Upload folder using huggingface_hub
Browse files- README.md +202 -0
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +14 -0
- all_results.json +7 -0
- checkpoint-10/README.md +202 -0
- checkpoint-10/adapter_config.json +31 -0
- checkpoint-10/adapter_model.safetensors +3 -0
- checkpoint-10/added_tokens.json +14 -0
- checkpoint-10/optimizer.pt +3 -0
- checkpoint-10/rng_state.pth +3 -0
- checkpoint-10/scheduler.pt +3 -0
- checkpoint-10/special_tokens_map.json +24 -0
- checkpoint-10/tokenizer.json +0 -0
- checkpoint-10/tokenizer.model +3 -0
- checkpoint-10/tokenizer_config.json +139 -0
- checkpoint-10/trainer_state.json +183 -0
- checkpoint-10/training_args.bin +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +139 -0
- train_results.json +7 -0
- trainer_state.json +1707 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: microsoft/Phi-3-mini-4k-instruct
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.11.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"o_proj",
|
| 24 |
+
"qkv_proj",
|
| 25 |
+
"gate_up_proj",
|
| 26 |
+
"down_proj"
|
| 27 |
+
],
|
| 28 |
+
"task_type": "CAUSAL_LM",
|
| 29 |
+
"use_dora": false,
|
| 30 |
+
"use_rslora": false
|
| 31 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d13c24a529177b9344d22e9bfdfbb3376529db0c0275d237f97cd4ada3322a5
|
| 3 |
+
size 201361312
|
added_tokens.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|assistant|>": 32001,
|
| 3 |
+
"<|endoftext|>": 32000,
|
| 4 |
+
"<|end|>": 32007,
|
| 5 |
+
"<|placeholder1|>": 32002,
|
| 6 |
+
"<|placeholder2|>": 32003,
|
| 7 |
+
"<|placeholder3|>": 32004,
|
| 8 |
+
"<|placeholder4|>": 32005,
|
| 9 |
+
"<|placeholder5|>": 32008,
|
| 10 |
+
"<|placeholder6|>": 32009,
|
| 11 |
+
"<|system|>": 32006,
|
| 12 |
+
"<|user|>": 32010,
|
| 13 |
+
"eos_token": 32011
|
| 14 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 1.148636352371525,
|
| 4 |
+
"train_runtime": 2293.4445,
|
| 5 |
+
"train_samples_per_second": 1.54,
|
| 6 |
+
"train_steps_per_second": 0.048
|
| 7 |
+
}
|
checkpoint-10/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: microsoft/Phi-3-mini-4k-instruct
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.11.1
|
checkpoint-10/adapter_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"o_proj",
|
| 24 |
+
"qkv_proj",
|
| 25 |
+
"gate_up_proj",
|
| 26 |
+
"down_proj"
|
| 27 |
+
],
|
| 28 |
+
"task_type": "CAUSAL_LM",
|
| 29 |
+
"use_dora": false,
|
| 30 |
+
"use_rslora": false
|
| 31 |
+
}
|
checkpoint-10/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00ef7979849dbdb54bec6486272352da5976014038e9fcd7616fc6de452fa80a
|
| 3 |
+
size 201361312
|
checkpoint-10/added_tokens.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|assistant|>": 32001,
|
| 3 |
+
"<|endoftext|>": 32000,
|
| 4 |
+
"<|end|>": 32007,
|
| 5 |
+
"<|placeholder1|>": 32002,
|
| 6 |
+
"<|placeholder2|>": 32003,
|
| 7 |
+
"<|placeholder3|>": 32004,
|
| 8 |
+
"<|placeholder4|>": 32005,
|
| 9 |
+
"<|placeholder5|>": 32008,
|
| 10 |
+
"<|placeholder6|>": 32009,
|
| 11 |
+
"<|system|>": 32006,
|
| 12 |
+
"<|user|>": 32010,
|
| 13 |
+
"eos_token": 32011
|
| 14 |
+
}
|
checkpoint-10/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:563f60e45dcc6ff8468092af9eb71c60ade7cfd1cfd644c4a00f05f9c31b3f36
|
| 3 |
+
size 402807738
|
checkpoint-10/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9d25458d250308b66b3252c4b210a54c82239cfc07eac3e5e9e49c8c3fee9f7
|
| 3 |
+
size 14180
|
checkpoint-10/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10cc3c3d255f5b898f9c622d4bd3b366e433e74a31b326b8e9ea7996bcf6b027
|
| 3 |
+
size 1064
|
checkpoint-10/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<unk>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-10/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-10/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-10/tokenizer_config.json
ADDED
|
@@ -0,0 +1,139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": true,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": false
|
| 28 |
+
},
|
| 29 |
+
"32000": {
|
| 30 |
+
"content": "<|endoftext|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"32001": {
|
| 38 |
+
"content": "<|assistant|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": true,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"32002": {
|
| 46 |
+
"content": "<|placeholder1|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": true,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"32003": {
|
| 54 |
+
"content": "<|placeholder2|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": true,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"32004": {
|
| 62 |
+
"content": "<|placeholder3|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": true,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"32005": {
|
| 70 |
+
"content": "<|placeholder4|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": true,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"32006": {
|
| 78 |
+
"content": "<|system|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": true,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"32007": {
|
| 86 |
+
"content": "<|end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": true,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"32008": {
|
| 94 |
+
"content": "<|placeholder5|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": true,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"32009": {
|
| 102 |
+
"content": "<|placeholder6|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": true,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"32010": {
|
| 110 |
+
"content": "<|user|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": true,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"32011": {
|
| 118 |
+
"content": "eos_token",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": true
|
| 124 |
+
}
|
| 125 |
+
},
|
| 126 |
+
"bos_token": "<s>",
|
| 127 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
|
| 128 |
+
"clean_up_tokenization_spaces": false,
|
| 129 |
+
"eos_token": "<|endoftext|>",
|
| 130 |
+
"legacy": false,
|
| 131 |
+
"model_max_length": 4096,
|
| 132 |
+
"pad_token": "<unk>",
|
| 133 |
+
"padding_side": "right",
|
| 134 |
+
"sp_model_kwargs": {},
|
| 135 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 136 |
+
"truncation_side": "left",
|
| 137 |
+
"unk_token": "<unk>",
|
| 138 |
+
"use_default_system_prompt": false
|
| 139 |
+
}
|
checkpoint-10/trainer_state.json
ADDED
|
@@ -0,0 +1,183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.6195639371871948,
|
| 3 |
+
"best_model_checkpoint": "./output/checkpoints/2024-06-11_15-20-56/checkpoint-10",
|
| 4 |
+
"epoch": 0.2702702702702703,
|
| 5 |
+
"eval_steps": 1,
|
| 6 |
+
"global_step": 10,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02702702702702703,
|
| 13 |
+
"grad_norm": 3.045227289199829,
|
| 14 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 15 |
+
"loss": 5.5922,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02702702702702703,
|
| 20 |
+
"eval_loss": 5.6431684494018555,
|
| 21 |
+
"eval_runtime": 11.0821,
|
| 22 |
+
"eval_samples_per_second": 11.189,
|
| 23 |
+
"eval_steps_per_second": 0.722,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05405405405405406,
|
| 28 |
+
"grad_norm": 3.084507942199707,
|
| 29 |
+
"learning_rate": 6.666666666666667e-05,
|
| 30 |
+
"loss": 5.6812,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.05405405405405406,
|
| 35 |
+
"eval_loss": 5.540425777435303,
|
| 36 |
+
"eval_runtime": 11.083,
|
| 37 |
+
"eval_samples_per_second": 11.188,
|
| 38 |
+
"eval_steps_per_second": 0.722,
|
| 39 |
+
"step": 2
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.08108108108108109,
|
| 43 |
+
"grad_norm": 3.1143131256103516,
|
| 44 |
+
"learning_rate": 0.0001,
|
| 45 |
+
"loss": 5.5805,
|
| 46 |
+
"step": 3
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.08108108108108109,
|
| 50 |
+
"eval_loss": 5.062227725982666,
|
| 51 |
+
"eval_runtime": 11.1285,
|
| 52 |
+
"eval_samples_per_second": 11.143,
|
| 53 |
+
"eval_steps_per_second": 0.719,
|
| 54 |
+
"step": 3
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.10810810810810811,
|
| 58 |
+
"grad_norm": 3.3044817447662354,
|
| 59 |
+
"learning_rate": 0.00013333333333333334,
|
| 60 |
+
"loss": 5.0744,
|
| 61 |
+
"step": 4
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.10810810810810811,
|
| 65 |
+
"eval_loss": 4.176051139831543,
|
| 66 |
+
"eval_runtime": 11.2317,
|
| 67 |
+
"eval_samples_per_second": 11.04,
|
| 68 |
+
"eval_steps_per_second": 0.712,
|
| 69 |
+
"step": 4
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.13513513513513514,
|
| 73 |
+
"grad_norm": 3.3503236770629883,
|
| 74 |
+
"learning_rate": 0.0001666666666666667,
|
| 75 |
+
"loss": 4.1348,
|
| 76 |
+
"step": 5
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.13513513513513514,
|
| 80 |
+
"eval_loss": 3.137871265411377,
|
| 81 |
+
"eval_runtime": 11.1384,
|
| 82 |
+
"eval_samples_per_second": 11.133,
|
| 83 |
+
"eval_steps_per_second": 0.718,
|
| 84 |
+
"step": 5
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.16216216216216217,
|
| 88 |
+
"grad_norm": 2.9682626724243164,
|
| 89 |
+
"learning_rate": 0.0002,
|
| 90 |
+
"loss": 3.0425,
|
| 91 |
+
"step": 6
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.16216216216216217,
|
| 95 |
+
"eval_loss": 2.459784746170044,
|
| 96 |
+
"eval_runtime": 11.1086,
|
| 97 |
+
"eval_samples_per_second": 11.163,
|
| 98 |
+
"eval_steps_per_second": 0.72,
|
| 99 |
+
"step": 6
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.1891891891891892,
|
| 103 |
+
"grad_norm": 1.8949077129364014,
|
| 104 |
+
"learning_rate": 0.00023333333333333336,
|
| 105 |
+
"loss": 2.3291,
|
| 106 |
+
"step": 7
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.1891891891891892,
|
| 110 |
+
"eval_loss": 2.064051866531372,
|
| 111 |
+
"eval_runtime": 11.1293,
|
| 112 |
+
"eval_samples_per_second": 11.142,
|
| 113 |
+
"eval_steps_per_second": 0.719,
|
| 114 |
+
"step": 7
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.21621621621621623,
|
| 118 |
+
"grad_norm": 1.2975975275039673,
|
| 119 |
+
"learning_rate": 0.0002666666666666667,
|
| 120 |
+
"loss": 1.9481,
|
| 121 |
+
"step": 8
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.21621621621621623,
|
| 125 |
+
"eval_loss": 1.826060175895691,
|
| 126 |
+
"eval_runtime": 11.1457,
|
| 127 |
+
"eval_samples_per_second": 11.125,
|
| 128 |
+
"eval_steps_per_second": 0.718,
|
| 129 |
+
"step": 8
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.24324324324324326,
|
| 133 |
+
"grad_norm": 0.9844012260437012,
|
| 134 |
+
"learning_rate": 0.00030000000000000003,
|
| 135 |
+
"loss": 1.6863,
|
| 136 |
+
"step": 9
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.24324324324324326,
|
| 140 |
+
"eval_loss": 1.7158275842666626,
|
| 141 |
+
"eval_runtime": 11.1384,
|
| 142 |
+
"eval_samples_per_second": 11.133,
|
| 143 |
+
"eval_steps_per_second": 0.718,
|
| 144 |
+
"step": 9
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.2702702702702703,
|
| 148 |
+
"grad_norm": 0.9899163246154785,
|
| 149 |
+
"learning_rate": 0.0003333333333333334,
|
| 150 |
+
"loss": 1.6293,
|
| 151 |
+
"step": 10
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.2702702702702703,
|
| 155 |
+
"eval_loss": 1.6195639371871948,
|
| 156 |
+
"eval_runtime": 11.1633,
|
| 157 |
+
"eval_samples_per_second": 11.108,
|
| 158 |
+
"eval_steps_per_second": 0.717,
|
| 159 |
+
"step": 10
|
| 160 |
+
}
|
| 161 |
+
],
|
| 162 |
+
"logging_steps": 1,
|
| 163 |
+
"max_steps": 111,
|
| 164 |
+
"num_input_tokens_seen": 0,
|
| 165 |
+
"num_train_epochs": 3,
|
| 166 |
+
"save_steps": 10,
|
| 167 |
+
"stateful_callbacks": {
|
| 168 |
+
"TrainerControl": {
|
| 169 |
+
"args": {
|
| 170 |
+
"should_epoch_stop": false,
|
| 171 |
+
"should_evaluate": false,
|
| 172 |
+
"should_log": false,
|
| 173 |
+
"should_save": true,
|
| 174 |
+
"should_training_stop": false
|
| 175 |
+
},
|
| 176 |
+
"attributes": {}
|
| 177 |
+
}
|
| 178 |
+
},
|
| 179 |
+
"total_flos": 3708922028359680.0,
|
| 180 |
+
"train_batch_size": 32,
|
| 181 |
+
"trial_name": null,
|
| 182 |
+
"trial_params": null
|
| 183 |
+
}
|
checkpoint-10/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ea070c2faa734be8923d94fa3856f14e164a5abfa05c6110801b96bd6a62aca
|
| 3 |
+
size 5688
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<unk>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": true,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": false
|
| 28 |
+
},
|
| 29 |
+
"32000": {
|
| 30 |
+
"content": "<|endoftext|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"32001": {
|
| 38 |
+
"content": "<|assistant|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": true,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"32002": {
|
| 46 |
+
"content": "<|placeholder1|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": true,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"32003": {
|
| 54 |
+
"content": "<|placeholder2|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": true,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"32004": {
|
| 62 |
+
"content": "<|placeholder3|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": true,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"32005": {
|
| 70 |
+
"content": "<|placeholder4|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": true,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"32006": {
|
| 78 |
+
"content": "<|system|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": true,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"32007": {
|
| 86 |
+
"content": "<|end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": true,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"32008": {
|
| 94 |
+
"content": "<|placeholder5|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": true,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"32009": {
|
| 102 |
+
"content": "<|placeholder6|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": true,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"32010": {
|
| 110 |
+
"content": "<|user|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": true,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"32011": {
|
| 118 |
+
"content": "eos_token",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": true
|
| 124 |
+
}
|
| 125 |
+
},
|
| 126 |
+
"bos_token": "<s>",
|
| 127 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
|
| 128 |
+
"clean_up_tokenization_spaces": false,
|
| 129 |
+
"eos_token": "<|endoftext|>",
|
| 130 |
+
"legacy": false,
|
| 131 |
+
"model_max_length": 4096,
|
| 132 |
+
"pad_token": "<unk>",
|
| 133 |
+
"padding_side": "right",
|
| 134 |
+
"sp_model_kwargs": {},
|
| 135 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 136 |
+
"truncation_side": "left",
|
| 137 |
+
"unk_token": "<unk>",
|
| 138 |
+
"use_default_system_prompt": false
|
| 139 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 1.148636352371525,
|
| 4 |
+
"train_runtime": 2293.4445,
|
| 5 |
+
"train_samples_per_second": 1.54,
|
| 6 |
+
"train_steps_per_second": 0.048
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1707 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.6195639371871948,
|
| 3 |
+
"best_model_checkpoint": "./output/checkpoints/2024-06-11_15-20-56/checkpoint-10",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 1,
|
| 6 |
+
"global_step": 111,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02702702702702703,
|
| 13 |
+
"grad_norm": 3.045227289199829,
|
| 14 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 15 |
+
"loss": 5.5922,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02702702702702703,
|
| 20 |
+
"eval_loss": 5.6431684494018555,
|
| 21 |
+
"eval_runtime": 11.0821,
|
| 22 |
+
"eval_samples_per_second": 11.189,
|
| 23 |
+
"eval_steps_per_second": 0.722,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05405405405405406,
|
| 28 |
+
"grad_norm": 3.084507942199707,
|
| 29 |
+
"learning_rate": 6.666666666666667e-05,
|
| 30 |
+
"loss": 5.6812,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.05405405405405406,
|
| 35 |
+
"eval_loss": 5.540425777435303,
|
| 36 |
+
"eval_runtime": 11.083,
|
| 37 |
+
"eval_samples_per_second": 11.188,
|
| 38 |
+
"eval_steps_per_second": 0.722,
|
| 39 |
+
"step": 2
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.08108108108108109,
|
| 43 |
+
"grad_norm": 3.1143131256103516,
|
| 44 |
+
"learning_rate": 0.0001,
|
| 45 |
+
"loss": 5.5805,
|
| 46 |
+
"step": 3
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.08108108108108109,
|
| 50 |
+
"eval_loss": 5.062227725982666,
|
| 51 |
+
"eval_runtime": 11.1285,
|
| 52 |
+
"eval_samples_per_second": 11.143,
|
| 53 |
+
"eval_steps_per_second": 0.719,
|
| 54 |
+
"step": 3
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.10810810810810811,
|
| 58 |
+
"grad_norm": 3.3044817447662354,
|
| 59 |
+
"learning_rate": 0.00013333333333333334,
|
| 60 |
+
"loss": 5.0744,
|
| 61 |
+
"step": 4
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.10810810810810811,
|
| 65 |
+
"eval_loss": 4.176051139831543,
|
| 66 |
+
"eval_runtime": 11.2317,
|
| 67 |
+
"eval_samples_per_second": 11.04,
|
| 68 |
+
"eval_steps_per_second": 0.712,
|
| 69 |
+
"step": 4
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.13513513513513514,
|
| 73 |
+
"grad_norm": 3.3503236770629883,
|
| 74 |
+
"learning_rate": 0.0001666666666666667,
|
| 75 |
+
"loss": 4.1348,
|
| 76 |
+
"step": 5
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.13513513513513514,
|
| 80 |
+
"eval_loss": 3.137871265411377,
|
| 81 |
+
"eval_runtime": 11.1384,
|
| 82 |
+
"eval_samples_per_second": 11.133,
|
| 83 |
+
"eval_steps_per_second": 0.718,
|
| 84 |
+
"step": 5
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.16216216216216217,
|
| 88 |
+
"grad_norm": 2.9682626724243164,
|
| 89 |
+
"learning_rate": 0.0002,
|
| 90 |
+
"loss": 3.0425,
|
| 91 |
+
"step": 6
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.16216216216216217,
|
| 95 |
+
"eval_loss": 2.459784746170044,
|
| 96 |
+
"eval_runtime": 11.1086,
|
| 97 |
+
"eval_samples_per_second": 11.163,
|
| 98 |
+
"eval_steps_per_second": 0.72,
|
| 99 |
+
"step": 6
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.1891891891891892,
|
| 103 |
+
"grad_norm": 1.8949077129364014,
|
| 104 |
+
"learning_rate": 0.00023333333333333336,
|
| 105 |
+
"loss": 2.3291,
|
| 106 |
+
"step": 7
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.1891891891891892,
|
| 110 |
+
"eval_loss": 2.064051866531372,
|
| 111 |
+
"eval_runtime": 11.1293,
|
| 112 |
+
"eval_samples_per_second": 11.142,
|
| 113 |
+
"eval_steps_per_second": 0.719,
|
| 114 |
+
"step": 7
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.21621621621621623,
|
| 118 |
+
"grad_norm": 1.2975975275039673,
|
| 119 |
+
"learning_rate": 0.0002666666666666667,
|
| 120 |
+
"loss": 1.9481,
|
| 121 |
+
"step": 8
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.21621621621621623,
|
| 125 |
+
"eval_loss": 1.826060175895691,
|
| 126 |
+
"eval_runtime": 11.1457,
|
| 127 |
+
"eval_samples_per_second": 11.125,
|
| 128 |
+
"eval_steps_per_second": 0.718,
|
| 129 |
+
"step": 8
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.24324324324324326,
|
| 133 |
+
"grad_norm": 0.9844012260437012,
|
| 134 |
+
"learning_rate": 0.00030000000000000003,
|
| 135 |
+
"loss": 1.6863,
|
| 136 |
+
"step": 9
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.24324324324324326,
|
| 140 |
+
"eval_loss": 1.7158275842666626,
|
| 141 |
+
"eval_runtime": 11.1384,
|
| 142 |
+
"eval_samples_per_second": 11.133,
|
| 143 |
+
"eval_steps_per_second": 0.718,
|
| 144 |
+
"step": 9
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.2702702702702703,
|
| 148 |
+
"grad_norm": 0.9899163246154785,
|
| 149 |
+
"learning_rate": 0.0003333333333333334,
|
| 150 |
+
"loss": 1.6293,
|
| 151 |
+
"step": 10
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.2702702702702703,
|
| 155 |
+
"eval_loss": 1.6195639371871948,
|
| 156 |
+
"eval_runtime": 11.1633,
|
| 157 |
+
"eval_samples_per_second": 11.108,
|
| 158 |
+
"eval_steps_per_second": 0.717,
|
| 159 |
+
"step": 10
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.2972972972972973,
|
| 163 |
+
"grad_norm": 0.2760697901248932,
|
| 164 |
+
"learning_rate": 0.00036666666666666667,
|
| 165 |
+
"loss": 1.5182,
|
| 166 |
+
"step": 11
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.2972972972972973,
|
| 170 |
+
"eval_loss": 1.5875523090362549,
|
| 171 |
+
"eval_runtime": 11.1331,
|
| 172 |
+
"eval_samples_per_second": 11.138,
|
| 173 |
+
"eval_steps_per_second": 0.719,
|
| 174 |
+
"step": 11
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.32432432432432434,
|
| 178 |
+
"grad_norm": 0.4246121644973755,
|
| 179 |
+
"learning_rate": 0.0004,
|
| 180 |
+
"loss": 1.432,
|
| 181 |
+
"step": 12
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.32432432432432434,
|
| 185 |
+
"eval_loss": 1.574428677558899,
|
| 186 |
+
"eval_runtime": 11.1913,
|
| 187 |
+
"eval_samples_per_second": 11.08,
|
| 188 |
+
"eval_steps_per_second": 0.715,
|
| 189 |
+
"step": 12
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.35135135135135137,
|
| 193 |
+
"grad_norm": 0.4968096911907196,
|
| 194 |
+
"learning_rate": 0.000395959595959596,
|
| 195 |
+
"loss": 1.3155,
|
| 196 |
+
"step": 13
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.35135135135135137,
|
| 200 |
+
"eval_loss": 1.6574310064315796,
|
| 201 |
+
"eval_runtime": 11.1636,
|
| 202 |
+
"eval_samples_per_second": 11.108,
|
| 203 |
+
"eval_steps_per_second": 0.717,
|
| 204 |
+
"step": 13
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.3783783783783784,
|
| 208 |
+
"grad_norm": 0.2221263200044632,
|
| 209 |
+
"learning_rate": 0.0003919191919191919,
|
| 210 |
+
"loss": 1.2013,
|
| 211 |
+
"step": 14
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.3783783783783784,
|
| 215 |
+
"eval_loss": 1.7277523279190063,
|
| 216 |
+
"eval_runtime": 11.2226,
|
| 217 |
+
"eval_samples_per_second": 11.049,
|
| 218 |
+
"eval_steps_per_second": 0.713,
|
| 219 |
+
"step": 14
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.40540540540540543,
|
| 223 |
+
"grad_norm": 0.24387121200561523,
|
| 224 |
+
"learning_rate": 0.0003878787878787879,
|
| 225 |
+
"loss": 1.1303,
|
| 226 |
+
"step": 15
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.40540540540540543,
|
| 230 |
+
"eval_loss": 1.7132700681686401,
|
| 231 |
+
"eval_runtime": 11.1622,
|
| 232 |
+
"eval_samples_per_second": 11.109,
|
| 233 |
+
"eval_steps_per_second": 0.717,
|
| 234 |
+
"step": 15
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.43243243243243246,
|
| 238 |
+
"grad_norm": 0.2101132869720459,
|
| 239 |
+
"learning_rate": 0.00038383838383838383,
|
| 240 |
+
"loss": 1.1181,
|
| 241 |
+
"step": 16
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.43243243243243246,
|
| 245 |
+
"eval_loss": 1.6620469093322754,
|
| 246 |
+
"eval_runtime": 11.1581,
|
| 247 |
+
"eval_samples_per_second": 11.113,
|
| 248 |
+
"eval_steps_per_second": 0.717,
|
| 249 |
+
"step": 16
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.4594594594594595,
|
| 253 |
+
"grad_norm": 0.1956334114074707,
|
| 254 |
+
"learning_rate": 0.0003797979797979798,
|
| 255 |
+
"loss": 1.0897,
|
| 256 |
+
"step": 17
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.4594594594594595,
|
| 260 |
+
"eval_loss": 1.6307740211486816,
|
| 261 |
+
"eval_runtime": 11.1407,
|
| 262 |
+
"eval_samples_per_second": 11.13,
|
| 263 |
+
"eval_steps_per_second": 0.718,
|
| 264 |
+
"step": 17
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.4864864864864865,
|
| 268 |
+
"grad_norm": 0.1778702437877655,
|
| 269 |
+
"learning_rate": 0.0003757575757575758,
|
| 270 |
+
"loss": 1.0865,
|
| 271 |
+
"step": 18
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.4864864864864865,
|
| 275 |
+
"eval_loss": 1.6229671239852905,
|
| 276 |
+
"eval_runtime": 11.2453,
|
| 277 |
+
"eval_samples_per_second": 11.027,
|
| 278 |
+
"eval_steps_per_second": 0.711,
|
| 279 |
+
"step": 18
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.5135135135135135,
|
| 283 |
+
"grad_norm": 0.15137992799282074,
|
| 284 |
+
"learning_rate": 0.0003717171717171717,
|
| 285 |
+
"loss": 1.0591,
|
| 286 |
+
"step": 19
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.5135135135135135,
|
| 290 |
+
"eval_loss": 1.6271958351135254,
|
| 291 |
+
"eval_runtime": 11.1705,
|
| 292 |
+
"eval_samples_per_second": 11.101,
|
| 293 |
+
"eval_steps_per_second": 0.716,
|
| 294 |
+
"step": 19
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.5405405405405406,
|
| 298 |
+
"grad_norm": 0.11392053216695786,
|
| 299 |
+
"learning_rate": 0.0003676767676767677,
|
| 300 |
+
"loss": 1.0392,
|
| 301 |
+
"step": 20
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.5405405405405406,
|
| 305 |
+
"eval_loss": 1.6411267518997192,
|
| 306 |
+
"eval_runtime": 11.1409,
|
| 307 |
+
"eval_samples_per_second": 11.13,
|
| 308 |
+
"eval_steps_per_second": 0.718,
|
| 309 |
+
"step": 20
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.5675675675675675,
|
| 313 |
+
"grad_norm": 0.0866568386554718,
|
| 314 |
+
"learning_rate": 0.00036363636363636367,
|
| 315 |
+
"loss": 1.0073,
|
| 316 |
+
"step": 21
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.5675675675675675,
|
| 320 |
+
"eval_loss": 1.6590908765792847,
|
| 321 |
+
"eval_runtime": 11.1242,
|
| 322 |
+
"eval_samples_per_second": 11.147,
|
| 323 |
+
"eval_steps_per_second": 0.719,
|
| 324 |
+
"step": 21
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.5945945945945946,
|
| 328 |
+
"grad_norm": 0.10577922314405441,
|
| 329 |
+
"learning_rate": 0.0003595959595959596,
|
| 330 |
+
"loss": 0.9898,
|
| 331 |
+
"step": 22
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5945945945945946,
|
| 335 |
+
"eval_loss": 1.6635982990264893,
|
| 336 |
+
"eval_runtime": 11.2221,
|
| 337 |
+
"eval_samples_per_second": 11.05,
|
| 338 |
+
"eval_steps_per_second": 0.713,
|
| 339 |
+
"step": 22
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.6216216216216216,
|
| 343 |
+
"grad_norm": 0.1029527559876442,
|
| 344 |
+
"learning_rate": 0.00035555555555555557,
|
| 345 |
+
"loss": 1.0017,
|
| 346 |
+
"step": 23
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.6216216216216216,
|
| 350 |
+
"eval_loss": 1.6551401615142822,
|
| 351 |
+
"eval_runtime": 11.1896,
|
| 352 |
+
"eval_samples_per_second": 11.082,
|
| 353 |
+
"eval_steps_per_second": 0.715,
|
| 354 |
+
"step": 23
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.6486486486486487,
|
| 358 |
+
"grad_norm": 0.09740535914897919,
|
| 359 |
+
"learning_rate": 0.00035151515151515155,
|
| 360 |
+
"loss": 1.0052,
|
| 361 |
+
"step": 24
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.6486486486486487,
|
| 365 |
+
"eval_loss": 1.642539620399475,
|
| 366 |
+
"eval_runtime": 11.1624,
|
| 367 |
+
"eval_samples_per_second": 11.109,
|
| 368 |
+
"eval_steps_per_second": 0.717,
|
| 369 |
+
"step": 24
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.6756756756756757,
|
| 373 |
+
"grad_norm": 0.09230296313762665,
|
| 374 |
+
"learning_rate": 0.00034747474747474753,
|
| 375 |
+
"loss": 0.9873,
|
| 376 |
+
"step": 25
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.6756756756756757,
|
| 380 |
+
"eval_loss": 1.6282507181167603,
|
| 381 |
+
"eval_runtime": 11.0959,
|
| 382 |
+
"eval_samples_per_second": 11.175,
|
| 383 |
+
"eval_steps_per_second": 0.721,
|
| 384 |
+
"step": 25
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.7027027027027027,
|
| 388 |
+
"grad_norm": 0.08403297513723373,
|
| 389 |
+
"learning_rate": 0.00034343434343434346,
|
| 390 |
+
"loss": 0.9743,
|
| 391 |
+
"step": 26
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.7027027027027027,
|
| 395 |
+
"eval_loss": 1.6223111152648926,
|
| 396 |
+
"eval_runtime": 11.143,
|
| 397 |
+
"eval_samples_per_second": 11.128,
|
| 398 |
+
"eval_steps_per_second": 0.718,
|
| 399 |
+
"step": 26
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.7297297297297297,
|
| 403 |
+
"grad_norm": 0.0808207094669342,
|
| 404 |
+
"learning_rate": 0.00033939393939393943,
|
| 405 |
+
"loss": 0.9752,
|
| 406 |
+
"step": 27
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.7297297297297297,
|
| 410 |
+
"eval_loss": 1.6211432218551636,
|
| 411 |
+
"eval_runtime": 11.2057,
|
| 412 |
+
"eval_samples_per_second": 11.066,
|
| 413 |
+
"eval_steps_per_second": 0.714,
|
| 414 |
+
"step": 27
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.7567567567567568,
|
| 418 |
+
"grad_norm": 0.08751657605171204,
|
| 419 |
+
"learning_rate": 0.00033535353535353536,
|
| 420 |
+
"loss": 0.984,
|
| 421 |
+
"step": 28
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.7567567567567568,
|
| 425 |
+
"eval_loss": 1.6278128623962402,
|
| 426 |
+
"eval_runtime": 11.2228,
|
| 427 |
+
"eval_samples_per_second": 11.049,
|
| 428 |
+
"eval_steps_per_second": 0.713,
|
| 429 |
+
"step": 28
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.7837837837837838,
|
| 433 |
+
"grad_norm": 0.08614286035299301,
|
| 434 |
+
"learning_rate": 0.00033131313131313134,
|
| 435 |
+
"loss": 0.9609,
|
| 436 |
+
"step": 29
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.7837837837837838,
|
| 440 |
+
"eval_loss": 1.640842318534851,
|
| 441 |
+
"eval_runtime": 11.1451,
|
| 442 |
+
"eval_samples_per_second": 11.126,
|
| 443 |
+
"eval_steps_per_second": 0.718,
|
| 444 |
+
"step": 29
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.8108108108108109,
|
| 448 |
+
"grad_norm": 0.09667662531137466,
|
| 449 |
+
"learning_rate": 0.0003272727272727273,
|
| 450 |
+
"loss": 0.9947,
|
| 451 |
+
"step": 30
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.8108108108108109,
|
| 455 |
+
"eval_loss": 1.6455894708633423,
|
| 456 |
+
"eval_runtime": 11.163,
|
| 457 |
+
"eval_samples_per_second": 11.108,
|
| 458 |
+
"eval_steps_per_second": 0.717,
|
| 459 |
+
"step": 30
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.8378378378378378,
|
| 463 |
+
"grad_norm": 0.07943412661552429,
|
| 464 |
+
"learning_rate": 0.00032323232323232324,
|
| 465 |
+
"loss": 0.9682,
|
| 466 |
+
"step": 31
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.8378378378378378,
|
| 470 |
+
"eval_loss": 1.6466931104660034,
|
| 471 |
+
"eval_runtime": 11.1798,
|
| 472 |
+
"eval_samples_per_second": 11.091,
|
| 473 |
+
"eval_steps_per_second": 0.716,
|
| 474 |
+
"step": 31
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.8648648648648649,
|
| 478 |
+
"grad_norm": 0.08821859955787659,
|
| 479 |
+
"learning_rate": 0.0003191919191919192,
|
| 480 |
+
"loss": 0.9828,
|
| 481 |
+
"step": 32
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.8648648648648649,
|
| 485 |
+
"eval_loss": 1.6367429494857788,
|
| 486 |
+
"eval_runtime": 11.1174,
|
| 487 |
+
"eval_samples_per_second": 11.154,
|
| 488 |
+
"eval_steps_per_second": 0.72,
|
| 489 |
+
"step": 32
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.8918918918918919,
|
| 493 |
+
"grad_norm": 0.07129044830799103,
|
| 494 |
+
"learning_rate": 0.00031515151515151515,
|
| 495 |
+
"loss": 0.9315,
|
| 496 |
+
"step": 33
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.8918918918918919,
|
| 500 |
+
"eval_loss": 1.632204294204712,
|
| 501 |
+
"eval_runtime": 11.1509,
|
| 502 |
+
"eval_samples_per_second": 11.12,
|
| 503 |
+
"eval_steps_per_second": 0.717,
|
| 504 |
+
"step": 33
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.918918918918919,
|
| 508 |
+
"grad_norm": 0.06505230814218521,
|
| 509 |
+
"learning_rate": 0.0003111111111111111,
|
| 510 |
+
"loss": 0.9541,
|
| 511 |
+
"step": 34
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.918918918918919,
|
| 515 |
+
"eval_loss": 1.6281696557998657,
|
| 516 |
+
"eval_runtime": 11.2284,
|
| 517 |
+
"eval_samples_per_second": 11.043,
|
| 518 |
+
"eval_steps_per_second": 0.712,
|
| 519 |
+
"step": 34
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.9459459459459459,
|
| 523 |
+
"grad_norm": 0.0691852867603302,
|
| 524 |
+
"learning_rate": 0.00030707070707070705,
|
| 525 |
+
"loss": 0.9753,
|
| 526 |
+
"step": 35
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.9459459459459459,
|
| 530 |
+
"eval_loss": 1.6272518634796143,
|
| 531 |
+
"eval_runtime": 11.1646,
|
| 532 |
+
"eval_samples_per_second": 11.106,
|
| 533 |
+
"eval_steps_per_second": 0.717,
|
| 534 |
+
"step": 35
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.972972972972973,
|
| 538 |
+
"grad_norm": 0.07006494700908661,
|
| 539 |
+
"learning_rate": 0.00030303030303030303,
|
| 540 |
+
"loss": 0.9399,
|
| 541 |
+
"step": 36
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.972972972972973,
|
| 545 |
+
"eval_loss": 1.6321260929107666,
|
| 546 |
+
"eval_runtime": 11.2226,
|
| 547 |
+
"eval_samples_per_second": 11.049,
|
| 548 |
+
"eval_steps_per_second": 0.713,
|
| 549 |
+
"step": 36
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.0,
|
| 553 |
+
"grad_norm": 0.08096865564584732,
|
| 554 |
+
"learning_rate": 0.000298989898989899,
|
| 555 |
+
"loss": 0.9456,
|
| 556 |
+
"step": 37
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.0,
|
| 560 |
+
"eval_loss": 1.6329066753387451,
|
| 561 |
+
"eval_runtime": 11.1546,
|
| 562 |
+
"eval_samples_per_second": 11.116,
|
| 563 |
+
"eval_steps_per_second": 0.717,
|
| 564 |
+
"step": 37
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.027027027027027,
|
| 568 |
+
"grad_norm": 0.06808632612228394,
|
| 569 |
+
"learning_rate": 0.00029494949494949493,
|
| 570 |
+
"loss": 0.9535,
|
| 571 |
+
"step": 38
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.027027027027027,
|
| 575 |
+
"eval_loss": 1.6349523067474365,
|
| 576 |
+
"eval_runtime": 11.1118,
|
| 577 |
+
"eval_samples_per_second": 11.159,
|
| 578 |
+
"eval_steps_per_second": 0.72,
|
| 579 |
+
"step": 38
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.054054054054054,
|
| 583 |
+
"grad_norm": 0.06536230444908142,
|
| 584 |
+
"learning_rate": 0.0002909090909090909,
|
| 585 |
+
"loss": 0.913,
|
| 586 |
+
"step": 39
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.054054054054054,
|
| 590 |
+
"eval_loss": 1.6410040855407715,
|
| 591 |
+
"eval_runtime": 11.252,
|
| 592 |
+
"eval_samples_per_second": 11.02,
|
| 593 |
+
"eval_steps_per_second": 0.711,
|
| 594 |
+
"step": 39
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.0810810810810811,
|
| 598 |
+
"grad_norm": 0.06929512321949005,
|
| 599 |
+
"learning_rate": 0.00028686868686868684,
|
| 600 |
+
"loss": 0.8924,
|
| 601 |
+
"step": 40
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.0810810810810811,
|
| 605 |
+
"eval_loss": 1.6510140895843506,
|
| 606 |
+
"eval_runtime": 11.1385,
|
| 607 |
+
"eval_samples_per_second": 11.133,
|
| 608 |
+
"eval_steps_per_second": 0.718,
|
| 609 |
+
"step": 40
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.1081081081081081,
|
| 613 |
+
"grad_norm": 0.06684686243534088,
|
| 614 |
+
"learning_rate": 0.0002828282828282828,
|
| 615 |
+
"loss": 0.901,
|
| 616 |
+
"step": 41
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.1081081081081081,
|
| 620 |
+
"eval_loss": 1.6621599197387695,
|
| 621 |
+
"eval_runtime": 11.1957,
|
| 622 |
+
"eval_samples_per_second": 11.076,
|
| 623 |
+
"eval_steps_per_second": 0.715,
|
| 624 |
+
"step": 41
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 1.135135135135135,
|
| 628 |
+
"grad_norm": 0.07049503922462463,
|
| 629 |
+
"learning_rate": 0.0002787878787878788,
|
| 630 |
+
"loss": 0.9256,
|
| 631 |
+
"step": 42
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 1.135135135135135,
|
| 635 |
+
"eval_loss": 1.6734611988067627,
|
| 636 |
+
"eval_runtime": 11.1581,
|
| 637 |
+
"eval_samples_per_second": 11.113,
|
| 638 |
+
"eval_steps_per_second": 0.717,
|
| 639 |
+
"step": 42
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.1621621621621623,
|
| 643 |
+
"grad_norm": 0.07425494492053986,
|
| 644 |
+
"learning_rate": 0.0002747474747474748,
|
| 645 |
+
"loss": 0.9002,
|
| 646 |
+
"step": 43
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.1621621621621623,
|
| 650 |
+
"eval_loss": 1.6794347763061523,
|
| 651 |
+
"eval_runtime": 11.0906,
|
| 652 |
+
"eval_samples_per_second": 11.181,
|
| 653 |
+
"eval_steps_per_second": 0.721,
|
| 654 |
+
"step": 43
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.1891891891891893,
|
| 658 |
+
"grad_norm": 0.07607400417327881,
|
| 659 |
+
"learning_rate": 0.00027070707070707075,
|
| 660 |
+
"loss": 0.8958,
|
| 661 |
+
"step": 44
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.1891891891891893,
|
| 665 |
+
"eval_loss": 1.6791983842849731,
|
| 666 |
+
"eval_runtime": 11.9226,
|
| 667 |
+
"eval_samples_per_second": 10.4,
|
| 668 |
+
"eval_steps_per_second": 0.671,
|
| 669 |
+
"step": 44
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.2162162162162162,
|
| 673 |
+
"grad_norm": 0.08622392266988754,
|
| 674 |
+
"learning_rate": 0.0002666666666666667,
|
| 675 |
+
"loss": 0.9143,
|
| 676 |
+
"step": 45
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.2162162162162162,
|
| 680 |
+
"eval_loss": 1.671402096748352,
|
| 681 |
+
"eval_runtime": 11.1349,
|
| 682 |
+
"eval_samples_per_second": 11.136,
|
| 683 |
+
"eval_steps_per_second": 0.718,
|
| 684 |
+
"step": 45
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 1.2432432432432432,
|
| 688 |
+
"grad_norm": 0.07751356065273285,
|
| 689 |
+
"learning_rate": 0.00026262626262626266,
|
| 690 |
+
"loss": 0.9092,
|
| 691 |
+
"step": 46
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 1.2432432432432432,
|
| 695 |
+
"eval_loss": 1.6581931114196777,
|
| 696 |
+
"eval_runtime": 11.1166,
|
| 697 |
+
"eval_samples_per_second": 11.154,
|
| 698 |
+
"eval_steps_per_second": 0.72,
|
| 699 |
+
"step": 46
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.2702702702702702,
|
| 703 |
+
"grad_norm": 0.07954052835702896,
|
| 704 |
+
"learning_rate": 0.00025858585858585864,
|
| 705 |
+
"loss": 0.9116,
|
| 706 |
+
"step": 47
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.2702702702702702,
|
| 710 |
+
"eval_loss": 1.6473214626312256,
|
| 711 |
+
"eval_runtime": 11.1774,
|
| 712 |
+
"eval_samples_per_second": 11.094,
|
| 713 |
+
"eval_steps_per_second": 0.716,
|
| 714 |
+
"step": 47
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.2972972972972974,
|
| 718 |
+
"grad_norm": 0.08470755070447922,
|
| 719 |
+
"learning_rate": 0.00025454545454545456,
|
| 720 |
+
"loss": 0.9039,
|
| 721 |
+
"step": 48
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 1.2972972972972974,
|
| 725 |
+
"eval_loss": 1.6490856409072876,
|
| 726 |
+
"eval_runtime": 11.1926,
|
| 727 |
+
"eval_samples_per_second": 11.079,
|
| 728 |
+
"eval_steps_per_second": 0.715,
|
| 729 |
+
"step": 48
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.3243243243243243,
|
| 733 |
+
"grad_norm": 0.08538611233234406,
|
| 734 |
+
"learning_rate": 0.00025050505050505054,
|
| 735 |
+
"loss": 0.8945,
|
| 736 |
+
"step": 49
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 1.3243243243243243,
|
| 740 |
+
"eval_loss": 1.6652594804763794,
|
| 741 |
+
"eval_runtime": 11.189,
|
| 742 |
+
"eval_samples_per_second": 11.082,
|
| 743 |
+
"eval_steps_per_second": 0.715,
|
| 744 |
+
"step": 49
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.3513513513513513,
|
| 748 |
+
"grad_norm": 0.08962593227624893,
|
| 749 |
+
"learning_rate": 0.00024646464646464647,
|
| 750 |
+
"loss": 0.8878,
|
| 751 |
+
"step": 50
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.3513513513513513,
|
| 755 |
+
"eval_loss": 1.6737427711486816,
|
| 756 |
+
"eval_runtime": 11.194,
|
| 757 |
+
"eval_samples_per_second": 11.077,
|
| 758 |
+
"eval_steps_per_second": 0.715,
|
| 759 |
+
"step": 50
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.3783783783783785,
|
| 763 |
+
"grad_norm": 0.09344533085823059,
|
| 764 |
+
"learning_rate": 0.00024242424242424245,
|
| 765 |
+
"loss": 0.8921,
|
| 766 |
+
"step": 51
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.3783783783783785,
|
| 770 |
+
"eval_loss": 1.6767627000808716,
|
| 771 |
+
"eval_runtime": 11.9154,
|
| 772 |
+
"eval_samples_per_second": 10.407,
|
| 773 |
+
"eval_steps_per_second": 0.671,
|
| 774 |
+
"step": 51
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 1.4054054054054055,
|
| 778 |
+
"grad_norm": 0.08334413915872574,
|
| 779 |
+
"learning_rate": 0.00023838383838383837,
|
| 780 |
+
"loss": 0.8879,
|
| 781 |
+
"step": 52
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 1.4054054054054055,
|
| 785 |
+
"eval_loss": 1.6724966764450073,
|
| 786 |
+
"eval_runtime": 11.0787,
|
| 787 |
+
"eval_samples_per_second": 11.193,
|
| 788 |
+
"eval_steps_per_second": 0.722,
|
| 789 |
+
"step": 52
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.4324324324324325,
|
| 793 |
+
"grad_norm": 0.0849594995379448,
|
| 794 |
+
"learning_rate": 0.00023434343434343435,
|
| 795 |
+
"loss": 0.9021,
|
| 796 |
+
"step": 53
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 1.4324324324324325,
|
| 800 |
+
"eval_loss": 1.6656012535095215,
|
| 801 |
+
"eval_runtime": 11.1933,
|
| 802 |
+
"eval_samples_per_second": 11.078,
|
| 803 |
+
"eval_steps_per_second": 0.715,
|
| 804 |
+
"step": 53
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 1.4594594594594594,
|
| 808 |
+
"grad_norm": 0.09131031483411789,
|
| 809 |
+
"learning_rate": 0.00023030303030303033,
|
| 810 |
+
"loss": 0.8975,
|
| 811 |
+
"step": 54
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 1.4594594594594594,
|
| 815 |
+
"eval_loss": 1.6548563241958618,
|
| 816 |
+
"eval_runtime": 11.2025,
|
| 817 |
+
"eval_samples_per_second": 11.069,
|
| 818 |
+
"eval_steps_per_second": 0.714,
|
| 819 |
+
"step": 54
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.4864864864864864,
|
| 823 |
+
"grad_norm": 0.0867348462343216,
|
| 824 |
+
"learning_rate": 0.00022626262626262625,
|
| 825 |
+
"loss": 0.8746,
|
| 826 |
+
"step": 55
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.4864864864864864,
|
| 830 |
+
"eval_loss": 1.6583256721496582,
|
| 831 |
+
"eval_runtime": 11.1258,
|
| 832 |
+
"eval_samples_per_second": 11.145,
|
| 833 |
+
"eval_steps_per_second": 0.719,
|
| 834 |
+
"step": 55
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 1.5135135135135136,
|
| 838 |
+
"grad_norm": 0.0924694687128067,
|
| 839 |
+
"learning_rate": 0.00022222222222222223,
|
| 840 |
+
"loss": 0.8818,
|
| 841 |
+
"step": 56
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 1.5135135135135136,
|
| 845 |
+
"eval_loss": 1.6754804849624634,
|
| 846 |
+
"eval_runtime": 11.1671,
|
| 847 |
+
"eval_samples_per_second": 11.104,
|
| 848 |
+
"eval_steps_per_second": 0.716,
|
| 849 |
+
"step": 56
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.5405405405405406,
|
| 853 |
+
"grad_norm": 0.09178721904754639,
|
| 854 |
+
"learning_rate": 0.00021818181818181818,
|
| 855 |
+
"loss": 0.9022,
|
| 856 |
+
"step": 57
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.5405405405405406,
|
| 860 |
+
"eval_loss": 1.690301775932312,
|
| 861 |
+
"eval_runtime": 11.0856,
|
| 862 |
+
"eval_samples_per_second": 11.186,
|
| 863 |
+
"eval_steps_per_second": 0.722,
|
| 864 |
+
"step": 57
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.5675675675675675,
|
| 868 |
+
"grad_norm": 0.08697674423456192,
|
| 869 |
+
"learning_rate": 0.00021414141414141416,
|
| 870 |
+
"loss": 0.8596,
|
| 871 |
+
"step": 58
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.5675675675675675,
|
| 875 |
+
"eval_loss": 1.7041698694229126,
|
| 876 |
+
"eval_runtime": 11.2652,
|
| 877 |
+
"eval_samples_per_second": 11.007,
|
| 878 |
+
"eval_steps_per_second": 0.71,
|
| 879 |
+
"step": 58
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.5945945945945947,
|
| 883 |
+
"grad_norm": 0.08802448958158493,
|
| 884 |
+
"learning_rate": 0.00021010101010101014,
|
| 885 |
+
"loss": 0.8572,
|
| 886 |
+
"step": 59
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 1.5945945945945947,
|
| 890 |
+
"eval_loss": 1.7124710083007812,
|
| 891 |
+
"eval_runtime": 11.152,
|
| 892 |
+
"eval_samples_per_second": 11.119,
|
| 893 |
+
"eval_steps_per_second": 0.717,
|
| 894 |
+
"step": 59
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 1.6216216216216215,
|
| 898 |
+
"grad_norm": 0.10100586712360382,
|
| 899 |
+
"learning_rate": 0.00020606060606060607,
|
| 900 |
+
"loss": 0.8883,
|
| 901 |
+
"step": 60
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 1.6216216216216215,
|
| 905 |
+
"eval_loss": 1.7054810523986816,
|
| 906 |
+
"eval_runtime": 11.1538,
|
| 907 |
+
"eval_samples_per_second": 11.117,
|
| 908 |
+
"eval_steps_per_second": 0.717,
|
| 909 |
+
"step": 60
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 1.6486486486486487,
|
| 913 |
+
"grad_norm": 0.11259682476520538,
|
| 914 |
+
"learning_rate": 0.00020202020202020205,
|
| 915 |
+
"loss": 0.8968,
|
| 916 |
+
"step": 61
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 1.6486486486486487,
|
| 920 |
+
"eval_loss": 1.683681845664978,
|
| 921 |
+
"eval_runtime": 11.1309,
|
| 922 |
+
"eval_samples_per_second": 11.14,
|
| 923 |
+
"eval_steps_per_second": 0.719,
|
| 924 |
+
"step": 61
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 1.6756756756756757,
|
| 928 |
+
"grad_norm": 0.0911870002746582,
|
| 929 |
+
"learning_rate": 0.000197979797979798,
|
| 930 |
+
"loss": 0.8287,
|
| 931 |
+
"step": 62
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 1.6756756756756757,
|
| 935 |
+
"eval_loss": 1.6670082807540894,
|
| 936 |
+
"eval_runtime": 11.1469,
|
| 937 |
+
"eval_samples_per_second": 11.124,
|
| 938 |
+
"eval_steps_per_second": 0.718,
|
| 939 |
+
"step": 62
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 1.7027027027027026,
|
| 943 |
+
"grad_norm": 0.08852899819612503,
|
| 944 |
+
"learning_rate": 0.00019393939393939395,
|
| 945 |
+
"loss": 0.8699,
|
| 946 |
+
"step": 63
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 1.7027027027027026,
|
| 950 |
+
"eval_loss": 1.6602628231048584,
|
| 951 |
+
"eval_runtime": 11.2189,
|
| 952 |
+
"eval_samples_per_second": 11.053,
|
| 953 |
+
"eval_steps_per_second": 0.713,
|
| 954 |
+
"step": 63
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.7297297297297298,
|
| 958 |
+
"grad_norm": 0.0944983959197998,
|
| 959 |
+
"learning_rate": 0.0001898989898989899,
|
| 960 |
+
"loss": 0.8812,
|
| 961 |
+
"step": 64
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.7297297297297298,
|
| 965 |
+
"eval_loss": 1.664315104484558,
|
| 966 |
+
"eval_runtime": 11.1484,
|
| 967 |
+
"eval_samples_per_second": 11.123,
|
| 968 |
+
"eval_steps_per_second": 0.718,
|
| 969 |
+
"step": 64
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.7567567567567568,
|
| 973 |
+
"grad_norm": 0.09581159055233002,
|
| 974 |
+
"learning_rate": 0.00018585858585858586,
|
| 975 |
+
"loss": 0.8671,
|
| 976 |
+
"step": 65
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.7567567567567568,
|
| 980 |
+
"eval_loss": 1.6748771667480469,
|
| 981 |
+
"eval_runtime": 11.2306,
|
| 982 |
+
"eval_samples_per_second": 11.041,
|
| 983 |
+
"eval_steps_per_second": 0.712,
|
| 984 |
+
"step": 65
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 1.7837837837837838,
|
| 988 |
+
"grad_norm": 0.09136416763067245,
|
| 989 |
+
"learning_rate": 0.00018181818181818183,
|
| 990 |
+
"loss": 0.8857,
|
| 991 |
+
"step": 66
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 1.7837837837837838,
|
| 995 |
+
"eval_loss": 1.6853251457214355,
|
| 996 |
+
"eval_runtime": 11.1546,
|
| 997 |
+
"eval_samples_per_second": 11.116,
|
| 998 |
+
"eval_steps_per_second": 0.717,
|
| 999 |
+
"step": 66
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 1.810810810810811,
|
| 1003 |
+
"grad_norm": 0.09602421522140503,
|
| 1004 |
+
"learning_rate": 0.00017777777777777779,
|
| 1005 |
+
"loss": 0.8578,
|
| 1006 |
+
"step": 67
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 1.810810810810811,
|
| 1010 |
+
"eval_loss": 1.6973600387573242,
|
| 1011 |
+
"eval_runtime": 11.2294,
|
| 1012 |
+
"eval_samples_per_second": 11.042,
|
| 1013 |
+
"eval_steps_per_second": 0.712,
|
| 1014 |
+
"step": 67
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 1.8378378378378377,
|
| 1018 |
+
"grad_norm": 0.10458902269601822,
|
| 1019 |
+
"learning_rate": 0.00017373737373737377,
|
| 1020 |
+
"loss": 0.8767,
|
| 1021 |
+
"step": 68
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 1.8378378378378377,
|
| 1025 |
+
"eval_loss": 1.7042148113250732,
|
| 1026 |
+
"eval_runtime": 11.1244,
|
| 1027 |
+
"eval_samples_per_second": 11.147,
|
| 1028 |
+
"eval_steps_per_second": 0.719,
|
| 1029 |
+
"step": 68
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 1.864864864864865,
|
| 1033 |
+
"grad_norm": 0.12431007623672485,
|
| 1034 |
+
"learning_rate": 0.00016969696969696972,
|
| 1035 |
+
"loss": 0.8914,
|
| 1036 |
+
"step": 69
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 1.864864864864865,
|
| 1040 |
+
"eval_loss": 1.702877402305603,
|
| 1041 |
+
"eval_runtime": 11.144,
|
| 1042 |
+
"eval_samples_per_second": 11.127,
|
| 1043 |
+
"eval_steps_per_second": 0.718,
|
| 1044 |
+
"step": 69
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 1.8918918918918919,
|
| 1048 |
+
"grad_norm": 0.11106838285923004,
|
| 1049 |
+
"learning_rate": 0.00016565656565656567,
|
| 1050 |
+
"loss": 0.8843,
|
| 1051 |
+
"step": 70
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 1.8918918918918919,
|
| 1055 |
+
"eval_loss": 1.691541314125061,
|
| 1056 |
+
"eval_runtime": 11.1751,
|
| 1057 |
+
"eval_samples_per_second": 11.096,
|
| 1058 |
+
"eval_steps_per_second": 0.716,
|
| 1059 |
+
"step": 70
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.9189189189189189,
|
| 1063 |
+
"grad_norm": 0.0916941687464714,
|
| 1064 |
+
"learning_rate": 0.00016161616161616162,
|
| 1065 |
+
"loss": 0.8576,
|
| 1066 |
+
"step": 71
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.9189189189189189,
|
| 1070 |
+
"eval_loss": 1.68495774269104,
|
| 1071 |
+
"eval_runtime": 11.208,
|
| 1072 |
+
"eval_samples_per_second": 11.063,
|
| 1073 |
+
"eval_steps_per_second": 0.714,
|
| 1074 |
+
"step": 71
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.945945945945946,
|
| 1078 |
+
"grad_norm": 0.10394521802663803,
|
| 1079 |
+
"learning_rate": 0.00015757575757575757,
|
| 1080 |
+
"loss": 0.853,
|
| 1081 |
+
"step": 72
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.945945945945946,
|
| 1085 |
+
"eval_loss": 1.6894781589508057,
|
| 1086 |
+
"eval_runtime": 11.1546,
|
| 1087 |
+
"eval_samples_per_second": 11.117,
|
| 1088 |
+
"eval_steps_per_second": 0.717,
|
| 1089 |
+
"step": 72
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 1.972972972972973,
|
| 1093 |
+
"grad_norm": 0.09884631633758545,
|
| 1094 |
+
"learning_rate": 0.00015353535353535353,
|
| 1095 |
+
"loss": 0.8346,
|
| 1096 |
+
"step": 73
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 1.972972972972973,
|
| 1100 |
+
"eval_loss": 1.7004313468933105,
|
| 1101 |
+
"eval_runtime": 11.107,
|
| 1102 |
+
"eval_samples_per_second": 11.164,
|
| 1103 |
+
"eval_steps_per_second": 0.72,
|
| 1104 |
+
"step": 73
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 2.0,
|
| 1108 |
+
"grad_norm": 0.11277178674936295,
|
| 1109 |
+
"learning_rate": 0.0001494949494949495,
|
| 1110 |
+
"loss": 0.8524,
|
| 1111 |
+
"step": 74
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 2.0,
|
| 1115 |
+
"eval_loss": 1.704146385192871,
|
| 1116 |
+
"eval_runtime": 11.1746,
|
| 1117 |
+
"eval_samples_per_second": 11.097,
|
| 1118 |
+
"eval_steps_per_second": 0.716,
|
| 1119 |
+
"step": 74
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 2.027027027027027,
|
| 1123 |
+
"grad_norm": 0.0982976108789444,
|
| 1124 |
+
"learning_rate": 0.00014545454545454546,
|
| 1125 |
+
"loss": 0.8267,
|
| 1126 |
+
"step": 75
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 2.027027027027027,
|
| 1130 |
+
"eval_loss": 1.7128726243972778,
|
| 1131 |
+
"eval_runtime": 11.1189,
|
| 1132 |
+
"eval_samples_per_second": 11.152,
|
| 1133 |
+
"eval_steps_per_second": 0.719,
|
| 1134 |
+
"step": 75
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 2.054054054054054,
|
| 1138 |
+
"grad_norm": 0.09641794860363007,
|
| 1139 |
+
"learning_rate": 0.0001414141414141414,
|
| 1140 |
+
"loss": 0.8157,
|
| 1141 |
+
"step": 76
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 2.054054054054054,
|
| 1145 |
+
"eval_loss": 1.7283172607421875,
|
| 1146 |
+
"eval_runtime": 11.1515,
|
| 1147 |
+
"eval_samples_per_second": 11.12,
|
| 1148 |
+
"eval_steps_per_second": 0.717,
|
| 1149 |
+
"step": 76
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 2.081081081081081,
|
| 1153 |
+
"grad_norm": 0.10205162316560745,
|
| 1154 |
+
"learning_rate": 0.0001373737373737374,
|
| 1155 |
+
"loss": 0.7977,
|
| 1156 |
+
"step": 77
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 2.081081081081081,
|
| 1160 |
+
"eval_loss": 1.7365342378616333,
|
| 1161 |
+
"eval_runtime": 11.0683,
|
| 1162 |
+
"eval_samples_per_second": 11.203,
|
| 1163 |
+
"eval_steps_per_second": 0.723,
|
| 1164 |
+
"step": 77
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 2.108108108108108,
|
| 1168 |
+
"grad_norm": 0.1005796566605568,
|
| 1169 |
+
"learning_rate": 0.00013333333333333334,
|
| 1170 |
+
"loss": 0.815,
|
| 1171 |
+
"step": 78
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 2.108108108108108,
|
| 1175 |
+
"eval_loss": 1.7438631057739258,
|
| 1176 |
+
"eval_runtime": 11.1586,
|
| 1177 |
+
"eval_samples_per_second": 11.113,
|
| 1178 |
+
"eval_steps_per_second": 0.717,
|
| 1179 |
+
"step": 78
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.135135135135135,
|
| 1183 |
+
"grad_norm": 0.111351877450943,
|
| 1184 |
+
"learning_rate": 0.00012929292929292932,
|
| 1185 |
+
"loss": 0.7987,
|
| 1186 |
+
"step": 79
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.135135135135135,
|
| 1190 |
+
"eval_loss": 1.7426629066467285,
|
| 1191 |
+
"eval_runtime": 11.1248,
|
| 1192 |
+
"eval_samples_per_second": 11.146,
|
| 1193 |
+
"eval_steps_per_second": 0.719,
|
| 1194 |
+
"step": 79
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 2.1621621621621623,
|
| 1198 |
+
"grad_norm": 0.10649854689836502,
|
| 1199 |
+
"learning_rate": 0.00012525252525252527,
|
| 1200 |
+
"loss": 0.8072,
|
| 1201 |
+
"step": 80
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 2.1621621621621623,
|
| 1205 |
+
"eval_loss": 1.7457417249679565,
|
| 1206 |
+
"eval_runtime": 11.1907,
|
| 1207 |
+
"eval_samples_per_second": 11.081,
|
| 1208 |
+
"eval_steps_per_second": 0.715,
|
| 1209 |
+
"step": 80
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 2.189189189189189,
|
| 1213 |
+
"grad_norm": 0.09818455576896667,
|
| 1214 |
+
"learning_rate": 0.00012121212121212122,
|
| 1215 |
+
"loss": 0.8024,
|
| 1216 |
+
"step": 81
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 2.189189189189189,
|
| 1220 |
+
"eval_loss": 1.7508054971694946,
|
| 1221 |
+
"eval_runtime": 11.1556,
|
| 1222 |
+
"eval_samples_per_second": 11.115,
|
| 1223 |
+
"eval_steps_per_second": 0.717,
|
| 1224 |
+
"step": 81
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 2.2162162162162162,
|
| 1228 |
+
"grad_norm": 0.1122928112745285,
|
| 1229 |
+
"learning_rate": 0.00011717171717171717,
|
| 1230 |
+
"loss": 0.8208,
|
| 1231 |
+
"step": 82
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 2.2162162162162162,
|
| 1235 |
+
"eval_loss": 1.7618576288223267,
|
| 1236 |
+
"eval_runtime": 11.2048,
|
| 1237 |
+
"eval_samples_per_second": 11.067,
|
| 1238 |
+
"eval_steps_per_second": 0.714,
|
| 1239 |
+
"step": 82
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 2.2432432432432434,
|
| 1243 |
+
"grad_norm": 0.10680953413248062,
|
| 1244 |
+
"learning_rate": 0.00011313131313131313,
|
| 1245 |
+
"loss": 0.7858,
|
| 1246 |
+
"step": 83
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 2.2432432432432434,
|
| 1250 |
+
"eval_loss": 1.7693935632705688,
|
| 1251 |
+
"eval_runtime": 11.1465,
|
| 1252 |
+
"eval_samples_per_second": 11.125,
|
| 1253 |
+
"eval_steps_per_second": 0.718,
|
| 1254 |
+
"step": 83
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 2.27027027027027,
|
| 1258 |
+
"grad_norm": 0.11239504814147949,
|
| 1259 |
+
"learning_rate": 0.00010909090909090909,
|
| 1260 |
+
"loss": 0.8082,
|
| 1261 |
+
"step": 84
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 2.27027027027027,
|
| 1265 |
+
"eval_loss": 1.780279517173767,
|
| 1266 |
+
"eval_runtime": 11.1781,
|
| 1267 |
+
"eval_samples_per_second": 11.093,
|
| 1268 |
+
"eval_steps_per_second": 0.716,
|
| 1269 |
+
"step": 84
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 2.2972972972972974,
|
| 1273 |
+
"grad_norm": 0.12527017295360565,
|
| 1274 |
+
"learning_rate": 0.00010505050505050507,
|
| 1275 |
+
"loss": 0.7943,
|
| 1276 |
+
"step": 85
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 2.2972972972972974,
|
| 1280 |
+
"eval_loss": 1.7797414064407349,
|
| 1281 |
+
"eval_runtime": 11.1811,
|
| 1282 |
+
"eval_samples_per_second": 11.09,
|
| 1283 |
+
"eval_steps_per_second": 0.715,
|
| 1284 |
+
"step": 85
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.3243243243243246,
|
| 1288 |
+
"grad_norm": 0.13715100288391113,
|
| 1289 |
+
"learning_rate": 0.00010101010101010102,
|
| 1290 |
+
"loss": 0.8338,
|
| 1291 |
+
"step": 86
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.3243243243243246,
|
| 1295 |
+
"eval_loss": 1.7673975229263306,
|
| 1296 |
+
"eval_runtime": 11.217,
|
| 1297 |
+
"eval_samples_per_second": 11.055,
|
| 1298 |
+
"eval_steps_per_second": 0.713,
|
| 1299 |
+
"step": 86
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 2.3513513513513513,
|
| 1303 |
+
"grad_norm": 0.11464574187994003,
|
| 1304 |
+
"learning_rate": 9.696969696969698e-05,
|
| 1305 |
+
"loss": 0.8038,
|
| 1306 |
+
"step": 87
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 2.3513513513513513,
|
| 1310 |
+
"eval_loss": 1.75497305393219,
|
| 1311 |
+
"eval_runtime": 11.1384,
|
| 1312 |
+
"eval_samples_per_second": 11.133,
|
| 1313 |
+
"eval_steps_per_second": 0.718,
|
| 1314 |
+
"step": 87
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 2.3783783783783785,
|
| 1318 |
+
"grad_norm": 0.11703913658857346,
|
| 1319 |
+
"learning_rate": 9.292929292929293e-05,
|
| 1320 |
+
"loss": 0.812,
|
| 1321 |
+
"step": 88
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 2.3783783783783785,
|
| 1325 |
+
"eval_loss": 1.7427462339401245,
|
| 1326 |
+
"eval_runtime": 11.1796,
|
| 1327 |
+
"eval_samples_per_second": 11.092,
|
| 1328 |
+
"eval_steps_per_second": 0.716,
|
| 1329 |
+
"step": 88
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 2.4054054054054053,
|
| 1333 |
+
"grad_norm": 0.1178952306509018,
|
| 1334 |
+
"learning_rate": 8.888888888888889e-05,
|
| 1335 |
+
"loss": 0.8117,
|
| 1336 |
+
"step": 89
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 2.4054054054054053,
|
| 1340 |
+
"eval_loss": 1.7358033657073975,
|
| 1341 |
+
"eval_runtime": 11.1223,
|
| 1342 |
+
"eval_samples_per_second": 11.149,
|
| 1343 |
+
"eval_steps_per_second": 0.719,
|
| 1344 |
+
"step": 89
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 2.4324324324324325,
|
| 1348 |
+
"grad_norm": 0.1348622441291809,
|
| 1349 |
+
"learning_rate": 8.484848484848486e-05,
|
| 1350 |
+
"loss": 0.8172,
|
| 1351 |
+
"step": 90
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 2.4324324324324325,
|
| 1355 |
+
"eval_loss": 1.7397310733795166,
|
| 1356 |
+
"eval_runtime": 11.1841,
|
| 1357 |
+
"eval_samples_per_second": 11.087,
|
| 1358 |
+
"eval_steps_per_second": 0.715,
|
| 1359 |
+
"step": 90
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 2.4594594594594597,
|
| 1363 |
+
"grad_norm": 0.12706562876701355,
|
| 1364 |
+
"learning_rate": 8.080808080808081e-05,
|
| 1365 |
+
"loss": 0.808,
|
| 1366 |
+
"step": 91
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 2.4594594594594597,
|
| 1370 |
+
"eval_loss": 1.751862645149231,
|
| 1371 |
+
"eval_runtime": 11.0963,
|
| 1372 |
+
"eval_samples_per_second": 11.175,
|
| 1373 |
+
"eval_steps_per_second": 0.721,
|
| 1374 |
+
"step": 91
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 2.4864864864864864,
|
| 1378 |
+
"grad_norm": 0.11583199352025986,
|
| 1379 |
+
"learning_rate": 7.676767676767676e-05,
|
| 1380 |
+
"loss": 0.8108,
|
| 1381 |
+
"step": 92
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 2.4864864864864864,
|
| 1385 |
+
"eval_loss": 1.764027714729309,
|
| 1386 |
+
"eval_runtime": 11.1926,
|
| 1387 |
+
"eval_samples_per_second": 11.079,
|
| 1388 |
+
"eval_steps_per_second": 0.715,
|
| 1389 |
+
"step": 92
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.5135135135135136,
|
| 1393 |
+
"grad_norm": 0.12227907031774521,
|
| 1394 |
+
"learning_rate": 7.272727272727273e-05,
|
| 1395 |
+
"loss": 0.8086,
|
| 1396 |
+
"step": 93
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.5135135135135136,
|
| 1400 |
+
"eval_loss": 1.7744636535644531,
|
| 1401 |
+
"eval_runtime": 11.1394,
|
| 1402 |
+
"eval_samples_per_second": 11.132,
|
| 1403 |
+
"eval_steps_per_second": 0.718,
|
| 1404 |
+
"step": 93
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 2.5405405405405403,
|
| 1408 |
+
"grad_norm": 0.1270534247159958,
|
| 1409 |
+
"learning_rate": 6.86868686868687e-05,
|
| 1410 |
+
"loss": 0.8079,
|
| 1411 |
+
"step": 94
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 2.5405405405405403,
|
| 1415 |
+
"eval_loss": 1.7796293497085571,
|
| 1416 |
+
"eval_runtime": 11.1924,
|
| 1417 |
+
"eval_samples_per_second": 11.079,
|
| 1418 |
+
"eval_steps_per_second": 0.715,
|
| 1419 |
+
"step": 94
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 2.5675675675675675,
|
| 1423 |
+
"grad_norm": 0.1266915649175644,
|
| 1424 |
+
"learning_rate": 6.464646464646466e-05,
|
| 1425 |
+
"loss": 0.7876,
|
| 1426 |
+
"step": 95
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 2.5675675675675675,
|
| 1430 |
+
"eval_loss": 1.7799245119094849,
|
| 1431 |
+
"eval_runtime": 11.1921,
|
| 1432 |
+
"eval_samples_per_second": 11.079,
|
| 1433 |
+
"eval_steps_per_second": 0.715,
|
| 1434 |
+
"step": 95
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 2.5945945945945947,
|
| 1438 |
+
"grad_norm": 0.13456638157367706,
|
| 1439 |
+
"learning_rate": 6.060606060606061e-05,
|
| 1440 |
+
"loss": 0.7756,
|
| 1441 |
+
"step": 96
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 2.5945945945945947,
|
| 1445 |
+
"eval_loss": 1.7748299837112427,
|
| 1446 |
+
"eval_runtime": 11.1592,
|
| 1447 |
+
"eval_samples_per_second": 11.112,
|
| 1448 |
+
"eval_steps_per_second": 0.717,
|
| 1449 |
+
"step": 96
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 2.6216216216216215,
|
| 1453 |
+
"grad_norm": 0.12409545481204987,
|
| 1454 |
+
"learning_rate": 5.6565656565656563e-05,
|
| 1455 |
+
"loss": 0.795,
|
| 1456 |
+
"step": 97
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 2.6216216216216215,
|
| 1460 |
+
"eval_loss": 1.7676475048065186,
|
| 1461 |
+
"eval_runtime": 11.1442,
|
| 1462 |
+
"eval_samples_per_second": 11.127,
|
| 1463 |
+
"eval_steps_per_second": 0.718,
|
| 1464 |
+
"step": 97
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 2.6486486486486487,
|
| 1468 |
+
"grad_norm": 0.11815664917230606,
|
| 1469 |
+
"learning_rate": 5.2525252525252536e-05,
|
| 1470 |
+
"loss": 0.7706,
|
| 1471 |
+
"step": 98
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 2.6486486486486487,
|
| 1475 |
+
"eval_loss": 1.7634869813919067,
|
| 1476 |
+
"eval_runtime": 11.2593,
|
| 1477 |
+
"eval_samples_per_second": 11.013,
|
| 1478 |
+
"eval_steps_per_second": 0.711,
|
| 1479 |
+
"step": 98
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 2.6756756756756754,
|
| 1483 |
+
"grad_norm": 0.11971355229616165,
|
| 1484 |
+
"learning_rate": 4.848484848484849e-05,
|
| 1485 |
+
"loss": 0.792,
|
| 1486 |
+
"step": 99
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 2.6756756756756754,
|
| 1490 |
+
"eval_loss": 1.7610678672790527,
|
| 1491 |
+
"eval_runtime": 11.1535,
|
| 1492 |
+
"eval_samples_per_second": 11.118,
|
| 1493 |
+
"eval_steps_per_second": 0.717,
|
| 1494 |
+
"step": 99
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.7027027027027026,
|
| 1498 |
+
"grad_norm": 0.12585307657718658,
|
| 1499 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 1500 |
+
"loss": 0.7942,
|
| 1501 |
+
"step": 100
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.7027027027027026,
|
| 1505 |
+
"eval_loss": 1.7610435485839844,
|
| 1506 |
+
"eval_runtime": 11.0721,
|
| 1507 |
+
"eval_samples_per_second": 11.199,
|
| 1508 |
+
"eval_steps_per_second": 0.723,
|
| 1509 |
+
"step": 100
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 2.72972972972973,
|
| 1513 |
+
"grad_norm": 0.11809434741735458,
|
| 1514 |
+
"learning_rate": 4.0404040404040405e-05,
|
| 1515 |
+
"loss": 0.7697,
|
| 1516 |
+
"step": 101
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 2.72972972972973,
|
| 1520 |
+
"eval_loss": 1.7632513046264648,
|
| 1521 |
+
"eval_runtime": 11.1597,
|
| 1522 |
+
"eval_samples_per_second": 11.111,
|
| 1523 |
+
"eval_steps_per_second": 0.717,
|
| 1524 |
+
"step": 101
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 2.756756756756757,
|
| 1528 |
+
"grad_norm": 0.12419259548187256,
|
| 1529 |
+
"learning_rate": 3.6363636363636364e-05,
|
| 1530 |
+
"loss": 0.7789,
|
| 1531 |
+
"step": 102
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 2.756756756756757,
|
| 1535 |
+
"eval_loss": 1.7658323049545288,
|
| 1536 |
+
"eval_runtime": 11.1861,
|
| 1537 |
+
"eval_samples_per_second": 11.085,
|
| 1538 |
+
"eval_steps_per_second": 0.715,
|
| 1539 |
+
"step": 102
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 2.7837837837837838,
|
| 1543 |
+
"grad_norm": 0.12964174151420593,
|
| 1544 |
+
"learning_rate": 3.232323232323233e-05,
|
| 1545 |
+
"loss": 0.8047,
|
| 1546 |
+
"step": 103
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 2.7837837837837838,
|
| 1550 |
+
"eval_loss": 1.7687405347824097,
|
| 1551 |
+
"eval_runtime": 11.0868,
|
| 1552 |
+
"eval_samples_per_second": 11.184,
|
| 1553 |
+
"eval_steps_per_second": 0.722,
|
| 1554 |
+
"step": 103
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 2.810810810810811,
|
| 1558 |
+
"grad_norm": 0.1257963329553604,
|
| 1559 |
+
"learning_rate": 2.8282828282828282e-05,
|
| 1560 |
+
"loss": 0.7653,
|
| 1561 |
+
"step": 104
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 2.810810810810811,
|
| 1565 |
+
"eval_loss": 1.7723119258880615,
|
| 1566 |
+
"eval_runtime": 11.1173,
|
| 1567 |
+
"eval_samples_per_second": 11.154,
|
| 1568 |
+
"eval_steps_per_second": 0.72,
|
| 1569 |
+
"step": 104
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 2.8378378378378377,
|
| 1573 |
+
"grad_norm": 0.12039487063884735,
|
| 1574 |
+
"learning_rate": 2.4242424242424244e-05,
|
| 1575 |
+
"loss": 0.7753,
|
| 1576 |
+
"step": 105
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 2.8378378378378377,
|
| 1580 |
+
"eval_loss": 1.7749425172805786,
|
| 1581 |
+
"eval_runtime": 11.157,
|
| 1582 |
+
"eval_samples_per_second": 11.114,
|
| 1583 |
+
"eval_steps_per_second": 0.717,
|
| 1584 |
+
"step": 105
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 2.864864864864865,
|
| 1588 |
+
"grad_norm": 0.13161887228488922,
|
| 1589 |
+
"learning_rate": 2.0202020202020203e-05,
|
| 1590 |
+
"loss": 0.7631,
|
| 1591 |
+
"step": 106
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 2.864864864864865,
|
| 1595 |
+
"eval_loss": 1.7760539054870605,
|
| 1596 |
+
"eval_runtime": 11.1933,
|
| 1597 |
+
"eval_samples_per_second": 11.078,
|
| 1598 |
+
"eval_steps_per_second": 0.715,
|
| 1599 |
+
"step": 106
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.891891891891892,
|
| 1603 |
+
"grad_norm": 0.12347672879695892,
|
| 1604 |
+
"learning_rate": 1.6161616161616165e-05,
|
| 1605 |
+
"loss": 0.7821,
|
| 1606 |
+
"step": 107
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 2.891891891891892,
|
| 1610 |
+
"eval_loss": 1.7769430875778198,
|
| 1611 |
+
"eval_runtime": 11.169,
|
| 1612 |
+
"eval_samples_per_second": 11.102,
|
| 1613 |
+
"eval_steps_per_second": 0.716,
|
| 1614 |
+
"step": 107
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 2.918918918918919,
|
| 1618 |
+
"grad_norm": 0.12539447844028473,
|
| 1619 |
+
"learning_rate": 1.2121212121212122e-05,
|
| 1620 |
+
"loss": 0.7682,
|
| 1621 |
+
"step": 108
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 2.918918918918919,
|
| 1625 |
+
"eval_loss": 1.77769136428833,
|
| 1626 |
+
"eval_runtime": 11.2241,
|
| 1627 |
+
"eval_samples_per_second": 11.048,
|
| 1628 |
+
"eval_steps_per_second": 0.713,
|
| 1629 |
+
"step": 108
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 2.945945945945946,
|
| 1633 |
+
"grad_norm": 0.12666372954845428,
|
| 1634 |
+
"learning_rate": 8.080808080808082e-06,
|
| 1635 |
+
"loss": 0.7893,
|
| 1636 |
+
"step": 109
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 2.945945945945946,
|
| 1640 |
+
"eval_loss": 1.7779371738433838,
|
| 1641 |
+
"eval_runtime": 11.1071,
|
| 1642 |
+
"eval_samples_per_second": 11.164,
|
| 1643 |
+
"eval_steps_per_second": 0.72,
|
| 1644 |
+
"step": 109
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 2.972972972972973,
|
| 1648 |
+
"grad_norm": 0.11765623837709427,
|
| 1649 |
+
"learning_rate": 4.040404040404041e-06,
|
| 1650 |
+
"loss": 0.7729,
|
| 1651 |
+
"step": 110
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 2.972972972972973,
|
| 1655 |
+
"eval_loss": 1.7782450914382935,
|
| 1656 |
+
"eval_runtime": 11.121,
|
| 1657 |
+
"eval_samples_per_second": 11.15,
|
| 1658 |
+
"eval_steps_per_second": 0.719,
|
| 1659 |
+
"step": 110
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 3.0,
|
| 1663 |
+
"grad_norm": 0.14280778169631958,
|
| 1664 |
+
"learning_rate": 0.0,
|
| 1665 |
+
"loss": 0.7783,
|
| 1666 |
+
"step": 111
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 3.0,
|
| 1670 |
+
"eval_loss": 1.7782894372940063,
|
| 1671 |
+
"eval_runtime": 11.0882,
|
| 1672 |
+
"eval_samples_per_second": 11.183,
|
| 1673 |
+
"eval_steps_per_second": 0.721,
|
| 1674 |
+
"step": 111
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 3.0,
|
| 1678 |
+
"step": 111,
|
| 1679 |
+
"total_flos": 4.092563650668134e+16,
|
| 1680 |
+
"train_loss": 1.148636352371525,
|
| 1681 |
+
"train_runtime": 2293.4445,
|
| 1682 |
+
"train_samples_per_second": 1.54,
|
| 1683 |
+
"train_steps_per_second": 0.048
|
| 1684 |
+
}
|
| 1685 |
+
],
|
| 1686 |
+
"logging_steps": 1,
|
| 1687 |
+
"max_steps": 111,
|
| 1688 |
+
"num_input_tokens_seen": 0,
|
| 1689 |
+
"num_train_epochs": 3,
|
| 1690 |
+
"save_steps": 10,
|
| 1691 |
+
"stateful_callbacks": {
|
| 1692 |
+
"TrainerControl": {
|
| 1693 |
+
"args": {
|
| 1694 |
+
"should_epoch_stop": false,
|
| 1695 |
+
"should_evaluate": false,
|
| 1696 |
+
"should_log": false,
|
| 1697 |
+
"should_save": true,
|
| 1698 |
+
"should_training_stop": false
|
| 1699 |
+
},
|
| 1700 |
+
"attributes": {}
|
| 1701 |
+
}
|
| 1702 |
+
},
|
| 1703 |
+
"total_flos": 4.092563650668134e+16,
|
| 1704 |
+
"train_batch_size": 32,
|
| 1705 |
+
"trial_name": null,
|
| 1706 |
+
"trial_params": null
|
| 1707 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ea070c2faa734be8923d94fa3856f14e164a5abfa05c6110801b96bd6a62aca
|
| 3 |
+
size 5688
|