Upload folder using huggingface_hub
Browse files- sft/checkpoint-3150/README.md +206 -0
- sft/checkpoint-3150/optimizer.pt +3 -0
- sft/checkpoint-3150/rng_state_0.pth +3 -0
- sft/checkpoint-3150/scaler.pt +3 -0
- sft/checkpoint-3150/scheduler.pt +3 -0
- sft/checkpoint-3150/sft/adapter_config.json +50 -0
- sft/checkpoint-3150/sft/adapter_model.safetensors +3 -0
- sft/checkpoint-3150/tokenizer.json +0 -0
- sft/checkpoint-3150/tokenizer_config.json +19 -0
- sft/checkpoint-3150/trainer_state.json +1714 -0
- sft/checkpoint-3150/training_args.bin +3 -0
sft/checkpoint-3150/README.md
ADDED
|
@@ -0,0 +1,206 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: heitorrosa/logun-base
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- base_model:adapter:heitorrosa/logun-base
|
| 6 |
+
- lora
|
| 7 |
+
- transformers
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# Model Card for Model ID
|
| 11 |
+
|
| 12 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
## Model Details
|
| 17 |
+
|
| 18 |
+
### Model Description
|
| 19 |
+
|
| 20 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
- **Developed by:** [More Information Needed]
|
| 25 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 26 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 27 |
+
- **Model type:** [More Information Needed]
|
| 28 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 29 |
+
- **License:** [More Information Needed]
|
| 30 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 31 |
+
|
| 32 |
+
### Model Sources [optional]
|
| 33 |
+
|
| 34 |
+
<!-- Provide the basic links for the model. -->
|
| 35 |
+
|
| 36 |
+
- **Repository:** [More Information Needed]
|
| 37 |
+
- **Paper [optional]:** [More Information Needed]
|
| 38 |
+
- **Demo [optional]:** [More Information Needed]
|
| 39 |
+
|
| 40 |
+
## Uses
|
| 41 |
+
|
| 42 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 43 |
+
|
| 44 |
+
### Direct Use
|
| 45 |
+
|
| 46 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 47 |
+
|
| 48 |
+
[More Information Needed]
|
| 49 |
+
|
| 50 |
+
### Downstream Use [optional]
|
| 51 |
+
|
| 52 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 53 |
+
|
| 54 |
+
[More Information Needed]
|
| 55 |
+
|
| 56 |
+
### Out-of-Scope Use
|
| 57 |
+
|
| 58 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 59 |
+
|
| 60 |
+
[More Information Needed]
|
| 61 |
+
|
| 62 |
+
## Bias, Risks, and Limitations
|
| 63 |
+
|
| 64 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 65 |
+
|
| 66 |
+
[More Information Needed]
|
| 67 |
+
|
| 68 |
+
### Recommendations
|
| 69 |
+
|
| 70 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 71 |
+
|
| 72 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 73 |
+
|
| 74 |
+
## How to Get Started with the Model
|
| 75 |
+
|
| 76 |
+
Use the code below to get started with the model.
|
| 77 |
+
|
| 78 |
+
[More Information Needed]
|
| 79 |
+
|
| 80 |
+
## Training Details
|
| 81 |
+
|
| 82 |
+
### Training Data
|
| 83 |
+
|
| 84 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 85 |
+
|
| 86 |
+
[More Information Needed]
|
| 87 |
+
|
| 88 |
+
### Training Procedure
|
| 89 |
+
|
| 90 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 91 |
+
|
| 92 |
+
#### Preprocessing [optional]
|
| 93 |
+
|
| 94 |
+
[More Information Needed]
|
| 95 |
+
|
| 96 |
+
|
| 97 |
+
#### Training Hyperparameters
|
| 98 |
+
|
| 99 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 100 |
+
|
| 101 |
+
#### Speeds, Sizes, Times [optional]
|
| 102 |
+
|
| 103 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 104 |
+
|
| 105 |
+
[More Information Needed]
|
| 106 |
+
|
| 107 |
+
## Evaluation
|
| 108 |
+
|
| 109 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 110 |
+
|
| 111 |
+
### Testing Data, Factors & Metrics
|
| 112 |
+
|
| 113 |
+
#### Testing Data
|
| 114 |
+
|
| 115 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 116 |
+
|
| 117 |
+
[More Information Needed]
|
| 118 |
+
|
| 119 |
+
#### Factors
|
| 120 |
+
|
| 121 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 122 |
+
|
| 123 |
+
[More Information Needed]
|
| 124 |
+
|
| 125 |
+
#### Metrics
|
| 126 |
+
|
| 127 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
### Results
|
| 132 |
+
|
| 133 |
+
[More Information Needed]
|
| 134 |
+
|
| 135 |
+
#### Summary
|
| 136 |
+
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
## Model Examination [optional]
|
| 140 |
+
|
| 141 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 142 |
+
|
| 143 |
+
[More Information Needed]
|
| 144 |
+
|
| 145 |
+
## Environmental Impact
|
| 146 |
+
|
| 147 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 148 |
+
|
| 149 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 150 |
+
|
| 151 |
+
- **Hardware Type:** [More Information Needed]
|
| 152 |
+
- **Hours used:** [More Information Needed]
|
| 153 |
+
- **Cloud Provider:** [More Information Needed]
|
| 154 |
+
- **Compute Region:** [More Information Needed]
|
| 155 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 156 |
+
|
| 157 |
+
## Technical Specifications [optional]
|
| 158 |
+
|
| 159 |
+
### Model Architecture and Objective
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
### Compute Infrastructure
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Hardware
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
#### Software
|
| 172 |
+
|
| 173 |
+
[More Information Needed]
|
| 174 |
+
|
| 175 |
+
## Citation [optional]
|
| 176 |
+
|
| 177 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 178 |
+
|
| 179 |
+
**BibTeX:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
**APA:**
|
| 184 |
+
|
| 185 |
+
[More Information Needed]
|
| 186 |
+
|
| 187 |
+
## Glossary [optional]
|
| 188 |
+
|
| 189 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## More Information [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Authors [optional]
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
## Model Card Contact
|
| 202 |
+
|
| 203 |
+
[More Information Needed]
|
| 204 |
+
### Framework versions
|
| 205 |
+
|
| 206 |
+
- PEFT 0.20.0
|
sft/checkpoint-3150/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da841432a54d2cc1aeb9abbe79ac833ace3cf9354566c2fafe3f304af83254af
|
| 3 |
+
size 27204427
|
sft/checkpoint-3150/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6188d1ee31213908f94d0b7fd7e2809c1d140311cd7660e2e6bea5c119953f81
|
| 3 |
+
size 14917
|
sft/checkpoint-3150/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d239bf6705a855ee272a421929703bfda69117f3213372b7fc1d1e8aea43da8b
|
| 3 |
+
size 1383
|
sft/checkpoint-3150/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86709a0819a96903a66d9e54c1bf18f17e18d0b4470c7cb9e6b30113469e44af
|
| 3 |
+
size 1465
|
sft/checkpoint-3150/sft/adapter_config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "heitorrosa/logun-base",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 32,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": [
|
| 26 |
+
"classifier",
|
| 27 |
+
"classifier",
|
| 28 |
+
"score"
|
| 29 |
+
],
|
| 30 |
+
"monteclora_config": null,
|
| 31 |
+
"peft_type": "LORA",
|
| 32 |
+
"peft_version": "0.20.0",
|
| 33 |
+
"qalora_group_size": 16,
|
| 34 |
+
"r": 16,
|
| 35 |
+
"rank_pattern": {},
|
| 36 |
+
"revision": null,
|
| 37 |
+
"target_modules": [
|
| 38 |
+
"Wqkv",
|
| 39 |
+
"Wo",
|
| 40 |
+
"Wi"
|
| 41 |
+
],
|
| 42 |
+
"target_parameters": null,
|
| 43 |
+
"task_type": "SEQ_CLS",
|
| 44 |
+
"trainable_token_indices": null,
|
| 45 |
+
"use_bdlora": null,
|
| 46 |
+
"use_dora": false,
|
| 47 |
+
"use_qalora": false,
|
| 48 |
+
"use_rslora": false,
|
| 49 |
+
"velora_config": null
|
| 50 |
+
}
|
sft/checkpoint-3150/sft/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2c73d6937665221cf90993b0c1159c3ca6c0b26a8b6f95d7b1a6884c256d008
|
| 3 |
+
size 13547940
|
sft/checkpoint-3150/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
sft/checkpoint-3150/tokenizer_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "[CLS]",
|
| 4 |
+
"clean_up_tokenization_spaces": false,
|
| 5 |
+
"eos_token": "[SEP]",
|
| 6 |
+
"is_local": false,
|
| 7 |
+
"local_files_only": false,
|
| 8 |
+
"mask_token": "[MASK]",
|
| 9 |
+
"model_input_names": [
|
| 10 |
+
"input_ids",
|
| 11 |
+
"attention_mask"
|
| 12 |
+
],
|
| 13 |
+
"model_max_length": 8192,
|
| 14 |
+
"pad_token": "[PAD]",
|
| 15 |
+
"padding_side": "right",
|
| 16 |
+
"tokenizer_class": "TokenizersBackend",
|
| 17 |
+
"truncation_side": "right",
|
| 18 |
+
"unk_token": "[UNK]"
|
| 19 |
+
}
|
sft/checkpoint-3150/trainer_state.json
ADDED
|
@@ -0,0 +1,1714 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 5.9000351576233445,
|
| 6 |
+
"eval_steps": 150,
|
| 7 |
+
"global_step": 3150,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.02812609867572952,
|
| 14 |
+
"grad_norm": NaN,
|
| 15 |
+
"learning_rate": 4.666666666666667e-06,
|
| 16 |
+
"loss": 40.91645100911458,
|
| 17 |
+
"step": 15
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.05625219735145904,
|
| 21 |
+
"grad_norm": 108.49263000488281,
|
| 22 |
+
"learning_rate": 9.666666666666667e-06,
|
| 23 |
+
"loss": 38.68733317057292,
|
| 24 |
+
"step": 30
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.08437829602718856,
|
| 28 |
+
"grad_norm": 87.13339233398438,
|
| 29 |
+
"learning_rate": 1.4666666666666668e-05,
|
| 30 |
+
"loss": 37.54708658854167,
|
| 31 |
+
"step": 45
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.11250439470291808,
|
| 35 |
+
"grad_norm": 82.61961364746094,
|
| 36 |
+
"learning_rate": 1.9666666666666666e-05,
|
| 37 |
+
"loss": 35.59373372395833,
|
| 38 |
+
"step": 60
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1406304933786476,
|
| 42 |
+
"grad_norm": 94.90762329101562,
|
| 43 |
+
"learning_rate": 2.466666666666667e-05,
|
| 44 |
+
"loss": 34.33445638020833,
|
| 45 |
+
"step": 75
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.16875659205437712,
|
| 49 |
+
"grad_norm": 64.12799072265625,
|
| 50 |
+
"learning_rate": 2.9666666666666672e-05,
|
| 51 |
+
"loss": 33.768391927083336,
|
| 52 |
+
"step": 90
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.19688269073010664,
|
| 56 |
+
"grad_norm": 61.35285568237305,
|
| 57 |
+
"learning_rate": 3.466666666666667e-05,
|
| 58 |
+
"loss": 33.065120442708334,
|
| 59 |
+
"step": 105
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.22500878940583616,
|
| 63 |
+
"grad_norm": 56.75034713745117,
|
| 64 |
+
"learning_rate": 3.966666666666667e-05,
|
| 65 |
+
"loss": 32.87635091145833,
|
| 66 |
+
"step": 120
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.2531348880815657,
|
| 70 |
+
"grad_norm": 88.83663177490234,
|
| 71 |
+
"learning_rate": 4.466666666666667e-05,
|
| 72 |
+
"loss": 31.945328776041666,
|
| 73 |
+
"step": 135
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.2812609867572952,
|
| 77 |
+
"grad_norm": 53.496788024902344,
|
| 78 |
+
"learning_rate": 4.966666666666667e-05,
|
| 79 |
+
"loss": 32.28165283203125,
|
| 80 |
+
"step": 150
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.2812609867572952,
|
| 84 |
+
"eval_accuracy": 0.4985507246376812,
|
| 85 |
+
"eval_loss": 1.9326186180114746,
|
| 86 |
+
"eval_macro_f1": 0.4513996326113265,
|
| 87 |
+
"eval_runtime": 7.0971,
|
| 88 |
+
"eval_samples_per_second": 48.611,
|
| 89 |
+
"eval_steps_per_second": 6.2,
|
| 90 |
+
"step": 150
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.30938708543302473,
|
| 94 |
+
"grad_norm": 54.809783935546875,
|
| 95 |
+
"learning_rate": 4.9830179524502674e-05,
|
| 96 |
+
"loss": 30.544930013020835,
|
| 97 |
+
"step": 165
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.33751318410875425,
|
| 101 |
+
"grad_norm": 68.34676361083984,
|
| 102 |
+
"learning_rate": 4.964822901504124e-05,
|
| 103 |
+
"loss": 29.883894856770834,
|
| 104 |
+
"step": 180
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.36563928278448377,
|
| 108 |
+
"grad_norm": 70.30874633789062,
|
| 109 |
+
"learning_rate": 4.9466278505579815e-05,
|
| 110 |
+
"loss": 29.711442057291666,
|
| 111 |
+
"step": 195
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.3937653814602133,
|
| 115 |
+
"grad_norm": 105.4150161743164,
|
| 116 |
+
"learning_rate": 4.928432799611839e-05,
|
| 117 |
+
"loss": 29.863224283854166,
|
| 118 |
+
"step": 210
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.4218914801359428,
|
| 122 |
+
"grad_norm": 81.67976379394531,
|
| 123 |
+
"learning_rate": 4.910237748665696e-05,
|
| 124 |
+
"loss": 29.67599080403646,
|
| 125 |
+
"step": 225
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.4500175788116723,
|
| 129 |
+
"grad_norm": 78.1202621459961,
|
| 130 |
+
"learning_rate": 4.8920426977195536e-05,
|
| 131 |
+
"loss": 28.802783203125,
|
| 132 |
+
"step": 240
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.47814367748740183,
|
| 136 |
+
"grad_norm": 73.63782501220703,
|
| 137 |
+
"learning_rate": 4.873847646773411e-05,
|
| 138 |
+
"loss": 27.798103841145835,
|
| 139 |
+
"step": 255
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 0.5062697761631314,
|
| 143 |
+
"grad_norm": 77.5123519897461,
|
| 144 |
+
"learning_rate": 4.855652595827268e-05,
|
| 145 |
+
"loss": 26.746952311197916,
|
| 146 |
+
"step": 270
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.5343958748388609,
|
| 150 |
+
"grad_norm": 70.0318603515625,
|
| 151 |
+
"learning_rate": 4.837457544881126e-05,
|
| 152 |
+
"loss": 26.3315673828125,
|
| 153 |
+
"step": 285
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.5625219735145904,
|
| 157 |
+
"grad_norm": 66.42996215820312,
|
| 158 |
+
"learning_rate": 4.819262493934984e-05,
|
| 159 |
+
"loss": 26.488555908203125,
|
| 160 |
+
"step": 300
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.5625219735145904,
|
| 164 |
+
"eval_accuracy": 0.6318840579710145,
|
| 165 |
+
"eval_loss": 1.615958333015442,
|
| 166 |
+
"eval_macro_f1": 0.6129856465867943,
|
| 167 |
+
"eval_runtime": 2.3114,
|
| 168 |
+
"eval_samples_per_second": 149.263,
|
| 169 |
+
"eval_steps_per_second": 19.036,
|
| 170 |
+
"step": 300
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.5906480721903199,
|
| 174 |
+
"grad_norm": 68.63166046142578,
|
| 175 |
+
"learning_rate": 4.801067442988841e-05,
|
| 176 |
+
"loss": 26.851969401041668,
|
| 177 |
+
"step": 315
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.6187741708660495,
|
| 181 |
+
"grad_norm": 94.37174224853516,
|
| 182 |
+
"learning_rate": 4.7828723920426985e-05,
|
| 183 |
+
"loss": 26.854146321614582,
|
| 184 |
+
"step": 330
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.6469002695417789,
|
| 188 |
+
"grad_norm": 85.5411605834961,
|
| 189 |
+
"learning_rate": 4.764677341096555e-05,
|
| 190 |
+
"loss": 24.6757080078125,
|
| 191 |
+
"step": 345
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.6750263682175085,
|
| 195 |
+
"grad_norm": 64.81537628173828,
|
| 196 |
+
"learning_rate": 4.7464822901504125e-05,
|
| 197 |
+
"loss": 27.398944091796874,
|
| 198 |
+
"step": 360
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.7031524668932381,
|
| 202 |
+
"grad_norm": 98.3795394897461,
|
| 203 |
+
"learning_rate": 4.72828723920427e-05,
|
| 204 |
+
"loss": 25.361378987630207,
|
| 205 |
+
"step": 375
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.7312785655689675,
|
| 209 |
+
"grad_norm": 60.86552810668945,
|
| 210 |
+
"learning_rate": 4.710092188258127e-05,
|
| 211 |
+
"loss": 23.455232747395833,
|
| 212 |
+
"step": 390
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.7594046642446971,
|
| 216 |
+
"grad_norm": 65.06398010253906,
|
| 217 |
+
"learning_rate": 4.6918971373119846e-05,
|
| 218 |
+
"loss": 25.147119140625,
|
| 219 |
+
"step": 405
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.7875307629204266,
|
| 223 |
+
"grad_norm": 64.24246978759766,
|
| 224 |
+
"learning_rate": 4.673702086365842e-05,
|
| 225 |
+
"loss": 26.254545084635417,
|
| 226 |
+
"step": 420
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.8156568615961561,
|
| 230 |
+
"grad_norm": 85.69407653808594,
|
| 231 |
+
"learning_rate": 4.6555070354196993e-05,
|
| 232 |
+
"loss": 25.228023274739584,
|
| 233 |
+
"step": 435
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.8437829602718856,
|
| 237 |
+
"grad_norm": 91.77117919921875,
|
| 238 |
+
"learning_rate": 4.637311984473557e-05,
|
| 239 |
+
"loss": 24.674845377604168,
|
| 240 |
+
"step": 450
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.8437829602718856,
|
| 244 |
+
"eval_accuracy": 0.6579710144927536,
|
| 245 |
+
"eval_loss": 1.529452919960022,
|
| 246 |
+
"eval_macro_f1": 0.6434151685975086,
|
| 247 |
+
"eval_runtime": 2.2932,
|
| 248 |
+
"eval_samples_per_second": 150.442,
|
| 249 |
+
"eval_steps_per_second": 19.187,
|
| 250 |
+
"step": 450
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.8719090589476152,
|
| 254 |
+
"grad_norm": 59.32505798339844,
|
| 255 |
+
"learning_rate": 4.619116933527414e-05,
|
| 256 |
+
"loss": 25.152834065755208,
|
| 257 |
+
"step": 465
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.9000351576233446,
|
| 261 |
+
"grad_norm": 68.90987396240234,
|
| 262 |
+
"learning_rate": 4.6009218825812714e-05,
|
| 263 |
+
"loss": 23.644384765625,
|
| 264 |
+
"step": 480
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.9281612562990742,
|
| 268 |
+
"grad_norm": 78.69176483154297,
|
| 269 |
+
"learning_rate": 4.582726831635129e-05,
|
| 270 |
+
"loss": 24.69483642578125,
|
| 271 |
+
"step": 495
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.9562873549748037,
|
| 275 |
+
"grad_norm": 71.7799072265625,
|
| 276 |
+
"learning_rate": 4.564531780688986e-05,
|
| 277 |
+
"loss": 23.468556722005207,
|
| 278 |
+
"step": 510
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.9844134536505332,
|
| 282 |
+
"grad_norm": 99.54678344726562,
|
| 283 |
+
"learning_rate": 4.5463367297428435e-05,
|
| 284 |
+
"loss": 24.51992390950521,
|
| 285 |
+
"step": 525
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.011250439470292,
|
| 289 |
+
"grad_norm": 81.2381362915039,
|
| 290 |
+
"learning_rate": 4.528141678796701e-05,
|
| 291 |
+
"loss": 22.73736572265625,
|
| 292 |
+
"step": 540
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.0393765381460214,
|
| 296 |
+
"grad_norm": 72.6605224609375,
|
| 297 |
+
"learning_rate": 4.509946627850558e-05,
|
| 298 |
+
"loss": 24.33416748046875,
|
| 299 |
+
"step": 555
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.0675026368217508,
|
| 303 |
+
"grad_norm": 80.05354309082031,
|
| 304 |
+
"learning_rate": 4.4917515769044156e-05,
|
| 305 |
+
"loss": 22.052213541666667,
|
| 306 |
+
"step": 570
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.0956287354974803,
|
| 310 |
+
"grad_norm": 90.22277069091797,
|
| 311 |
+
"learning_rate": 4.473556525958273e-05,
|
| 312 |
+
"loss": 22.770609537760418,
|
| 313 |
+
"step": 585
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.12375483417321,
|
| 317 |
+
"grad_norm": 69.45885467529297,
|
| 318 |
+
"learning_rate": 4.4553614750121304e-05,
|
| 319 |
+
"loss": 24.028635660807293,
|
| 320 |
+
"step": 600
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.12375483417321,
|
| 324 |
+
"eval_accuracy": 0.6608695652173913,
|
| 325 |
+
"eval_loss": 1.49661386013031,
|
| 326 |
+
"eval_macro_f1": 0.6466193853427896,
|
| 327 |
+
"eval_runtime": 2.2405,
|
| 328 |
+
"eval_samples_per_second": 153.984,
|
| 329 |
+
"eval_steps_per_second": 19.639,
|
| 330 |
+
"step": 600
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.1518809328489394,
|
| 334 |
+
"grad_norm": 109.61043548583984,
|
| 335 |
+
"learning_rate": 4.437166424065988e-05,
|
| 336 |
+
"loss": 23.77248331705729,
|
| 337 |
+
"step": 615
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 1.180007031524669,
|
| 341 |
+
"grad_norm": 71.86944580078125,
|
| 342 |
+
"learning_rate": 4.418971373119845e-05,
|
| 343 |
+
"loss": 22.4523193359375,
|
| 344 |
+
"step": 630
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.2081331302003984,
|
| 348 |
+
"grad_norm": 79.43173217773438,
|
| 349 |
+
"learning_rate": 4.4007763221737025e-05,
|
| 350 |
+
"loss": 23.30051472981771,
|
| 351 |
+
"step": 645
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.236259228876128,
|
| 355 |
+
"grad_norm": 73.39543914794922,
|
| 356 |
+
"learning_rate": 4.38258127122756e-05,
|
| 357 |
+
"loss": 23.162101236979165,
|
| 358 |
+
"step": 660
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.2643853275518575,
|
| 362 |
+
"grad_norm": 92.3052978515625,
|
| 363 |
+
"learning_rate": 4.3643862202814165e-05,
|
| 364 |
+
"loss": 22.967840576171874,
|
| 365 |
+
"step": 675
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.292511426227587,
|
| 369 |
+
"grad_norm": 79.57266998291016,
|
| 370 |
+
"learning_rate": 4.346191169335274e-05,
|
| 371 |
+
"loss": 24.993180338541666,
|
| 372 |
+
"step": 690
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.3206375249033164,
|
| 376 |
+
"grad_norm": 81.71668243408203,
|
| 377 |
+
"learning_rate": 4.327996118389131e-05,
|
| 378 |
+
"loss": 23.013671875,
|
| 379 |
+
"step": 705
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 1.3487636235790461,
|
| 383 |
+
"grad_norm": 64.0071029663086,
|
| 384 |
+
"learning_rate": 4.3098010674429886e-05,
|
| 385 |
+
"loss": 23.570048014322918,
|
| 386 |
+
"step": 720
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.3768897222547756,
|
| 390 |
+
"grad_norm": 98.42646789550781,
|
| 391 |
+
"learning_rate": 4.291606016496847e-05,
|
| 392 |
+
"loss": 22.822066243489584,
|
| 393 |
+
"step": 735
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.405015820930505,
|
| 397 |
+
"grad_norm": 77.34905242919922,
|
| 398 |
+
"learning_rate": 4.273410965550704e-05,
|
| 399 |
+
"loss": 24.35296630859375,
|
| 400 |
+
"step": 750
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.405015820930505,
|
| 404 |
+
"eval_accuracy": 0.6608695652173913,
|
| 405 |
+
"eval_loss": 1.4775240421295166,
|
| 406 |
+
"eval_macro_f1": 0.6485427050773,
|
| 407 |
+
"eval_runtime": 2.2991,
|
| 408 |
+
"eval_samples_per_second": 150.061,
|
| 409 |
+
"eval_steps_per_second": 19.138,
|
| 410 |
+
"step": 750
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.4331419196062347,
|
| 414 |
+
"grad_norm": 74.36935424804688,
|
| 415 |
+
"learning_rate": 4.2552159146045614e-05,
|
| 416 |
+
"loss": 24.365966796875,
|
| 417 |
+
"step": 765
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.4612680182819642,
|
| 421 |
+
"grad_norm": 72.57489013671875,
|
| 422 |
+
"learning_rate": 4.237020863658419e-05,
|
| 423 |
+
"loss": 22.283140055338542,
|
| 424 |
+
"step": 780
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.4893941169576936,
|
| 428 |
+
"grad_norm": 66.50872039794922,
|
| 429 |
+
"learning_rate": 4.218825812712276e-05,
|
| 430 |
+
"loss": 22.849454752604167,
|
| 431 |
+
"step": 795
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.5175202156334233,
|
| 435 |
+
"grad_norm": 73.18653869628906,
|
| 436 |
+
"learning_rate": 4.2006307617661335e-05,
|
| 437 |
+
"loss": 23.213165283203125,
|
| 438 |
+
"step": 810
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.5456463143091526,
|
| 442 |
+
"grad_norm": 100.36980438232422,
|
| 443 |
+
"learning_rate": 4.182435710819991e-05,
|
| 444 |
+
"loss": 22.919950358072917,
|
| 445 |
+
"step": 825
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 1.5737724129848822,
|
| 449 |
+
"grad_norm": 92.35721588134766,
|
| 450 |
+
"learning_rate": 4.1642406598738476e-05,
|
| 451 |
+
"loss": 23.443257649739582,
|
| 452 |
+
"step": 840
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.6018985116606117,
|
| 456 |
+
"grad_norm": 79.11441802978516,
|
| 457 |
+
"learning_rate": 4.146045608927705e-05,
|
| 458 |
+
"loss": 23.26278076171875,
|
| 459 |
+
"step": 855
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.6300246103363412,
|
| 463 |
+
"grad_norm": 92.07249450683594,
|
| 464 |
+
"learning_rate": 4.127850557981562e-05,
|
| 465 |
+
"loss": 21.62847900390625,
|
| 466 |
+
"step": 870
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.6581507090120708,
|
| 470 |
+
"grad_norm": 62.01802444458008,
|
| 471 |
+
"learning_rate": 4.1096555070354197e-05,
|
| 472 |
+
"loss": 22.551171875,
|
| 473 |
+
"step": 885
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.6862768076878003,
|
| 477 |
+
"grad_norm": 87.6247787475586,
|
| 478 |
+
"learning_rate": 4.091460456089277e-05,
|
| 479 |
+
"loss": 23.632059733072918,
|
| 480 |
+
"step": 900
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.6862768076878003,
|
| 484 |
+
"eval_accuracy": 0.6898550724637681,
|
| 485 |
+
"eval_loss": 1.4343311786651611,
|
| 486 |
+
"eval_macro_f1": 0.6784067065231657,
|
| 487 |
+
"eval_runtime": 2.2935,
|
| 488 |
+
"eval_samples_per_second": 150.428,
|
| 489 |
+
"eval_steps_per_second": 19.185,
|
| 490 |
+
"step": 900
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.7144029063635298,
|
| 494 |
+
"grad_norm": 77.10883331298828,
|
| 495 |
+
"learning_rate": 4.0732654051431344e-05,
|
| 496 |
+
"loss": 23.429276529947916,
|
| 497 |
+
"step": 915
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.7425290050392594,
|
| 501 |
+
"grad_norm": 88.47496795654297,
|
| 502 |
+
"learning_rate": 4.055070354196992e-05,
|
| 503 |
+
"loss": 23.187703450520832,
|
| 504 |
+
"step": 930
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.770655103714989,
|
| 508 |
+
"grad_norm": 104.27533721923828,
|
| 509 |
+
"learning_rate": 4.036875303250849e-05,
|
| 510 |
+
"loss": 24.269075520833333,
|
| 511 |
+
"step": 945
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 1.7987812023907184,
|
| 515 |
+
"grad_norm": 67.3711166381836,
|
| 516 |
+
"learning_rate": 4.0186802523047065e-05,
|
| 517 |
+
"loss": 22.98969930013021,
|
| 518 |
+
"step": 960
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.826907301066448,
|
| 522 |
+
"grad_norm": 67.43853759765625,
|
| 523 |
+
"learning_rate": 4.0004852013585645e-05,
|
| 524 |
+
"loss": 23.56575724283854,
|
| 525 |
+
"step": 975
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.8550333997421773,
|
| 529 |
+
"grad_norm": 77.04778289794922,
|
| 530 |
+
"learning_rate": 3.982290150412422e-05,
|
| 531 |
+
"loss": 22.3833251953125,
|
| 532 |
+
"step": 990
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 1.883159498417907,
|
| 536 |
+
"grad_norm": 83.1104507446289,
|
| 537 |
+
"learning_rate": 3.9640950994662786e-05,
|
| 538 |
+
"loss": 22.058768717447915,
|
| 539 |
+
"step": 1005
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.9112855970936364,
|
| 543 |
+
"grad_norm": 67.31427001953125,
|
| 544 |
+
"learning_rate": 3.945900048520136e-05,
|
| 545 |
+
"loss": 23.626953125,
|
| 546 |
+
"step": 1020
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.939411695769366,
|
| 550 |
+
"grad_norm": 78.14697265625,
|
| 551 |
+
"learning_rate": 3.927704997573993e-05,
|
| 552 |
+
"loss": 23.199896240234374,
|
| 553 |
+
"step": 1035
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 1.9675377944450956,
|
| 557 |
+
"grad_norm": 86.21821594238281,
|
| 558 |
+
"learning_rate": 3.909509946627851e-05,
|
| 559 |
+
"loss": 22.229060872395834,
|
| 560 |
+
"step": 1050
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.9675377944450956,
|
| 564 |
+
"eval_accuracy": 0.6840579710144927,
|
| 565 |
+
"eval_loss": 1.3762412071228027,
|
| 566 |
+
"eval_macro_f1": 0.6729193842335214,
|
| 567 |
+
"eval_runtime": 2.2854,
|
| 568 |
+
"eval_samples_per_second": 150.959,
|
| 569 |
+
"eval_steps_per_second": 19.253,
|
| 570 |
+
"step": 1050
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.995663893120825,
|
| 574 |
+
"grad_norm": 109.04509735107422,
|
| 575 |
+
"learning_rate": 3.891314895681708e-05,
|
| 576 |
+
"loss": 22.08022664388021,
|
| 577 |
+
"step": 1065
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 2.022500878940584,
|
| 581 |
+
"grad_norm": 63.62330627441406,
|
| 582 |
+
"learning_rate": 3.8731198447355654e-05,
|
| 583 |
+
"loss": 19.795827229817707,
|
| 584 |
+
"step": 1080
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.050626977616313,
|
| 588 |
+
"grad_norm": 92.98448181152344,
|
| 589 |
+
"learning_rate": 3.854924793789423e-05,
|
| 590 |
+
"loss": 21.829217529296876,
|
| 591 |
+
"step": 1095
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 2.0787530762920428,
|
| 595 |
+
"grad_norm": 108.95834350585938,
|
| 596 |
+
"learning_rate": 3.83672974284328e-05,
|
| 597 |
+
"loss": 21.407171630859374,
|
| 598 |
+
"step": 1110
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 2.106879174967772,
|
| 602 |
+
"grad_norm": 86.67636108398438,
|
| 603 |
+
"learning_rate": 3.8185346918971375e-05,
|
| 604 |
+
"loss": 22.318717447916665,
|
| 605 |
+
"step": 1125
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 2.1350052736435017,
|
| 609 |
+
"grad_norm": 90.65144348144531,
|
| 610 |
+
"learning_rate": 3.800339640950995e-05,
|
| 611 |
+
"loss": 22.579439290364583,
|
| 612 |
+
"step": 1140
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 2.1631313723192314,
|
| 616 |
+
"grad_norm": 160.0935516357422,
|
| 617 |
+
"learning_rate": 3.782144590004852e-05,
|
| 618 |
+
"loss": 21.32430419921875,
|
| 619 |
+
"step": 1155
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 2.1912574709949606,
|
| 623 |
+
"grad_norm": 80.67872619628906,
|
| 624 |
+
"learning_rate": 3.7639495390587096e-05,
|
| 625 |
+
"loss": 22.795635986328126,
|
| 626 |
+
"step": 1170
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 2.2193835696706903,
|
| 630 |
+
"grad_norm": 78.44005584716797,
|
| 631 |
+
"learning_rate": 3.745754488112567e-05,
|
| 632 |
+
"loss": 21.308553059895832,
|
| 633 |
+
"step": 1185
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.24750966834642,
|
| 637 |
+
"grad_norm": 95.2944107055664,
|
| 638 |
+
"learning_rate": 3.7275594371664243e-05,
|
| 639 |
+
"loss": 20.899271647135418,
|
| 640 |
+
"step": 1200
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.24750966834642,
|
| 644 |
+
"eval_accuracy": 0.6985507246376812,
|
| 645 |
+
"eval_loss": 1.3909375667572021,
|
| 646 |
+
"eval_macro_f1": 0.6854383677464303,
|
| 647 |
+
"eval_runtime": 2.3405,
|
| 648 |
+
"eval_samples_per_second": 147.407,
|
| 649 |
+
"eval_steps_per_second": 18.8,
|
| 650 |
+
"step": 1200
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 2.275635767022149,
|
| 654 |
+
"grad_norm": 83.903076171875,
|
| 655 |
+
"learning_rate": 3.709364386220282e-05,
|
| 656 |
+
"loss": 23.106620279947915,
|
| 657 |
+
"step": 1215
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 2.303761865697879,
|
| 661 |
+
"grad_norm": 89.56684875488281,
|
| 662 |
+
"learning_rate": 3.691169335274139e-05,
|
| 663 |
+
"loss": 20.57239990234375,
|
| 664 |
+
"step": 1230
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 2.3318879643736086,
|
| 668 |
+
"grad_norm": 99.3587417602539,
|
| 669 |
+
"learning_rate": 3.6729742843279964e-05,
|
| 670 |
+
"loss": 21.402762858072915,
|
| 671 |
+
"step": 1245
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 2.360014063049338,
|
| 675 |
+
"grad_norm": 95.15524291992188,
|
| 676 |
+
"learning_rate": 3.654779233381854e-05,
|
| 677 |
+
"loss": 20.991483561197917,
|
| 678 |
+
"step": 1260
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 2.3881401617250675,
|
| 682 |
+
"grad_norm": 87.97482299804688,
|
| 683 |
+
"learning_rate": 3.636584182435711e-05,
|
| 684 |
+
"loss": 22.1961669921875,
|
| 685 |
+
"step": 1275
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 2.4162662604007967,
|
| 689 |
+
"grad_norm": 105.3332290649414,
|
| 690 |
+
"learning_rate": 3.6183891314895685e-05,
|
| 691 |
+
"loss": 21.362872314453124,
|
| 692 |
+
"step": 1290
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 2.4443923590765264,
|
| 696 |
+
"grad_norm": 67.10509490966797,
|
| 697 |
+
"learning_rate": 3.600194080543426e-05,
|
| 698 |
+
"loss": 21.770963541666667,
|
| 699 |
+
"step": 1305
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 2.472518457752256,
|
| 703 |
+
"grad_norm": 93.77086639404297,
|
| 704 |
+
"learning_rate": 3.581999029597283e-05,
|
| 705 |
+
"loss": 22.990873209635417,
|
| 706 |
+
"step": 1320
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 2.5006445564279853,
|
| 710 |
+
"grad_norm": 67.30560302734375,
|
| 711 |
+
"learning_rate": 3.56380397865114e-05,
|
| 712 |
+
"loss": 21.035380045572918,
|
| 713 |
+
"step": 1335
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 2.528770655103715,
|
| 717 |
+
"grad_norm": 127.03382873535156,
|
| 718 |
+
"learning_rate": 3.545608927704997e-05,
|
| 719 |
+
"loss": 21.682499186197916,
|
| 720 |
+
"step": 1350
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 2.528770655103715,
|
| 724 |
+
"eval_accuracy": 0.6811594202898551,
|
| 725 |
+
"eval_loss": 1.4433109760284424,
|
| 726 |
+
"eval_macro_f1": 0.6794718548394098,
|
| 727 |
+
"eval_runtime": 2.2369,
|
| 728 |
+
"eval_samples_per_second": 154.234,
|
| 729 |
+
"eval_steps_per_second": 19.67,
|
| 730 |
+
"step": 1350
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 2.5568967537794443,
|
| 734 |
+
"grad_norm": 92.79231262207031,
|
| 735 |
+
"learning_rate": 3.527413876758855e-05,
|
| 736 |
+
"loss": 21.885359700520834,
|
| 737 |
+
"step": 1365
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 2.585022852455174,
|
| 741 |
+
"grad_norm": 111.23881530761719,
|
| 742 |
+
"learning_rate": 3.509218825812712e-05,
|
| 743 |
+
"loss": 20.30838623046875,
|
| 744 |
+
"step": 1380
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 2.6131489511309036,
|
| 748 |
+
"grad_norm": 72.55780029296875,
|
| 749 |
+
"learning_rate": 3.4910237748665694e-05,
|
| 750 |
+
"loss": 18.903086344401043,
|
| 751 |
+
"step": 1395
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 2.641275049806633,
|
| 755 |
+
"grad_norm": 73.78776550292969,
|
| 756 |
+
"learning_rate": 3.472828723920427e-05,
|
| 757 |
+
"loss": 22.561869303385418,
|
| 758 |
+
"step": 1410
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.6694011484823625,
|
| 762 |
+
"grad_norm": 86.27180480957031,
|
| 763 |
+
"learning_rate": 3.454633672974285e-05,
|
| 764 |
+
"loss": 21.844730631510416,
|
| 765 |
+
"step": 1425
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 2.6975272471580922,
|
| 769 |
+
"grad_norm": 65.71673583984375,
|
| 770 |
+
"learning_rate": 3.436438622028142e-05,
|
| 771 |
+
"loss": 21.621647135416666,
|
| 772 |
+
"step": 1440
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 2.7256533458338215,
|
| 776 |
+
"grad_norm": 94.1865463256836,
|
| 777 |
+
"learning_rate": 3.4182435710819996e-05,
|
| 778 |
+
"loss": 21.298856608072917,
|
| 779 |
+
"step": 1455
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 2.753779444509551,
|
| 783 |
+
"grad_norm": 82.48493957519531,
|
| 784 |
+
"learning_rate": 3.400048520135857e-05,
|
| 785 |
+
"loss": 21.100826009114584,
|
| 786 |
+
"step": 1470
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 2.781905543185281,
|
| 790 |
+
"grad_norm": 96.52738952636719,
|
| 791 |
+
"learning_rate": 3.381853469189714e-05,
|
| 792 |
+
"loss": 22.47982177734375,
|
| 793 |
+
"step": 1485
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 2.81003164186101,
|
| 797 |
+
"grad_norm": 87.80317687988281,
|
| 798 |
+
"learning_rate": 3.363658418243571e-05,
|
| 799 |
+
"loss": 21.95230916341146,
|
| 800 |
+
"step": 1500
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 2.81003164186101,
|
| 804 |
+
"eval_accuracy": 0.6869565217391305,
|
| 805 |
+
"eval_loss": 1.3259601593017578,
|
| 806 |
+
"eval_macro_f1": 0.6715942315942316,
|
| 807 |
+
"eval_runtime": 2.2965,
|
| 808 |
+
"eval_samples_per_second": 150.226,
|
| 809 |
+
"eval_steps_per_second": 19.159,
|
| 810 |
+
"step": 1500
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 2.8381577405367397,
|
| 814 |
+
"grad_norm": 134.34188842773438,
|
| 815 |
+
"learning_rate": 3.3454633672974284e-05,
|
| 816 |
+
"loss": 22.170475260416666,
|
| 817 |
+
"step": 1515
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 2.8662838392124694,
|
| 821 |
+
"grad_norm": 72.98772430419922,
|
| 822 |
+
"learning_rate": 3.327268316351286e-05,
|
| 823 |
+
"loss": 23.180810546875,
|
| 824 |
+
"step": 1530
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 2.8944099378881987,
|
| 828 |
+
"grad_norm": 131.15469360351562,
|
| 829 |
+
"learning_rate": 3.309073265405143e-05,
|
| 830 |
+
"loss": 21.58048095703125,
|
| 831 |
+
"step": 1545
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 2.9225360365639284,
|
| 835 |
+
"grad_norm": 75.53298950195312,
|
| 836 |
+
"learning_rate": 3.2908782144590005e-05,
|
| 837 |
+
"loss": 20.257352701822917,
|
| 838 |
+
"step": 1560
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 2.950662135239658,
|
| 842 |
+
"grad_norm": 100.07022094726562,
|
| 843 |
+
"learning_rate": 3.272683163512858e-05,
|
| 844 |
+
"loss": 19.97838134765625,
|
| 845 |
+
"step": 1575
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 2.9787882339153873,
|
| 849 |
+
"grad_norm": 78.29119110107422,
|
| 850 |
+
"learning_rate": 3.254488112566715e-05,
|
| 851 |
+
"loss": 20.777811686197918,
|
| 852 |
+
"step": 1590
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 3.005625219735146,
|
| 856 |
+
"grad_norm": 92.47520446777344,
|
| 857 |
+
"learning_rate": 3.2362930616205726e-05,
|
| 858 |
+
"loss": 22.04563191731771,
|
| 859 |
+
"step": 1605
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 3.0337513184108755,
|
| 863 |
+
"grad_norm": 77.91747283935547,
|
| 864 |
+
"learning_rate": 3.21809801067443e-05,
|
| 865 |
+
"loss": 20.988616943359375,
|
| 866 |
+
"step": 1620
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 3.0618774170866048,
|
| 870 |
+
"grad_norm": 80.09091186523438,
|
| 871 |
+
"learning_rate": 3.199902959728287e-05,
|
| 872 |
+
"loss": 20.8621826171875,
|
| 873 |
+
"step": 1635
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 3.0900035157623345,
|
| 877 |
+
"grad_norm": 94.06583404541016,
|
| 878 |
+
"learning_rate": 3.1817079087821447e-05,
|
| 879 |
+
"loss": 21.464599609375,
|
| 880 |
+
"step": 1650
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 3.0900035157623345,
|
| 884 |
+
"eval_accuracy": 0.7014492753623188,
|
| 885 |
+
"eval_loss": 1.3364124298095703,
|
| 886 |
+
"eval_macro_f1": 0.6895917207672184,
|
| 887 |
+
"eval_runtime": 2.2934,
|
| 888 |
+
"eval_samples_per_second": 150.431,
|
| 889 |
+
"eval_steps_per_second": 19.185,
|
| 890 |
+
"step": 1650
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 3.118129614438064,
|
| 894 |
+
"grad_norm": 116.02384948730469,
|
| 895 |
+
"learning_rate": 3.163512857836002e-05,
|
| 896 |
+
"loss": 20.88741455078125,
|
| 897 |
+
"step": 1665
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 3.1462557131137934,
|
| 901 |
+
"grad_norm": 94.62155151367188,
|
| 902 |
+
"learning_rate": 3.1453178068898594e-05,
|
| 903 |
+
"loss": 18.302730305989584,
|
| 904 |
+
"step": 1680
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 3.174381811789523,
|
| 908 |
+
"grad_norm": 121.826904296875,
|
| 909 |
+
"learning_rate": 3.127122755943717e-05,
|
| 910 |
+
"loss": 21.009354654947916,
|
| 911 |
+
"step": 1695
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 3.2025079104652527,
|
| 915 |
+
"grad_norm": 79.9039535522461,
|
| 916 |
+
"learning_rate": 3.108927704997574e-05,
|
| 917 |
+
"loss": 20.241634114583334,
|
| 918 |
+
"step": 1710
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 3.230634009140982,
|
| 922 |
+
"grad_norm": 125.52740478515625,
|
| 923 |
+
"learning_rate": 3.0907326540514315e-05,
|
| 924 |
+
"loss": 19.953243001302084,
|
| 925 |
+
"step": 1725
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 3.2587601078167117,
|
| 929 |
+
"grad_norm": 88.08680725097656,
|
| 930 |
+
"learning_rate": 3.072537603105289e-05,
|
| 931 |
+
"loss": 20.15721435546875,
|
| 932 |
+
"step": 1740
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 3.286886206492441,
|
| 936 |
+
"grad_norm": 116.15298461914062,
|
| 937 |
+
"learning_rate": 3.054342552159146e-05,
|
| 938 |
+
"loss": 20.75643310546875,
|
| 939 |
+
"step": 1755
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 3.3150123051681706,
|
| 943 |
+
"grad_norm": 99.74699401855469,
|
| 944 |
+
"learning_rate": 3.0361475012130036e-05,
|
| 945 |
+
"loss": 20.680021158854167,
|
| 946 |
+
"step": 1770
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 3.3431384038439003,
|
| 950 |
+
"grad_norm": 102.29747772216797,
|
| 951 |
+
"learning_rate": 3.017952450266861e-05,
|
| 952 |
+
"loss": 21.737186686197916,
|
| 953 |
+
"step": 1785
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 3.3712645025196295,
|
| 957 |
+
"grad_norm": 123.22283935546875,
|
| 958 |
+
"learning_rate": 2.9997573993207183e-05,
|
| 959 |
+
"loss": 20.67413330078125,
|
| 960 |
+
"step": 1800
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 3.3712645025196295,
|
| 964 |
+
"eval_accuracy": 0.6956521739130435,
|
| 965 |
+
"eval_loss": 1.3445881605148315,
|
| 966 |
+
"eval_macro_f1": 0.6889659175345941,
|
| 967 |
+
"eval_runtime": 2.3189,
|
| 968 |
+
"eval_samples_per_second": 148.775,
|
| 969 |
+
"eval_steps_per_second": 18.974,
|
| 970 |
+
"step": 1800
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 3.399390601195359,
|
| 974 |
+
"grad_norm": 87.35185241699219,
|
| 975 |
+
"learning_rate": 2.9815623483745757e-05,
|
| 976 |
+
"loss": 19.203857421875,
|
| 977 |
+
"step": 1815
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 3.427516699871089,
|
| 981 |
+
"grad_norm": 90.06853485107422,
|
| 982 |
+
"learning_rate": 2.9633672974284327e-05,
|
| 983 |
+
"loss": 20.904638671875,
|
| 984 |
+
"step": 1830
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 3.455642798546818,
|
| 988 |
+
"grad_norm": 65.26019287109375,
|
| 989 |
+
"learning_rate": 2.94517224648229e-05,
|
| 990 |
+
"loss": 22.2024658203125,
|
| 991 |
+
"step": 1845
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 3.483768897222548,
|
| 995 |
+
"grad_norm": 110.0214614868164,
|
| 996 |
+
"learning_rate": 2.9269771955361474e-05,
|
| 997 |
+
"loss": 19.504443359375,
|
| 998 |
+
"step": 1860
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 3.5118949958982775,
|
| 1002 |
+
"grad_norm": 92.55294799804688,
|
| 1003 |
+
"learning_rate": 2.9087821445900048e-05,
|
| 1004 |
+
"loss": 20.45948486328125,
|
| 1005 |
+
"step": 1875
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 3.5400210945740067,
|
| 1009 |
+
"grad_norm": 86.1778564453125,
|
| 1010 |
+
"learning_rate": 2.8905870936438622e-05,
|
| 1011 |
+
"loss": 19.796297200520833,
|
| 1012 |
+
"step": 1890
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 3.5681471932497364,
|
| 1016 |
+
"grad_norm": 132.0889892578125,
|
| 1017 |
+
"learning_rate": 2.8723920426977195e-05,
|
| 1018 |
+
"loss": 20.499460856119793,
|
| 1019 |
+
"step": 1905
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 3.596273291925466,
|
| 1023 |
+
"grad_norm": 144.37742614746094,
|
| 1024 |
+
"learning_rate": 2.854196991751577e-05,
|
| 1025 |
+
"loss": 19.9392333984375,
|
| 1026 |
+
"step": 1920
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 3.6243993906011953,
|
| 1030 |
+
"grad_norm": 121.33406829833984,
|
| 1031 |
+
"learning_rate": 2.8360019408054346e-05,
|
| 1032 |
+
"loss": 20.427311197916666,
|
| 1033 |
+
"step": 1935
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 3.652525489276925,
|
| 1037 |
+
"grad_norm": 106.86882019042969,
|
| 1038 |
+
"learning_rate": 2.817806889859292e-05,
|
| 1039 |
+
"loss": 19.858015950520834,
|
| 1040 |
+
"step": 1950
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 3.652525489276925,
|
| 1044 |
+
"eval_accuracy": 0.7043478260869566,
|
| 1045 |
+
"eval_loss": 1.2970499992370605,
|
| 1046 |
+
"eval_macro_f1": 0.6880047900054095,
|
| 1047 |
+
"eval_runtime": 2.2884,
|
| 1048 |
+
"eval_samples_per_second": 150.763,
|
| 1049 |
+
"eval_steps_per_second": 19.228,
|
| 1050 |
+
"step": 1950
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 3.6806515879526542,
|
| 1054 |
+
"grad_norm": 97.60050964355469,
|
| 1055 |
+
"learning_rate": 2.7996118389131493e-05,
|
| 1056 |
+
"loss": 20.116133626302084,
|
| 1057 |
+
"step": 1965
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 3.708777686628384,
|
| 1061 |
+
"grad_norm": 92.11235046386719,
|
| 1062 |
+
"learning_rate": 2.7814167879670067e-05,
|
| 1063 |
+
"loss": 20.657806396484375,
|
| 1064 |
+
"step": 1980
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 3.7369037853041136,
|
| 1068 |
+
"grad_norm": 117.19283294677734,
|
| 1069 |
+
"learning_rate": 2.763221737020864e-05,
|
| 1070 |
+
"loss": 20.737459309895833,
|
| 1071 |
+
"step": 1995
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 3.765029883979843,
|
| 1075 |
+
"grad_norm": 101.78399658203125,
|
| 1076 |
+
"learning_rate": 2.7450266860747208e-05,
|
| 1077 |
+
"loss": 19.397184244791667,
|
| 1078 |
+
"step": 2010
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 3.7931559826555725,
|
| 1082 |
+
"grad_norm": 90.56041717529297,
|
| 1083 |
+
"learning_rate": 2.7268316351285785e-05,
|
| 1084 |
+
"loss": 20.284912109375,
|
| 1085 |
+
"step": 2025
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 3.8212820813313018,
|
| 1089 |
+
"grad_norm": 90.52794647216797,
|
| 1090 |
+
"learning_rate": 2.708636584182436e-05,
|
| 1091 |
+
"loss": 19.95211181640625,
|
| 1092 |
+
"step": 2040
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 3.8494081800070314,
|
| 1096 |
+
"grad_norm": 78.75577545166016,
|
| 1097 |
+
"learning_rate": 2.6904415332362932e-05,
|
| 1098 |
+
"loss": 20.411405436197917,
|
| 1099 |
+
"step": 2055
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 3.877534278682761,
|
| 1103 |
+
"grad_norm": 110.91737365722656,
|
| 1104 |
+
"learning_rate": 2.6722464822901506e-05,
|
| 1105 |
+
"loss": 19.89073486328125,
|
| 1106 |
+
"step": 2070
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 3.9056603773584904,
|
| 1110 |
+
"grad_norm": 88.76385498046875,
|
| 1111 |
+
"learning_rate": 2.654051431344008e-05,
|
| 1112 |
+
"loss": 20.76527099609375,
|
| 1113 |
+
"step": 2085
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 3.93378647603422,
|
| 1117 |
+
"grad_norm": 119.09017181396484,
|
| 1118 |
+
"learning_rate": 2.6358563803978653e-05,
|
| 1119 |
+
"loss": 18.4523193359375,
|
| 1120 |
+
"step": 2100
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 3.93378647603422,
|
| 1124 |
+
"eval_accuracy": 0.7101449275362319,
|
| 1125 |
+
"eval_loss": 1.3066604137420654,
|
| 1126 |
+
"eval_macro_f1": 0.7006373828280611,
|
| 1127 |
+
"eval_runtime": 2.3801,
|
| 1128 |
+
"eval_samples_per_second": 144.955,
|
| 1129 |
+
"eval_steps_per_second": 18.487,
|
| 1130 |
+
"step": 2100
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 3.9619125747099497,
|
| 1134 |
+
"grad_norm": 114.07467651367188,
|
| 1135 |
+
"learning_rate": 2.6176613294517227e-05,
|
| 1136 |
+
"loss": 20.802079264322916,
|
| 1137 |
+
"step": 2115
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 3.990038673385679,
|
| 1141 |
+
"grad_norm": 106.22249603271484,
|
| 1142 |
+
"learning_rate": 2.59946627850558e-05,
|
| 1143 |
+
"loss": 19.819669596354167,
|
| 1144 |
+
"step": 2130
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 4.0168756592054375,
|
| 1148 |
+
"grad_norm": 107.52822875976562,
|
| 1149 |
+
"learning_rate": 2.5812712275594374e-05,
|
| 1150 |
+
"loss": 18.571612548828124,
|
| 1151 |
+
"step": 2145
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 4.045001757881168,
|
| 1155 |
+
"grad_norm": 118.39415740966797,
|
| 1156 |
+
"learning_rate": 2.5630761766132948e-05,
|
| 1157 |
+
"loss": 19.24214070638021,
|
| 1158 |
+
"step": 2160
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 4.073127856556897,
|
| 1162 |
+
"grad_norm": 98.87726593017578,
|
| 1163 |
+
"learning_rate": 2.5448811256671518e-05,
|
| 1164 |
+
"loss": 19.012089029947916,
|
| 1165 |
+
"step": 2175
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 4.101253955232626,
|
| 1169 |
+
"grad_norm": 117.30307006835938,
|
| 1170 |
+
"learning_rate": 2.526686074721009e-05,
|
| 1171 |
+
"loss": 18.63901570638021,
|
| 1172 |
+
"step": 2190
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 4.129380053908355,
|
| 1176 |
+
"grad_norm": 131.8447723388672,
|
| 1177 |
+
"learning_rate": 2.5084910237748665e-05,
|
| 1178 |
+
"loss": 18.810434977213543,
|
| 1179 |
+
"step": 2205
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 4.1575061525840855,
|
| 1183 |
+
"grad_norm": 127.37617492675781,
|
| 1184 |
+
"learning_rate": 2.490295972828724e-05,
|
| 1185 |
+
"loss": 18.742826334635417,
|
| 1186 |
+
"step": 2220
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 4.185632251259815,
|
| 1190 |
+
"grad_norm": 123.80364227294922,
|
| 1191 |
+
"learning_rate": 2.4721009218825813e-05,
|
| 1192 |
+
"loss": 19.374788411458333,
|
| 1193 |
+
"step": 2235
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 4.213758349935544,
|
| 1197 |
+
"grad_norm": 88.60491180419922,
|
| 1198 |
+
"learning_rate": 2.4539058709364386e-05,
|
| 1199 |
+
"loss": 18.840421549479167,
|
| 1200 |
+
"step": 2250
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 4.213758349935544,
|
| 1204 |
+
"eval_accuracy": 0.7101449275362319,
|
| 1205 |
+
"eval_loss": 1.294223427772522,
|
| 1206 |
+
"eval_macro_f1": 0.7018989690942834,
|
| 1207 |
+
"eval_runtime": 2.2332,
|
| 1208 |
+
"eval_samples_per_second": 154.49,
|
| 1209 |
+
"eval_steps_per_second": 19.703,
|
| 1210 |
+
"step": 2250
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 4.241884448611274,
|
| 1214 |
+
"grad_norm": 111.5672836303711,
|
| 1215 |
+
"learning_rate": 2.435710819990296e-05,
|
| 1216 |
+
"loss": 19.6460205078125,
|
| 1217 |
+
"step": 2265
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 4.270010547287003,
|
| 1221 |
+
"grad_norm": 84.75606536865234,
|
| 1222 |
+
"learning_rate": 2.4175157690441537e-05,
|
| 1223 |
+
"loss": 19.300996907552083,
|
| 1224 |
+
"step": 2280
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 4.298136645962733,
|
| 1228 |
+
"grad_norm": 113.91012573242188,
|
| 1229 |
+
"learning_rate": 2.3993207180980107e-05,
|
| 1230 |
+
"loss": 19.68141072591146,
|
| 1231 |
+
"step": 2295
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 4.326262744638463,
|
| 1235 |
+
"grad_norm": 92.45838928222656,
|
| 1236 |
+
"learning_rate": 2.381125667151868e-05,
|
| 1237 |
+
"loss": 20.36899617513021,
|
| 1238 |
+
"step": 2310
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 4.354388843314192,
|
| 1242 |
+
"grad_norm": 90.0018310546875,
|
| 1243 |
+
"learning_rate": 2.3629306162057255e-05,
|
| 1244 |
+
"loss": 20.173634847005207,
|
| 1245 |
+
"step": 2325
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 4.382514941989921,
|
| 1249 |
+
"grad_norm": 110.76561737060547,
|
| 1250 |
+
"learning_rate": 2.3447355652595828e-05,
|
| 1251 |
+
"loss": 19.140922037760415,
|
| 1252 |
+
"step": 2340
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 4.410641040665651,
|
| 1256 |
+
"grad_norm": 90.89640808105469,
|
| 1257 |
+
"learning_rate": 2.3265405143134402e-05,
|
| 1258 |
+
"loss": 18.70762939453125,
|
| 1259 |
+
"step": 2355
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 4.438767139341381,
|
| 1263 |
+
"grad_norm": 119.49583435058594,
|
| 1264 |
+
"learning_rate": 2.3083454633672976e-05,
|
| 1265 |
+
"loss": 19.42769775390625,
|
| 1266 |
+
"step": 2370
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 4.46689323801711,
|
| 1270 |
+
"grad_norm": 145.5922088623047,
|
| 1271 |
+
"learning_rate": 2.290150412421155e-05,
|
| 1272 |
+
"loss": 17.96015625,
|
| 1273 |
+
"step": 2385
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 4.49501933669284,
|
| 1277 |
+
"grad_norm": 138.03018188476562,
|
| 1278 |
+
"learning_rate": 2.2719553614750123e-05,
|
| 1279 |
+
"loss": 19.798982747395833,
|
| 1280 |
+
"step": 2400
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 4.49501933669284,
|
| 1284 |
+
"eval_accuracy": 0.7275362318840579,
|
| 1285 |
+
"eval_loss": 1.2909643650054932,
|
| 1286 |
+
"eval_macro_f1": 0.7214296921618338,
|
| 1287 |
+
"eval_runtime": 2.3353,
|
| 1288 |
+
"eval_samples_per_second": 147.734,
|
| 1289 |
+
"eval_steps_per_second": 18.841,
|
| 1290 |
+
"step": 2400
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 4.523145435368569,
|
| 1294 |
+
"grad_norm": 110.0138931274414,
|
| 1295 |
+
"learning_rate": 2.2537603105288697e-05,
|
| 1296 |
+
"loss": 19.334220377604165,
|
| 1297 |
+
"step": 2415
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 4.551271534044298,
|
| 1301 |
+
"grad_norm": 138.44602966308594,
|
| 1302 |
+
"learning_rate": 2.235565259582727e-05,
|
| 1303 |
+
"loss": 19.689516194661458,
|
| 1304 |
+
"step": 2430
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 4.579397632720028,
|
| 1308 |
+
"grad_norm": 128.7583465576172,
|
| 1309 |
+
"learning_rate": 2.2173702086365844e-05,
|
| 1310 |
+
"loss": 18.79603271484375,
|
| 1311 |
+
"step": 2445
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 4.607523731395758,
|
| 1315 |
+
"grad_norm": 112.34595489501953,
|
| 1316 |
+
"learning_rate": 2.1991751576904414e-05,
|
| 1317 |
+
"loss": 19.47750244140625,
|
| 1318 |
+
"step": 2460
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 4.635649830071487,
|
| 1322 |
+
"grad_norm": 146.0894317626953,
|
| 1323 |
+
"learning_rate": 2.1809801067442988e-05,
|
| 1324 |
+
"loss": 17.751841227213543,
|
| 1325 |
+
"step": 2475
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 4.663775928747217,
|
| 1329 |
+
"grad_norm": 119.35760498046875,
|
| 1330 |
+
"learning_rate": 2.1627850557981565e-05,
|
| 1331 |
+
"loss": 20.366532389322916,
|
| 1332 |
+
"step": 2490
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 4.691902027422946,
|
| 1336 |
+
"grad_norm": 155.166259765625,
|
| 1337 |
+
"learning_rate": 2.144590004852014e-05,
|
| 1338 |
+
"loss": 18.987797037760416,
|
| 1339 |
+
"step": 2505
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 4.720028126098676,
|
| 1343 |
+
"grad_norm": 117.52566528320312,
|
| 1344 |
+
"learning_rate": 2.1263949539058712e-05,
|
| 1345 |
+
"loss": 19.627958170572917,
|
| 1346 |
+
"step": 2520
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 4.748154224774405,
|
| 1350 |
+
"grad_norm": 116.88736724853516,
|
| 1351 |
+
"learning_rate": 2.1081999029597286e-05,
|
| 1352 |
+
"loss": 19.34803670247396,
|
| 1353 |
+
"step": 2535
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 4.776280323450135,
|
| 1357 |
+
"grad_norm": 123.58113098144531,
|
| 1358 |
+
"learning_rate": 2.0900048520135856e-05,
|
| 1359 |
+
"loss": 18.269120279947916,
|
| 1360 |
+
"step": 2550
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 4.776280323450135,
|
| 1364 |
+
"eval_accuracy": 0.7159420289855073,
|
| 1365 |
+
"eval_loss": 1.2964649200439453,
|
| 1366 |
+
"eval_macro_f1": 0.7079967625416551,
|
| 1367 |
+
"eval_runtime": 2.2441,
|
| 1368 |
+
"eval_samples_per_second": 153.737,
|
| 1369 |
+
"eval_steps_per_second": 19.607,
|
| 1370 |
+
"step": 2550
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 4.804406422125864,
|
| 1374 |
+
"grad_norm": 112.25335693359375,
|
| 1375 |
+
"learning_rate": 2.071809801067443e-05,
|
| 1376 |
+
"loss": 20.070353190104168,
|
| 1377 |
+
"step": 2565
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 4.8325325208015935,
|
| 1381 |
+
"grad_norm": 93.22418212890625,
|
| 1382 |
+
"learning_rate": 2.0536147501213003e-05,
|
| 1383 |
+
"loss": 19.409814453125,
|
| 1384 |
+
"step": 2580
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 4.860658619477324,
|
| 1388 |
+
"grad_norm": 118.93272399902344,
|
| 1389 |
+
"learning_rate": 2.0354196991751577e-05,
|
| 1390 |
+
"loss": 19.28167724609375,
|
| 1391 |
+
"step": 2595
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 4.888784718153053,
|
| 1395 |
+
"grad_norm": 89.56037902832031,
|
| 1396 |
+
"learning_rate": 2.0172246482290154e-05,
|
| 1397 |
+
"loss": 18.811210123697915,
|
| 1398 |
+
"step": 2610
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 4.916910816828782,
|
| 1402 |
+
"grad_norm": 111.18524169921875,
|
| 1403 |
+
"learning_rate": 1.9990295972828724e-05,
|
| 1404 |
+
"loss": 19.25428466796875,
|
| 1405 |
+
"step": 2625
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 4.945036915504512,
|
| 1409 |
+
"grad_norm": 136.34375,
|
| 1410 |
+
"learning_rate": 1.9808345463367298e-05,
|
| 1411 |
+
"loss": 19.659928385416666,
|
| 1412 |
+
"step": 2640
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 4.973163014180241,
|
| 1416 |
+
"grad_norm": 118.25164031982422,
|
| 1417 |
+
"learning_rate": 1.9626394953905872e-05,
|
| 1418 |
+
"loss": 19.45357666015625,
|
| 1419 |
+
"step": 2655
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 5.0,
|
| 1423 |
+
"grad_norm": 57.6742057800293,
|
| 1424 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 1425 |
+
"loss": 17.84049072265625,
|
| 1426 |
+
"step": 2670
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 5.028126098675729,
|
| 1430 |
+
"grad_norm": 147.96412658691406,
|
| 1431 |
+
"learning_rate": 1.926249393498302e-05,
|
| 1432 |
+
"loss": 19.337980143229167,
|
| 1433 |
+
"step": 2685
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 5.056252197351459,
|
| 1437 |
+
"grad_norm": 132.63999938964844,
|
| 1438 |
+
"learning_rate": 1.9080543425521593e-05,
|
| 1439 |
+
"loss": 18.337638346354165,
|
| 1440 |
+
"step": 2700
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 5.056252197351459,
|
| 1444 |
+
"eval_accuracy": 0.7217391304347827,
|
| 1445 |
+
"eval_loss": 1.26863694190979,
|
| 1446 |
+
"eval_macro_f1": 0.7099575104335049,
|
| 1447 |
+
"eval_runtime": 2.3349,
|
| 1448 |
+
"eval_samples_per_second": 147.757,
|
| 1449 |
+
"eval_steps_per_second": 18.844,
|
| 1450 |
+
"step": 2700
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 5.084378296027189,
|
| 1454 |
+
"grad_norm": 155.00131225585938,
|
| 1455 |
+
"learning_rate": 1.8898592916060166e-05,
|
| 1456 |
+
"loss": 18.018782552083334,
|
| 1457 |
+
"step": 2715
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 5.112504394702918,
|
| 1461 |
+
"grad_norm": 101.11901092529297,
|
| 1462 |
+
"learning_rate": 1.871664240659874e-05,
|
| 1463 |
+
"loss": 17.31574910481771,
|
| 1464 |
+
"step": 2730
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 5.140630493378648,
|
| 1468 |
+
"grad_norm": 122.56869506835938,
|
| 1469 |
+
"learning_rate": 1.8534691897137314e-05,
|
| 1470 |
+
"loss": 17.734781901041668,
|
| 1471 |
+
"step": 2745
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 5.168756592054377,
|
| 1475 |
+
"grad_norm": 144.50408935546875,
|
| 1476 |
+
"learning_rate": 1.8352741387675887e-05,
|
| 1477 |
+
"loss": 18.0669189453125,
|
| 1478 |
+
"step": 2760
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 5.1968826907301064,
|
| 1482 |
+
"grad_norm": 139.19400024414062,
|
| 1483 |
+
"learning_rate": 1.817079087821446e-05,
|
| 1484 |
+
"loss": 18.6113037109375,
|
| 1485 |
+
"step": 2775
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 5.225008789405837,
|
| 1489 |
+
"grad_norm": 135.64263916015625,
|
| 1490 |
+
"learning_rate": 1.798884036875303e-05,
|
| 1491 |
+
"loss": 18.706892903645834,
|
| 1492 |
+
"step": 2790
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 5.253134888081566,
|
| 1496 |
+
"grad_norm": 105.34918975830078,
|
| 1497 |
+
"learning_rate": 1.7806889859291605e-05,
|
| 1498 |
+
"loss": 19.1353759765625,
|
| 1499 |
+
"step": 2805
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 5.281260986757295,
|
| 1503 |
+
"grad_norm": 151.3452911376953,
|
| 1504 |
+
"learning_rate": 1.762493934983018e-05,
|
| 1505 |
+
"loss": 16.799456787109374,
|
| 1506 |
+
"step": 2820
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 5.309387085433025,
|
| 1510 |
+
"grad_norm": 140.87081909179688,
|
| 1511 |
+
"learning_rate": 1.7442988840368756e-05,
|
| 1512 |
+
"loss": 17.74376220703125,
|
| 1513 |
+
"step": 2835
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 5.337513184108754,
|
| 1517 |
+
"grad_norm": 117.46965026855469,
|
| 1518 |
+
"learning_rate": 1.726103833090733e-05,
|
| 1519 |
+
"loss": 18.106500244140626,
|
| 1520 |
+
"step": 2850
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 5.337513184108754,
|
| 1524 |
+
"eval_accuracy": 0.7217391304347827,
|
| 1525 |
+
"eval_loss": 1.3104764223098755,
|
| 1526 |
+
"eval_macro_f1": 0.715025948306076,
|
| 1527 |
+
"eval_runtime": 2.2885,
|
| 1528 |
+
"eval_samples_per_second": 150.756,
|
| 1529 |
+
"eval_steps_per_second": 19.227,
|
| 1530 |
+
"step": 2850
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 5.365639282784484,
|
| 1534 |
+
"grad_norm": 98.67291259765625,
|
| 1535 |
+
"learning_rate": 1.7079087821445903e-05,
|
| 1536 |
+
"loss": 18.2799560546875,
|
| 1537 |
+
"step": 2865
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 5.393765381460213,
|
| 1541 |
+
"grad_norm": 127.13220977783203,
|
| 1542 |
+
"learning_rate": 1.6897137311984473e-05,
|
| 1543 |
+
"loss": 17.490669759114585,
|
| 1544 |
+
"step": 2880
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 5.421891480135943,
|
| 1548 |
+
"grad_norm": 125.16355895996094,
|
| 1549 |
+
"learning_rate": 1.6715186802523047e-05,
|
| 1550 |
+
"loss": 17.682118733723957,
|
| 1551 |
+
"step": 2895
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 5.450017578811672,
|
| 1555 |
+
"grad_norm": 178.70425415039062,
|
| 1556 |
+
"learning_rate": 1.653323629306162e-05,
|
| 1557 |
+
"loss": 18.41064453125,
|
| 1558 |
+
"step": 2910
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 5.4781436774874015,
|
| 1562 |
+
"grad_norm": 110.43656158447266,
|
| 1563 |
+
"learning_rate": 1.6351285783600194e-05,
|
| 1564 |
+
"loss": 19.174123128255207,
|
| 1565 |
+
"step": 2925
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 5.506269776163132,
|
| 1569 |
+
"grad_norm": 142.0528564453125,
|
| 1570 |
+
"learning_rate": 1.6169335274138768e-05,
|
| 1571 |
+
"loss": 17.642256673177084,
|
| 1572 |
+
"step": 2940
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 5.534395874838861,
|
| 1576 |
+
"grad_norm": 142.0417938232422,
|
| 1577 |
+
"learning_rate": 1.598738476467734e-05,
|
| 1578 |
+
"loss": 18.506465657552084,
|
| 1579 |
+
"step": 2955
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 5.56252197351459,
|
| 1583 |
+
"grad_norm": 117.37004852294922,
|
| 1584 |
+
"learning_rate": 1.5805434255215915e-05,
|
| 1585 |
+
"loss": 18.689676920572918,
|
| 1586 |
+
"step": 2970
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 5.59064807219032,
|
| 1590 |
+
"grad_norm": 103.04515075683594,
|
| 1591 |
+
"learning_rate": 1.562348374575449e-05,
|
| 1592 |
+
"loss": 16.94833780924479,
|
| 1593 |
+
"step": 2985
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 5.6187741708660495,
|
| 1597 |
+
"grad_norm": 124.92719268798828,
|
| 1598 |
+
"learning_rate": 1.5441533236293063e-05,
|
| 1599 |
+
"loss": 18.226180013020834,
|
| 1600 |
+
"step": 3000
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 5.6187741708660495,
|
| 1604 |
+
"eval_accuracy": 0.7159420289855073,
|
| 1605 |
+
"eval_loss": 1.288421392440796,
|
| 1606 |
+
"eval_macro_f1": 0.7073266993046686,
|
| 1607 |
+
"eval_runtime": 2.3046,
|
| 1608 |
+
"eval_samples_per_second": 149.702,
|
| 1609 |
+
"eval_steps_per_second": 19.092,
|
| 1610 |
+
"step": 3000
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 5.646900269541779,
|
| 1614 |
+
"grad_norm": 154.59812927246094,
|
| 1615 |
+
"learning_rate": 1.5259582726831636e-05,
|
| 1616 |
+
"loss": 18.67647501627604,
|
| 1617 |
+
"step": 3015
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 5.675026368217509,
|
| 1621 |
+
"grad_norm": 147.4285888671875,
|
| 1622 |
+
"learning_rate": 1.507763221737021e-05,
|
| 1623 |
+
"loss": 19.404524739583334,
|
| 1624 |
+
"step": 3030
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 5.703152466893238,
|
| 1628 |
+
"grad_norm": 105.8755111694336,
|
| 1629 |
+
"learning_rate": 1.4895681707908782e-05,
|
| 1630 |
+
"loss": 17.03916015625,
|
| 1631 |
+
"step": 3045
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 5.731278565568967,
|
| 1635 |
+
"grad_norm": 98.16700744628906,
|
| 1636 |
+
"learning_rate": 1.4713731198447356e-05,
|
| 1637 |
+
"loss": 17.873494466145832,
|
| 1638 |
+
"step": 3060
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 5.759404664244697,
|
| 1642 |
+
"grad_norm": 117.6919937133789,
|
| 1643 |
+
"learning_rate": 1.453178068898593e-05,
|
| 1644 |
+
"loss": 18.405171712239582,
|
| 1645 |
+
"step": 3075
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 5.787530762920427,
|
| 1649 |
+
"grad_norm": 140.4221954345703,
|
| 1650 |
+
"learning_rate": 1.4349830179524505e-05,
|
| 1651 |
+
"loss": 18.83017578125,
|
| 1652 |
+
"step": 3090
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 5.815656861596156,
|
| 1656 |
+
"grad_norm": 119.00141143798828,
|
| 1657 |
+
"learning_rate": 1.4167879670063078e-05,
|
| 1658 |
+
"loss": 18.715022786458334,
|
| 1659 |
+
"step": 3105
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 5.843782960271886,
|
| 1663 |
+
"grad_norm": 133.66452026367188,
|
| 1664 |
+
"learning_rate": 1.3985929160601648e-05,
|
| 1665 |
+
"loss": 17.813726806640624,
|
| 1666 |
+
"step": 3120
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 5.871909058947615,
|
| 1670 |
+
"grad_norm": 146.09732055664062,
|
| 1671 |
+
"learning_rate": 1.3803978651140224e-05,
|
| 1672 |
+
"loss": 19.055594889322915,
|
| 1673 |
+
"step": 3135
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 5.9000351576233445,
|
| 1677 |
+
"grad_norm": 112.73065948486328,
|
| 1678 |
+
"learning_rate": 1.3622028141678797e-05,
|
| 1679 |
+
"loss": 18.702596028645832,
|
| 1680 |
+
"step": 3150
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 5.9000351576233445,
|
| 1684 |
+
"eval_accuracy": 0.7130434782608696,
|
| 1685 |
+
"eval_loss": 1.2940000295639038,
|
| 1686 |
+
"eval_macro_f1": 0.7047758284600389,
|
| 1687 |
+
"eval_runtime": 2.2267,
|
| 1688 |
+
"eval_samples_per_second": 154.939,
|
| 1689 |
+
"eval_steps_per_second": 19.76,
|
| 1690 |
+
"step": 3150
|
| 1691 |
+
}
|
| 1692 |
+
],
|
| 1693 |
+
"logging_steps": 15,
|
| 1694 |
+
"max_steps": 4272,
|
| 1695 |
+
"num_input_tokens_seen": 0,
|
| 1696 |
+
"num_train_epochs": 8,
|
| 1697 |
+
"save_steps": 150,
|
| 1698 |
+
"stateful_callbacks": {
|
| 1699 |
+
"TrainerControl": {
|
| 1700 |
+
"args": {
|
| 1701 |
+
"should_epoch_stop": false,
|
| 1702 |
+
"should_evaluate": false,
|
| 1703 |
+
"should_log": false,
|
| 1704 |
+
"should_save": true,
|
| 1705 |
+
"should_training_stop": false
|
| 1706 |
+
},
|
| 1707 |
+
"attributes": {}
|
| 1708 |
+
}
|
| 1709 |
+
},
|
| 1710 |
+
"total_flos": 7413379027173376.0,
|
| 1711 |
+
"train_batch_size": 2,
|
| 1712 |
+
"trial_name": null,
|
| 1713 |
+
"trial_params": null
|
| 1714 |
+
}
|
sft/checkpoint-3150/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37d5b6b59a9b3ebbb703393ea1b80963b65b36ea5e43b5614682c24b6cd469ff
|
| 3 |
+
size 5201
|