Training in progress, epoch 24, checkpoint
Browse files- checkpoint-86376/README.md +202 -0
- checkpoint-86376/adapter_config.json +32 -0
- checkpoint-86376/adapter_model.safetensors +3 -0
- checkpoint-86376/optimizer.pt +3 -0
- checkpoint-86376/rng_state_0.pth +3 -0
- checkpoint-86376/rng_state_1.pth +3 -0
- checkpoint-86376/rng_state_2.pth +3 -0
- checkpoint-86376/rng_state_3.pth +3 -0
- checkpoint-86376/rng_state_4.pth +3 -0
- checkpoint-86376/rng_state_5.pth +3 -0
- checkpoint-86376/rng_state_6.pth +3 -0
- checkpoint-86376/rng_state_7.pth +3 -0
- checkpoint-86376/scheduler.pt +3 -0
- checkpoint-86376/trainer_state.json +1709 -0
- checkpoint-86376/training_args.bin +3 -0
checkpoint-86376/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/deepseek-coder-1.3b-base
|
| 3 |
+
library_name: peft
|
| 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 0.14.0
|
checkpoint-86376/adapter_config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-coder-1.3b-base",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"eva_config": null,
|
| 7 |
+
"exclude_modules": null,
|
| 8 |
+
"fan_in_fan_out": false,
|
| 9 |
+
"inference_mode": true,
|
| 10 |
+
"init_lora_weights": true,
|
| 11 |
+
"layer_replication": null,
|
| 12 |
+
"layers_pattern": null,
|
| 13 |
+
"layers_to_transform": null,
|
| 14 |
+
"loftq_config": {},
|
| 15 |
+
"lora_alpha": 32,
|
| 16 |
+
"lora_bias": false,
|
| 17 |
+
"lora_dropout": 0.05,
|
| 18 |
+
"megatron_config": null,
|
| 19 |
+
"megatron_core": "megatron.core",
|
| 20 |
+
"modules_to_save": null,
|
| 21 |
+
"peft_type": "LORA",
|
| 22 |
+
"r": 8,
|
| 23 |
+
"rank_pattern": {},
|
| 24 |
+
"revision": null,
|
| 25 |
+
"target_modules": [
|
| 26 |
+
"q_proj",
|
| 27 |
+
"v_proj"
|
| 28 |
+
],
|
| 29 |
+
"task_type": "CAUSAL_LM",
|
| 30 |
+
"use_dora": false,
|
| 31 |
+
"use_rslora": false
|
| 32 |
+
}
|
checkpoint-86376/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ec13b4b8f0bf41960a0443b6e68466c155383cce526caf79082fdbfd53d04e1
|
| 3 |
+
size 268636736
|
checkpoint-86376/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48a3265fee11f8bacf52c459bd4d35206be5d33ef8d11c2f0d6296ccd8e5aad7
|
| 3 |
+
size 12663802
|
checkpoint-86376/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5d23e0d917859eeec2639187de4b3c142d0f594a03ce41dcd6b2ff0055e584b
|
| 3 |
+
size 15984
|
checkpoint-86376/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b0aa0ca6da05ce956cb3eab55a3dce71df78d5f340d4adf15f7179dde219028
|
| 3 |
+
size 15984
|
checkpoint-86376/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:501db2d504307ce1b8f681b12f5ac065e6e1185fde07890f53fd644944ac9579
|
| 3 |
+
size 15984
|
checkpoint-86376/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87b038cd816d885864d9d05ba7525bf6b96721bf0830d4a1aa0a2eb503528292
|
| 3 |
+
size 15984
|
checkpoint-86376/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1aaeab9ee8c051c767259572fdd634b159eaf1717163f12b596458184adb6063
|
| 3 |
+
size 15984
|
checkpoint-86376/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91a083e9cac699e66e7ce3d62f4cf0263e0f308fbe48a47536edbf57106301e7
|
| 3 |
+
size 15984
|
checkpoint-86376/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:602620d493109520286df7f2fa15397c05b72141a0b7e68a10b66e072ba2d123
|
| 3 |
+
size 15984
|
checkpoint-86376/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:924732f575c818e793076be3bf88d7f2759f3af9cb4c316c0ac257d6121422f3
|
| 3 |
+
size 15984
|
checkpoint-86376/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf3dff378a2e804fcf1f2e381b8befcf5607c4aedc7b6e5450a106218580b718
|
| 3 |
+
size 1064
|
checkpoint-86376/trainer_state.json
ADDED
|
@@ -0,0 +1,1709 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 24.0,
|
| 5 |
+
"eval_steps": 1440,
|
| 6 |
+
"global_step": 86376,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.13892747985551543,
|
| 13 |
+
"grad_norm": 0.9003118872642517,
|
| 14 |
+
"learning_rate": 0.000795387607668797,
|
| 15 |
+
"loss": 0.4296,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.27785495971103086,
|
| 20 |
+
"grad_norm": 2.5679404735565186,
|
| 21 |
+
"learning_rate": 0.0007907566916736131,
|
| 22 |
+
"loss": 0.3243,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.4001111419838844,
|
| 27 |
+
"eval_loss": 0.2947143018245697,
|
| 28 |
+
"eval_runtime": 5.7176,
|
| 29 |
+
"eval_samples_per_second": 87.449,
|
| 30 |
+
"eval_steps_per_second": 5.597,
|
| 31 |
+
"step": 1440
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.41678243956654626,
|
| 35 |
+
"grad_norm": 0.6454382538795471,
|
| 36 |
+
"learning_rate": 0.0007861257756784293,
|
| 37 |
+
"loss": 0.2985,
|
| 38 |
+
"step": 1500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.5557099194220617,
|
| 42 |
+
"grad_norm": 0.6851354837417603,
|
| 43 |
+
"learning_rate": 0.0007815041215152357,
|
| 44 |
+
"loss": 0.2829,
|
| 45 |
+
"step": 2000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.6946373992775771,
|
| 49 |
+
"grad_norm": 0.7469644546508789,
|
| 50 |
+
"learning_rate": 0.0007768732055200519,
|
| 51 |
+
"loss": 0.2737,
|
| 52 |
+
"step": 2500
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.8002222839677688,
|
| 56 |
+
"eval_loss": 0.2755357623100281,
|
| 57 |
+
"eval_runtime": 5.6548,
|
| 58 |
+
"eval_samples_per_second": 88.421,
|
| 59 |
+
"eval_steps_per_second": 5.659,
|
| 60 |
+
"step": 2880
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.8335648791330925,
|
| 64 |
+
"grad_norm": 0.6683129072189331,
|
| 65 |
+
"learning_rate": 0.0007722422895248681,
|
| 66 |
+
"loss": 0.2653,
|
| 67 |
+
"step": 3000
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.972492358988608,
|
| 71 |
+
"grad_norm": 0.7536308169364929,
|
| 72 |
+
"learning_rate": 0.0007676113735296843,
|
| 73 |
+
"loss": 0.2628,
|
| 74 |
+
"step": 3500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.1114198388441234,
|
| 78 |
+
"grad_norm": 0.6173604726791382,
|
| 79 |
+
"learning_rate": 0.0007629804575345004,
|
| 80 |
+
"loss": 0.2463,
|
| 81 |
+
"step": 4000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.2003334259516532,
|
| 85 |
+
"eval_loss": 0.2620045840740204,
|
| 86 |
+
"eval_runtime": 5.6897,
|
| 87 |
+
"eval_samples_per_second": 87.877,
|
| 88 |
+
"eval_steps_per_second": 5.624,
|
| 89 |
+
"step": 4320
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.2503473186996388,
|
| 93 |
+
"grad_norm": 0.9441823363304138,
|
| 94 |
+
"learning_rate": 0.0007583495415393165,
|
| 95 |
+
"loss": 0.2476,
|
| 96 |
+
"step": 4500
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.3892747985551543,
|
| 100 |
+
"grad_norm": 1.179303526878357,
|
| 101 |
+
"learning_rate": 0.0007537186255441327,
|
| 102 |
+
"loss": 0.2448,
|
| 103 |
+
"step": 5000
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.5282022784106695,
|
| 107 |
+
"grad_norm": 0.9045144319534302,
|
| 108 |
+
"learning_rate": 0.0007490877095489488,
|
| 109 |
+
"loss": 0.2389,
|
| 110 |
+
"step": 5500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.6004445679355377,
|
| 114 |
+
"eval_loss": 0.25695353746414185,
|
| 115 |
+
"eval_runtime": 5.6542,
|
| 116 |
+
"eval_samples_per_second": 88.43,
|
| 117 |
+
"eval_steps_per_second": 5.66,
|
| 118 |
+
"step": 5760
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.667129758266185,
|
| 122 |
+
"grad_norm": 0.6623045206069946,
|
| 123 |
+
"learning_rate": 0.0007444660553857554,
|
| 124 |
+
"loss": 0.2409,
|
| 125 |
+
"step": 6000
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.8060572381217006,
|
| 129 |
+
"grad_norm": 0.6902622580528259,
|
| 130 |
+
"learning_rate": 0.0007398351393905715,
|
| 131 |
+
"loss": 0.234,
|
| 132 |
+
"step": 6500
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.9449847179772157,
|
| 136 |
+
"grad_norm": 0.7465945482254028,
|
| 137 |
+
"learning_rate": 0.0007352042233953876,
|
| 138 |
+
"loss": 0.2342,
|
| 139 |
+
"step": 7000
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 2.000555709919422,
|
| 143 |
+
"eval_loss": 0.25181135535240173,
|
| 144 |
+
"eval_runtime": 5.6993,
|
| 145 |
+
"eval_samples_per_second": 87.731,
|
| 146 |
+
"eval_steps_per_second": 5.615,
|
| 147 |
+
"step": 7200
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 2.0839121978327313,
|
| 151 |
+
"grad_norm": 0.7666770219802856,
|
| 152 |
+
"learning_rate": 0.0007305825692321942,
|
| 153 |
+
"loss": 0.226,
|
| 154 |
+
"step": 7500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 2.222839677688247,
|
| 158 |
+
"grad_norm": 0.6436336636543274,
|
| 159 |
+
"learning_rate": 0.0007259516532370103,
|
| 160 |
+
"loss": 0.2247,
|
| 161 |
+
"step": 8000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 2.361767157543762,
|
| 165 |
+
"grad_norm": 0.6064488291740417,
|
| 166 |
+
"learning_rate": 0.0007213207372418264,
|
| 167 |
+
"loss": 0.2237,
|
| 168 |
+
"step": 8500
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.4006668519033063,
|
| 172 |
+
"eval_loss": 0.24924051761627197,
|
| 173 |
+
"eval_runtime": 5.9651,
|
| 174 |
+
"eval_samples_per_second": 83.821,
|
| 175 |
+
"eval_steps_per_second": 5.365,
|
| 176 |
+
"step": 8640
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.5006946373992776,
|
| 180 |
+
"grad_norm": 1.0091792345046997,
|
| 181 |
+
"learning_rate": 0.0007166898212466426,
|
| 182 |
+
"loss": 0.2203,
|
| 183 |
+
"step": 9000
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 2.639622117254793,
|
| 187 |
+
"grad_norm": 0.8089786767959595,
|
| 188 |
+
"learning_rate": 0.0007120589052514588,
|
| 189 |
+
"loss": 0.2196,
|
| 190 |
+
"step": 9500
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 2.7785495971103087,
|
| 194 |
+
"grad_norm": 0.5441291928291321,
|
| 195 |
+
"learning_rate": 0.0007074372510882653,
|
| 196 |
+
"loss": 0.2216,
|
| 197 |
+
"step": 10000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 2.800777993887191,
|
| 201 |
+
"eval_loss": 0.2379860281944275,
|
| 202 |
+
"eval_runtime": 5.6823,
|
| 203 |
+
"eval_samples_per_second": 87.992,
|
| 204 |
+
"eval_steps_per_second": 5.632,
|
| 205 |
+
"step": 10080
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 2.917477076965824,
|
| 209 |
+
"grad_norm": 0.5629907250404358,
|
| 210 |
+
"learning_rate": 0.0007028063350930814,
|
| 211 |
+
"loss": 0.2209,
|
| 212 |
+
"step": 10500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 3.0564045568213394,
|
| 216 |
+
"grad_norm": 0.7793105840682983,
|
| 217 |
+
"learning_rate": 0.0006981754190978975,
|
| 218 |
+
"loss": 0.2153,
|
| 219 |
+
"step": 11000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 3.1953320366768545,
|
| 223 |
+
"grad_norm": 0.5668399333953857,
|
| 224 |
+
"learning_rate": 0.0006935445031027137,
|
| 225 |
+
"loss": 0.2104,
|
| 226 |
+
"step": 11500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 3.2008891358710754,
|
| 230 |
+
"eval_loss": 0.23175135254859924,
|
| 231 |
+
"eval_runtime": 5.6868,
|
| 232 |
+
"eval_samples_per_second": 87.922,
|
| 233 |
+
"eval_steps_per_second": 5.627,
|
| 234 |
+
"step": 11520
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 3.33425951653237,
|
| 238 |
+
"grad_norm": 0.8093000650405884,
|
| 239 |
+
"learning_rate": 0.0006889228489395203,
|
| 240 |
+
"loss": 0.2136,
|
| 241 |
+
"step": 12000
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 3.4731869963878856,
|
| 245 |
+
"grad_norm": 0.9104741215705872,
|
| 246 |
+
"learning_rate": 0.0006842919329443364,
|
| 247 |
+
"loss": 0.2076,
|
| 248 |
+
"step": 12500
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 3.6010002778549595,
|
| 252 |
+
"eval_loss": 0.22807475924491882,
|
| 253 |
+
"eval_runtime": 5.7081,
|
| 254 |
+
"eval_samples_per_second": 87.595,
|
| 255 |
+
"eval_steps_per_second": 5.606,
|
| 256 |
+
"step": 12960
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 3.612114476243401,
|
| 260 |
+
"grad_norm": 0.688875675201416,
|
| 261 |
+
"learning_rate": 0.0006796610169491525,
|
| 262 |
+
"loss": 0.2109,
|
| 263 |
+
"step": 13000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.7510419560989163,
|
| 267 |
+
"grad_norm": 0.985016405582428,
|
| 268 |
+
"learning_rate": 0.0006750301009539687,
|
| 269 |
+
"loss": 0.209,
|
| 270 |
+
"step": 13500
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 3.889969435954432,
|
| 274 |
+
"grad_norm": 0.792914628982544,
|
| 275 |
+
"learning_rate": 0.0006703991849587848,
|
| 276 |
+
"loss": 0.2087,
|
| 277 |
+
"step": 14000
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 4.001111419838844,
|
| 281 |
+
"eval_loss": 0.2299247533082962,
|
| 282 |
+
"eval_runtime": 5.9644,
|
| 283 |
+
"eval_samples_per_second": 83.831,
|
| 284 |
+
"eval_steps_per_second": 5.365,
|
| 285 |
+
"step": 14400
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 4.0288969158099475,
|
| 289 |
+
"grad_norm": 0.8050146698951721,
|
| 290 |
+
"learning_rate": 0.000665768268963601,
|
| 291 |
+
"loss": 0.2043,
|
| 292 |
+
"step": 14500
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 4.167824395665463,
|
| 296 |
+
"grad_norm": 0.6686243414878845,
|
| 297 |
+
"learning_rate": 0.0006611373529684172,
|
| 298 |
+
"loss": 0.1997,
|
| 299 |
+
"step": 15000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 4.306751875520978,
|
| 303 |
+
"grad_norm": 0.5832377076148987,
|
| 304 |
+
"learning_rate": 0.0006565064369732334,
|
| 305 |
+
"loss": 0.2011,
|
| 306 |
+
"step": 15500
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 4.4012225618227285,
|
| 310 |
+
"eval_loss": 0.22105582058429718,
|
| 311 |
+
"eval_runtime": 5.6811,
|
| 312 |
+
"eval_samples_per_second": 88.011,
|
| 313 |
+
"eval_steps_per_second": 5.633,
|
| 314 |
+
"step": 15840
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 4.445679355376494,
|
| 318 |
+
"grad_norm": 0.5768308639526367,
|
| 319 |
+
"learning_rate": 0.0006518847828100398,
|
| 320 |
+
"loss": 0.2029,
|
| 321 |
+
"step": 16000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 4.584606835232009,
|
| 325 |
+
"grad_norm": 0.7500970959663391,
|
| 326 |
+
"learning_rate": 0.000647253866814856,
|
| 327 |
+
"loss": 0.1985,
|
| 328 |
+
"step": 16500
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 4.723534315087524,
|
| 332 |
+
"grad_norm": 0.7904524207115173,
|
| 333 |
+
"learning_rate": 0.0006426322126516625,
|
| 334 |
+
"loss": 0.199,
|
| 335 |
+
"step": 17000
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 4.801333703806613,
|
| 339 |
+
"eval_loss": 0.2192094475030899,
|
| 340 |
+
"eval_runtime": 5.6808,
|
| 341 |
+
"eval_samples_per_second": 88.016,
|
| 342 |
+
"eval_steps_per_second": 5.633,
|
| 343 |
+
"step": 17280
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 4.86246179494304,
|
| 347 |
+
"grad_norm": 0.539150059223175,
|
| 348 |
+
"learning_rate": 0.0006380012966564787,
|
| 349 |
+
"loss": 0.2009,
|
| 350 |
+
"step": 17500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 5.001389274798555,
|
| 354 |
+
"grad_norm": 0.8565651178359985,
|
| 355 |
+
"learning_rate": 0.0006333703806612948,
|
| 356 |
+
"loss": 0.1971,
|
| 357 |
+
"step": 18000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 5.14031675465407,
|
| 361 |
+
"grad_norm": 0.7713454365730286,
|
| 362 |
+
"learning_rate": 0.0006287394646661109,
|
| 363 |
+
"loss": 0.1893,
|
| 364 |
+
"step": 18500
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 5.201444845790498,
|
| 368 |
+
"eval_loss": 0.21168488264083862,
|
| 369 |
+
"eval_runtime": 5.6835,
|
| 370 |
+
"eval_samples_per_second": 87.974,
|
| 371 |
+
"eval_steps_per_second": 5.63,
|
| 372 |
+
"step": 18720
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 5.279244234509586,
|
| 376 |
+
"grad_norm": 0.6991382241249084,
|
| 377 |
+
"learning_rate": 0.0006241085486709271,
|
| 378 |
+
"loss": 0.1893,
|
| 379 |
+
"step": 19000
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 5.418171714365101,
|
| 383 |
+
"grad_norm": 0.8312591314315796,
|
| 384 |
+
"learning_rate": 0.0006194776326757433,
|
| 385 |
+
"loss": 0.1922,
|
| 386 |
+
"step": 19500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 5.5570991942206165,
|
| 390 |
+
"grad_norm": 0.5211935043334961,
|
| 391 |
+
"learning_rate": 0.0006148467166805595,
|
| 392 |
+
"loss": 0.1935,
|
| 393 |
+
"step": 20000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 5.601555987774382,
|
| 397 |
+
"eval_loss": 0.21850116550922394,
|
| 398 |
+
"eval_runtime": 5.755,
|
| 399 |
+
"eval_samples_per_second": 86.881,
|
| 400 |
+
"eval_steps_per_second": 5.56,
|
| 401 |
+
"step": 20160
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 5.6960266740761325,
|
| 405 |
+
"grad_norm": 0.6599379777908325,
|
| 406 |
+
"learning_rate": 0.000610225062517366,
|
| 407 |
+
"loss": 0.1926,
|
| 408 |
+
"step": 20500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 5.834954153931648,
|
| 412 |
+
"grad_norm": 0.5970427393913269,
|
| 413 |
+
"learning_rate": 0.0006055941465221821,
|
| 414 |
+
"loss": 0.1909,
|
| 415 |
+
"step": 21000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 5.973881633787163,
|
| 419 |
+
"grad_norm": 1.023311734199524,
|
| 420 |
+
"learning_rate": 0.0006009632305269982,
|
| 421 |
+
"loss": 0.1895,
|
| 422 |
+
"step": 21500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 6.001667129758266,
|
| 426 |
+
"eval_loss": 0.207980215549469,
|
| 427 |
+
"eval_runtime": 5.7482,
|
| 428 |
+
"eval_samples_per_second": 86.984,
|
| 429 |
+
"eval_steps_per_second": 5.567,
|
| 430 |
+
"step": 21600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 6.112809113642679,
|
| 434 |
+
"grad_norm": 0.91774582862854,
|
| 435 |
+
"learning_rate": 0.0005963323145318144,
|
| 436 |
+
"loss": 0.1816,
|
| 437 |
+
"step": 22000
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 6.251736593498194,
|
| 441 |
+
"grad_norm": 1.0004245042800903,
|
| 442 |
+
"learning_rate": 0.0005917013985366306,
|
| 443 |
+
"loss": 0.1851,
|
| 444 |
+
"step": 22500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 6.390664073353709,
|
| 448 |
+
"grad_norm": 0.662783145904541,
|
| 449 |
+
"learning_rate": 0.0005870704825414468,
|
| 450 |
+
"loss": 0.1841,
|
| 451 |
+
"step": 23000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 6.401778271742151,
|
| 455 |
+
"eval_loss": 0.20145055651664734,
|
| 456 |
+
"eval_runtime": 5.7129,
|
| 457 |
+
"eval_samples_per_second": 87.521,
|
| 458 |
+
"eval_steps_per_second": 5.601,
|
| 459 |
+
"step": 23040
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 6.529591553209225,
|
| 463 |
+
"grad_norm": 0.7809537053108215,
|
| 464 |
+
"learning_rate": 0.0005824395665462628,
|
| 465 |
+
"loss": 0.1818,
|
| 466 |
+
"step": 23500
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 6.66851903306474,
|
| 470 |
+
"grad_norm": 0.7120875120162964,
|
| 471 |
+
"learning_rate": 0.000577808650551079,
|
| 472 |
+
"loss": 0.184,
|
| 473 |
+
"step": 24000
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 6.801889413726035,
|
| 477 |
+
"eval_loss": 0.20286568999290466,
|
| 478 |
+
"eval_runtime": 5.6944,
|
| 479 |
+
"eval_samples_per_second": 87.805,
|
| 480 |
+
"eval_steps_per_second": 5.62,
|
| 481 |
+
"step": 24480
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 6.807446512920255,
|
| 485 |
+
"grad_norm": 0.6878994107246399,
|
| 486 |
+
"learning_rate": 0.0005731869963878856,
|
| 487 |
+
"loss": 0.1837,
|
| 488 |
+
"step": 24500
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 6.946373992775771,
|
| 492 |
+
"grad_norm": 1.3410155773162842,
|
| 493 |
+
"learning_rate": 0.0005685560803927017,
|
| 494 |
+
"loss": 0.181,
|
| 495 |
+
"step": 25000
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 7.085301472631286,
|
| 499 |
+
"grad_norm": 0.7791838049888611,
|
| 500 |
+
"learning_rate": 0.0005639344262295083,
|
| 501 |
+
"loss": 0.1755,
|
| 502 |
+
"step": 25500
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 7.20200055570992,
|
| 506 |
+
"eval_loss": 0.2010478526353836,
|
| 507 |
+
"eval_runtime": 5.7186,
|
| 508 |
+
"eval_samples_per_second": 87.434,
|
| 509 |
+
"eval_steps_per_second": 5.596,
|
| 510 |
+
"step": 25920
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 7.2242289524868015,
|
| 514 |
+
"grad_norm": 1.0793170928955078,
|
| 515 |
+
"learning_rate": 0.0005593035102343244,
|
| 516 |
+
"loss": 0.1728,
|
| 517 |
+
"step": 26000
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 7.3631564323423175,
|
| 521 |
+
"grad_norm": 0.901263415813446,
|
| 522 |
+
"learning_rate": 0.0005546725942391405,
|
| 523 |
+
"loss": 0.1761,
|
| 524 |
+
"step": 26500
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 7.502083912197833,
|
| 528 |
+
"grad_norm": 0.5980243682861328,
|
| 529 |
+
"learning_rate": 0.0005500416782439567,
|
| 530 |
+
"loss": 0.1762,
|
| 531 |
+
"step": 27000
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 7.602111697693804,
|
| 535 |
+
"eval_loss": 0.2034424990415573,
|
| 536 |
+
"eval_runtime": 5.7241,
|
| 537 |
+
"eval_samples_per_second": 87.35,
|
| 538 |
+
"eval_steps_per_second": 5.59,
|
| 539 |
+
"step": 27360
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 7.641011392053348,
|
| 543 |
+
"grad_norm": 0.7678053975105286,
|
| 544 |
+
"learning_rate": 0.0005454200240807632,
|
| 545 |
+
"loss": 0.1754,
|
| 546 |
+
"step": 27500
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 7.779938871908864,
|
| 550 |
+
"grad_norm": 0.626030683517456,
|
| 551 |
+
"learning_rate": 0.0005407891080855794,
|
| 552 |
+
"loss": 0.1741,
|
| 553 |
+
"step": 28000
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 7.918866351764379,
|
| 557 |
+
"grad_norm": 0.6907975673675537,
|
| 558 |
+
"learning_rate": 0.0005361581920903956,
|
| 559 |
+
"loss": 0.1775,
|
| 560 |
+
"step": 28500
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 8.002222839677689,
|
| 564 |
+
"eval_loss": 0.19579829275608063,
|
| 565 |
+
"eval_runtime": 5.7531,
|
| 566 |
+
"eval_samples_per_second": 86.91,
|
| 567 |
+
"eval_steps_per_second": 5.562,
|
| 568 |
+
"step": 28800
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 8.057793831619895,
|
| 572 |
+
"grad_norm": 0.8500244617462158,
|
| 573 |
+
"learning_rate": 0.000531536537927202,
|
| 574 |
+
"loss": 0.1707,
|
| 575 |
+
"step": 29000
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 8.19672131147541,
|
| 579 |
+
"grad_norm": 1.2416728734970093,
|
| 580 |
+
"learning_rate": 0.0005269056219320182,
|
| 581 |
+
"loss": 0.1674,
|
| 582 |
+
"step": 29500
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 8.335648791330925,
|
| 586 |
+
"grad_norm": 0.7363243103027344,
|
| 587 |
+
"learning_rate": 0.0005222747059368344,
|
| 588 |
+
"loss": 0.1666,
|
| 589 |
+
"step": 30000
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 8.402333981661572,
|
| 593 |
+
"eval_loss": 0.19788900017738342,
|
| 594 |
+
"eval_runtime": 5.7008,
|
| 595 |
+
"eval_samples_per_second": 87.706,
|
| 596 |
+
"eval_steps_per_second": 5.613,
|
| 597 |
+
"step": 30240
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 8.474576271186441,
|
| 601 |
+
"grad_norm": 0.8667612671852112,
|
| 602 |
+
"learning_rate": 0.0005176437899416505,
|
| 603 |
+
"loss": 0.1681,
|
| 604 |
+
"step": 30500
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 8.613503751041955,
|
| 608 |
+
"grad_norm": 0.7073860168457031,
|
| 609 |
+
"learning_rate": 0.0005130128739464667,
|
| 610 |
+
"loss": 0.1706,
|
| 611 |
+
"step": 31000
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 8.752431230897471,
|
| 615 |
+
"grad_norm": 0.813298761844635,
|
| 616 |
+
"learning_rate": 0.0005083819579512828,
|
| 617 |
+
"loss": 0.1673,
|
| 618 |
+
"step": 31500
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 8.802445123645457,
|
| 622 |
+
"eval_loss": 0.2012454718351364,
|
| 623 |
+
"eval_runtime": 6.7505,
|
| 624 |
+
"eval_samples_per_second": 74.068,
|
| 625 |
+
"eval_steps_per_second": 4.74,
|
| 626 |
+
"step": 31680
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 8.891358710752987,
|
| 630 |
+
"grad_norm": 0.8721699118614197,
|
| 631 |
+
"learning_rate": 0.000503751041956099,
|
| 632 |
+
"loss": 0.1683,
|
| 633 |
+
"step": 32000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 9.030286190608502,
|
| 637 |
+
"grad_norm": 0.7278200387954712,
|
| 638 |
+
"learning_rate": 0.000499120125960915,
|
| 639 |
+
"loss": 0.1661,
|
| 640 |
+
"step": 32500
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 9.169213670464018,
|
| 644 |
+
"grad_norm": 0.9835706949234009,
|
| 645 |
+
"learning_rate": 0.0004944984717977217,
|
| 646 |
+
"loss": 0.1606,
|
| 647 |
+
"step": 33000
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 9.202556265629342,
|
| 651 |
+
"eval_loss": 0.19326406717300415,
|
| 652 |
+
"eval_runtime": 5.7204,
|
| 653 |
+
"eval_samples_per_second": 87.406,
|
| 654 |
+
"eval_steps_per_second": 5.594,
|
| 655 |
+
"step": 33120
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 9.308141150319534,
|
| 659 |
+
"grad_norm": 0.7659234404563904,
|
| 660 |
+
"learning_rate": 0.0004898675558025378,
|
| 661 |
+
"loss": 0.1592,
|
| 662 |
+
"step": 33500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 9.447068630175048,
|
| 666 |
+
"grad_norm": 0.8680823445320129,
|
| 667 |
+
"learning_rate": 0.00048523663980735385,
|
| 668 |
+
"loss": 0.1609,
|
| 669 |
+
"step": 34000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 9.585996110030564,
|
| 673 |
+
"grad_norm": 0.7252190709114075,
|
| 674 |
+
"learning_rate": 0.00048060572381217003,
|
| 675 |
+
"loss": 0.1629,
|
| 676 |
+
"step": 34500
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 9.602667407613225,
|
| 680 |
+
"eval_loss": 0.18949145078659058,
|
| 681 |
+
"eval_runtime": 5.6933,
|
| 682 |
+
"eval_samples_per_second": 87.822,
|
| 683 |
+
"eval_steps_per_second": 5.621,
|
| 684 |
+
"step": 34560
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 9.72492358988608,
|
| 688 |
+
"grad_norm": 0.787493884563446,
|
| 689 |
+
"learning_rate": 0.0004759748078169862,
|
| 690 |
+
"loss": 0.162,
|
| 691 |
+
"step": 35000
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 9.863851069741594,
|
| 695 |
+
"grad_norm": 0.7298120856285095,
|
| 696 |
+
"learning_rate": 0.0004713438918218024,
|
| 697 |
+
"loss": 0.1628,
|
| 698 |
+
"step": 35500
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 10.00277854959711,
|
| 702 |
+
"grad_norm": 0.9931182861328125,
|
| 703 |
+
"learning_rate": 0.00046672223765860887,
|
| 704 |
+
"loss": 0.1596,
|
| 705 |
+
"step": 36000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 10.00277854959711,
|
| 709 |
+
"eval_loss": 0.1884983777999878,
|
| 710 |
+
"eval_runtime": 5.7787,
|
| 711 |
+
"eval_samples_per_second": 86.525,
|
| 712 |
+
"eval_steps_per_second": 5.538,
|
| 713 |
+
"step": 36000
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 10.141706029452626,
|
| 717 |
+
"grad_norm": 0.8843297958374023,
|
| 718 |
+
"learning_rate": 0.00046209132166342504,
|
| 719 |
+
"loss": 0.1509,
|
| 720 |
+
"step": 36500
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 10.28063350930814,
|
| 724 |
+
"grad_norm": 0.6324813961982727,
|
| 725 |
+
"learning_rate": 0.00045746040566824116,
|
| 726 |
+
"loss": 0.1526,
|
| 727 |
+
"step": 37000
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 10.402889691580995,
|
| 731 |
+
"eval_loss": 0.1883215308189392,
|
| 732 |
+
"eval_runtime": 5.7012,
|
| 733 |
+
"eval_samples_per_second": 87.701,
|
| 734 |
+
"eval_steps_per_second": 5.613,
|
| 735 |
+
"step": 37440
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 10.419560989163656,
|
| 739 |
+
"grad_norm": 0.7793643474578857,
|
| 740 |
+
"learning_rate": 0.00045282948967305734,
|
| 741 |
+
"loss": 0.1548,
|
| 742 |
+
"step": 37500
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 10.558488469019172,
|
| 746 |
+
"grad_norm": 0.7698658108711243,
|
| 747 |
+
"learning_rate": 0.0004481985736778735,
|
| 748 |
+
"loss": 0.1528,
|
| 749 |
+
"step": 38000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 10.697415948874687,
|
| 753 |
+
"grad_norm": 0.8198125958442688,
|
| 754 |
+
"learning_rate": 0.0004435676576826897,
|
| 755 |
+
"loss": 0.1545,
|
| 756 |
+
"step": 38500
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 10.803000833564878,
|
| 760 |
+
"eval_loss": 0.18633407354354858,
|
| 761 |
+
"eval_runtime": 5.7061,
|
| 762 |
+
"eval_samples_per_second": 87.626,
|
| 763 |
+
"eval_steps_per_second": 5.608,
|
| 764 |
+
"step": 38880
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 10.836343428730203,
|
| 768 |
+
"grad_norm": 0.6395444273948669,
|
| 769 |
+
"learning_rate": 0.0004389367416875058,
|
| 770 |
+
"loss": 0.1565,
|
| 771 |
+
"step": 39000
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 10.975270908585719,
|
| 775 |
+
"grad_norm": 0.6487806439399719,
|
| 776 |
+
"learning_rate": 0.000434305825692322,
|
| 777 |
+
"loss": 0.1553,
|
| 778 |
+
"step": 39500
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 11.114198388441233,
|
| 782 |
+
"grad_norm": 0.8223088383674622,
|
| 783 |
+
"learning_rate": 0.00042967490969713815,
|
| 784 |
+
"loss": 0.1454,
|
| 785 |
+
"step": 40000
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 11.203111975548763,
|
| 789 |
+
"eval_loss": 0.18568813800811768,
|
| 790 |
+
"eval_runtime": 5.7105,
|
| 791 |
+
"eval_samples_per_second": 87.558,
|
| 792 |
+
"eval_steps_per_second": 5.604,
|
| 793 |
+
"step": 40320
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 11.253125868296749,
|
| 797 |
+
"grad_norm": 0.5098241567611694,
|
| 798 |
+
"learning_rate": 0.00042505325553394464,
|
| 799 |
+
"loss": 0.147,
|
| 800 |
+
"step": 40500
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 11.392053348152265,
|
| 804 |
+
"grad_norm": 0.7084653377532959,
|
| 805 |
+
"learning_rate": 0.0004204223395387608,
|
| 806 |
+
"loss": 0.148,
|
| 807 |
+
"step": 41000
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 11.53098082800778,
|
| 811 |
+
"grad_norm": 0.6648092269897461,
|
| 812 |
+
"learning_rate": 0.00041579142354357694,
|
| 813 |
+
"loss": 0.146,
|
| 814 |
+
"step": 41500
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 11.603223117532648,
|
| 818 |
+
"eval_loss": 0.1823151409626007,
|
| 819 |
+
"eval_runtime": 5.7015,
|
| 820 |
+
"eval_samples_per_second": 87.696,
|
| 821 |
+
"eval_steps_per_second": 5.613,
|
| 822 |
+
"step": 41760
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 11.669908307863295,
|
| 826 |
+
"grad_norm": 0.7884602546691895,
|
| 827 |
+
"learning_rate": 0.0004111605075483931,
|
| 828 |
+
"loss": 0.1461,
|
| 829 |
+
"step": 42000
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 11.808835787718811,
|
| 833 |
+
"grad_norm": 0.6522942185401917,
|
| 834 |
+
"learning_rate": 0.0004065388533851996,
|
| 835 |
+
"loss": 0.1485,
|
| 836 |
+
"step": 42500
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 11.947763267574325,
|
| 840 |
+
"grad_norm": 0.8539688587188721,
|
| 841 |
+
"learning_rate": 0.0004019079373900158,
|
| 842 |
+
"loss": 0.1491,
|
| 843 |
+
"step": 43000
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 12.003334259516532,
|
| 847 |
+
"eval_loss": 0.17908716201782227,
|
| 848 |
+
"eval_runtime": 5.7458,
|
| 849 |
+
"eval_samples_per_second": 87.021,
|
| 850 |
+
"eval_steps_per_second": 5.569,
|
| 851 |
+
"step": 43200
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 12.086690747429842,
|
| 855 |
+
"grad_norm": 0.7807750701904297,
|
| 856 |
+
"learning_rate": 0.00039728628322682226,
|
| 857 |
+
"loss": 0.1401,
|
| 858 |
+
"step": 43500
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 12.225618227285358,
|
| 862 |
+
"grad_norm": 0.9898711442947388,
|
| 863 |
+
"learning_rate": 0.00039265536723163844,
|
| 864 |
+
"loss": 0.1368,
|
| 865 |
+
"step": 44000
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 12.364545707140872,
|
| 869 |
+
"grad_norm": 0.6105939149856567,
|
| 870 |
+
"learning_rate": 0.0003880244512364546,
|
| 871 |
+
"loss": 0.1395,
|
| 872 |
+
"step": 44500
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 12.403445401500417,
|
| 876 |
+
"eval_loss": 0.1828669160604477,
|
| 877 |
+
"eval_runtime": 5.7589,
|
| 878 |
+
"eval_samples_per_second": 86.822,
|
| 879 |
+
"eval_steps_per_second": 5.557,
|
| 880 |
+
"step": 44640
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 12.503473186996388,
|
| 884 |
+
"grad_norm": 0.659959077835083,
|
| 885 |
+
"learning_rate": 0.00038339353524127073,
|
| 886 |
+
"loss": 0.1437,
|
| 887 |
+
"step": 45000
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 12.642400666851904,
|
| 891 |
+
"grad_norm": 0.8805100321769714,
|
| 892 |
+
"learning_rate": 0.0003787626192460869,
|
| 893 |
+
"loss": 0.1414,
|
| 894 |
+
"step": 45500
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 12.781328146707418,
|
| 898 |
+
"grad_norm": 1.0838948488235474,
|
| 899 |
+
"learning_rate": 0.000374131703250903,
|
| 900 |
+
"loss": 0.142,
|
| 901 |
+
"step": 46000
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 12.803556543484301,
|
| 905 |
+
"eval_loss": 0.17811129987239838,
|
| 906 |
+
"eval_runtime": 5.7271,
|
| 907 |
+
"eval_samples_per_second": 87.304,
|
| 908 |
+
"eval_steps_per_second": 5.587,
|
| 909 |
+
"step": 46080
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 12.920255626562934,
|
| 913 |
+
"grad_norm": 0.5533807277679443,
|
| 914 |
+
"learning_rate": 0.0003695007872557192,
|
| 915 |
+
"loss": 0.1417,
|
| 916 |
+
"step": 46500
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 13.05918310641845,
|
| 920 |
+
"grad_norm": 0.6328546404838562,
|
| 921 |
+
"learning_rate": 0.0003648698712605354,
|
| 922 |
+
"loss": 0.1363,
|
| 923 |
+
"step": 47000
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 13.198110586273964,
|
| 927 |
+
"grad_norm": 0.8364810347557068,
|
| 928 |
+
"learning_rate": 0.0003602389552653515,
|
| 929 |
+
"loss": 0.131,
|
| 930 |
+
"step": 47500
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 13.203667685468186,
|
| 934 |
+
"eval_loss": 0.17920471727848053,
|
| 935 |
+
"eval_runtime": 5.6832,
|
| 936 |
+
"eval_samples_per_second": 87.979,
|
| 937 |
+
"eval_steps_per_second": 5.631,
|
| 938 |
+
"step": 47520
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 13.33703806612948,
|
| 942 |
+
"grad_norm": 0.754403829574585,
|
| 943 |
+
"learning_rate": 0.0003556080392701676,
|
| 944 |
+
"loss": 0.1334,
|
| 945 |
+
"step": 48000
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 13.475965545984996,
|
| 949 |
+
"grad_norm": 0.7372345924377441,
|
| 950 |
+
"learning_rate": 0.0003509771232749838,
|
| 951 |
+
"loss": 0.1323,
|
| 952 |
+
"step": 48500
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 13.60377882745207,
|
| 956 |
+
"eval_loss": 0.18234029412269592,
|
| 957 |
+
"eval_runtime": 5.692,
|
| 958 |
+
"eval_samples_per_second": 87.843,
|
| 959 |
+
"eval_steps_per_second": 5.622,
|
| 960 |
+
"step": 48960
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 13.61489302584051,
|
| 964 |
+
"grad_norm": 0.5553024411201477,
|
| 965 |
+
"learning_rate": 0.00034635546911179033,
|
| 966 |
+
"loss": 0.1345,
|
| 967 |
+
"step": 49000
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 13.753820505696027,
|
| 971 |
+
"grad_norm": 0.6826585531234741,
|
| 972 |
+
"learning_rate": 0.0003417245531166065,
|
| 973 |
+
"loss": 0.1329,
|
| 974 |
+
"step": 49500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 13.892747985551543,
|
| 978 |
+
"grad_norm": 0.622280478477478,
|
| 979 |
+
"learning_rate": 0.00033709363712142263,
|
| 980 |
+
"loss": 0.1339,
|
| 981 |
+
"step": 50000
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 14.003889969435955,
|
| 985 |
+
"eval_loss": 0.1794731467962265,
|
| 986 |
+
"eval_runtime": 5.7345,
|
| 987 |
+
"eval_samples_per_second": 87.192,
|
| 988 |
+
"eval_steps_per_second": 5.58,
|
| 989 |
+
"step": 50400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 14.031675465407057,
|
| 993 |
+
"grad_norm": 0.7773860692977905,
|
| 994 |
+
"learning_rate": 0.00033246272112623875,
|
| 995 |
+
"loss": 0.1324,
|
| 996 |
+
"step": 50500
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 14.170602945262573,
|
| 1000 |
+
"grad_norm": 0.6761751174926758,
|
| 1001 |
+
"learning_rate": 0.0003278410669630453,
|
| 1002 |
+
"loss": 0.1225,
|
| 1003 |
+
"step": 51000
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 14.309530425118089,
|
| 1007 |
+
"grad_norm": 0.6650680303573608,
|
| 1008 |
+
"learning_rate": 0.00032321015096786147,
|
| 1009 |
+
"loss": 0.1261,
|
| 1010 |
+
"step": 51500
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 14.40400111141984,
|
| 1014 |
+
"eval_loss": 0.17374251782894135,
|
| 1015 |
+
"eval_runtime": 5.7241,
|
| 1016 |
+
"eval_samples_per_second": 87.351,
|
| 1017 |
+
"eval_steps_per_second": 5.59,
|
| 1018 |
+
"step": 51840
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 14.448457904973603,
|
| 1022 |
+
"grad_norm": 0.8033860921859741,
|
| 1023 |
+
"learning_rate": 0.00031857923497267764,
|
| 1024 |
+
"loss": 0.1264,
|
| 1025 |
+
"step": 52000
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 14.587385384829119,
|
| 1029 |
+
"grad_norm": 1.125452995300293,
|
| 1030 |
+
"learning_rate": 0.00031394831897749376,
|
| 1031 |
+
"loss": 0.1283,
|
| 1032 |
+
"step": 52500
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 14.726312864684635,
|
| 1036 |
+
"grad_norm": 0.7282013297080994,
|
| 1037 |
+
"learning_rate": 0.00030931740298230994,
|
| 1038 |
+
"loss": 0.1279,
|
| 1039 |
+
"step": 53000
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 14.804112253403723,
|
| 1043 |
+
"eval_loss": 0.17884068191051483,
|
| 1044 |
+
"eval_runtime": 5.7161,
|
| 1045 |
+
"eval_samples_per_second": 87.473,
|
| 1046 |
+
"eval_steps_per_second": 5.598,
|
| 1047 |
+
"step": 53280
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 14.86524034454015,
|
| 1051 |
+
"grad_norm": 0.763498842716217,
|
| 1052 |
+
"learning_rate": 0.0003046957488191164,
|
| 1053 |
+
"loss": 0.1272,
|
| 1054 |
+
"step": 53500
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 15.004167824395665,
|
| 1058 |
+
"grad_norm": 0.5262055993080139,
|
| 1059 |
+
"learning_rate": 0.0003000648328239326,
|
| 1060 |
+
"loss": 0.1263,
|
| 1061 |
+
"step": 54000
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 15.143095304251181,
|
| 1065 |
+
"grad_norm": 0.6095721125602722,
|
| 1066 |
+
"learning_rate": 0.0002954339168287487,
|
| 1067 |
+
"loss": 0.1168,
|
| 1068 |
+
"step": 54500
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 15.204223395387608,
|
| 1072 |
+
"eval_loss": 0.17539146542549133,
|
| 1073 |
+
"eval_runtime": 5.7056,
|
| 1074 |
+
"eval_samples_per_second": 87.634,
|
| 1075 |
+
"eval_steps_per_second": 5.609,
|
| 1076 |
+
"step": 54720
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 15.282022784106696,
|
| 1080 |
+
"grad_norm": 0.7185012698173523,
|
| 1081 |
+
"learning_rate": 0.0002908030008335649,
|
| 1082 |
+
"loss": 0.1194,
|
| 1083 |
+
"step": 55000
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 15.420950263962212,
|
| 1087 |
+
"grad_norm": 0.8502697944641113,
|
| 1088 |
+
"learning_rate": 0.00028617208483838107,
|
| 1089 |
+
"loss": 0.1172,
|
| 1090 |
+
"step": 55500
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 15.559877743817728,
|
| 1094 |
+
"grad_norm": 0.7366784811019897,
|
| 1095 |
+
"learning_rate": 0.0002815411688431972,
|
| 1096 |
+
"loss": 0.1199,
|
| 1097 |
+
"step": 56000
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 15.604334537371493,
|
| 1101 |
+
"eval_loss": 0.174043670296669,
|
| 1102 |
+
"eval_runtime": 5.6949,
|
| 1103 |
+
"eval_samples_per_second": 87.798,
|
| 1104 |
+
"eval_steps_per_second": 5.619,
|
| 1105 |
+
"step": 56160
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 15.698805223673242,
|
| 1109 |
+
"grad_norm": 0.7937948703765869,
|
| 1110 |
+
"learning_rate": 0.0002769102528480133,
|
| 1111 |
+
"loss": 0.1216,
|
| 1112 |
+
"step": 56500
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 15.837732703528758,
|
| 1116 |
+
"grad_norm": 0.6836448311805725,
|
| 1117 |
+
"learning_rate": 0.0002722793368528295,
|
| 1118 |
+
"loss": 0.1201,
|
| 1119 |
+
"step": 57000
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 15.976660183384274,
|
| 1123 |
+
"grad_norm": 0.8301613330841064,
|
| 1124 |
+
"learning_rate": 0.0002676669445216264,
|
| 1125 |
+
"loss": 0.121,
|
| 1126 |
+
"step": 57500
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 16.004445679355378,
|
| 1130 |
+
"eval_loss": 0.17525814473628998,
|
| 1131 |
+
"eval_runtime": 5.7223,
|
| 1132 |
+
"eval_samples_per_second": 87.378,
|
| 1133 |
+
"eval_steps_per_second": 5.592,
|
| 1134 |
+
"step": 57600
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 16.11558766323979,
|
| 1138 |
+
"grad_norm": 0.801866352558136,
|
| 1139 |
+
"learning_rate": 0.00026303602852644257,
|
| 1140 |
+
"loss": 0.1109,
|
| 1141 |
+
"step": 58000
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 16.254515143095304,
|
| 1145 |
+
"grad_norm": 0.7740326523780823,
|
| 1146 |
+
"learning_rate": 0.0002584051125312587,
|
| 1147 |
+
"loss": 0.1102,
|
| 1148 |
+
"step": 58500
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 16.39344262295082,
|
| 1152 |
+
"grad_norm": 0.6305615305900574,
|
| 1153 |
+
"learning_rate": 0.00025377419653607486,
|
| 1154 |
+
"loss": 0.1125,
|
| 1155 |
+
"step": 59000
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 16.40455682133926,
|
| 1159 |
+
"eval_loss": 0.17229421436786652,
|
| 1160 |
+
"eval_runtime": 5.7155,
|
| 1161 |
+
"eval_samples_per_second": 87.482,
|
| 1162 |
+
"eval_steps_per_second": 5.599,
|
| 1163 |
+
"step": 59040
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 16.532370102806336,
|
| 1167 |
+
"grad_norm": 0.8209009766578674,
|
| 1168 |
+
"learning_rate": 0.000249143280540891,
|
| 1169 |
+
"loss": 0.1139,
|
| 1170 |
+
"step": 59500
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 16.67129758266185,
|
| 1174 |
+
"grad_norm": 1.0618516206741333,
|
| 1175 |
+
"learning_rate": 0.00024451236454570716,
|
| 1176 |
+
"loss": 0.1151,
|
| 1177 |
+
"step": 60000
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 16.804667963323144,
|
| 1181 |
+
"eval_loss": 0.17186084389686584,
|
| 1182 |
+
"eval_runtime": 5.724,
|
| 1183 |
+
"eval_samples_per_second": 87.352,
|
| 1184 |
+
"eval_steps_per_second": 5.591,
|
| 1185 |
+
"step": 60480
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 16.810225062517365,
|
| 1189 |
+
"grad_norm": 1.1203557252883911,
|
| 1190 |
+
"learning_rate": 0.0002398907103825137,
|
| 1191 |
+
"loss": 0.1127,
|
| 1192 |
+
"step": 60500
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 16.949152542372882,
|
| 1196 |
+
"grad_norm": 0.9507138729095459,
|
| 1197 |
+
"learning_rate": 0.00023525979438732982,
|
| 1198 |
+
"loss": 0.1138,
|
| 1199 |
+
"step": 61000
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 17.088080022228397,
|
| 1203 |
+
"grad_norm": 0.50418621301651,
|
| 1204 |
+
"learning_rate": 0.00023062887839214597,
|
| 1205 |
+
"loss": 0.1053,
|
| 1206 |
+
"step": 61500
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 17.20477910530703,
|
| 1210 |
+
"eval_loss": 0.17183047533035278,
|
| 1211 |
+
"eval_runtime": 5.7075,
|
| 1212 |
+
"eval_samples_per_second": 87.604,
|
| 1213 |
+
"eval_steps_per_second": 5.607,
|
| 1214 |
+
"step": 61920
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 17.22700750208391,
|
| 1218 |
+
"grad_norm": 0.8892719149589539,
|
| 1219 |
+
"learning_rate": 0.00022599796239696214,
|
| 1220 |
+
"loss": 0.1053,
|
| 1221 |
+
"step": 62000
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 17.36593498193943,
|
| 1225 |
+
"grad_norm": 0.4419918358325958,
|
| 1226 |
+
"learning_rate": 0.00022137630823376866,
|
| 1227 |
+
"loss": 0.1055,
|
| 1228 |
+
"step": 62500
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 17.504862461794943,
|
| 1232 |
+
"grad_norm": 0.7942801117897034,
|
| 1233 |
+
"learning_rate": 0.00021674539223858478,
|
| 1234 |
+
"loss": 0.106,
|
| 1235 |
+
"step": 63000
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 17.604890247290914,
|
| 1239 |
+
"eval_loss": 0.16908669471740723,
|
| 1240 |
+
"eval_runtime": 5.6994,
|
| 1241 |
+
"eval_samples_per_second": 87.728,
|
| 1242 |
+
"eval_steps_per_second": 5.615,
|
| 1243 |
+
"step": 63360
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 17.643789941650457,
|
| 1247 |
+
"grad_norm": 0.72785884141922,
|
| 1248 |
+
"learning_rate": 0.00021211447624340095,
|
| 1249 |
+
"loss": 0.1061,
|
| 1250 |
+
"step": 63500
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 17.782717421505975,
|
| 1254 |
+
"grad_norm": 0.6169493198394775,
|
| 1255 |
+
"learning_rate": 0.0002074835602482171,
|
| 1256 |
+
"loss": 0.105,
|
| 1257 |
+
"step": 64000
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 17.92164490136149,
|
| 1261 |
+
"grad_norm": 0.6713001132011414,
|
| 1262 |
+
"learning_rate": 0.00020285264425303328,
|
| 1263 |
+
"loss": 0.1073,
|
| 1264 |
+
"step": 64500
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 18.0050013892748,
|
| 1268 |
+
"eval_loss": 0.17229732871055603,
|
| 1269 |
+
"eval_runtime": 5.7663,
|
| 1270 |
+
"eval_samples_per_second": 86.711,
|
| 1271 |
+
"eval_steps_per_second": 5.55,
|
| 1272 |
+
"step": 64800
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 18.060572381217003,
|
| 1276 |
+
"grad_norm": 0.5809840559959412,
|
| 1277 |
+
"learning_rate": 0.00019822172825784942,
|
| 1278 |
+
"loss": 0.1034,
|
| 1279 |
+
"step": 65000
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 18.19949986107252,
|
| 1283 |
+
"grad_norm": 0.5985963344573975,
|
| 1284 |
+
"learning_rate": 0.00019359081226266554,
|
| 1285 |
+
"loss": 0.097,
|
| 1286 |
+
"step": 65500
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 18.338427340928035,
|
| 1290 |
+
"grad_norm": 0.8002266883850098,
|
| 1291 |
+
"learning_rate": 0.00018895989626748172,
|
| 1292 |
+
"loss": 0.0973,
|
| 1293 |
+
"step": 66000
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 18.405112531258684,
|
| 1297 |
+
"eval_loss": 0.16905440390110016,
|
| 1298 |
+
"eval_runtime": 5.6988,
|
| 1299 |
+
"eval_samples_per_second": 87.738,
|
| 1300 |
+
"eval_steps_per_second": 5.615,
|
| 1301 |
+
"step": 66240
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 18.47735482078355,
|
| 1305 |
+
"grad_norm": 0.841440737247467,
|
| 1306 |
+
"learning_rate": 0.0001843289802722979,
|
| 1307 |
+
"loss": 0.0992,
|
| 1308 |
+
"step": 66500
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 18.616282300639067,
|
| 1312 |
+
"grad_norm": 0.8495504260063171,
|
| 1313 |
+
"learning_rate": 0.000179698064277114,
|
| 1314 |
+
"loss": 0.1002,
|
| 1315 |
+
"step": 67000
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 18.75520978049458,
|
| 1319 |
+
"grad_norm": 0.6956267952919006,
|
| 1320 |
+
"learning_rate": 0.00017507641011392055,
|
| 1321 |
+
"loss": 0.1009,
|
| 1322 |
+
"step": 67500
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 18.80522367324257,
|
| 1326 |
+
"eval_loss": 0.1660514622926712,
|
| 1327 |
+
"eval_runtime": 5.719,
|
| 1328 |
+
"eval_samples_per_second": 87.428,
|
| 1329 |
+
"eval_steps_per_second": 5.595,
|
| 1330 |
+
"step": 67680
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 18.894137260350096,
|
| 1334 |
+
"grad_norm": 0.6415526270866394,
|
| 1335 |
+
"learning_rate": 0.0001704454941187367,
|
| 1336 |
+
"loss": 0.1011,
|
| 1337 |
+
"step": 68000
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 19.033064740205614,
|
| 1341 |
+
"grad_norm": 0.6368350982666016,
|
| 1342 |
+
"learning_rate": 0.00016581457812355285,
|
| 1343 |
+
"loss": 0.0989,
|
| 1344 |
+
"step": 68500
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 19.171992220061128,
|
| 1348 |
+
"grad_norm": 0.9284315705299377,
|
| 1349 |
+
"learning_rate": 0.000161183662128369,
|
| 1350 |
+
"loss": 0.0908,
|
| 1351 |
+
"step": 69000
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 19.20533481522645,
|
| 1355 |
+
"eval_loss": 0.17813153564929962,
|
| 1356 |
+
"eval_runtime": 5.7094,
|
| 1357 |
+
"eval_samples_per_second": 87.574,
|
| 1358 |
+
"eval_steps_per_second": 5.605,
|
| 1359 |
+
"step": 69120
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 19.310919699916642,
|
| 1363 |
+
"grad_norm": 0.905992329120636,
|
| 1364 |
+
"learning_rate": 0.00015655274613318515,
|
| 1365 |
+
"loss": 0.0924,
|
| 1366 |
+
"step": 69500
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 19.44984717977216,
|
| 1370 |
+
"grad_norm": 0.6849103569984436,
|
| 1371 |
+
"learning_rate": 0.0001519218301380013,
|
| 1372 |
+
"loss": 0.0935,
|
| 1373 |
+
"step": 70000
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 19.588774659627674,
|
| 1377 |
+
"grad_norm": 1.106966495513916,
|
| 1378 |
+
"learning_rate": 0.00014729091414281747,
|
| 1379 |
+
"loss": 0.0926,
|
| 1380 |
+
"step": 70500
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 19.605445957210335,
|
| 1384 |
+
"eval_loss": 0.1741752326488495,
|
| 1385 |
+
"eval_runtime": 5.7045,
|
| 1386 |
+
"eval_samples_per_second": 87.651,
|
| 1387 |
+
"eval_steps_per_second": 5.61,
|
| 1388 |
+
"step": 70560
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 19.72770213948319,
|
| 1392 |
+
"grad_norm": 0.8819716572761536,
|
| 1393 |
+
"learning_rate": 0.0001426599981476336,
|
| 1394 |
+
"loss": 0.0941,
|
| 1395 |
+
"step": 71000
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 19.866629619338706,
|
| 1399 |
+
"grad_norm": 0.7679275870323181,
|
| 1400 |
+
"learning_rate": 0.00013803834398444013,
|
| 1401 |
+
"loss": 0.0934,
|
| 1402 |
+
"step": 71500
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 20.00555709919422,
|
| 1406 |
+
"grad_norm": 0.34947940707206726,
|
| 1407 |
+
"learning_rate": 0.00013340742798925628,
|
| 1408 |
+
"loss": 0.093,
|
| 1409 |
+
"step": 72000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 20.00555709919422,
|
| 1413 |
+
"eval_loss": 0.1732003092765808,
|
| 1414 |
+
"eval_runtime": 5.8688,
|
| 1415 |
+
"eval_samples_per_second": 85.196,
|
| 1416 |
+
"eval_steps_per_second": 5.453,
|
| 1417 |
+
"step": 72000
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 20.144484579049735,
|
| 1421 |
+
"grad_norm": 0.6382136940956116,
|
| 1422 |
+
"learning_rate": 0.00012877651199407243,
|
| 1423 |
+
"loss": 0.0846,
|
| 1424 |
+
"step": 72500
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 20.283412058905252,
|
| 1428 |
+
"grad_norm": 0.741828441619873,
|
| 1429 |
+
"learning_rate": 0.00012414559599888857,
|
| 1430 |
+
"loss": 0.086,
|
| 1431 |
+
"step": 73000
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 20.405668241178105,
|
| 1435 |
+
"eval_loss": 0.17495346069335938,
|
| 1436 |
+
"eval_runtime": 5.7142,
|
| 1437 |
+
"eval_samples_per_second": 87.501,
|
| 1438 |
+
"eval_steps_per_second": 5.6,
|
| 1439 |
+
"step": 73440
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 20.422339538760767,
|
| 1443 |
+
"grad_norm": 0.4870929419994354,
|
| 1444 |
+
"learning_rate": 0.00011951468000370473,
|
| 1445 |
+
"loss": 0.0865,
|
| 1446 |
+
"step": 73500
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 20.56126701861628,
|
| 1450 |
+
"grad_norm": 0.7282450199127197,
|
| 1451 |
+
"learning_rate": 0.0001148837640085209,
|
| 1452 |
+
"loss": 0.0881,
|
| 1453 |
+
"step": 74000
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 20.7001944984718,
|
| 1457 |
+
"grad_norm": 0.6929375529289246,
|
| 1458 |
+
"learning_rate": 0.00011027137167731778,
|
| 1459 |
+
"loss": 0.0881,
|
| 1460 |
+
"step": 74500
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 20.80577938316199,
|
| 1464 |
+
"eval_loss": 0.17535780370235443,
|
| 1465 |
+
"eval_runtime": 5.701,
|
| 1466 |
+
"eval_samples_per_second": 87.704,
|
| 1467 |
+
"eval_steps_per_second": 5.613,
|
| 1468 |
+
"step": 74880
|
| 1469 |
+
},
|
| 1470 |
+
{
|
| 1471 |
+
"epoch": 20.839121978327313,
|
| 1472 |
+
"grad_norm": 0.4819177985191345,
|
| 1473 |
+
"learning_rate": 0.00010564045568213392,
|
| 1474 |
+
"loss": 0.0876,
|
| 1475 |
+
"step": 75000
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 20.978049458182827,
|
| 1479 |
+
"grad_norm": 0.39928701519966125,
|
| 1480 |
+
"learning_rate": 0.00010100953968695009,
|
| 1481 |
+
"loss": 0.0858,
|
| 1482 |
+
"step": 75500
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 21.116976938038345,
|
| 1486 |
+
"grad_norm": 0.6018040180206299,
|
| 1487 |
+
"learning_rate": 9.637862369176623e-05,
|
| 1488 |
+
"loss": 0.0818,
|
| 1489 |
+
"step": 76000
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 21.205890525145875,
|
| 1493 |
+
"eval_loss": 0.1778721660375595,
|
| 1494 |
+
"eval_runtime": 5.7497,
|
| 1495 |
+
"eval_samples_per_second": 86.961,
|
| 1496 |
+
"eval_steps_per_second": 5.566,
|
| 1497 |
+
"step": 76320
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 21.25590441789386,
|
| 1501 |
+
"grad_norm": 0.3916943669319153,
|
| 1502 |
+
"learning_rate": 9.174770769658238e-05,
|
| 1503 |
+
"loss": 0.0787,
|
| 1504 |
+
"step": 76500
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 21.394831897749373,
|
| 1508 |
+
"grad_norm": 0.705409586429596,
|
| 1509 |
+
"learning_rate": 8.711679170139854e-05,
|
| 1510 |
+
"loss": 0.08,
|
| 1511 |
+
"step": 77000
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 21.53375937760489,
|
| 1515 |
+
"grad_norm": 0.9091788530349731,
|
| 1516 |
+
"learning_rate": 8.248587570621469e-05,
|
| 1517 |
+
"loss": 0.0809,
|
| 1518 |
+
"step": 77500
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 21.606001667129757,
|
| 1522 |
+
"eval_loss": 0.17738312482833862,
|
| 1523 |
+
"eval_runtime": 5.71,
|
| 1524 |
+
"eval_samples_per_second": 87.565,
|
| 1525 |
+
"eval_steps_per_second": 5.604,
|
| 1526 |
+
"step": 77760
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 21.672686857460405,
|
| 1530 |
+
"grad_norm": 0.6103039979934692,
|
| 1531 |
+
"learning_rate": 7.785495971103085e-05,
|
| 1532 |
+
"loss": 0.081,
|
| 1533 |
+
"step": 78000
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 21.81161433731592,
|
| 1537 |
+
"grad_norm": 0.37460607290267944,
|
| 1538 |
+
"learning_rate": 7.3224043715847e-05,
|
| 1539 |
+
"loss": 0.0818,
|
| 1540 |
+
"step": 78500
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 21.950541817171437,
|
| 1544 |
+
"grad_norm": 0.5228636264801025,
|
| 1545 |
+
"learning_rate": 6.859312772066316e-05,
|
| 1546 |
+
"loss": 0.0815,
|
| 1547 |
+
"step": 79000
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 22.00611280911364,
|
| 1551 |
+
"eval_loss": 0.17903722822666168,
|
| 1552 |
+
"eval_runtime": 5.7717,
|
| 1553 |
+
"eval_samples_per_second": 86.63,
|
| 1554 |
+
"eval_steps_per_second": 5.544,
|
| 1555 |
+
"step": 79200
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 22.08946929702695,
|
| 1559 |
+
"grad_norm": 0.5907357335090637,
|
| 1560 |
+
"learning_rate": 6.397147355746967e-05,
|
| 1561 |
+
"loss": 0.0776,
|
| 1562 |
+
"step": 79500
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 22.228396776882466,
|
| 1566 |
+
"grad_norm": 0.6144934892654419,
|
| 1567 |
+
"learning_rate": 5.934055756228583e-05,
|
| 1568 |
+
"loss": 0.0758,
|
| 1569 |
+
"step": 80000
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 22.367324256737984,
|
| 1573 |
+
"grad_norm": 0.4704384207725525,
|
| 1574 |
+
"learning_rate": 5.4709641567101976e-05,
|
| 1575 |
+
"loss": 0.0746,
|
| 1576 |
+
"step": 80500
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 22.406223951097527,
|
| 1580 |
+
"eval_loss": 0.18559402227401733,
|
| 1581 |
+
"eval_runtime": 5.7,
|
| 1582 |
+
"eval_samples_per_second": 87.72,
|
| 1583 |
+
"eval_steps_per_second": 5.614,
|
| 1584 |
+
"step": 80640
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 22.506251736593498,
|
| 1588 |
+
"grad_norm": 0.6509094834327698,
|
| 1589 |
+
"learning_rate": 5.007872557191813e-05,
|
| 1590 |
+
"loss": 0.076,
|
| 1591 |
+
"step": 81000
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 22.645179216449012,
|
| 1595 |
+
"grad_norm": 0.542117178440094,
|
| 1596 |
+
"learning_rate": 4.544780957673428e-05,
|
| 1597 |
+
"loss": 0.0763,
|
| 1598 |
+
"step": 81500
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 22.78410669630453,
|
| 1602 |
+
"grad_norm": 0.4861942529678345,
|
| 1603 |
+
"learning_rate": 4.081689358155043e-05,
|
| 1604 |
+
"loss": 0.0752,
|
| 1605 |
+
"step": 82000
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 22.80633509308141,
|
| 1609 |
+
"eval_loss": 0.18306955695152283,
|
| 1610 |
+
"eval_runtime": 5.7177,
|
| 1611 |
+
"eval_samples_per_second": 87.448,
|
| 1612 |
+
"eval_steps_per_second": 5.597,
|
| 1613 |
+
"step": 82080
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 22.923034176160044,
|
| 1617 |
+
"grad_norm": 0.530936598777771,
|
| 1618 |
+
"learning_rate": 3.618597758636659e-05,
|
| 1619 |
+
"loss": 0.0757,
|
| 1620 |
+
"step": 82500
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 23.06196165601556,
|
| 1624 |
+
"grad_norm": 0.275852233171463,
|
| 1625 |
+
"learning_rate": 3.155506159118274e-05,
|
| 1626 |
+
"loss": 0.0736,
|
| 1627 |
+
"step": 83000
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 23.200889135871076,
|
| 1631 |
+
"grad_norm": 0.36974436044692993,
|
| 1632 |
+
"learning_rate": 2.693340742798926e-05,
|
| 1633 |
+
"loss": 0.0706,
|
| 1634 |
+
"step": 83500
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 23.206446235065297,
|
| 1638 |
+
"eval_loss": 0.1868555247783661,
|
| 1639 |
+
"eval_runtime": 5.7466,
|
| 1640 |
+
"eval_samples_per_second": 87.008,
|
| 1641 |
+
"eval_steps_per_second": 5.569,
|
| 1642 |
+
"step": 83520
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 23.33981661572659,
|
| 1646 |
+
"grad_norm": 0.4906619191169739,
|
| 1647 |
+
"learning_rate": 2.230249143280541e-05,
|
| 1648 |
+
"loss": 0.0711,
|
| 1649 |
+
"step": 84000
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 23.478744095582105,
|
| 1653 |
+
"grad_norm": 0.7002485394477844,
|
| 1654 |
+
"learning_rate": 1.767157543762156e-05,
|
| 1655 |
+
"loss": 0.071,
|
| 1656 |
+
"step": 84500
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 23.60655737704918,
|
| 1660 |
+
"eval_loss": 0.18815889954566956,
|
| 1661 |
+
"eval_runtime": 5.7463,
|
| 1662 |
+
"eval_samples_per_second": 87.013,
|
| 1663 |
+
"eval_steps_per_second": 5.569,
|
| 1664 |
+
"step": 84960
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 23.617671575437623,
|
| 1668 |
+
"grad_norm": 0.7239441871643066,
|
| 1669 |
+
"learning_rate": 1.3040659442437714e-05,
|
| 1670 |
+
"loss": 0.0709,
|
| 1671 |
+
"step": 85000
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 23.756599055293137,
|
| 1675 |
+
"grad_norm": 0.3651985824108124,
|
| 1676 |
+
"learning_rate": 8.409743447253868e-06,
|
| 1677 |
+
"loss": 0.0714,
|
| 1678 |
+
"step": 85500
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 23.89552653514865,
|
| 1682 |
+
"grad_norm": 0.5195123553276062,
|
| 1683 |
+
"learning_rate": 3.7788274520700198e-06,
|
| 1684 |
+
"loss": 0.0723,
|
| 1685 |
+
"step": 86000
|
| 1686 |
+
}
|
| 1687 |
+
],
|
| 1688 |
+
"logging_steps": 500,
|
| 1689 |
+
"max_steps": 86376,
|
| 1690 |
+
"num_input_tokens_seen": 0,
|
| 1691 |
+
"num_train_epochs": 24,
|
| 1692 |
+
"save_steps": 500,
|
| 1693 |
+
"stateful_callbacks": {
|
| 1694 |
+
"TrainerControl": {
|
| 1695 |
+
"args": {
|
| 1696 |
+
"should_epoch_stop": false,
|
| 1697 |
+
"should_evaluate": false,
|
| 1698 |
+
"should_log": false,
|
| 1699 |
+
"should_save": true,
|
| 1700 |
+
"should_training_stop": true
|
| 1701 |
+
},
|
| 1702 |
+
"attributes": {}
|
| 1703 |
+
}
|
| 1704 |
+
},
|
| 1705 |
+
"total_flos": 4.320203831553032e+18,
|
| 1706 |
+
"train_batch_size": 2,
|
| 1707 |
+
"trial_name": null,
|
| 1708 |
+
"trial_params": null
|
| 1709 |
+
}
|
checkpoint-86376/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20f04554acd1689dfcf765ddfc83593c217e6ad8c0837409b2e0544a3f5759a0
|
| 3 |
+
size 5496
|