Upload 9 files
Browse files- README.md +202 -0
- adapter_config.json +33 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1463 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: mistralai/Mistral-7B-v0.1
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.9.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": null,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 16,
|
| 13 |
+
"lora_dropout": 0.05,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 32,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"q_proj",
|
| 23 |
+
"v_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
+
"k_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"down_proj",
|
| 28 |
+
"up_proj"
|
| 29 |
+
],
|
| 30 |
+
"task_type": "CAUSAL_LM",
|
| 31 |
+
"use_dora": false,
|
| 32 |
+
"use_rslora": false
|
| 33 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8da3d6940a0710a4b3d188fdccdb370e9112726b25d4c59167b9cd4620489e1
|
| 3 |
+
size 167832688
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cacaabab08b0f795a13d2985e6a316f11bb4337ac03346ad329fbf9d6ee38274
|
| 3 |
+
size 335922450
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e4d28e39f27ee044f5ee49f5a7645695b76932948b11c1b00584d14fc5b1d8e
|
| 3 |
+
size 14512
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34510b901a214f68e833527d44cd53f157ee8d7281a702ad5a5e36a5552e8f41
|
| 3 |
+
size 14512
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4cb081055c2974be825162360067e630830a5dee1233c8f964bb185bd4f65142
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1463 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.963855421686747,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 206,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"grad_norm": 4.03125,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 4.8216,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02,
|
| 20 |
+
"grad_norm": 3.75,
|
| 21 |
+
"learning_rate": 4e-05,
|
| 22 |
+
"loss": 4.7468,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03,
|
| 27 |
+
"grad_norm": 3.046875,
|
| 28 |
+
"learning_rate": 6e-05,
|
| 29 |
+
"loss": 4.6897,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.04,
|
| 34 |
+
"grad_norm": 3.609375,
|
| 35 |
+
"learning_rate": 8e-05,
|
| 36 |
+
"loss": 4.871,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.05,
|
| 41 |
+
"grad_norm": 2.625,
|
| 42 |
+
"learning_rate": 0.0001,
|
| 43 |
+
"loss": 4.3603,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.06,
|
| 48 |
+
"grad_norm": 2.265625,
|
| 49 |
+
"learning_rate": 0.00012,
|
| 50 |
+
"loss": 4.1471,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07,
|
| 55 |
+
"grad_norm": 2.375,
|
| 56 |
+
"learning_rate": 0.00014,
|
| 57 |
+
"loss": 4.1348,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.08,
|
| 62 |
+
"grad_norm": 2.875,
|
| 63 |
+
"learning_rate": 0.00016,
|
| 64 |
+
"loss": 3.7162,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.09,
|
| 69 |
+
"grad_norm": 3.09375,
|
| 70 |
+
"learning_rate": 0.00018,
|
| 71 |
+
"loss": 3.4262,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.1,
|
| 76 |
+
"grad_norm": 3.203125,
|
| 77 |
+
"learning_rate": 0.0002,
|
| 78 |
+
"loss": 3.3557,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.11,
|
| 83 |
+
"grad_norm": 3.84375,
|
| 84 |
+
"learning_rate": 0.00019998715457999314,
|
| 85 |
+
"loss": 2.8991,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.12,
|
| 90 |
+
"grad_norm": 3.578125,
|
| 91 |
+
"learning_rate": 0.0001999486216200688,
|
| 92 |
+
"loss": 3.058,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.13,
|
| 97 |
+
"grad_norm": 4.1875,
|
| 98 |
+
"learning_rate": 0.0001998844110196681,
|
| 99 |
+
"loss": 2.9225,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.13,
|
| 104 |
+
"grad_norm": 2.84375,
|
| 105 |
+
"learning_rate": 0.00019979453927503364,
|
| 106 |
+
"loss": 2.7459,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.14,
|
| 111 |
+
"grad_norm": 7.875,
|
| 112 |
+
"learning_rate": 0.00019967902947497156,
|
| 113 |
+
"loss": 2.7172,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.15,
|
| 118 |
+
"grad_norm": 3.65625,
|
| 119 |
+
"learning_rate": 0.00019953791129491983,
|
| 120 |
+
"loss": 2.5032,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.16,
|
| 125 |
+
"grad_norm": 7.6875,
|
| 126 |
+
"learning_rate": 0.00019937122098932428,
|
| 127 |
+
"loss": 2.756,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.17,
|
| 132 |
+
"grad_norm": 6.875,
|
| 133 |
+
"learning_rate": 0.0001991790013823246,
|
| 134 |
+
"loss": 2.7377,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.18,
|
| 139 |
+
"grad_norm": 1.734375,
|
| 140 |
+
"learning_rate": 0.00019896130185675261,
|
| 141 |
+
"loss": 2.3483,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.19,
|
| 146 |
+
"grad_norm": 23.75,
|
| 147 |
+
"learning_rate": 0.00019871817834144504,
|
| 148 |
+
"loss": 2.7189,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.2,
|
| 153 |
+
"grad_norm": 6.40625,
|
| 154 |
+
"learning_rate": 0.00019844969329687527,
|
| 155 |
+
"loss": 2.2662,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.21,
|
| 160 |
+
"grad_norm": 1.8671875,
|
| 161 |
+
"learning_rate": 0.00019815591569910654,
|
| 162 |
+
"loss": 2.172,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.22,
|
| 167 |
+
"grad_norm": 1.6328125,
|
| 168 |
+
"learning_rate": 0.00019783692102207155,
|
| 169 |
+
"loss": 2.3391,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.23,
|
| 174 |
+
"grad_norm": 2.078125,
|
| 175 |
+
"learning_rate": 0.00019749279121818235,
|
| 176 |
+
"loss": 2.2976,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.24,
|
| 181 |
+
"grad_norm": 1.6484375,
|
| 182 |
+
"learning_rate": 0.0001971236146972764,
|
| 183 |
+
"loss": 2.3962,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.25,
|
| 188 |
+
"grad_norm": 4.78125,
|
| 189 |
+
"learning_rate": 0.00019672948630390294,
|
| 190 |
+
"loss": 2.4274,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.26,
|
| 195 |
+
"grad_norm": 3.375,
|
| 196 |
+
"learning_rate": 0.00019631050729295707,
|
| 197 |
+
"loss": 2.0537,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.27,
|
| 202 |
+
"grad_norm": 1.625,
|
| 203 |
+
"learning_rate": 0.00019586678530366606,
|
| 204 |
+
"loss": 2.204,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.28,
|
| 209 |
+
"grad_norm": 1.6484375,
|
| 210 |
+
"learning_rate": 0.00019539843433193639,
|
| 211 |
+
"loss": 2.2146,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.29,
|
| 216 |
+
"grad_norm": 1.375,
|
| 217 |
+
"learning_rate": 0.00019490557470106686,
|
| 218 |
+
"loss": 2.1501,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.3,
|
| 223 |
+
"grad_norm": 3.84375,
|
| 224 |
+
"learning_rate": 0.00019438833303083678,
|
| 225 |
+
"loss": 2.295,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.31,
|
| 230 |
+
"grad_norm": 1.59375,
|
| 231 |
+
"learning_rate": 0.00019384684220497605,
|
| 232 |
+
"loss": 2.215,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.32,
|
| 237 |
+
"grad_norm": 2.046875,
|
| 238 |
+
"learning_rate": 0.0001932812413370265,
|
| 239 |
+
"loss": 2.0909,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.33,
|
| 244 |
+
"grad_norm": 1.7734375,
|
| 245 |
+
"learning_rate": 0.0001926916757346022,
|
| 246 |
+
"loss": 2.0389,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.34,
|
| 251 |
+
"grad_norm": 1.2734375,
|
| 252 |
+
"learning_rate": 0.00019207829686205882,
|
| 253 |
+
"loss": 2.071,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.35,
|
| 258 |
+
"grad_norm": 2.0,
|
| 259 |
+
"learning_rate": 0.00019144126230158127,
|
| 260 |
+
"loss": 2.099,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.36,
|
| 265 |
+
"grad_norm": 1.5,
|
| 266 |
+
"learning_rate": 0.00019078073571269922,
|
| 267 |
+
"loss": 1.9823,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.37,
|
| 272 |
+
"grad_norm": 2.171875,
|
| 273 |
+
"learning_rate": 0.0001900968867902419,
|
| 274 |
+
"loss": 2.2366,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.38,
|
| 279 |
+
"grad_norm": 1.796875,
|
| 280 |
+
"learning_rate": 0.00018938989122074197,
|
| 281 |
+
"loss": 1.9585,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.39,
|
| 286 |
+
"grad_norm": 1.203125,
|
| 287 |
+
"learning_rate": 0.00018865993063730004,
|
| 288 |
+
"loss": 2.0241,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.4,
|
| 293 |
+
"grad_norm": 2.3125,
|
| 294 |
+
"learning_rate": 0.00018790719257292174,
|
| 295 |
+
"loss": 2.1073,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.4,
|
| 300 |
+
"grad_norm": 2.65625,
|
| 301 |
+
"learning_rate": 0.00018713187041233896,
|
| 302 |
+
"loss": 2.0247,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.41,
|
| 307 |
+
"grad_norm": 1.171875,
|
| 308 |
+
"learning_rate": 0.00018633416334232753,
|
| 309 |
+
"loss": 2.1386,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.42,
|
| 314 |
+
"grad_norm": 1.2890625,
|
| 315 |
+
"learning_rate": 0.00018551427630053463,
|
| 316 |
+
"loss": 1.9789,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.43,
|
| 321 |
+
"grad_norm": 1.2421875,
|
| 322 |
+
"learning_rate": 0.00018467241992282843,
|
| 323 |
+
"loss": 2.0121,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.44,
|
| 328 |
+
"grad_norm": 1.1484375,
|
| 329 |
+
"learning_rate": 0.00018380881048918405,
|
| 330 |
+
"loss": 1.8511,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.45,
|
| 335 |
+
"grad_norm": 1.5,
|
| 336 |
+
"learning_rate": 0.0001829236698681195,
|
| 337 |
+
"loss": 1.9241,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.46,
|
| 342 |
+
"grad_norm": 1.5078125,
|
| 343 |
+
"learning_rate": 0.0001820172254596956,
|
| 344 |
+
"loss": 2.1745,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.47,
|
| 349 |
+
"grad_norm": 1.3984375,
|
| 350 |
+
"learning_rate": 0.0001810897101370951,
|
| 351 |
+
"loss": 2.129,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.48,
|
| 356 |
+
"grad_norm": 1.21875,
|
| 357 |
+
"learning_rate": 0.00018014136218679567,
|
| 358 |
+
"loss": 2.0897,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.49,
|
| 363 |
+
"grad_norm": 1.6015625,
|
| 364 |
+
"learning_rate": 0.000179172425247352,
|
| 365 |
+
"loss": 1.9669,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.5,
|
| 370 |
+
"grad_norm": 1.1015625,
|
| 371 |
+
"learning_rate": 0.000178183148246803,
|
| 372 |
+
"loss": 2.1534,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.51,
|
| 377 |
+
"grad_norm": 1.453125,
|
| 378 |
+
"learning_rate": 0.00017717378533872017,
|
| 379 |
+
"loss": 2.0392,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.52,
|
| 384 |
+
"grad_norm": 1.25,
|
| 385 |
+
"learning_rate": 0.00017614459583691346,
|
| 386 |
+
"loss": 2.0854,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.53,
|
| 391 |
+
"grad_norm": 1.90625,
|
| 392 |
+
"learning_rate": 0.00017509584414881113,
|
| 393 |
+
"loss": 2.0876,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.54,
|
| 398 |
+
"grad_norm": 2.953125,
|
| 399 |
+
"learning_rate": 0.00017402779970753155,
|
| 400 |
+
"loss": 2.056,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.55,
|
| 405 |
+
"grad_norm": 1.0703125,
|
| 406 |
+
"learning_rate": 0.00017294073690266344,
|
| 407 |
+
"loss": 2.1355,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.56,
|
| 412 |
+
"grad_norm": 0.99609375,
|
| 413 |
+
"learning_rate": 0.00017183493500977278,
|
| 414 |
+
"loss": 2.1969,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.57,
|
| 419 |
+
"grad_norm": 1.2578125,
|
| 420 |
+
"learning_rate": 0.00017071067811865476,
|
| 421 |
+
"loss": 2.1154,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.58,
|
| 426 |
+
"grad_norm": 1.234375,
|
| 427 |
+
"learning_rate": 0.00016956825506034867,
|
| 428 |
+
"loss": 2.1209,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.59,
|
| 433 |
+
"grad_norm": 1.078125,
|
| 434 |
+
"learning_rate": 0.00016840795933293463,
|
| 435 |
+
"loss": 1.8669,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.6,
|
| 440 |
+
"grad_norm": 1.1484375,
|
| 441 |
+
"learning_rate": 0.0001672300890261317,
|
| 442 |
+
"loss": 2.1942,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.61,
|
| 447 |
+
"grad_norm": 1.1328125,
|
| 448 |
+
"learning_rate": 0.00016603494674471593,
|
| 449 |
+
"loss": 1.9799,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.62,
|
| 454 |
+
"grad_norm": 1.03125,
|
| 455 |
+
"learning_rate": 0.00016482283953077887,
|
| 456 |
+
"loss": 2.0549,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.63,
|
| 461 |
+
"grad_norm": 1.0,
|
| 462 |
+
"learning_rate": 0.00016359407878484552,
|
| 463 |
+
"loss": 2.0861,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.64,
|
| 468 |
+
"grad_norm": 0.93359375,
|
| 469 |
+
"learning_rate": 0.00016234898018587337,
|
| 470 |
+
"loss": 1.9708,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.65,
|
| 475 |
+
"grad_norm": 1.2265625,
|
| 476 |
+
"learning_rate": 0.00016108786361015143,
|
| 477 |
+
"loss": 1.9662,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.66,
|
| 482 |
+
"grad_norm": 1.328125,
|
| 483 |
+
"learning_rate": 0.00015981105304912162,
|
| 484 |
+
"loss": 2.1796,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.67,
|
| 489 |
+
"grad_norm": 1.375,
|
| 490 |
+
"learning_rate": 0.00015851887652614237,
|
| 491 |
+
"loss": 2.1684,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.67,
|
| 496 |
+
"grad_norm": 1.0546875,
|
| 497 |
+
"learning_rate": 0.00015721166601221698,
|
| 498 |
+
"loss": 2.0407,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.68,
|
| 503 |
+
"grad_norm": 0.95703125,
|
| 504 |
+
"learning_rate": 0.00015588975734070717,
|
| 505 |
+
"loss": 1.9925,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.69,
|
| 510 |
+
"grad_norm": 1.203125,
|
| 511 |
+
"learning_rate": 0.00015455349012105486,
|
| 512 |
+
"loss": 1.9737,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.7,
|
| 517 |
+
"grad_norm": 1.3515625,
|
| 518 |
+
"learning_rate": 0.00015320320765153367,
|
| 519 |
+
"loss": 1.9839,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.71,
|
| 524 |
+
"grad_norm": 0.98046875,
|
| 525 |
+
"learning_rate": 0.00015183925683105254,
|
| 526 |
+
"loss": 2.0463,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.72,
|
| 531 |
+
"grad_norm": 0.8203125,
|
| 532 |
+
"learning_rate": 0.0001504619880700346,
|
| 533 |
+
"loss": 1.9362,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.73,
|
| 538 |
+
"grad_norm": 1.046875,
|
| 539 |
+
"learning_rate": 0.0001490717552003938,
|
| 540 |
+
"loss": 1.9806,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.74,
|
| 545 |
+
"grad_norm": 1.7109375,
|
| 546 |
+
"learning_rate": 0.00014766891538463254,
|
| 547 |
+
"loss": 2.0698,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.75,
|
| 552 |
+
"grad_norm": 1.25,
|
| 553 |
+
"learning_rate": 0.00014625382902408356,
|
| 554 |
+
"loss": 2.1027,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.76,
|
| 559 |
+
"grad_norm": 1.3203125,
|
| 560 |
+
"learning_rate": 0.0001448268596663197,
|
| 561 |
+
"loss": 2.1428,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.77,
|
| 566 |
+
"grad_norm": 1.0625,
|
| 567 |
+
"learning_rate": 0.00014338837391175582,
|
| 568 |
+
"loss": 1.9171,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.78,
|
| 573 |
+
"grad_norm": 1.2421875,
|
| 574 |
+
"learning_rate": 0.0001419387413194657,
|
| 575 |
+
"loss": 2.0363,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.79,
|
| 580 |
+
"grad_norm": 0.9140625,
|
| 581 |
+
"learning_rate": 0.00014047833431223938,
|
| 582 |
+
"loss": 2.1144,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.8,
|
| 587 |
+
"grad_norm": 1.046875,
|
| 588 |
+
"learning_rate": 0.00013900752808090468,
|
| 589 |
+
"loss": 2.0149,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.81,
|
| 594 |
+
"grad_norm": 1.15625,
|
| 595 |
+
"learning_rate": 0.00013752670048793744,
|
| 596 |
+
"loss": 1.9503,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.82,
|
| 601 |
+
"grad_norm": 1.0859375,
|
| 602 |
+
"learning_rate": 0.00013603623197038536,
|
| 603 |
+
"loss": 1.9914,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.83,
|
| 608 |
+
"grad_norm": 0.88671875,
|
| 609 |
+
"learning_rate": 0.00013453650544213076,
|
| 610 |
+
"loss": 1.9256,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.84,
|
| 615 |
+
"grad_norm": 1.15625,
|
| 616 |
+
"learning_rate": 0.00013302790619551674,
|
| 617 |
+
"loss": 1.9014,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.85,
|
| 622 |
+
"grad_norm": 1.6953125,
|
| 623 |
+
"learning_rate": 0.0001315108218023621,
|
| 624 |
+
"loss": 1.8,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.86,
|
| 629 |
+
"grad_norm": 0.875,
|
| 630 |
+
"learning_rate": 0.00012998564201439116,
|
| 631 |
+
"loss": 1.9711,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.87,
|
| 636 |
+
"grad_norm": 0.921875,
|
| 637 |
+
"learning_rate": 0.00012845275866310324,
|
| 638 |
+
"loss": 1.9172,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.88,
|
| 643 |
+
"grad_norm": 1.0078125,
|
| 644 |
+
"learning_rate": 0.00012691256555910768,
|
| 645 |
+
"loss": 1.8175,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.89,
|
| 650 |
+
"grad_norm": 0.94140625,
|
| 651 |
+
"learning_rate": 0.00012536545839095074,
|
| 652 |
+
"loss": 1.8827,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.9,
|
| 657 |
+
"grad_norm": 0.83203125,
|
| 658 |
+
"learning_rate": 0.00012381183462345982,
|
| 659 |
+
"loss": 1.8027,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.91,
|
| 664 |
+
"grad_norm": 0.9609375,
|
| 665 |
+
"learning_rate": 0.00012225209339563145,
|
| 666 |
+
"loss": 2.0469,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.92,
|
| 671 |
+
"grad_norm": 0.91015625,
|
| 672 |
+
"learning_rate": 0.00012068663541808909,
|
| 673 |
+
"loss": 1.9651,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.93,
|
| 678 |
+
"grad_norm": 0.83203125,
|
| 679 |
+
"learning_rate": 0.00011911586287013725,
|
| 680 |
+
"loss": 1.8538,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.93,
|
| 685 |
+
"grad_norm": 0.91796875,
|
| 686 |
+
"learning_rate": 0.00011754017929643817,
|
| 687 |
+
"loss": 1.8906,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.94,
|
| 692 |
+
"grad_norm": 1.0625,
|
| 693 |
+
"learning_rate": 0.00011595998950333793,
|
| 694 |
+
"loss": 1.9807,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.95,
|
| 699 |
+
"grad_norm": 1.0078125,
|
| 700 |
+
"learning_rate": 0.00011437569945486819,
|
| 701 |
+
"loss": 1.8098,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.96,
|
| 706 |
+
"grad_norm": 1.5390625,
|
| 707 |
+
"learning_rate": 0.00011278771616845061,
|
| 708 |
+
"loss": 1.9236,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.97,
|
| 713 |
+
"grad_norm": 1.015625,
|
| 714 |
+
"learning_rate": 0.00011119644761033078,
|
| 715 |
+
"loss": 1.9111,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.98,
|
| 720 |
+
"grad_norm": 0.890625,
|
| 721 |
+
"learning_rate": 0.00010960230259076818,
|
| 722 |
+
"loss": 2.0487,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.99,
|
| 727 |
+
"grad_norm": 1.15625,
|
| 728 |
+
"learning_rate": 0.00010800569065900933,
|
| 729 |
+
"loss": 2.025,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.0,
|
| 734 |
+
"grad_norm": 1.0859375,
|
| 735 |
+
"learning_rate": 0.0001064070219980713,
|
| 736 |
+
"loss": 1.833,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.01,
|
| 741 |
+
"grad_norm": 1.4609375,
|
| 742 |
+
"learning_rate": 0.00010480670731936208,
|
| 743 |
+
"loss": 1.886,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.02,
|
| 748 |
+
"grad_norm": 1.1015625,
|
| 749 |
+
"learning_rate": 0.00010320515775716555,
|
| 750 |
+
"loss": 1.8777,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.01,
|
| 755 |
+
"grad_norm": 1.0546875,
|
| 756 |
+
"learning_rate": 0.0001016027847630174,
|
| 757 |
+
"loss": 1.6924,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.02,
|
| 762 |
+
"grad_norm": 0.85546875,
|
| 763 |
+
"learning_rate": 0.0001,
|
| 764 |
+
"loss": 1.673,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.03,
|
| 769 |
+
"grad_norm": 1.234375,
|
| 770 |
+
"learning_rate": 9.839721523698264e-05,
|
| 771 |
+
"loss": 1.9082,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.04,
|
| 776 |
+
"grad_norm": 0.92578125,
|
| 777 |
+
"learning_rate": 9.679484224283449e-05,
|
| 778 |
+
"loss": 1.8195,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.05,
|
| 783 |
+
"grad_norm": 1.0390625,
|
| 784 |
+
"learning_rate": 9.519329268063795e-05,
|
| 785 |
+
"loss": 1.6165,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.06,
|
| 790 |
+
"grad_norm": 0.85546875,
|
| 791 |
+
"learning_rate": 9.359297800192872e-05,
|
| 792 |
+
"loss": 1.7139,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.07,
|
| 797 |
+
"grad_norm": 0.83203125,
|
| 798 |
+
"learning_rate": 9.199430934099068e-05,
|
| 799 |
+
"loss": 1.6608,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.08,
|
| 804 |
+
"grad_norm": 0.79296875,
|
| 805 |
+
"learning_rate": 9.039769740923183e-05,
|
| 806 |
+
"loss": 1.8531,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.09,
|
| 811 |
+
"grad_norm": 0.83203125,
|
| 812 |
+
"learning_rate": 8.880355238966923e-05,
|
| 813 |
+
"loss": 1.7978,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.1,
|
| 818 |
+
"grad_norm": 1.015625,
|
| 819 |
+
"learning_rate": 8.721228383154939e-05,
|
| 820 |
+
"loss": 1.5377,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.11,
|
| 825 |
+
"grad_norm": 1.078125,
|
| 826 |
+
"learning_rate": 8.562430054513184e-05,
|
| 827 |
+
"loss": 1.7113,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.12,
|
| 832 |
+
"grad_norm": 2.53125,
|
| 833 |
+
"learning_rate": 8.404001049666211e-05,
|
| 834 |
+
"loss": 1.681,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.13,
|
| 839 |
+
"grad_norm": 0.96875,
|
| 840 |
+
"learning_rate": 8.245982070356185e-05,
|
| 841 |
+
"loss": 1.5415,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.13,
|
| 846 |
+
"grad_norm": 0.94140625,
|
| 847 |
+
"learning_rate": 8.08841371298628e-05,
|
| 848 |
+
"loss": 1.6291,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.14,
|
| 853 |
+
"grad_norm": 0.9921875,
|
| 854 |
+
"learning_rate": 7.931336458191092e-05,
|
| 855 |
+
"loss": 1.6358,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.15,
|
| 860 |
+
"grad_norm": 1.1015625,
|
| 861 |
+
"learning_rate": 7.774790660436858e-05,
|
| 862 |
+
"loss": 1.7496,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.16,
|
| 867 |
+
"grad_norm": 1.0859375,
|
| 868 |
+
"learning_rate": 7.618816537654018e-05,
|
| 869 |
+
"loss": 1.8027,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.17,
|
| 874 |
+
"grad_norm": 0.9140625,
|
| 875 |
+
"learning_rate": 7.463454160904928e-05,
|
| 876 |
+
"loss": 1.7852,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.18,
|
| 881 |
+
"grad_norm": 0.91015625,
|
| 882 |
+
"learning_rate": 7.308743444089232e-05,
|
| 883 |
+
"loss": 1.6982,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.19,
|
| 888 |
+
"grad_norm": 0.98046875,
|
| 889 |
+
"learning_rate": 7.154724133689677e-05,
|
| 890 |
+
"loss": 1.8611,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.2,
|
| 895 |
+
"grad_norm": 0.85546875,
|
| 896 |
+
"learning_rate": 7.001435798560883e-05,
|
| 897 |
+
"loss": 1.5955,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.21,
|
| 902 |
+
"grad_norm": 0.84765625,
|
| 903 |
+
"learning_rate": 6.848917819763793e-05,
|
| 904 |
+
"loss": 1.7338,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.22,
|
| 909 |
+
"grad_norm": 1.0546875,
|
| 910 |
+
"learning_rate": 6.697209380448333e-05,
|
| 911 |
+
"loss": 1.6586,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.23,
|
| 916 |
+
"grad_norm": 0.8671875,
|
| 917 |
+
"learning_rate": 6.546349455786926e-05,
|
| 918 |
+
"loss": 1.6435,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.24,
|
| 923 |
+
"grad_norm": 0.953125,
|
| 924 |
+
"learning_rate": 6.396376802961468e-05,
|
| 925 |
+
"loss": 1.7111,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.25,
|
| 930 |
+
"grad_norm": 1.1015625,
|
| 931 |
+
"learning_rate": 6.24732995120626e-05,
|
| 932 |
+
"loss": 1.5686,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.26,
|
| 937 |
+
"grad_norm": 0.9453125,
|
| 938 |
+
"learning_rate": 6.0992471919095315e-05,
|
| 939 |
+
"loss": 1.7383,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.27,
|
| 944 |
+
"grad_norm": 0.9375,
|
| 945 |
+
"learning_rate": 5.952166568776062e-05,
|
| 946 |
+
"loss": 1.7647,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.28,
|
| 951 |
+
"grad_norm": 0.99609375,
|
| 952 |
+
"learning_rate": 5.806125868053433e-05,
|
| 953 |
+
"loss": 1.8344,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.29,
|
| 958 |
+
"grad_norm": 0.984375,
|
| 959 |
+
"learning_rate": 5.6611626088244194e-05,
|
| 960 |
+
"loss": 1.8154,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.3,
|
| 965 |
+
"grad_norm": 1.1953125,
|
| 966 |
+
"learning_rate": 5.5173140333680306e-05,
|
| 967 |
+
"loss": 1.5994,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.31,
|
| 972 |
+
"grad_norm": 1.1484375,
|
| 973 |
+
"learning_rate": 5.37461709759165e-05,
|
| 974 |
+
"loss": 1.6497,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.32,
|
| 979 |
+
"grad_norm": 0.9296875,
|
| 980 |
+
"learning_rate": 5.2331084615367485e-05,
|
| 981 |
+
"loss": 1.8425,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.33,
|
| 986 |
+
"grad_norm": 1.078125,
|
| 987 |
+
"learning_rate": 5.092824479960625e-05,
|
| 988 |
+
"loss": 1.8534,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.34,
|
| 993 |
+
"grad_norm": 1.03125,
|
| 994 |
+
"learning_rate": 4.953801192996543e-05,
|
| 995 |
+
"loss": 1.6864,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.35,
|
| 1000 |
+
"grad_norm": 0.9765625,
|
| 1001 |
+
"learning_rate": 4.8160743168947496e-05,
|
| 1002 |
+
"loss": 1.6976,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 1.36,
|
| 1007 |
+
"grad_norm": 1.0625,
|
| 1008 |
+
"learning_rate": 4.6796792348466356e-05,
|
| 1009 |
+
"loss": 1.7416,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.37,
|
| 1014 |
+
"grad_norm": 0.91015625,
|
| 1015 |
+
"learning_rate": 4.544650987894514e-05,
|
| 1016 |
+
"loss": 1.485,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.38,
|
| 1021 |
+
"grad_norm": 0.93359375,
|
| 1022 |
+
"learning_rate": 4.4110242659292836e-05,
|
| 1023 |
+
"loss": 1.6244,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.39,
|
| 1028 |
+
"grad_norm": 1.0,
|
| 1029 |
+
"learning_rate": 4.278833398778306e-05,
|
| 1030 |
+
"loss": 1.6941,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.4,
|
| 1035 |
+
"grad_norm": 1.0390625,
|
| 1036 |
+
"learning_rate": 4.148112347385762e-05,
|
| 1037 |
+
"loss": 1.7538,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 1.4,
|
| 1042 |
+
"grad_norm": 0.9609375,
|
| 1043 |
+
"learning_rate": 4.0188946950878404e-05,
|
| 1044 |
+
"loss": 1.7124,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 1.41,
|
| 1049 |
+
"grad_norm": 1.046875,
|
| 1050 |
+
"learning_rate": 3.8912136389848576e-05,
|
| 1051 |
+
"loss": 1.668,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.42,
|
| 1056 |
+
"grad_norm": 1.1015625,
|
| 1057 |
+
"learning_rate": 3.7651019814126654e-05,
|
| 1058 |
+
"loss": 1.6419,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.43,
|
| 1063 |
+
"grad_norm": 1.171875,
|
| 1064 |
+
"learning_rate": 3.6405921215154494e-05,
|
| 1065 |
+
"loss": 1.6867,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.44,
|
| 1070 |
+
"grad_norm": 0.99609375,
|
| 1071 |
+
"learning_rate": 3.517716046922118e-05,
|
| 1072 |
+
"loss": 1.8303,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 1.45,
|
| 1077 |
+
"grad_norm": 0.9921875,
|
| 1078 |
+
"learning_rate": 3.3965053255284084e-05,
|
| 1079 |
+
"loss": 1.6061,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 1.46,
|
| 1084 |
+
"grad_norm": 1.0078125,
|
| 1085 |
+
"learning_rate": 3.276991097386831e-05,
|
| 1086 |
+
"loss": 1.5528,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.47,
|
| 1091 |
+
"grad_norm": 1.2109375,
|
| 1092 |
+
"learning_rate": 3.159204066706539e-05,
|
| 1093 |
+
"loss": 1.6806,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 1.48,
|
| 1098 |
+
"grad_norm": 1.0859375,
|
| 1099 |
+
"learning_rate": 3.0431744939651364e-05,
|
| 1100 |
+
"loss": 1.7271,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.49,
|
| 1105 |
+
"grad_norm": 1.0625,
|
| 1106 |
+
"learning_rate": 2.9289321881345254e-05,
|
| 1107 |
+
"loss": 1.6939,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.5,
|
| 1112 |
+
"grad_norm": 1.1875,
|
| 1113 |
+
"learning_rate": 2.8165064990227252e-05,
|
| 1114 |
+
"loss": 1.9148,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.51,
|
| 1119 |
+
"grad_norm": 1.0078125,
|
| 1120 |
+
"learning_rate": 2.7059263097336597e-05,
|
| 1121 |
+
"loss": 1.5374,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.52,
|
| 1126 |
+
"grad_norm": 1.2265625,
|
| 1127 |
+
"learning_rate": 2.5972200292468464e-05,
|
| 1128 |
+
"loss": 1.6695,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.53,
|
| 1133 |
+
"grad_norm": 0.96875,
|
| 1134 |
+
"learning_rate": 2.4904155851188872e-05,
|
| 1135 |
+
"loss": 1.6876,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.54,
|
| 1140 |
+
"grad_norm": 1.046875,
|
| 1141 |
+
"learning_rate": 2.3855404163086558e-05,
|
| 1142 |
+
"loss": 1.731,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.55,
|
| 1147 |
+
"grad_norm": 1.0625,
|
| 1148 |
+
"learning_rate": 2.282621466127982e-05,
|
| 1149 |
+
"loss": 1.5561,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.56,
|
| 1154 |
+
"grad_norm": 1.171875,
|
| 1155 |
+
"learning_rate": 2.181685175319702e-05,
|
| 1156 |
+
"loss": 1.7871,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.57,
|
| 1161 |
+
"grad_norm": 1.25,
|
| 1162 |
+
"learning_rate": 2.0827574752648038e-05,
|
| 1163 |
+
"loss": 1.7695,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.58,
|
| 1168 |
+
"grad_norm": 1.03125,
|
| 1169 |
+
"learning_rate": 1.985863781320435e-05,
|
| 1170 |
+
"loss": 1.6149,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.59,
|
| 1175 |
+
"grad_norm": 0.9609375,
|
| 1176 |
+
"learning_rate": 1.891028986290492e-05,
|
| 1177 |
+
"loss": 1.5127,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.6,
|
| 1182 |
+
"grad_norm": 1.0546875,
|
| 1183 |
+
"learning_rate": 1.7982774540304403e-05,
|
| 1184 |
+
"loss": 1.757,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.61,
|
| 1189 |
+
"grad_norm": 1.0390625,
|
| 1190 |
+
"learning_rate": 1.7076330131880526e-05,
|
| 1191 |
+
"loss": 1.5873,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.62,
|
| 1196 |
+
"grad_norm": 1.140625,
|
| 1197 |
+
"learning_rate": 1.619118951081594e-05,
|
| 1198 |
+
"loss": 1.6649,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.63,
|
| 1203 |
+
"grad_norm": 1.1015625,
|
| 1204 |
+
"learning_rate": 1.5327580077171587e-05,
|
| 1205 |
+
"loss": 1.7183,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.64,
|
| 1210 |
+
"grad_norm": 1.0,
|
| 1211 |
+
"learning_rate": 1.4485723699465392e-05,
|
| 1212 |
+
"loss": 1.7235,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.65,
|
| 1217 |
+
"grad_norm": 1.1328125,
|
| 1218 |
+
"learning_rate": 1.3665836657672493e-05,
|
| 1219 |
+
"loss": 1.758,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.66,
|
| 1224 |
+
"grad_norm": 1.140625,
|
| 1225 |
+
"learning_rate": 1.286812958766106e-05,
|
| 1226 |
+
"loss": 1.8054,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.67,
|
| 1231 |
+
"grad_norm": 0.95703125,
|
| 1232 |
+
"learning_rate": 1.2092807427078279e-05,
|
| 1233 |
+
"loss": 1.7808,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.67,
|
| 1238 |
+
"grad_norm": 1.0390625,
|
| 1239 |
+
"learning_rate": 1.134006936269999e-05,
|
| 1240 |
+
"loss": 1.7116,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.68,
|
| 1245 |
+
"grad_norm": 0.98828125,
|
| 1246 |
+
"learning_rate": 1.0610108779258044e-05,
|
| 1247 |
+
"loss": 1.6665,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.69,
|
| 1252 |
+
"grad_norm": 0.9921875,
|
| 1253 |
+
"learning_rate": 9.903113209758096e-06,
|
| 1254 |
+
"loss": 1.6648,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.7,
|
| 1259 |
+
"grad_norm": 1.1171875,
|
| 1260 |
+
"learning_rate": 9.219264287300799e-06,
|
| 1261 |
+
"loss": 1.6068,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.71,
|
| 1266 |
+
"grad_norm": 1.0625,
|
| 1267 |
+
"learning_rate": 8.558737698418761e-06,
|
| 1268 |
+
"loss": 1.6528,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.72,
|
| 1273 |
+
"grad_norm": 1.0234375,
|
| 1274 |
+
"learning_rate": 7.921703137941173e-06,
|
| 1275 |
+
"loss": 1.6026,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.73,
|
| 1280 |
+
"grad_norm": 0.984375,
|
| 1281 |
+
"learning_rate": 7.308324265397836e-06,
|
| 1282 |
+
"loss": 1.7228,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.74,
|
| 1287 |
+
"grad_norm": 1.234375,
|
| 1288 |
+
"learning_rate": 6.718758662973523e-06,
|
| 1289 |
+
"loss": 1.7112,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.75,
|
| 1294 |
+
"grad_norm": 0.96875,
|
| 1295 |
+
"learning_rate": 6.153157795023956e-06,
|
| 1296 |
+
"loss": 1.6732,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.76,
|
| 1301 |
+
"grad_norm": 1.0390625,
|
| 1302 |
+
"learning_rate": 5.611666969163243e-06,
|
| 1303 |
+
"loss": 1.6743,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 1.77,
|
| 1308 |
+
"grad_norm": 1.1015625,
|
| 1309 |
+
"learning_rate": 5.094425298933136e-06,
|
| 1310 |
+
"loss": 1.5847,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.78,
|
| 1315 |
+
"grad_norm": 1.21875,
|
| 1316 |
+
"learning_rate": 4.601565668063623e-06,
|
| 1317 |
+
"loss": 1.6576,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 1.79,
|
| 1322 |
+
"grad_norm": 0.984375,
|
| 1323 |
+
"learning_rate": 4.133214696333942e-06,
|
| 1324 |
+
"loss": 1.6032,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.8,
|
| 1329 |
+
"grad_norm": 1.0390625,
|
| 1330 |
+
"learning_rate": 3.689492707042974e-06,
|
| 1331 |
+
"loss": 1.634,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 1.81,
|
| 1336 |
+
"grad_norm": 1.0234375,
|
| 1337 |
+
"learning_rate": 3.270513696097055e-06,
|
| 1338 |
+
"loss": 1.6969,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 1.82,
|
| 1343 |
+
"grad_norm": 1.21875,
|
| 1344 |
+
"learning_rate": 2.876385302723628e-06,
|
| 1345 |
+
"loss": 1.6449,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 1.83,
|
| 1350 |
+
"grad_norm": 0.96484375,
|
| 1351 |
+
"learning_rate": 2.5072087818176382e-06,
|
| 1352 |
+
"loss": 1.4763,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 1.84,
|
| 1357 |
+
"grad_norm": 0.96875,
|
| 1358 |
+
"learning_rate": 2.1630789779284675e-06,
|
| 1359 |
+
"loss": 1.719,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 1.85,
|
| 1364 |
+
"grad_norm": 1.015625,
|
| 1365 |
+
"learning_rate": 1.8440843008934561e-06,
|
| 1366 |
+
"loss": 1.8517,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 1.86,
|
| 1371 |
+
"grad_norm": 0.9296875,
|
| 1372 |
+
"learning_rate": 1.5503067031247598e-06,
|
| 1373 |
+
"loss": 1.5597,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 1.87,
|
| 1378 |
+
"grad_norm": 1.140625,
|
| 1379 |
+
"learning_rate": 1.2818216585549825e-06,
|
| 1380 |
+
"loss": 1.7673,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 1.88,
|
| 1385 |
+
"grad_norm": 1.125,
|
| 1386 |
+
"learning_rate": 1.0386981432474074e-06,
|
| 1387 |
+
"loss": 1.6707,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 1.89,
|
| 1392 |
+
"grad_norm": 0.9453125,
|
| 1393 |
+
"learning_rate": 8.209986176753948e-07,
|
| 1394 |
+
"loss": 1.6395,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.9,
|
| 1399 |
+
"grad_norm": 1.1875,
|
| 1400 |
+
"learning_rate": 6.287790106757396e-07,
|
| 1401 |
+
"loss": 1.5912,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.91,
|
| 1406 |
+
"grad_norm": 1.0234375,
|
| 1407 |
+
"learning_rate": 4.62088705080177e-07,
|
| 1408 |
+
"loss": 1.5877,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 1.92,
|
| 1413 |
+
"grad_norm": 0.94140625,
|
| 1414 |
+
"learning_rate": 3.2097052502843007e-07,
|
| 1415 |
+
"loss": 1.5594,
|
| 1416 |
+
"step": 201
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 1.93,
|
| 1420 |
+
"grad_norm": 1.3125,
|
| 1421 |
+
"learning_rate": 2.054607249663665e-07,
|
| 1422 |
+
"loss": 1.6429,
|
| 1423 |
+
"step": 202
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 1.93,
|
| 1427 |
+
"grad_norm": 1.078125,
|
| 1428 |
+
"learning_rate": 1.1558898033191546e-07,
|
| 1429 |
+
"loss": 1.6142,
|
| 1430 |
+
"step": 203
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 1.94,
|
| 1434 |
+
"grad_norm": 1.0546875,
|
| 1435 |
+
"learning_rate": 5.137837993121064e-08,
|
| 1436 |
+
"loss": 1.6624,
|
| 1437 |
+
"step": 204
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 1.95,
|
| 1441 |
+
"grad_norm": 0.9765625,
|
| 1442 |
+
"learning_rate": 1.2845420006879494e-08,
|
| 1443 |
+
"loss": 1.5157,
|
| 1444 |
+
"step": 205
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 1.96,
|
| 1448 |
+
"grad_norm": 1.015625,
|
| 1449 |
+
"learning_rate": 0.0,
|
| 1450 |
+
"loss": 1.6079,
|
| 1451 |
+
"step": 206
|
| 1452 |
+
}
|
| 1453 |
+
],
|
| 1454 |
+
"logging_steps": 1,
|
| 1455 |
+
"max_steps": 206,
|
| 1456 |
+
"num_input_tokens_seen": 0,
|
| 1457 |
+
"num_train_epochs": 2,
|
| 1458 |
+
"save_steps": 103,
|
| 1459 |
+
"total_flos": 5.827761978432553e+17,
|
| 1460 |
+
"train_batch_size": 1,
|
| 1461 |
+
"trial_name": null,
|
| 1462 |
+
"trial_params": null
|
| 1463 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05285fd2f0f92792a9921a780968c1959edd9be78eac25715595f43216594e50
|
| 3 |
+
size 5624
|