },
1099
+ {
1100
+ "epoch": 0.72,
1101
+ "learning_rate": 3.980039686837568e-05,
1102
+ "loss": 0.8851,
1103
+ "step": 173
1104
+ },
1105
+ {
1106
+ "epoch": 0.72,
1107
+ "learning_rate": 3.872004128452231e-05,
1108
+ "loss": 0.8391,
1109
+ "step": 174
1110
+ },
1111
+ {
1112
+ "epoch": 0.73,
1113
+ "learning_rate": 3.7651019814126654e-05,
1114
+ "loss": 0.8218,
1115
+ "step": 175
1116
+ },
1117
+ {
1118
+ "epoch": 0.73,
1119
+ "eval_loss": 0.804731011390686,
1120
+ "eval_runtime": 32.6417,
1121
+ "eval_samples_per_second": 41.328,
1122
+ "eval_steps_per_second": 41.328,
1123
+ "step": 175
1124
+ },
1125
+ {
1126
+ "epoch": 0.73,
1127
+ "learning_rate": 3.6593530179427535e-05,
1128
+ "loss": 0.8804,
1129
+ "step": 176
1130
+ },
1131
+ {
1132
+ "epoch": 0.73,
1133
+ "learning_rate": 3.554776796977836e-05,
1134
+ "loss": 0.8532,
1135
+ "step": 177
1136
+ },
1137
+ {
1138
+ "epoch": 0.74,
1139
+ "learning_rate": 3.45139266054715e-05,
1140
+ "loss": 0.8992,
1141
+ "step": 178
1142
+ },
1143
+ {
1144
+ "epoch": 0.74,
1145
+ "learning_rate": 3.3492197301964145e-05,
1146
+ "loss": 0.8401,
1147
+ "step": 179
1148
+ },
1149
+ {
1150
+ "epoch": 0.75,
1151
+ "learning_rate": 3.248276903451171e-05,
1152
+ "loss": 0.8731,
1153
+ "step": 180
1154
+ },
1155
+ {
1156
+ "epoch": 0.75,
1157
+ "learning_rate": 3.1485828503215585e-05,
1158
+ "loss": 0.8648,
1159
+ "step": 181
1160
+ },
1161
+ {
1162
+ "epoch": 0.76,
1163
+ "learning_rate": 3.0501560098492056e-05,
1164
+ "loss": 0.8639,
1165
+ "step": 182
1166
+ },
1167
+ {
1168
+ "epoch": 0.76,
1169
+ "learning_rate": 2.9530145866967895e-05,
1170
+ "loss": 0.8416,
1171
+ "step": 183
1172
+ },
1173
+ {
1174
+ "epoch": 0.76,
1175
+ "learning_rate": 2.8571765477809643e-05,
1176
+ "loss": 0.8649,
1177
+ "step": 184
1178
+ },
1179
+ {
1180
+ "epoch": 0.77,
1181
+ "learning_rate": 2.7626596189492983e-05,
1182
+ "loss": 0.8535,
1183
+ "step": 185
1184
+ },
1185
+ {
1186
+ "epoch": 0.77,
1187
+ "learning_rate": 2.669481281701739e-05,
1188
+ "loss": 0.8669,
1189
+ "step": 186
1190
+ },
1191
+ {
1192
+ "epoch": 0.78,
1193
+ "learning_rate": 2.5776587699573006e-05,
1194
+ "loss": 0.8954,
1195
+ "step": 187
1196
+ },
1197
+ {
1198
+ "epoch": 0.78,
1199
+ "learning_rate": 2.487209066866565e-05,
1200
+ "loss": 0.859,
1201
+ "step": 188
1202
+ },
1203
+ {
1204
+ "epoch": 0.78,
1205
+ "learning_rate": 2.3981489016705205e-05,
1206
+ "loss": 0.8447,
1207
+ "step": 189
1208
+ },
1209
+ {
1210
+ "epoch": 0.79,
1211
+ "learning_rate": 2.3104947466063787e-05,
1212
+ "loss": 0.8812,
1213
+ "step": 190
1214
+ },
1215
+ {
1216
+ "epoch": 0.79,
1217
+ "learning_rate": 2.2242628138609623e-05,
1218
+ "loss": 0.8336,
1219
+ "step": 191
1220
+ },
1221
+ {
1222
+ "epoch": 0.8,
1223
+ "learning_rate": 2.139469052572127e-05,
1224
+ "loss": 0.8479,
1225
+ "step": 192
1226
+ },
1227
+ {
1228
+ "epoch": 0.8,
1229
+ "learning_rate": 2.0561291458788733e-05,
1230
+ "loss": 0.8142,
1231
+ "step": 193
1232
+ },
1233
+ {
1234
+ "epoch": 0.8,
1235
+ "learning_rate": 1.9742585080206755e-05,
1236
+ "loss": 0.8783,
1237
+ "step": 194
1238
+ },
1239
+ {
1240
+ "epoch": 0.81,
1241
+ "learning_rate": 1.893872281486486e-05,
1242
+ "loss": 0.8368,
1243
+ "step": 195
1244
+ },
1245
+ {
1246
+ "epoch": 0.81,
1247
+ "learning_rate": 1.8149853342140645e-05,
1248
+ "loss": 0.8694,
1249
+ "step": 196
1250
+ },
1251
+ {
1252
+ "epoch": 0.82,
1253
+ "learning_rate": 1.7376122568400532e-05,
1254
+ "loss": 0.8528,
1255
+ "step": 197
1256
+ },
1257
+ {
1258
+ "epoch": 0.82,
1259
+ "learning_rate": 1.6617673600013296e-05,
1260
+ "loss": 0.8638,
1261
+ "step": 198
1262
+ },
1263
+ {
1264
+ "epoch": 0.83,
1265
+ "learning_rate": 1.587464671688187e-05,
1266
+ "loss": 0.8548,
1267
+ "step": 199
1268
+ },
1269
+ {
1270
+ "epoch": 0.83,
1271
+ "learning_rate": 1.5147179346497664e-05,
1272
+ "loss": 0.8579,
1273
+ "step": 200
1274
+ },
1275
+ {
1276
+ "epoch": 0.83,
1277
+ "eval_loss": 0.7979977130889893,
1278
+ "eval_runtime": 32.6563,
1279
+ "eval_samples_per_second": 41.309,
1280
+ "eval_steps_per_second": 41.309,
1281
+ "step": 200
1282
+ },
1283
+ {
1284
+ "epoch": 0.83,
1285
+ "learning_rate": 1.443540603852227e-05,
1286
+ "loss": 0.8595,
1287
+ "step": 201
1288
+ },
1289
+ {
1290
+ "epoch": 0.84,
1291
+ "learning_rate": 1.373945843990192e-05,
1292
+ "loss": 0.8006,
1293
+ "step": 202
1294
+ },
1295
+ {
1296
+ "epoch": 0.84,
1297
+ "learning_rate": 1.3059465270518468e-05,
1298
+ "loss": 0.8871,
1299
+ "step": 203
1300
+ },
1301
+ {
1302
+ "epoch": 0.85,
1303
+ "learning_rate": 1.2395552299381741e-05,
1304
+ "loss": 0.8446,
1305
+ "step": 204
1306
+ },
1307
+ {
1308
+ "epoch": 0.85,
1309
+ "learning_rate": 1.1747842321367886e-05,
1310
+ "loss": 0.8541,
1311
+ "step": 205
1312
+ },
1313
+ {
1314
+ "epoch": 0.85,
1315
+ "learning_rate": 1.1116455134507664e-05,
1316
+ "loss": 0.8578,
1317
+ "step": 206
1318
+ },
1319
+ {
1320
+ "epoch": 0.86,
1321
+ "learning_rate": 1.0501507517829012e-05,
1322
+ "loss": 0.841,
1323
+ "step": 207
1324
+ },
1325
+ {
1326
+ "epoch": 0.86,
1327
+ "learning_rate": 9.903113209758096e-06,
1328
+ "loss": 0.8216,
1329
+ "step": 208
1330
+ },
1331
+ {
1332
+ "epoch": 0.87,
1333
+ "learning_rate": 9.321382887082563e-06,
1334
+ "loss": 0.8498,
1335
+ "step": 209
1336
+ },
1337
+ {
1338
+ "epoch": 0.87,
1339
+ "learning_rate": 8.756424144481312e-06,
1340
+ "loss": 0.841,
1341
+ "step": 210
1342
+ },
1343
+ {
1344
+ "epoch": 0.88,
1345
+ "learning_rate": 8.208341474624071e-06,
1346
+ "loss": 0.8336,
1347
+ "step": 211
1348
+ },
1349
+ {
1350
+ "epoch": 0.88,
1351
+ "learning_rate": 7.677236248844855e-06,
1352
+ "loss": 0.849,
1353
+ "step": 212
1354
+ },
1355
+ {
1356
+ "epoch": 0.88,
1357
+ "learning_rate": 7.163206698392744e-06,
1358
+ "loss": 0.8382,
1359
+ "step": 213
1360
+ },
1361
+ {
1362
+ "epoch": 0.89,
1363
+ "learning_rate": 6.666347896263325e-06,
1364
+ "loss": 0.8161,
1365
+ "step": 214
1366
+ },
1367
+ {
1368
+ "epoch": 0.89,
1369
+ "learning_rate": 6.186751739614405e-06,
1370
+ "loss": 0.8339,
1371
+ "step": 215
1372
+ },
1373
+ {
1374
+ "epoch": 0.9,
1375
+ "learning_rate": 5.724506932769014e-06,
1376
+ "loss": 0.8805,
1377
+ "step": 216
1378
+ },
1379
+ {
1380
+ "epoch": 0.9,
1381
+ "learning_rate": 5.27969897080901e-06,
1382
+ "loss": 0.841,
1383
+ "step": 217
1384
+ },
1385
+ {
1386
+ "epoch": 0.9,
1387
+ "learning_rate": 4.8524101237621635e-06,
1388
+ "loss": 0.8441,
1389
+ "step": 218
1390
+ },
1391
+ {
1392
+ "epoch": 0.91,
1393
+ "learning_rate": 4.442719421385922e-06,
1394
+ "loss": 0.8482,
1395
+ "step": 219
1396
+ },
1397
+ {
1398
+ "epoch": 0.91,
1399
+ "learning_rate": 4.050702638550275e-06,
1400
+ "loss": 0.9085,
1401
+ "step": 220
1402
+ },
1403
+ {
1404
+ "epoch": 0.92,
1405
+ "learning_rate": 3.6764322812226415e-06,
1406
+ "loss": 0.8255,
1407
+ "step": 221
1408
+ },
1409
+ {
1410
+ "epoch": 0.92,
1411
+ "learning_rate": 3.319977573057642e-06,
1412
+ "loss": 0.815,
1413
+ "step": 222
1414
+ },
1415
+ {
1416
+ "epoch": 0.93,
1417
+ "learning_rate": 2.9814044425935606e-06,
1418
+ "loss": 0.8746,
1419
+ "step": 223
1420
+ },
1421
+ {
1422
+ "epoch": 0.93,
1423
+ "learning_rate": 2.6607755110584887e-06,
1424
+ "loss": 0.8573,
1425
+ "step": 224
1426
+ },
1427
+ {
1428
+ "epoch": 0.93,
1429
+ "learning_rate": 2.3581500807882462e-06,
1430
+ "loss": 0.9001,
1431
+ "step": 225
1432
+ },
1433
+ {
1434
+ "epoch": 0.93,
1435
+ "eval_loss": 0.7941693663597107,
1436
+ "eval_runtime": 32.6617,
1437
+ "eval_samples_per_second": 41.302,
1438
+ "eval_steps_per_second": 41.302,
1439
+ "step": 225
1440
+ },
1441
+ {
1442
+ "epoch": 0.94,
1443
+ "learning_rate": 2.073584124257899e-06,
1444
+ "loss": 0.8361,
1445
+ "step": 226
1446
+ },
1447
+ {
1448
+ "epoch": 0.94,
1449
+ "learning_rate": 1.8071302737293295e-06,
1450
+ "loss": 0.8047,
1451
+ "step": 227
1452
+ },
1453
+ {
1454
+ "epoch": 0.95,
1455
+ "learning_rate": 1.5588378115166669e-06,
1456
+ "loss": 0.866,
1457
+ "step": 228
1458
+ },
1459
+ {
1460
+ "epoch": 0.95,
1461
+ "learning_rate": 1.3287526608711131e-06,
1462
+ "loss": 0.8823,
1463
+ "step": 229
1464
+ },
1465
+ {
1466
+ "epoch": 0.95,
1467
+ "learning_rate": 1.1169173774871478e-06,
1468
+ "loss": 0.8581,
1469
+ "step": 230
1470
+ },
1471
+ {
1472
+ "epoch": 0.96,
1473
+ "learning_rate": 9.233711416316571e-07,
1474
+ "loss": 0.8647,
1475
+ "step": 231
1476
+ },
1477
+ {
1478
+ "epoch": 0.96,
1479
+ "learning_rate": 7.481497508972312e-07,
1480
+ "loss": 0.8416,
1481
+ "step": 232
1482
+ },
1483
+ {
1484
+ "epoch": 0.97,
1485
+ "learning_rate": 5.912856135812051e-07,
1486
+ "loss": 0.8444,
1487
+ "step": 233
1488
+ },
1489
+ {
1490
+ "epoch": 0.97,
1491
+ "learning_rate": 4.5280774269154115e-07,
1492
+ "loss": 0.8581,
1493
+ "step": 234
1494
+ },
1495
+ {
1496
+ "epoch": 0.98,
1497
+ "learning_rate": 3.3274175058067846e-07,
1498
+ "loss": 0.8533,
1499
+ "step": 235
1500
+ },
1501
+ {
1502
+ "epoch": 0.98,
1503
+ "learning_rate": 2.311098442083659e-07,
1504
+ "loss": 0.8655,
1505
+ "step": 236
1506
+ },
1507
+ {
1508
+ "epoch": 0.98,
1509
+ "learning_rate": 1.4793082103435885e-07,
1510
+ "loss": 0.8142,
1511
+ "step": 237
1512
+ },
1513
+ {
1514
+ "epoch": 0.99,
1515
+ "learning_rate": 8.322006554171146e-08,
1516
+ "loss": 0.8559,
1517
+ "step": 238
1518
+ },
1519
+ {
1520
+ "epoch": 0.99,
1521
+ "learning_rate": 3.6989546391297256e-08,
1522
+ "loss": 0.8274,
1523
+ "step": 239
1524
+ },
1525
+ {
1526
+ "epoch": 1.0,
1527
+ "learning_rate": 9.24781420816867e-09,
1528
+ "loss": 0.8172,
1529
+ "step": 240
1530
+ },
1531
+ {
1532
+ "epoch": 1.0,
1533
+ "learning_rate": 0.0,
1534
+ "loss": 0.8452,
1535
+ "step": 241
1536
+ }
1537
+ ],
1538
+ "logging_steps": 1,
1539
+ "max_steps": 241,
1540
+ "num_input_tokens_seen": 0,
1541
+ "num_train_epochs": 1,
1542
+ "save_steps": 500,
1543
+ "total_flos": 1.845262501848023e+17,
1544
+ "train_batch_size": 1,
1545
+ "trial_name": null,
1546
+ "trial_params": null
1547
+ }
checkpoint-241/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a14fcf575ebeac4d237842934081e060d2daf53eaa2afea97de850210a620bbb
3
+ size 5240
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "aurora-m/aurora-m-v0.1",
3
+ "activation_function": "gelu",
4
+ "architectures": [
5
+ "GPTBigCodeForCausalLM"
6
+ ],
7
+ "attention_softmax_in_fp32": true,
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 0,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 0,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt_bigcode",
15
+ "multi_query": true,
16
+ "n_embd": 6144,
17
+ "n_head": 48,
18
+ "n_inner": 24576,
19
+ "n_layer": 40,
20
+ "n_positions": 8192,
21
+ "pad_token_id": 0,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attention_softmax_in_fp32": true,
24
+ "scale_attn_weights": true,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.38.0.dev0",
27
+ "use_cache": false,
28
+ "vocab_size": 49156
29
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<fim_prefix>",
5
+ "<fim_middle>",
6
+ "<fim_suffix>",
7
+ "<fim_pad>",
8
+ "<filename>",
9
+ "<gh_stars>",
10
+ "<issue_start>",
11
+ "<issue_comment>",
12
+ "<issue_closed>",
13
+ "<jupyter_start>",
14
+ "<jupyter_text>",
15
+ "<jupyter_code>",
16
+ "<jupyter_output>",
17
+ "<empty_output>",
18
+ "<commit_before>",
19
+ "<commit_msg>",
20
+ "<commit_after>",
21
+ "<reponame>"
22
+ ],
23
+ "bos_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "eos_token": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "pad_token": {
38
+ "content": "<|endoftext|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<|endoftext|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,218 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<fim_prefix>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<fim_middle>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<fim_suffix>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<fim_pad>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<|rating-x|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<|rating-r|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<|rating-pg|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<|rating-g|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_closed>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<jupyter_start>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_text>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_code>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_output>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<empty_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<commit_before>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<commit_msg>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "17": {
141
+ "content": "<commit_after>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "18": {
149
+ "content": "<reponame>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "49152": {
157
+ "content": "<filename>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "49153": {
165
+ "content": "<gh_stars>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "49154": {
173
+ "content": "<issue_start>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "49155": {
181
+ "content": "<issue_comment>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ }
188
+ },
189
+ "additional_special_tokens": [
190
+ "<|endoftext|>",
191
+ "<fim_prefix>",
192
+ "<fim_middle>",
193
+ "<fim_suffix>",
194
+ "<fim_pad>",
195
+ "<filename>",
196
+ "<gh_stars>",
197
+ "<issue_start>",
198
+ "<issue_comment>",
199
+ "<issue_closed>",
200
+ "<jupyter_start>",
201
+ "<jupyter_text>",
202
+ "<jupyter_code>",
203
+ "<jupyter_output>",
204
+ "<empty_output>",
205
+ "<commit_before>",
206
+ "<commit_msg>",
207
+ "<commit_after>",
208
+ "<reponame>"
209
+ ],
210
+ "bos_token": "<|endoftext|>",
211
+ "clean_up_tokenization_spaces": true,
212
+ "eos_token": "<|endoftext|>",
213
+ "model_max_length": 1000000000000000019884624838656,
214
+ "pad_token": "<|endoftext|>",
215
+ "tokenizer_class": "GPT2Tokenizer",
216
+ "unk_token": "<|endoftext|>",
217
+ "vocab_size": 49152
218
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff