checkpoint-11000 | loss=?
Browse files- checkpoint-11000/README.md +202 -0
- checkpoint-11000/adapter_config.json +31 -0
- checkpoint-11000/adapter_model.safetensors +3 -0
- checkpoint-11000/merges.txt +0 -0
- checkpoint-11000/optimizer.pt +3 -0
- checkpoint-11000/rng_state.pth +3 -0
- checkpoint-11000/scheduler.pt +3 -0
- checkpoint-11000/special_tokens_map.json +28 -0
- checkpoint-11000/tokenizer.json +0 -0
- checkpoint-11000/tokenizer_config.json +154 -0
- checkpoint-11000/trainer_state.json +2013 -0
- checkpoint-11000/training_args.bin +3 -0
- checkpoint-11000/vocab.json +0 -0
checkpoint-11000/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: HuggingFaceTB/SmolLM2-135M-Instruct
|
| 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 0.13.2
|
checkpoint-11000/adapter_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "HuggingFaceTB/SmolLM2-135M-Instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"k_proj",
|
| 26 |
+
"v_proj"
|
| 27 |
+
],
|
| 28 |
+
"task_type": "CAUSAL_LM",
|
| 29 |
+
"use_dora": false,
|
| 30 |
+
"use_rslora": false
|
| 31 |
+
}
|
checkpoint-11000/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e684d51a127df8cebeef57bbe51284ae62e7840db8ff2fe507e1bbe07eff2486
|
| 3 |
+
size 7404368
|
checkpoint-11000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-11000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2aadd7d4ccc815e59f9c1b0750aee749740d3df65c9f5c115d20d73803bf2ac
|
| 3 |
+
size 14947339
|
checkpoint-11000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e318d6097d4be0092f012e0c1d3d26cf5e37b22a2c2b7bc01d3e0b2e33b514dd
|
| 3 |
+
size 14645
|
checkpoint-11000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3a9064ddf20a42f0ecf32a04c58e85efea215cbe9ee45bb7d5fc8b33d36c3f0
|
| 3 |
+
size 1465
|
checkpoint-11000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": {
|
| 7 |
+
"content": "<|im_start|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"content": "<|im_end|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"pad_token": "<|im_end|>",
|
| 21 |
+
"unk_token": {
|
| 22 |
+
"content": "<|endoftext|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false
|
| 27 |
+
}
|
| 28 |
+
}
|
checkpoint-11000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-11000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<repo_name>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<reponame>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"5": {
|
| 45 |
+
"content": "<file_sep>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"6": {
|
| 53 |
+
"content": "<filename>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"7": {
|
| 61 |
+
"content": "<gh_stars>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"8": {
|
| 69 |
+
"content": "<issue_start>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"9": {
|
| 77 |
+
"content": "<issue_comment>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"10": {
|
| 85 |
+
"content": "<issue_closed>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"11": {
|
| 93 |
+
"content": "<jupyter_start>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"12": {
|
| 101 |
+
"content": "<jupyter_text>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"13": {
|
| 109 |
+
"content": "<jupyter_code>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"14": {
|
| 117 |
+
"content": "<jupyter_output>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"15": {
|
| 125 |
+
"content": "<jupyter_script>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"16": {
|
| 133 |
+
"content": "<empty_output>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
}
|
| 140 |
+
},
|
| 141 |
+
"additional_special_tokens": [
|
| 142 |
+
"<|im_start|>",
|
| 143 |
+
"<|im_end|>"
|
| 144 |
+
],
|
| 145 |
+
"bos_token": "<|im_start|>",
|
| 146 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 147 |
+
"clean_up_tokenization_spaces": false,
|
| 148 |
+
"eos_token": "<|im_end|>",
|
| 149 |
+
"model_max_length": 8192,
|
| 150 |
+
"pad_token": "<|im_end|>",
|
| 151 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 152 |
+
"unk_token": "<|endoftext|>",
|
| 153 |
+
"vocab_size": 49152
|
| 154 |
+
}
|
checkpoint-11000/trainer_state.json
ADDED
|
@@ -0,0 +1,2013 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7888354063034058,
|
| 3 |
+
"best_model_checkpoint": "/kaggle/working/checkpoints/checkpoint-11000",
|
| 4 |
+
"epoch": 1.957992168031328,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 11000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0088999644001424,
|
| 13 |
+
"grad_norm": 0.46537941694259644,
|
| 14 |
+
"learning_rate": 0.0001,
|
| 15 |
+
"loss": 3.2655,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0177999288002848,
|
| 20 |
+
"grad_norm": 0.5644003748893738,
|
| 21 |
+
"learning_rate": 0.0002,
|
| 22 |
+
"loss": 2.6912,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.026699893200427198,
|
| 27 |
+
"grad_norm": 0.5880550146102905,
|
| 28 |
+
"learning_rate": 0.00019999560489196446,
|
| 29 |
+
"loss": 2.2546,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0355998576005696,
|
| 34 |
+
"grad_norm": 0.7666159272193909,
|
| 35 |
+
"learning_rate": 0.00019998241995419736,
|
| 36 |
+
"loss": 2.0311,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0355998576005696,
|
| 41 |
+
"eval_loss": 1.959696650505066,
|
| 42 |
+
"eval_runtime": 50.7528,
|
| 43 |
+
"eval_samples_per_second": 93.197,
|
| 44 |
+
"eval_steps_per_second": 11.664,
|
| 45 |
+
"step": 200
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.044499822000711994,
|
| 49 |
+
"grad_norm": 0.92059725522995,
|
| 50 |
+
"learning_rate": 0.0001999604463456832,
|
| 51 |
+
"loss": 1.8378,
|
| 52 |
+
"step": 250
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.053399786400854396,
|
| 56 |
+
"grad_norm": 0.9128262400627136,
|
| 57 |
+
"learning_rate": 0.00019992968599794966,
|
| 58 |
+
"loss": 1.7162,
|
| 59 |
+
"step": 300
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.0622997508009968,
|
| 63 |
+
"grad_norm": 0.9777900576591492,
|
| 64 |
+
"learning_rate": 0.00019989014161489777,
|
| 65 |
+
"loss": 1.6289,
|
| 66 |
+
"step": 350
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0711997152011392,
|
| 70 |
+
"grad_norm": 0.8634700179100037,
|
| 71 |
+
"learning_rate": 0.00019984181667256418,
|
| 72 |
+
"loss": 1.5713,
|
| 73 |
+
"step": 400
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.0711997152011392,
|
| 77 |
+
"eval_loss": 1.5510551929473877,
|
| 78 |
+
"eval_runtime": 50.373,
|
| 79 |
+
"eval_samples_per_second": 93.9,
|
| 80 |
+
"eval_steps_per_second": 11.752,
|
| 81 |
+
"step": 400
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.0800996796012816,
|
| 85 |
+
"grad_norm": 1.018005609512329,
|
| 86 |
+
"learning_rate": 0.00019978471541881585,
|
| 87 |
+
"loss": 1.495,
|
| 88 |
+
"step": 450
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.08899964400142399,
|
| 92 |
+
"grad_norm": 0.9585720300674438,
|
| 93 |
+
"learning_rate": 0.0001997188428729763,
|
| 94 |
+
"loss": 1.4404,
|
| 95 |
+
"step": 500
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.09789960840156639,
|
| 99 |
+
"grad_norm": 0.9305699467658997,
|
| 100 |
+
"learning_rate": 0.00019964420482538464,
|
| 101 |
+
"loss": 1.4158,
|
| 102 |
+
"step": 550
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.10679957280170879,
|
| 106 |
+
"grad_norm": 1.0140578746795654,
|
| 107 |
+
"learning_rate": 0.00019956080783688652,
|
| 108 |
+
"loss": 1.4036,
|
| 109 |
+
"step": 600
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.10679957280170879,
|
| 113 |
+
"eval_loss": 1.3824176788330078,
|
| 114 |
+
"eval_runtime": 49.9585,
|
| 115 |
+
"eval_samples_per_second": 94.679,
|
| 116 |
+
"eval_steps_per_second": 11.85,
|
| 117 |
+
"step": 600
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.1156995372018512,
|
| 121 |
+
"grad_norm": 0.9531853199005127,
|
| 122 |
+
"learning_rate": 0.00019946865923825744,
|
| 123 |
+
"loss": 1.3574,
|
| 124 |
+
"step": 650
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.1245995016019936,
|
| 128 |
+
"grad_norm": 0.9434281587600708,
|
| 129 |
+
"learning_rate": 0.00019936776712955833,
|
| 130 |
+
"loss": 1.3519,
|
| 131 |
+
"step": 700
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.133499466002136,
|
| 135 |
+
"grad_norm": 0.9395330548286438,
|
| 136 |
+
"learning_rate": 0.00019925814037942353,
|
| 137 |
+
"loss": 1.2867,
|
| 138 |
+
"step": 750
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.1423994304022784,
|
| 142 |
+
"grad_norm": 0.8747947812080383,
|
| 143 |
+
"learning_rate": 0.00019913978862428128,
|
| 144 |
+
"loss": 1.276,
|
| 145 |
+
"step": 800
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.1423994304022784,
|
| 149 |
+
"eval_loss": 1.279874324798584,
|
| 150 |
+
"eval_runtime": 50.4803,
|
| 151 |
+
"eval_samples_per_second": 93.7,
|
| 152 |
+
"eval_steps_per_second": 11.727,
|
| 153 |
+
"step": 800
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.1512993948024208,
|
| 157 |
+
"grad_norm": 0.9898436665534973,
|
| 158 |
+
"learning_rate": 0.00019901272226750653,
|
| 159 |
+
"loss": 1.2522,
|
| 160 |
+
"step": 850
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.1601993592025632,
|
| 164 |
+
"grad_norm": 0.9309324026107788,
|
| 165 |
+
"learning_rate": 0.00019887695247850667,
|
| 166 |
+
"loss": 1.2622,
|
| 167 |
+
"step": 900
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.16909932360270558,
|
| 171 |
+
"grad_norm": 0.9160321950912476,
|
| 172 |
+
"learning_rate": 0.00019873249119173943,
|
| 173 |
+
"loss": 1.2217,
|
| 174 |
+
"step": 950
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.17799928800284798,
|
| 178 |
+
"grad_norm": 0.9408981800079346,
|
| 179 |
+
"learning_rate": 0.00019857935110566407,
|
| 180 |
+
"loss": 1.224,
|
| 181 |
+
"step": 1000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.17799928800284798,
|
| 185 |
+
"eval_loss": 1.2070544958114624,
|
| 186 |
+
"eval_runtime": 50.3603,
|
| 187 |
+
"eval_samples_per_second": 93.923,
|
| 188 |
+
"eval_steps_per_second": 11.755,
|
| 189 |
+
"step": 1000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.18689925240299038,
|
| 193 |
+
"grad_norm": 0.90412437915802,
|
| 194 |
+
"learning_rate": 0.00019841754568162507,
|
| 195 |
+
"loss": 1.1848,
|
| 196 |
+
"step": 1050
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.19579921680313278,
|
| 200 |
+
"grad_norm": 0.9094467759132385,
|
| 201 |
+
"learning_rate": 0.00019824708914266883,
|
| 202 |
+
"loss": 1.1649,
|
| 203 |
+
"step": 1100
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.20469918120327518,
|
| 207 |
+
"grad_norm": 0.9208333492279053,
|
| 208 |
+
"learning_rate": 0.00019806799647229345,
|
| 209 |
+
"loss": 1.1447,
|
| 210 |
+
"step": 1150
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.21359914560341758,
|
| 214 |
+
"grad_norm": 0.9170883893966675,
|
| 215 |
+
"learning_rate": 0.00019788028341313153,
|
| 216 |
+
"loss": 1.1734,
|
| 217 |
+
"step": 1200
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.21359914560341758,
|
| 221 |
+
"eval_loss": 1.158735752105713,
|
| 222 |
+
"eval_runtime": 50.4385,
|
| 223 |
+
"eval_samples_per_second": 93.778,
|
| 224 |
+
"eval_steps_per_second": 11.737,
|
| 225 |
+
"step": 1200
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.22249911000355999,
|
| 229 |
+
"grad_norm": 0.9168058633804321,
|
| 230 |
+
"learning_rate": 0.00019768396646556666,
|
| 231 |
+
"loss": 1.1433,
|
| 232 |
+
"step": 1250
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.2313990744037024,
|
| 236 |
+
"grad_norm": 0.9363458156585693,
|
| 237 |
+
"learning_rate": 0.00019747906288628266,
|
| 238 |
+
"loss": 1.1042,
|
| 239 |
+
"step": 1300
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.2402990388038448,
|
| 243 |
+
"grad_norm": 0.9948675036430359,
|
| 244 |
+
"learning_rate": 0.00019726559068674693,
|
| 245 |
+
"loss": 1.1074,
|
| 246 |
+
"step": 1350
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.2491990032039872,
|
| 250 |
+
"grad_norm": 0.9022513628005981,
|
| 251 |
+
"learning_rate": 0.00019704356863162702,
|
| 252 |
+
"loss": 1.1044,
|
| 253 |
+
"step": 1400
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.2491990032039872,
|
| 257 |
+
"eval_loss": 1.1200889348983765,
|
| 258 |
+
"eval_runtime": 50.4821,
|
| 259 |
+
"eval_samples_per_second": 93.697,
|
| 260 |
+
"eval_steps_per_second": 11.727,
|
| 261 |
+
"step": 1400
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.2580989676041296,
|
| 265 |
+
"grad_norm": 0.9583104848861694,
|
| 266 |
+
"learning_rate": 0.0001968130162371413,
|
| 267 |
+
"loss": 1.114,
|
| 268 |
+
"step": 1450
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.266998932004272,
|
| 272 |
+
"grad_norm": 1.0126705169677734,
|
| 273 |
+
"learning_rate": 0.00019657395376934344,
|
| 274 |
+
"loss": 1.0913,
|
| 275 |
+
"step": 1500
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.2758988964044144,
|
| 279 |
+
"grad_norm": 0.9019700288772583,
|
| 280 |
+
"learning_rate": 0.00019632640224234087,
|
| 281 |
+
"loss": 1.1114,
|
| 282 |
+
"step": 1550
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.2847988608045568,
|
| 286 |
+
"grad_norm": 0.9623306393623352,
|
| 287 |
+
"learning_rate": 0.00019607038341644772,
|
| 288 |
+
"loss": 1.0887,
|
| 289 |
+
"step": 1600
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.2847988608045568,
|
| 293 |
+
"eval_loss": 1.0876715183258057,
|
| 294 |
+
"eval_runtime": 50.0615,
|
| 295 |
+
"eval_samples_per_second": 94.484,
|
| 296 |
+
"eval_steps_per_second": 11.825,
|
| 297 |
+
"step": 1600
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.2936988252046992,
|
| 301 |
+
"grad_norm": 0.9978682994842529,
|
| 302 |
+
"learning_rate": 0.00019580591979627196,
|
| 303 |
+
"loss": 1.0646,
|
| 304 |
+
"step": 1650
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.3025987896048416,
|
| 308 |
+
"grad_norm": 0.9173294305801392,
|
| 309 |
+
"learning_rate": 0.00019553303462873723,
|
| 310 |
+
"loss": 1.0744,
|
| 311 |
+
"step": 1700
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.311498754004984,
|
| 315 |
+
"grad_norm": 0.8827286958694458,
|
| 316 |
+
"learning_rate": 0.00019525175190103941,
|
| 317 |
+
"loss": 1.0443,
|
| 318 |
+
"step": 1750
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.3203987184051264,
|
| 322 |
+
"grad_norm": 0.951848030090332,
|
| 323 |
+
"learning_rate": 0.000194962096338538,
|
| 324 |
+
"loss": 1.0641,
|
| 325 |
+
"step": 1800
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.3203987184051264,
|
| 329 |
+
"eval_loss": 1.0581151247024536,
|
| 330 |
+
"eval_runtime": 50.1826,
|
| 331 |
+
"eval_samples_per_second": 94.256,
|
| 332 |
+
"eval_steps_per_second": 11.797,
|
| 333 |
+
"step": 1800
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.3292986828052688,
|
| 337 |
+
"grad_norm": 0.8628537654876709,
|
| 338 |
+
"learning_rate": 0.0001946640934025828,
|
| 339 |
+
"loss": 1.044,
|
| 340 |
+
"step": 1850
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.33819864720541115,
|
| 344 |
+
"grad_norm": 0.9169789552688599,
|
| 345 |
+
"learning_rate": 0.00019435776928827583,
|
| 346 |
+
"loss": 1.0455,
|
| 347 |
+
"step": 1900
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.34709861160555355,
|
| 351 |
+
"grad_norm": 0.8911493420600891,
|
| 352 |
+
"learning_rate": 0.00019404315092216856,
|
| 353 |
+
"loss": 1.049,
|
| 354 |
+
"step": 1950
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.35599857600569595,
|
| 358 |
+
"grad_norm": 1.0085785388946533,
|
| 359 |
+
"learning_rate": 0.00019372026595989517,
|
| 360 |
+
"loss": 1.0416,
|
| 361 |
+
"step": 2000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.35599857600569595,
|
| 365 |
+
"eval_loss": 1.0355150699615479,
|
| 366 |
+
"eval_runtime": 49.9828,
|
| 367 |
+
"eval_samples_per_second": 94.633,
|
| 368 |
+
"eval_steps_per_second": 11.844,
|
| 369 |
+
"step": 2000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.36489854040583836,
|
| 373 |
+
"grad_norm": 0.9074106216430664,
|
| 374 |
+
"learning_rate": 0.0001933891427837416,
|
| 375 |
+
"loss": 1.0232,
|
| 376 |
+
"step": 2050
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.37379850480598076,
|
| 380 |
+
"grad_norm": 0.9280099272727966,
|
| 381 |
+
"learning_rate": 0.00019304981050015035,
|
| 382 |
+
"loss": 1.0294,
|
| 383 |
+
"step": 2100
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.38269846920612316,
|
| 387 |
+
"grad_norm": 0.9338967800140381,
|
| 388 |
+
"learning_rate": 0.00019270229893716243,
|
| 389 |
+
"loss": 1.0094,
|
| 390 |
+
"step": 2150
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.39159843360626556,
|
| 394 |
+
"grad_norm": 0.9141274094581604,
|
| 395 |
+
"learning_rate": 0.0001923466386417951,
|
| 396 |
+
"loss": 1.0234,
|
| 397 |
+
"step": 2200
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.39159843360626556,
|
| 401 |
+
"eval_loss": 1.017386794090271,
|
| 402 |
+
"eval_runtime": 50.0342,
|
| 403 |
+
"eval_samples_per_second": 94.535,
|
| 404 |
+
"eval_steps_per_second": 11.832,
|
| 405 |
+
"step": 2200
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.40049839800640796,
|
| 409 |
+
"grad_norm": 0.8689021468162537,
|
| 410 |
+
"learning_rate": 0.0001919828608773568,
|
| 411 |
+
"loss": 0.9944,
|
| 412 |
+
"step": 2250
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 0.40939836240655036,
|
| 416 |
+
"grad_norm": 1.0085052251815796,
|
| 417 |
+
"learning_rate": 0.00019161099762069904,
|
| 418 |
+
"loss": 0.9923,
|
| 419 |
+
"step": 2300
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.41829832680669277,
|
| 423 |
+
"grad_norm": 0.8979515433311462,
|
| 424 |
+
"learning_rate": 0.0001912310815594055,
|
| 425 |
+
"loss": 0.9986,
|
| 426 |
+
"step": 2350
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.42719829120683517,
|
| 430 |
+
"grad_norm": 0.8858252167701721,
|
| 431 |
+
"learning_rate": 0.00019084314608891899,
|
| 432 |
+
"loss": 0.9973,
|
| 433 |
+
"step": 2400
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.42719829120683517,
|
| 437 |
+
"eval_loss": 0.9972559213638306,
|
| 438 |
+
"eval_runtime": 49.8748,
|
| 439 |
+
"eval_samples_per_second": 94.837,
|
| 440 |
+
"eval_steps_per_second": 11.87,
|
| 441 |
+
"step": 2400
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.43609825560697757,
|
| 445 |
+
"grad_norm": 0.8094026446342468,
|
| 446 |
+
"learning_rate": 0.00019044722530960547,
|
| 447 |
+
"loss": 0.9786,
|
| 448 |
+
"step": 2450
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 0.44499822000711997,
|
| 452 |
+
"grad_norm": 0.9519333839416504,
|
| 453 |
+
"learning_rate": 0.00019004335402375696,
|
| 454 |
+
"loss": 0.9908,
|
| 455 |
+
"step": 2500
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 0.4538981844072624,
|
| 459 |
+
"grad_norm": 0.9498372673988342,
|
| 460 |
+
"learning_rate": 0.00018963156773253216,
|
| 461 |
+
"loss": 0.9748,
|
| 462 |
+
"step": 2550
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.4627981488074048,
|
| 466 |
+
"grad_norm": 0.8922374248504639,
|
| 467 |
+
"learning_rate": 0.00018921190263283575,
|
| 468 |
+
"loss": 0.9647,
|
| 469 |
+
"step": 2600
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 0.4627981488074048,
|
| 473 |
+
"eval_loss": 0.982623279094696,
|
| 474 |
+
"eval_runtime": 50.0541,
|
| 475 |
+
"eval_samples_per_second": 94.498,
|
| 476 |
+
"eval_steps_per_second": 11.827,
|
| 477 |
+
"step": 2600
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.4716981132075472,
|
| 481 |
+
"grad_norm": 0.883073091506958,
|
| 482 |
+
"learning_rate": 0.0001887843956141368,
|
| 483 |
+
"loss": 0.9845,
|
| 484 |
+
"step": 2650
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.4805980776076896,
|
| 488 |
+
"grad_norm": 0.8473624587059021,
|
| 489 |
+
"learning_rate": 0.00018834908425522596,
|
| 490 |
+
"loss": 0.9918,
|
| 491 |
+
"step": 2700
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.489498042007832,
|
| 495 |
+
"grad_norm": 0.902301013469696,
|
| 496 |
+
"learning_rate": 0.00018790600682091232,
|
| 497 |
+
"loss": 0.9891,
|
| 498 |
+
"step": 2750
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.4983980064079744,
|
| 502 |
+
"grad_norm": 0.915540337562561,
|
| 503 |
+
"learning_rate": 0.00018745520225865966,
|
| 504 |
+
"loss": 0.9596,
|
| 505 |
+
"step": 2800
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.4983980064079744,
|
| 509 |
+
"eval_loss": 0.971019446849823,
|
| 510 |
+
"eval_runtime": 50.1806,
|
| 511 |
+
"eval_samples_per_second": 94.26,
|
| 512 |
+
"eval_steps_per_second": 11.797,
|
| 513 |
+
"step": 2800
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.5072979708081168,
|
| 517 |
+
"grad_norm": 0.9331216216087341,
|
| 518 |
+
"learning_rate": 0.00018699671019516308,
|
| 519 |
+
"loss": 0.9719,
|
| 520 |
+
"step": 2850
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.5161979352082592,
|
| 524 |
+
"grad_norm": 0.9513929486274719,
|
| 525 |
+
"learning_rate": 0.00018653057093286562,
|
| 526 |
+
"loss": 0.9594,
|
| 527 |
+
"step": 2900
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.5250978996084016,
|
| 531 |
+
"grad_norm": 0.8859536051750183,
|
| 532 |
+
"learning_rate": 0.00018605682544641563,
|
| 533 |
+
"loss": 0.9504,
|
| 534 |
+
"step": 2950
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.533997864008544,
|
| 538 |
+
"grad_norm": 0.9426422715187073,
|
| 539 |
+
"learning_rate": 0.000185575515379065,
|
| 540 |
+
"loss": 0.9784,
|
| 541 |
+
"step": 3000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.533997864008544,
|
| 545 |
+
"eval_loss": 0.9557992815971375,
|
| 546 |
+
"eval_runtime": 50.0578,
|
| 547 |
+
"eval_samples_per_second": 94.491,
|
| 548 |
+
"eval_steps_per_second": 11.826,
|
| 549 |
+
"step": 3000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.5428978284086864,
|
| 553 |
+
"grad_norm": 0.903626561164856,
|
| 554 |
+
"learning_rate": 0.00018508668303900865,
|
| 555 |
+
"loss": 0.9536,
|
| 556 |
+
"step": 3050
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.5517977928088288,
|
| 560 |
+
"grad_norm": 0.9090939164161682,
|
| 561 |
+
"learning_rate": 0.0001845903713956654,
|
| 562 |
+
"loss": 0.9466,
|
| 563 |
+
"step": 3100
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.5606977572089712,
|
| 567 |
+
"grad_norm": 0.8735071420669556,
|
| 568 |
+
"learning_rate": 0.0001840866240759012,
|
| 569 |
+
"loss": 0.9496,
|
| 570 |
+
"step": 3150
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.5695977216091136,
|
| 574 |
+
"grad_norm": 0.9689593315124512,
|
| 575 |
+
"learning_rate": 0.00018357548536019388,
|
| 576 |
+
"loss": 0.9651,
|
| 577 |
+
"step": 3200
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.5695977216091136,
|
| 581 |
+
"eval_loss": 0.9453820586204529,
|
| 582 |
+
"eval_runtime": 48.7003,
|
| 583 |
+
"eval_samples_per_second": 97.125,
|
| 584 |
+
"eval_steps_per_second": 12.156,
|
| 585 |
+
"step": 3200
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.578497686009256,
|
| 589 |
+
"grad_norm": 0.968047022819519,
|
| 590 |
+
"learning_rate": 0.00018305700017874093,
|
| 591 |
+
"loss": 0.9538,
|
| 592 |
+
"step": 3250
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.5873976504093984,
|
| 596 |
+
"grad_norm": 0.9578290581703186,
|
| 597 |
+
"learning_rate": 0.00018253121410751014,
|
| 598 |
+
"loss": 0.9364,
|
| 599 |
+
"step": 3300
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.5962976148095408,
|
| 603 |
+
"grad_norm": 0.8788236975669861,
|
| 604 |
+
"learning_rate": 0.0001819981733642332,
|
| 605 |
+
"loss": 0.9253,
|
| 606 |
+
"step": 3350
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.6051975792096832,
|
| 610 |
+
"grad_norm": 0.9758558869361877,
|
| 611 |
+
"learning_rate": 0.00018145792480434323,
|
| 612 |
+
"loss": 0.9296,
|
| 613 |
+
"step": 3400
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.6051975792096832,
|
| 617 |
+
"eval_loss": 0.9375544786453247,
|
| 618 |
+
"eval_runtime": 48.8366,
|
| 619 |
+
"eval_samples_per_second": 96.854,
|
| 620 |
+
"eval_steps_per_second": 12.122,
|
| 621 |
+
"step": 3400
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.6140975436098256,
|
| 625 |
+
"grad_norm": 0.8886916637420654,
|
| 626 |
+
"learning_rate": 0.00018091051591685595,
|
| 627 |
+
"loss": 0.9159,
|
| 628 |
+
"step": 3450
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 0.622997508009968,
|
| 632 |
+
"grad_norm": 0.8160135746002197,
|
| 633 |
+
"learning_rate": 0.00018035599482019537,
|
| 634 |
+
"loss": 0.9225,
|
| 635 |
+
"step": 3500
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 0.6318974724101104,
|
| 639 |
+
"grad_norm": 0.8261973261833191,
|
| 640 |
+
"learning_rate": 0.00017979441025796401,
|
| 641 |
+
"loss": 0.9201,
|
| 642 |
+
"step": 3550
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.6407974368102528,
|
| 646 |
+
"grad_norm": 0.8609347343444824,
|
| 647 |
+
"learning_rate": 0.0001792258115946584,
|
| 648 |
+
"loss": 0.9175,
|
| 649 |
+
"step": 3600
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.6407974368102528,
|
| 653 |
+
"eval_loss": 0.9243019819259644,
|
| 654 |
+
"eval_runtime": 48.6128,
|
| 655 |
+
"eval_samples_per_second": 97.299,
|
| 656 |
+
"eval_steps_per_second": 12.178,
|
| 657 |
+
"step": 3600
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.6496974012103952,
|
| 661 |
+
"grad_norm": 0.8764597177505493,
|
| 662 |
+
"learning_rate": 0.00017865024881132954,
|
| 663 |
+
"loss": 0.9137,
|
| 664 |
+
"step": 3650
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.6585973656105376,
|
| 668 |
+
"grad_norm": 0.9511114358901978,
|
| 669 |
+
"learning_rate": 0.0001780677725011897,
|
| 670 |
+
"loss": 0.9204,
|
| 671 |
+
"step": 3700
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.66749733001068,
|
| 675 |
+
"grad_norm": 0.84784996509552,
|
| 676 |
+
"learning_rate": 0.00017747843386516516,
|
| 677 |
+
"loss": 0.9113,
|
| 678 |
+
"step": 3750
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.6763972944108223,
|
| 682 |
+
"grad_norm": 0.9484674334526062,
|
| 683 |
+
"learning_rate": 0.0001768822847073954,
|
| 684 |
+
"loss": 0.8995,
|
| 685 |
+
"step": 3800
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.6763972944108223,
|
| 689 |
+
"eval_loss": 0.9173856973648071,
|
| 690 |
+
"eval_runtime": 48.6184,
|
| 691 |
+
"eval_samples_per_second": 97.288,
|
| 692 |
+
"eval_steps_per_second": 12.176,
|
| 693 |
+
"step": 3800
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.6852972588109647,
|
| 697 |
+
"grad_norm": 0.8271557688713074,
|
| 698 |
+
"learning_rate": 0.00017627937743067945,
|
| 699 |
+
"loss": 0.898,
|
| 700 |
+
"step": 3850
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 0.6941972232111071,
|
| 704 |
+
"grad_norm": 0.8715105056762695,
|
| 705 |
+
"learning_rate": 0.0001756697650318697,
|
| 706 |
+
"loss": 0.9005,
|
| 707 |
+
"step": 3900
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 0.7030971876112495,
|
| 711 |
+
"grad_norm": 0.922903835773468,
|
| 712 |
+
"learning_rate": 0.00017505350109721322,
|
| 713 |
+
"loss": 0.9128,
|
| 714 |
+
"step": 3950
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.7119971520113919,
|
| 718 |
+
"grad_norm": 0.8187894225120544,
|
| 719 |
+
"learning_rate": 0.00017443063979764135,
|
| 720 |
+
"loss": 0.9054,
|
| 721 |
+
"step": 4000
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 0.7119971520113919,
|
| 725 |
+
"eval_loss": 0.908061683177948,
|
| 726 |
+
"eval_runtime": 48.7575,
|
| 727 |
+
"eval_samples_per_second": 97.011,
|
| 728 |
+
"eval_steps_per_second": 12.142,
|
| 729 |
+
"step": 4000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.7208971164115343,
|
| 733 |
+
"grad_norm": 0.949248194694519,
|
| 734 |
+
"learning_rate": 0.0001738012358840082,
|
| 735 |
+
"loss": 0.8977,
|
| 736 |
+
"step": 4050
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.7297970808116767,
|
| 740 |
+
"grad_norm": 0.8386827111244202,
|
| 741 |
+
"learning_rate": 0.00017316534468227776,
|
| 742 |
+
"loss": 0.9098,
|
| 743 |
+
"step": 4100
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.7386970452118191,
|
| 747 |
+
"grad_norm": 0.8928548097610474,
|
| 748 |
+
"learning_rate": 0.00017252302208866057,
|
| 749 |
+
"loss": 0.9104,
|
| 750 |
+
"step": 4150
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 0.7475970096119615,
|
| 754 |
+
"grad_norm": 0.9291919469833374,
|
| 755 |
+
"learning_rate": 0.00017187432456470053,
|
| 756 |
+
"loss": 0.8839,
|
| 757 |
+
"step": 4200
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.7475970096119615,
|
| 761 |
+
"eval_loss": 0.9017413854598999,
|
| 762 |
+
"eval_runtime": 48.6601,
|
| 763 |
+
"eval_samples_per_second": 97.205,
|
| 764 |
+
"eval_steps_per_second": 12.166,
|
| 765 |
+
"step": 4200
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.7564969740121039,
|
| 769 |
+
"grad_norm": 0.8346033692359924,
|
| 770 |
+
"learning_rate": 0.00017121930913231164,
|
| 771 |
+
"loss": 0.9197,
|
| 772 |
+
"step": 4250
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.7653969384122463,
|
| 776 |
+
"grad_norm": 0.9475340247154236,
|
| 777 |
+
"learning_rate": 0.0001705580333687657,
|
| 778 |
+
"loss": 0.9047,
|
| 779 |
+
"step": 4300
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.7742969028123887,
|
| 783 |
+
"grad_norm": 0.8356530666351318,
|
| 784 |
+
"learning_rate": 0.00016989055540163114,
|
| 785 |
+
"loss": 0.884,
|
| 786 |
+
"step": 4350
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.7831968672125311,
|
| 790 |
+
"grad_norm": 0.8256769180297852,
|
| 791 |
+
"learning_rate": 0.00016921693390366352,
|
| 792 |
+
"loss": 0.8972,
|
| 793 |
+
"step": 4400
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.7831968672125311,
|
| 797 |
+
"eval_loss": 0.8938359022140503,
|
| 798 |
+
"eval_runtime": 49.1385,
|
| 799 |
+
"eval_samples_per_second": 96.258,
|
| 800 |
+
"eval_steps_per_second": 12.048,
|
| 801 |
+
"step": 4400
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.7920968316126735,
|
| 805 |
+
"grad_norm": 0.8861626982688904,
|
| 806 |
+
"learning_rate": 0.000168537228087648,
|
| 807 |
+
"loss": 0.9027,
|
| 808 |
+
"step": 4450
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.8009967960128159,
|
| 812 |
+
"grad_norm": 0.8959323763847351,
|
| 813 |
+
"learning_rate": 0.00016785149770119441,
|
| 814 |
+
"loss": 0.8906,
|
| 815 |
+
"step": 4500
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.8098967604129583,
|
| 819 |
+
"grad_norm": 0.9219085574150085,
|
| 820 |
+
"learning_rate": 0.00016715980302148546,
|
| 821 |
+
"loss": 0.8815,
|
| 822 |
+
"step": 4550
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.8187967248131007,
|
| 826 |
+
"grad_norm": 0.861101508140564,
|
| 827 |
+
"learning_rate": 0.00016646220484997802,
|
| 828 |
+
"loss": 0.878,
|
| 829 |
+
"step": 4600
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.8187967248131007,
|
| 833 |
+
"eval_loss": 0.8885288238525391,
|
| 834 |
+
"eval_runtime": 48.686,
|
| 835 |
+
"eval_samples_per_second": 97.153,
|
| 836 |
+
"eval_steps_per_second": 12.16,
|
| 837 |
+
"step": 4600
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.8276966892132431,
|
| 841 |
+
"grad_norm": 0.9087807536125183,
|
| 842 |
+
"learning_rate": 0.0001657587645070587,
|
| 843 |
+
"loss": 0.8865,
|
| 844 |
+
"step": 4650
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 0.8365966536133855,
|
| 848 |
+
"grad_norm": 0.8985960483551025,
|
| 849 |
+
"learning_rate": 0.0001650495438266535,
|
| 850 |
+
"loss": 0.8775,
|
| 851 |
+
"step": 4700
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.8454966180135279,
|
| 855 |
+
"grad_norm": 0.7576650381088257,
|
| 856 |
+
"learning_rate": 0.00016433460515079276,
|
| 857 |
+
"loss": 0.8663,
|
| 858 |
+
"step": 4750
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.8543965824136703,
|
| 862 |
+
"grad_norm": 0.8818519711494446,
|
| 863 |
+
"learning_rate": 0.00016361401132413073,
|
| 864 |
+
"loss": 0.8739,
|
| 865 |
+
"step": 4800
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.8543965824136703,
|
| 869 |
+
"eval_loss": 0.8833577632904053,
|
| 870 |
+
"eval_runtime": 51.6423,
|
| 871 |
+
"eval_samples_per_second": 91.592,
|
| 872 |
+
"eval_steps_per_second": 11.463,
|
| 873 |
+
"step": 4800
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.8632965468138127,
|
| 877 |
+
"grad_norm": 0.9395806789398193,
|
| 878 |
+
"learning_rate": 0.00016288782568842186,
|
| 879 |
+
"loss": 0.8682,
|
| 880 |
+
"step": 4850
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.8721965112139551,
|
| 884 |
+
"grad_norm": 0.8389623165130615,
|
| 885 |
+
"learning_rate": 0.00016215611207695261,
|
| 886 |
+
"loss": 0.8699,
|
| 887 |
+
"step": 4900
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.8810964756140975,
|
| 891 |
+
"grad_norm": 0.900161623954773,
|
| 892 |
+
"learning_rate": 0.00016141893480893038,
|
| 893 |
+
"loss": 0.8719,
|
| 894 |
+
"step": 4950
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.8899964400142399,
|
| 898 |
+
"grad_norm": 0.8302805423736572,
|
| 899 |
+
"learning_rate": 0.00016067635868382993,
|
| 900 |
+
"loss": 0.8694,
|
| 901 |
+
"step": 5000
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.8899964400142399,
|
| 905 |
+
"eval_loss": 0.8769263029098511,
|
| 906 |
+
"eval_runtime": 50.6149,
|
| 907 |
+
"eval_samples_per_second": 93.451,
|
| 908 |
+
"eval_steps_per_second": 11.696,
|
| 909 |
+
"step": 5000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.8988964044143823,
|
| 913 |
+
"grad_norm": 0.8254596590995789,
|
| 914 |
+
"learning_rate": 0.0001599284489756971,
|
| 915 |
+
"loss": 0.8715,
|
| 916 |
+
"step": 5050
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 0.9077963688145247,
|
| 920 |
+
"grad_norm": 0.8947657346725464,
|
| 921 |
+
"learning_rate": 0.00015917527142741123,
|
| 922 |
+
"loss": 0.869,
|
| 923 |
+
"step": 5100
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 0.9166963332146671,
|
| 927 |
+
"grad_norm": 0.8894372582435608,
|
| 928 |
+
"learning_rate": 0.0001584168922449063,
|
| 929 |
+
"loss": 0.8696,
|
| 930 |
+
"step": 5150
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 0.9255962976148095,
|
| 934 |
+
"grad_norm": 0.8596253395080566,
|
| 935 |
+
"learning_rate": 0.00015765337809135104,
|
| 936 |
+
"loss": 0.8484,
|
| 937 |
+
"step": 5200
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 0.9255962976148095,
|
| 941 |
+
"eval_loss": 0.8699991106987,
|
| 942 |
+
"eval_runtime": 49.0174,
|
| 943 |
+
"eval_samples_per_second": 96.496,
|
| 944 |
+
"eval_steps_per_second": 12.077,
|
| 945 |
+
"step": 5200
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.934496262014952,
|
| 949 |
+
"grad_norm": 0.8539134860038757,
|
| 950 |
+
"learning_rate": 0.00015688479608128928,
|
| 951 |
+
"loss": 0.8624,
|
| 952 |
+
"step": 5250
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 0.9433962264150944,
|
| 956 |
+
"grad_norm": 0.8571669459342957,
|
| 957 |
+
"learning_rate": 0.00015611121377474035,
|
| 958 |
+
"loss": 0.8728,
|
| 959 |
+
"step": 5300
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 0.9522961908152368,
|
| 963 |
+
"grad_norm": 0.757992684841156,
|
| 964 |
+
"learning_rate": 0.00015533269917126057,
|
| 965 |
+
"loss": 0.8614,
|
| 966 |
+
"step": 5350
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 0.9611961552153792,
|
| 970 |
+
"grad_norm": 0.8510696887969971,
|
| 971 |
+
"learning_rate": 0.00015454932070396566,
|
| 972 |
+
"loss": 0.858,
|
| 973 |
+
"step": 5400
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 0.9611961552153792,
|
| 977 |
+
"eval_loss": 0.8654290437698364,
|
| 978 |
+
"eval_runtime": 49.1261,
|
| 979 |
+
"eval_samples_per_second": 96.283,
|
| 980 |
+
"eval_steps_per_second": 12.051,
|
| 981 |
+
"step": 5400
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.9700961196155216,
|
| 985 |
+
"grad_norm": 0.8071936964988708,
|
| 986 |
+
"learning_rate": 0.0001537611472335156,
|
| 987 |
+
"loss": 0.8538,
|
| 988 |
+
"step": 5450
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 0.978996084015664,
|
| 992 |
+
"grad_norm": 0.9007853269577026,
|
| 993 |
+
"learning_rate": 0.00015296824804206138,
|
| 994 |
+
"loss": 0.8691,
|
| 995 |
+
"step": 5500
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.9878960484158064,
|
| 999 |
+
"grad_norm": 0.8500368595123291,
|
| 1000 |
+
"learning_rate": 0.00015217069282715524,
|
| 1001 |
+
"loss": 0.837,
|
| 1002 |
+
"step": 5550
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.9967960128159488,
|
| 1006 |
+
"grad_norm": 0.8103012442588806,
|
| 1007 |
+
"learning_rate": 0.00015136855169562381,
|
| 1008 |
+
"loss": 0.8667,
|
| 1009 |
+
"step": 5600
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.9967960128159488,
|
| 1013 |
+
"eval_loss": 0.860339343547821,
|
| 1014 |
+
"eval_runtime": 48.9008,
|
| 1015 |
+
"eval_samples_per_second": 96.727,
|
| 1016 |
+
"eval_steps_per_second": 12.106,
|
| 1017 |
+
"step": 5600
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.0056959772160912,
|
| 1021 |
+
"grad_norm": 0.8337941765785217,
|
| 1022 |
+
"learning_rate": 0.00015056189515740576,
|
| 1023 |
+
"loss": 0.8551,
|
| 1024 |
+
"step": 5650
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.0145959416162336,
|
| 1028 |
+
"grad_norm": 0.878975510597229,
|
| 1029 |
+
"learning_rate": 0.00014975079411935373,
|
| 1030 |
+
"loss": 0.8412,
|
| 1031 |
+
"step": 5700
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.023495906016376,
|
| 1035 |
+
"grad_norm": 0.8881447315216064,
|
| 1036 |
+
"learning_rate": 0.00014893531987900157,
|
| 1037 |
+
"loss": 0.8407,
|
| 1038 |
+
"step": 5750
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 1.0323958704165184,
|
| 1042 |
+
"grad_norm": 0.92270427942276,
|
| 1043 |
+
"learning_rate": 0.00014811554411829696,
|
| 1044 |
+
"loss": 0.8312,
|
| 1045 |
+
"step": 5800
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 1.0323958704165184,
|
| 1049 |
+
"eval_loss": 0.8563101887702942,
|
| 1050 |
+
"eval_runtime": 48.9121,
|
| 1051 |
+
"eval_samples_per_second": 96.704,
|
| 1052 |
+
"eval_steps_per_second": 12.103,
|
| 1053 |
+
"step": 5800
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.0412958348166608,
|
| 1057 |
+
"grad_norm": 0.872711718082428,
|
| 1058 |
+
"learning_rate": 0.0001472915388973006,
|
| 1059 |
+
"loss": 0.8376,
|
| 1060 |
+
"step": 5850
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.0501957992168032,
|
| 1064 |
+
"grad_norm": 0.8568659424781799,
|
| 1065 |
+
"learning_rate": 0.0001464633766478518,
|
| 1066 |
+
"loss": 0.8552,
|
| 1067 |
+
"step": 5900
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.0590957636169456,
|
| 1071 |
+
"grad_norm": 0.8813678026199341,
|
| 1072 |
+
"learning_rate": 0.00014563113016720177,
|
| 1073 |
+
"loss": 0.8419,
|
| 1074 |
+
"step": 5950
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.067995728017088,
|
| 1078 |
+
"grad_norm": 0.8406676054000854,
|
| 1079 |
+
"learning_rate": 0.00014479487261161435,
|
| 1080 |
+
"loss": 0.8486,
|
| 1081 |
+
"step": 6000
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.067995728017088,
|
| 1085 |
+
"eval_loss": 0.8522692322731018,
|
| 1086 |
+
"eval_runtime": 48.7968,
|
| 1087 |
+
"eval_samples_per_second": 96.933,
|
| 1088 |
+
"eval_steps_per_second": 12.132,
|
| 1089 |
+
"step": 6000
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 1.0768956924172304,
|
| 1093 |
+
"grad_norm": 0.8959100246429443,
|
| 1094 |
+
"learning_rate": 0.00014395467748993564,
|
| 1095 |
+
"loss": 0.8336,
|
| 1096 |
+
"step": 6050
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 1.0857956568173728,
|
| 1100 |
+
"grad_norm": 1.0282095670700073,
|
| 1101 |
+
"learning_rate": 0.0001431106186571322,
|
| 1102 |
+
"loss": 0.8393,
|
| 1103 |
+
"step": 6100
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 1.0946956212175152,
|
| 1107 |
+
"grad_norm": 0.9017136096954346,
|
| 1108 |
+
"learning_rate": 0.00014226277030779922,
|
| 1109 |
+
"loss": 0.8475,
|
| 1110 |
+
"step": 6150
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 1.1035955856176576,
|
| 1114 |
+
"grad_norm": 0.7802528738975525,
|
| 1115 |
+
"learning_rate": 0.0001414112069696386,
|
| 1116 |
+
"loss": 0.8557,
|
| 1117 |
+
"step": 6200
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 1.1035955856176576,
|
| 1121 |
+
"eval_loss": 0.8481252789497375,
|
| 1122 |
+
"eval_runtime": 48.7795,
|
| 1123 |
+
"eval_samples_per_second": 96.967,
|
| 1124 |
+
"eval_steps_per_second": 12.136,
|
| 1125 |
+
"step": 6200
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 1.1124955500178,
|
| 1129 |
+
"grad_norm": 0.8971177339553833,
|
| 1130 |
+
"learning_rate": 0.00014055600349690767,
|
| 1131 |
+
"loss": 0.8364,
|
| 1132 |
+
"step": 6250
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 1.1213955144179424,
|
| 1136 |
+
"grad_norm": 0.8869891166687012,
|
| 1137 |
+
"learning_rate": 0.00013969723506383958,
|
| 1138 |
+
"loss": 0.8464,
|
| 1139 |
+
"step": 6300
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 1.1302954788180848,
|
| 1143 |
+
"grad_norm": 0.8413082957267761,
|
| 1144 |
+
"learning_rate": 0.00013883497715803516,
|
| 1145 |
+
"loss": 0.8297,
|
| 1146 |
+
"step": 6350
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 1.1391954432182272,
|
| 1150 |
+
"grad_norm": 0.8297756314277649,
|
| 1151 |
+
"learning_rate": 0.00013796930557382738,
|
| 1152 |
+
"loss": 0.841,
|
| 1153 |
+
"step": 6400
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 1.1391954432182272,
|
| 1157 |
+
"eval_loss": 0.8438305258750916,
|
| 1158 |
+
"eval_runtime": 49.0895,
|
| 1159 |
+
"eval_samples_per_second": 96.355,
|
| 1160 |
+
"eval_steps_per_second": 12.06,
|
| 1161 |
+
"step": 6400
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 1.1480954076183696,
|
| 1165 |
+
"grad_norm": 0.8817351460456848,
|
| 1166 |
+
"learning_rate": 0.000137100296405619,
|
| 1167 |
+
"loss": 0.842,
|
| 1168 |
+
"step": 6450
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 1.156995372018512,
|
| 1172 |
+
"grad_norm": 0.9958394169807434,
|
| 1173 |
+
"learning_rate": 0.00013622802604119355,
|
| 1174 |
+
"loss": 0.8586,
|
| 1175 |
+
"step": 6500
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 1.1658953364186544,
|
| 1179 |
+
"grad_norm": 0.8427689671516418,
|
| 1180 |
+
"learning_rate": 0.0001353525711550008,
|
| 1181 |
+
"loss": 0.8261,
|
| 1182 |
+
"step": 6550
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 1.1747953008187968,
|
| 1186 |
+
"grad_norm": 0.82032710313797,
|
| 1187 |
+
"learning_rate": 0.00013447400870141685,
|
| 1188 |
+
"loss": 0.8296,
|
| 1189 |
+
"step": 6600
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 1.1747953008187968,
|
| 1193 |
+
"eval_loss": 0.8405965566635132,
|
| 1194 |
+
"eval_runtime": 48.6251,
|
| 1195 |
+
"eval_samples_per_second": 97.275,
|
| 1196 |
+
"eval_steps_per_second": 12.175,
|
| 1197 |
+
"step": 6600
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 1.1836952652189392,
|
| 1201 |
+
"grad_norm": 0.8386394381523132,
|
| 1202 |
+
"learning_rate": 0.0001335924159079797,
|
| 1203 |
+
"loss": 0.8133,
|
| 1204 |
+
"step": 6650
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 1.1925952296190816,
|
| 1208 |
+
"grad_norm": 0.9160700440406799,
|
| 1209 |
+
"learning_rate": 0.0001327078702686007,
|
| 1210 |
+
"loss": 0.829,
|
| 1211 |
+
"step": 6700
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 1.201495194019224,
|
| 1215 |
+
"grad_norm": 0.9139155745506287,
|
| 1216 |
+
"learning_rate": 0.00013182044953675287,
|
| 1217 |
+
"loss": 0.828,
|
| 1218 |
+
"step": 6750
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 1.2103951584193664,
|
| 1222 |
+
"grad_norm": 0.8476113080978394,
|
| 1223 |
+
"learning_rate": 0.000130930231718636,
|
| 1224 |
+
"loss": 0.8292,
|
| 1225 |
+
"step": 6800
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 1.2103951584193664,
|
| 1229 |
+
"eval_loss": 0.8365323543548584,
|
| 1230 |
+
"eval_runtime": 48.9177,
|
| 1231 |
+
"eval_samples_per_second": 96.693,
|
| 1232 |
+
"eval_steps_per_second": 12.102,
|
| 1233 |
+
"step": 6800
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 1.2192951228195088,
|
| 1237 |
+
"grad_norm": 0.871322512626648,
|
| 1238 |
+
"learning_rate": 0.00013003729506631974,
|
| 1239 |
+
"loss": 0.832,
|
| 1240 |
+
"step": 6850
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 1.2281950872196512,
|
| 1244 |
+
"grad_norm": 0.8624529242515564,
|
| 1245 |
+
"learning_rate": 0.00012914171807086526,
|
| 1246 |
+
"loss": 0.8256,
|
| 1247 |
+
"step": 6900
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 1.2370950516197936,
|
| 1251 |
+
"grad_norm": 0.8633238673210144,
|
| 1252 |
+
"learning_rate": 0.00012824357945542554,
|
| 1253 |
+
"loss": 0.8172,
|
| 1254 |
+
"step": 6950
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 1.245995016019936,
|
| 1258 |
+
"grad_norm": 0.8030803799629211,
|
| 1259 |
+
"learning_rate": 0.00012734295816832549,
|
| 1260 |
+
"loss": 0.815,
|
| 1261 |
+
"step": 7000
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 1.245995016019936,
|
| 1265 |
+
"eval_loss": 0.8333725333213806,
|
| 1266 |
+
"eval_runtime": 48.6698,
|
| 1267 |
+
"eval_samples_per_second": 97.185,
|
| 1268 |
+
"eval_steps_per_second": 12.164,
|
| 1269 |
+
"step": 7000
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.2548949804200782,
|
| 1273 |
+
"grad_norm": 0.8886685967445374,
|
| 1274 |
+
"learning_rate": 0.00012643993337612221,
|
| 1275 |
+
"loss": 0.809,
|
| 1276 |
+
"step": 7050
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.2637949448202206,
|
| 1280 |
+
"grad_norm": 0.9337815642356873,
|
| 1281 |
+
"learning_rate": 0.00012553458445664612,
|
| 1282 |
+
"loss": 0.8358,
|
| 1283 |
+
"step": 7100
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.272694909220363,
|
| 1287 |
+
"grad_norm": 0.8476386666297913,
|
| 1288 |
+
"learning_rate": 0.00012462699099202346,
|
| 1289 |
+
"loss": 0.8163,
|
| 1290 |
+
"step": 7150
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.2815948736205054,
|
| 1294 |
+
"grad_norm": 0.83839350938797,
|
| 1295 |
+
"learning_rate": 0.00012371723276168077,
|
| 1296 |
+
"loss": 0.8318,
|
| 1297 |
+
"step": 7200
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.2815948736205054,
|
| 1301 |
+
"eval_loss": 0.8303682804107666,
|
| 1302 |
+
"eval_runtime": 48.6531,
|
| 1303 |
+
"eval_samples_per_second": 97.219,
|
| 1304 |
+
"eval_steps_per_second": 12.168,
|
| 1305 |
+
"step": 7200
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.2904948380206478,
|
| 1309 |
+
"grad_norm": 0.8890513181686401,
|
| 1310 |
+
"learning_rate": 0.00012280538973533228,
|
| 1311 |
+
"loss": 0.8407,
|
| 1312 |
+
"step": 7250
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.2993948024207902,
|
| 1316 |
+
"grad_norm": 0.8872727751731873,
|
| 1317 |
+
"learning_rate": 0.0001218915420659502,
|
| 1318 |
+
"loss": 0.8274,
|
| 1319 |
+
"step": 7300
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.3082947668209326,
|
| 1323 |
+
"grad_norm": 0.8165082335472107,
|
| 1324 |
+
"learning_rate": 0.0001209757700827192,
|
| 1325 |
+
"loss": 0.8047,
|
| 1326 |
+
"step": 7350
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.317194731221075,
|
| 1330 |
+
"grad_norm": 0.9536371231079102,
|
| 1331 |
+
"learning_rate": 0.00012005815428397541,
|
| 1332 |
+
"loss": 0.8267,
|
| 1333 |
+
"step": 7400
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.317194731221075,
|
| 1337 |
+
"eval_loss": 0.8276388645172119,
|
| 1338 |
+
"eval_runtime": 48.6799,
|
| 1339 |
+
"eval_samples_per_second": 97.165,
|
| 1340 |
+
"eval_steps_per_second": 12.161,
|
| 1341 |
+
"step": 7400
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 1.3260946956212174,
|
| 1345 |
+
"grad_norm": 0.9560860395431519,
|
| 1346 |
+
"learning_rate": 0.00011913877533013016,
|
| 1347 |
+
"loss": 0.8209,
|
| 1348 |
+
"step": 7450
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 1.3349946600213598,
|
| 1352 |
+
"grad_norm": 0.8105106353759766,
|
| 1353 |
+
"learning_rate": 0.00011821771403658006,
|
| 1354 |
+
"loss": 0.8091,
|
| 1355 |
+
"step": 7500
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 1.3438946244215022,
|
| 1359 |
+
"grad_norm": 0.8375486731529236,
|
| 1360 |
+
"learning_rate": 0.0001172950513666029,
|
| 1361 |
+
"loss": 0.831,
|
| 1362 |
+
"step": 7550
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 1.3527945888216446,
|
| 1366 |
+
"grad_norm": 0.8491958379745483,
|
| 1367 |
+
"learning_rate": 0.00011637086842424103,
|
| 1368 |
+
"loss": 0.8289,
|
| 1369 |
+
"step": 7600
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 1.3527945888216446,
|
| 1373 |
+
"eval_loss": 0.8254909515380859,
|
| 1374 |
+
"eval_runtime": 48.6549,
|
| 1375 |
+
"eval_samples_per_second": 97.215,
|
| 1376 |
+
"eval_steps_per_second": 12.167,
|
| 1377 |
+
"step": 7600
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 1.361694553221787,
|
| 1381 |
+
"grad_norm": 0.8541810512542725,
|
| 1382 |
+
"learning_rate": 0.00011544524644717196,
|
| 1383 |
+
"loss": 0.8207,
|
| 1384 |
+
"step": 7650
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 1.3705945176219294,
|
| 1388 |
+
"grad_norm": 0.8698812127113342,
|
| 1389 |
+
"learning_rate": 0.00011451826679956747,
|
| 1390 |
+
"loss": 0.8106,
|
| 1391 |
+
"step": 7700
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 1.3794944820220718,
|
| 1395 |
+
"grad_norm": 0.8412224650382996,
|
| 1396 |
+
"learning_rate": 0.00011359001096494155,
|
| 1397 |
+
"loss": 0.8204,
|
| 1398 |
+
"step": 7750
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 1.3883944464222142,
|
| 1402 |
+
"grad_norm": 1.045037865638733,
|
| 1403 |
+
"learning_rate": 0.00011266056053898773,
|
| 1404 |
+
"loss": 0.8317,
|
| 1405 |
+
"step": 7800
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 1.3883944464222142,
|
| 1409 |
+
"eval_loss": 0.8221540451049805,
|
| 1410 |
+
"eval_runtime": 48.8261,
|
| 1411 |
+
"eval_samples_per_second": 96.874,
|
| 1412 |
+
"eval_steps_per_second": 12.125,
|
| 1413 |
+
"step": 7800
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 1.3972944108223566,
|
| 1417 |
+
"grad_norm": 0.8666774034500122,
|
| 1418 |
+
"learning_rate": 0.00011172999722240669,
|
| 1419 |
+
"loss": 0.8155,
|
| 1420 |
+
"step": 7850
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 1.406194375222499,
|
| 1424 |
+
"grad_norm": 0.8055330514907837,
|
| 1425 |
+
"learning_rate": 0.00011079840281372468,
|
| 1426 |
+
"loss": 0.8042,
|
| 1427 |
+
"step": 7900
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 1.4150943396226414,
|
| 1431 |
+
"grad_norm": 0.9628292322158813,
|
| 1432 |
+
"learning_rate": 0.00010986585920210312,
|
| 1433 |
+
"loss": 0.8137,
|
| 1434 |
+
"step": 7950
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 1.4239943040227838,
|
| 1438 |
+
"grad_norm": 0.9325138330459595,
|
| 1439 |
+
"learning_rate": 0.00010893244836014043,
|
| 1440 |
+
"loss": 0.8136,
|
| 1441 |
+
"step": 8000
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 1.4239943040227838,
|
| 1445 |
+
"eval_loss": 0.8195136785507202,
|
| 1446 |
+
"eval_runtime": 48.7784,
|
| 1447 |
+
"eval_samples_per_second": 96.969,
|
| 1448 |
+
"eval_steps_per_second": 12.137,
|
| 1449 |
+
"step": 8000
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 1.4328942684229262,
|
| 1453 |
+
"grad_norm": 0.8651353120803833,
|
| 1454 |
+
"learning_rate": 0.00010799825233666645,
|
| 1455 |
+
"loss": 0.8152,
|
| 1456 |
+
"step": 8050
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 1.4417942328230686,
|
| 1460 |
+
"grad_norm": 0.9232978820800781,
|
| 1461 |
+
"learning_rate": 0.00010706335324953016,
|
| 1462 |
+
"loss": 0.7997,
|
| 1463 |
+
"step": 8100
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 1.450694197223211,
|
| 1467 |
+
"grad_norm": 0.9491880536079407,
|
| 1468 |
+
"learning_rate": 0.00010612783327838138,
|
| 1469 |
+
"loss": 0.8062,
|
| 1470 |
+
"step": 8150
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 1.4595941616233534,
|
| 1474 |
+
"grad_norm": 0.8898776769638062,
|
| 1475 |
+
"learning_rate": 0.00010519177465744696,
|
| 1476 |
+
"loss": 0.8149,
|
| 1477 |
+
"step": 8200
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 1.4595941616233534,
|
| 1481 |
+
"eval_loss": 0.815375566482544,
|
| 1482 |
+
"eval_runtime": 48.8123,
|
| 1483 |
+
"eval_samples_per_second": 96.902,
|
| 1484 |
+
"eval_steps_per_second": 12.128,
|
| 1485 |
+
"step": 8200
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 1.4684941260234958,
|
| 1489 |
+
"grad_norm": 0.938006579875946,
|
| 1490 |
+
"learning_rate": 0.00010425525966830225,
|
| 1491 |
+
"loss": 0.8016,
|
| 1492 |
+
"step": 8250
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 1.4773940904236382,
|
| 1496 |
+
"grad_norm": 0.847343921661377,
|
| 1497 |
+
"learning_rate": 0.00010331837063263827,
|
| 1498 |
+
"loss": 0.7986,
|
| 1499 |
+
"step": 8300
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 1.4862940548237806,
|
| 1503 |
+
"grad_norm": 0.9086883068084717,
|
| 1504 |
+
"learning_rate": 0.00010238118990502567,
|
| 1505 |
+
"loss": 0.8085,
|
| 1506 |
+
"step": 8350
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 1.495194019223923,
|
| 1510 |
+
"grad_norm": 0.828433632850647,
|
| 1511 |
+
"learning_rate": 0.00010144379986567533,
|
| 1512 |
+
"loss": 0.7942,
|
| 1513 |
+
"step": 8400
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 1.495194019223923,
|
| 1517 |
+
"eval_loss": 0.8140230178833008,
|
| 1518 |
+
"eval_runtime": 48.6474,
|
| 1519 |
+
"eval_samples_per_second": 97.23,
|
| 1520 |
+
"eval_steps_per_second": 12.169,
|
| 1521 |
+
"step": 8400
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 1.5040939836240654,
|
| 1525 |
+
"grad_norm": 0.828713059425354,
|
| 1526 |
+
"learning_rate": 0.00010050628291319719,
|
| 1527 |
+
"loss": 0.7984,
|
| 1528 |
+
"step": 8450
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 1.5129939480242078,
|
| 1532 |
+
"grad_norm": 0.989740252494812,
|
| 1533 |
+
"learning_rate": 9.956872145735705e-05,
|
| 1534 |
+
"loss": 0.8202,
|
| 1535 |
+
"step": 8500
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.5218939124243502,
|
| 1539 |
+
"grad_norm": 0.8692132830619812,
|
| 1540 |
+
"learning_rate": 9.863119791183265e-05,
|
| 1541 |
+
"loss": 0.7966,
|
| 1542 |
+
"step": 8550
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 1.5307938768244926,
|
| 1546 |
+
"grad_norm": 0.8006848692893982,
|
| 1547 |
+
"learning_rate": 9.76937946869694e-05,
|
| 1548 |
+
"loss": 0.8142,
|
| 1549 |
+
"step": 8600
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 1.5307938768244926,
|
| 1553 |
+
"eval_loss": 0.8105688691139221,
|
| 1554 |
+
"eval_runtime": 48.6038,
|
| 1555 |
+
"eval_samples_per_second": 97.317,
|
| 1556 |
+
"eval_steps_per_second": 12.18,
|
| 1557 |
+
"step": 8600
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.539693841224635,
|
| 1561 |
+
"grad_norm": 0.8285492062568665,
|
| 1562 |
+
"learning_rate": 9.675659418253619e-05,
|
| 1563 |
+
"loss": 0.8085,
|
| 1564 |
+
"step": 8650
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.5485938056247774,
|
| 1568 |
+
"grad_norm": 0.8491063117980957,
|
| 1569 |
+
"learning_rate": 9.581967878048244e-05,
|
| 1570 |
+
"loss": 0.7938,
|
| 1571 |
+
"step": 8700
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.5574937700249198,
|
| 1575 |
+
"grad_norm": 0.8797114491462708,
|
| 1576 |
+
"learning_rate": 9.488313083769629e-05,
|
| 1577 |
+
"loss": 0.8004,
|
| 1578 |
+
"step": 8750
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.5663937344250622,
|
| 1582 |
+
"grad_norm": 0.9647945165634155,
|
| 1583 |
+
"learning_rate": 9.394703267876563e-05,
|
| 1584 |
+
"loss": 0.8039,
|
| 1585 |
+
"step": 8800
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.5663937344250622,
|
| 1589 |
+
"eval_loss": 0.8091219067573547,
|
| 1590 |
+
"eval_runtime": 48.7657,
|
| 1591 |
+
"eval_samples_per_second": 96.994,
|
| 1592 |
+
"eval_steps_per_second": 12.14,
|
| 1593 |
+
"step": 8800
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 1.5752936988252046,
|
| 1597 |
+
"grad_norm": 0.9021193385124207,
|
| 1598 |
+
"learning_rate": 9.301146658874118e-05,
|
| 1599 |
+
"loss": 0.7833,
|
| 1600 |
+
"step": 8850
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 1.584193663225347,
|
| 1604 |
+
"grad_norm": 0.8533837199211121,
|
| 1605 |
+
"learning_rate": 9.207651480590383e-05,
|
| 1606 |
+
"loss": 0.7902,
|
| 1607 |
+
"step": 8900
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 1.5930936276254895,
|
| 1611 |
+
"grad_norm": 0.7925662398338318,
|
| 1612 |
+
"learning_rate": 9.114225951453534e-05,
|
| 1613 |
+
"loss": 0.792,
|
| 1614 |
+
"step": 8950
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 1.6019935920256319,
|
| 1618 |
+
"grad_norm": 0.8628392815589905,
|
| 1619 |
+
"learning_rate": 9.020878283769459e-05,
|
| 1620 |
+
"loss": 0.8047,
|
| 1621 |
+
"step": 9000
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 1.6019935920256319,
|
| 1625 |
+
"eval_loss": 0.8077049851417542,
|
| 1626 |
+
"eval_runtime": 48.6723,
|
| 1627 |
+
"eval_samples_per_second": 97.181,
|
| 1628 |
+
"eval_steps_per_second": 12.163,
|
| 1629 |
+
"step": 9000
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 1.6108935564257743,
|
| 1633 |
+
"grad_norm": 0.8858473896980286,
|
| 1634 |
+
"learning_rate": 8.927616682999837e-05,
|
| 1635 |
+
"loss": 0.7905,
|
| 1636 |
+
"step": 9050
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 1.6197935208259167,
|
| 1640 |
+
"grad_norm": 0.8647724390029907,
|
| 1641 |
+
"learning_rate": 8.834449347040887e-05,
|
| 1642 |
+
"loss": 0.8026,
|
| 1643 |
+
"step": 9100
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 1.628693485226059,
|
| 1647 |
+
"grad_norm": 0.8336294293403625,
|
| 1648 |
+
"learning_rate": 8.741384465502756e-05,
|
| 1649 |
+
"loss": 0.7946,
|
| 1650 |
+
"step": 9150
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 1.6375934496262015,
|
| 1654 |
+
"grad_norm": 0.8982174396514893,
|
| 1655 |
+
"learning_rate": 8.648430218989604e-05,
|
| 1656 |
+
"loss": 0.7944,
|
| 1657 |
+
"step": 9200
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 1.6375934496262015,
|
| 1661 |
+
"eval_loss": 0.8057986497879028,
|
| 1662 |
+
"eval_runtime": 48.6858,
|
| 1663 |
+
"eval_samples_per_second": 97.154,
|
| 1664 |
+
"eval_steps_per_second": 12.16,
|
| 1665 |
+
"step": 9200
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 1.6464934140263439,
|
| 1669 |
+
"grad_norm": 0.8794406056404114,
|
| 1670 |
+
"learning_rate": 8.55559477838056e-05,
|
| 1671 |
+
"loss": 0.7875,
|
| 1672 |
+
"step": 9250
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 1.6553933784264863,
|
| 1676 |
+
"grad_norm": 0.9118603467941284,
|
| 1677 |
+
"learning_rate": 8.462886304111433e-05,
|
| 1678 |
+
"loss": 0.7978,
|
| 1679 |
+
"step": 9300
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 1.6642933428266287,
|
| 1683 |
+
"grad_norm": 0.9038224816322327,
|
| 1684 |
+
"learning_rate": 8.370312945457437e-05,
|
| 1685 |
+
"loss": 0.814,
|
| 1686 |
+
"step": 9350
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 1.673193307226771,
|
| 1690 |
+
"grad_norm": 0.8720489740371704,
|
| 1691 |
+
"learning_rate": 8.277882839816812e-05,
|
| 1692 |
+
"loss": 0.7757,
|
| 1693 |
+
"step": 9400
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 1.673193307226771,
|
| 1697 |
+
"eval_loss": 0.8031893372535706,
|
| 1698 |
+
"eval_runtime": 49.0209,
|
| 1699 |
+
"eval_samples_per_second": 96.49,
|
| 1700 |
+
"eval_steps_per_second": 12.076,
|
| 1701 |
+
"step": 9400
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 1.6820932716269135,
|
| 1705 |
+
"grad_norm": 0.8191565275192261,
|
| 1706 |
+
"learning_rate": 8.18560411199557e-05,
|
| 1707 |
+
"loss": 0.7843,
|
| 1708 |
+
"step": 9450
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 1.6909932360270559,
|
| 1712 |
+
"grad_norm": 0.8189094066619873,
|
| 1713 |
+
"learning_rate": 8.095325642869662e-05,
|
| 1714 |
+
"loss": 0.8161,
|
| 1715 |
+
"step": 9500
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 1.6998932004271983,
|
| 1719 |
+
"grad_norm": 0.7863269448280334,
|
| 1720 |
+
"learning_rate": 8.00520796875218e-05,
|
| 1721 |
+
"loss": 0.7811,
|
| 1722 |
+
"step": 9550
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 1.7087931648273407,
|
| 1726 |
+
"grad_norm": 0.9392551183700562,
|
| 1727 |
+
"learning_rate": 7.913424804817525e-05,
|
| 1728 |
+
"loss": 0.7969,
|
| 1729 |
+
"step": 9600
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 1.7087931648273407,
|
| 1733 |
+
"eval_loss": 0.8000256419181824,
|
| 1734 |
+
"eval_runtime": 48.7526,
|
| 1735 |
+
"eval_samples_per_second": 97.02,
|
| 1736 |
+
"eval_steps_per_second": 12.143,
|
| 1737 |
+
"step": 9600
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 1.717693129227483,
|
| 1741 |
+
"grad_norm": 0.821388840675354,
|
| 1742 |
+
"learning_rate": 7.821825055351018e-05,
|
| 1743 |
+
"loss": 0.7947,
|
| 1744 |
+
"step": 9650
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 1.7265930936276255,
|
| 1748 |
+
"grad_norm": 0.9146565794944763,
|
| 1749 |
+
"learning_rate": 7.730416772168545e-05,
|
| 1750 |
+
"loss": 0.7777,
|
| 1751 |
+
"step": 9700
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 1.7354930580277679,
|
| 1755 |
+
"grad_norm": 0.9231836199760437,
|
| 1756 |
+
"learning_rate": 7.639207990255717e-05,
|
| 1757 |
+
"loss": 0.8166,
|
| 1758 |
+
"step": 9750
|
| 1759 |
+
},
|
| 1760 |
+
{
|
| 1761 |
+
"epoch": 1.7443930224279103,
|
| 1762 |
+
"grad_norm": 0.8416255116462708,
|
| 1763 |
+
"learning_rate": 7.548206727061529e-05,
|
| 1764 |
+
"loss": 0.772,
|
| 1765 |
+
"step": 9800
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 1.7443930224279103,
|
| 1769 |
+
"eval_loss": 0.7989854216575623,
|
| 1770 |
+
"eval_runtime": 49.3409,
|
| 1771 |
+
"eval_samples_per_second": 95.864,
|
| 1772 |
+
"eval_steps_per_second": 11.998,
|
| 1773 |
+
"step": 9800
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.7532929868280527,
|
| 1777 |
+
"grad_norm": 0.9181666374206543,
|
| 1778 |
+
"learning_rate": 7.457420981793652e-05,
|
| 1779 |
+
"loss": 0.796,
|
| 1780 |
+
"step": 9850
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 1.762192951228195,
|
| 1784 |
+
"grad_norm": 0.937517523765564,
|
| 1785 |
+
"learning_rate": 7.366858734715254e-05,
|
| 1786 |
+
"loss": 0.7987,
|
| 1787 |
+
"step": 9900
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 1.7710929156283375,
|
| 1791 |
+
"grad_norm": 0.8838592171669006,
|
| 1792 |
+
"learning_rate": 7.276527946443526e-05,
|
| 1793 |
+
"loss": 0.7908,
|
| 1794 |
+
"step": 9950
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 1.7799928800284799,
|
| 1798 |
+
"grad_norm": 0.8815340399742126,
|
| 1799 |
+
"learning_rate": 7.186436557249947e-05,
|
| 1800 |
+
"loss": 0.7875,
|
| 1801 |
+
"step": 10000
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 1.7799928800284799,
|
| 1805 |
+
"eval_loss": 0.7967162728309631,
|
| 1806 |
+
"eval_runtime": 48.9335,
|
| 1807 |
+
"eval_samples_per_second": 96.662,
|
| 1808 |
+
"eval_steps_per_second": 12.098,
|
| 1809 |
+
"step": 10000
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 1.7888928444286223,
|
| 1813 |
+
"grad_norm": 0.9804903864860535,
|
| 1814 |
+
"learning_rate": 7.096592486362275e-05,
|
| 1815 |
+
"loss": 0.7969,
|
| 1816 |
+
"step": 10050
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 1.7977928088287647,
|
| 1820 |
+
"grad_norm": 0.9025881290435791,
|
| 1821 |
+
"learning_rate": 7.00700363126848e-05,
|
| 1822 |
+
"loss": 0.7977,
|
| 1823 |
+
"step": 10100
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 1.806692773228907,
|
| 1827 |
+
"grad_norm": 0.9078325629234314,
|
| 1828 |
+
"learning_rate": 6.917677867022493e-05,
|
| 1829 |
+
"loss": 0.785,
|
| 1830 |
+
"step": 10150
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 1.8155927376290495,
|
| 1834 |
+
"grad_norm": 0.8123829364776611,
|
| 1835 |
+
"learning_rate": 6.828623045552005e-05,
|
| 1836 |
+
"loss": 0.7742,
|
| 1837 |
+
"step": 10200
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 1.8155927376290495,
|
| 1841 |
+
"eval_loss": 0.7950034737586975,
|
| 1842 |
+
"eval_runtime": 48.8445,
|
| 1843 |
+
"eval_samples_per_second": 96.838,
|
| 1844 |
+
"eval_steps_per_second": 12.12,
|
| 1845 |
+
"step": 10200
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 1.824492702029192,
|
| 1849 |
+
"grad_norm": 0.8655837178230286,
|
| 1850 |
+
"learning_rate": 6.739846994968235e-05,
|
| 1851 |
+
"loss": 0.7946,
|
| 1852 |
+
"step": 10250
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 1.8333926664293343,
|
| 1856 |
+
"grad_norm": 0.8942341208457947,
|
| 1857 |
+
"learning_rate": 6.651357518877861e-05,
|
| 1858 |
+
"loss": 0.8037,
|
| 1859 |
+
"step": 10300
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 1.8422926308294767,
|
| 1863 |
+
"grad_norm": 0.8432405591011047,
|
| 1864 |
+
"learning_rate": 6.563162395697022e-05,
|
| 1865 |
+
"loss": 0.7886,
|
| 1866 |
+
"step": 10350
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 1.851192595229619,
|
| 1870 |
+
"grad_norm": 0.8626817464828491,
|
| 1871 |
+
"learning_rate": 6.475269377967613e-05,
|
| 1872 |
+
"loss": 0.7674,
|
| 1873 |
+
"step": 10400
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 1.851192595229619,
|
| 1877 |
+
"eval_loss": 0.7928066253662109,
|
| 1878 |
+
"eval_runtime": 48.3616,
|
| 1879 |
+
"eval_samples_per_second": 97.805,
|
| 1880 |
+
"eval_steps_per_second": 12.241,
|
| 1881 |
+
"step": 10400
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 1.8600925596297615,
|
| 1885 |
+
"grad_norm": 0.8503168821334839,
|
| 1886 |
+
"learning_rate": 6.387686191675804e-05,
|
| 1887 |
+
"loss": 0.7992,
|
| 1888 |
+
"step": 10450
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 1.868992524029904,
|
| 1892 |
+
"grad_norm": 0.8525517582893372,
|
| 1893 |
+
"learning_rate": 6.300420535572912e-05,
|
| 1894 |
+
"loss": 0.7828,
|
| 1895 |
+
"step": 10500
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 1.8778924884300463,
|
| 1899 |
+
"grad_norm": 0.8483284711837769,
|
| 1900 |
+
"learning_rate": 6.213480080498667e-05,
|
| 1901 |
+
"loss": 0.7989,
|
| 1902 |
+
"step": 10550
|
| 1903 |
+
},
|
| 1904 |
+
{
|
| 1905 |
+
"epoch": 1.8867924528301887,
|
| 1906 |
+
"grad_norm": 0.9719367027282715,
|
| 1907 |
+
"learning_rate": 6.126872468706913e-05,
|
| 1908 |
+
"loss": 0.7885,
|
| 1909 |
+
"step": 10600
|
| 1910 |
+
},
|
| 1911 |
+
{
|
| 1912 |
+
"epoch": 1.8867924528301887,
|
| 1913 |
+
"eval_loss": 0.7926396131515503,
|
| 1914 |
+
"eval_runtime": 48.72,
|
| 1915 |
+
"eval_samples_per_second": 97.085,
|
| 1916 |
+
"eval_steps_per_second": 12.151,
|
| 1917 |
+
"step": 10600
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 1.895692417230331,
|
| 1921 |
+
"grad_norm": 0.8718783855438232,
|
| 1922 |
+
"learning_rate": 6.040605313193872e-05,
|
| 1923 |
+
"loss": 0.7828,
|
| 1924 |
+
"step": 10650
|
| 1925 |
+
},
|
| 1926 |
+
{
|
| 1927 |
+
"epoch": 1.9045923816304735,
|
| 1928 |
+
"grad_norm": 0.8642163872718811,
|
| 1929 |
+
"learning_rate": 5.954686197028908e-05,
|
| 1930 |
+
"loss": 0.8039,
|
| 1931 |
+
"step": 10700
|
| 1932 |
+
},
|
| 1933 |
+
{
|
| 1934 |
+
"epoch": 1.913492346030616,
|
| 1935 |
+
"grad_norm": 0.8736700415611267,
|
| 1936 |
+
"learning_rate": 5.869122672687977e-05,
|
| 1937 |
+
"loss": 0.7945,
|
| 1938 |
+
"step": 10750
|
| 1939 |
+
},
|
| 1940 |
+
{
|
| 1941 |
+
"epoch": 1.9223923104307583,
|
| 1942 |
+
"grad_norm": 0.8231788277626038,
|
| 1943 |
+
"learning_rate": 5.783922261389747e-05,
|
| 1944 |
+
"loss": 0.786,
|
| 1945 |
+
"step": 10800
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 1.9223923104307583,
|
| 1949 |
+
"eval_loss": 0.7904630899429321,
|
| 1950 |
+
"eval_runtime": 48.5769,
|
| 1951 |
+
"eval_samples_per_second": 97.371,
|
| 1952 |
+
"eval_steps_per_second": 12.187,
|
| 1953 |
+
"step": 10800
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 1.9312922748309007,
|
| 1957 |
+
"grad_norm": 0.8563975095748901,
|
| 1958 |
+
"learning_rate": 5.699092452434465e-05,
|
| 1959 |
+
"loss": 0.7793,
|
| 1960 |
+
"step": 10850
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 1.9401922392310431,
|
| 1964 |
+
"grad_norm": 0.8291860222816467,
|
| 1965 |
+
"learning_rate": 5.61464070254563e-05,
|
| 1966 |
+
"loss": 0.7796,
|
| 1967 |
+
"step": 10900
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 1.9490922036311855,
|
| 1971 |
+
"grad_norm": 0.835699200630188,
|
| 1972 |
+
"learning_rate": 5.530574435214535e-05,
|
| 1973 |
+
"loss": 0.7838,
|
| 1974 |
+
"step": 10950
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 1.957992168031328,
|
| 1978 |
+
"grad_norm": 0.7992449998855591,
|
| 1979 |
+
"learning_rate": 5.446901040047721e-05,
|
| 1980 |
+
"loss": 0.7886,
|
| 1981 |
+
"step": 11000
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 1.957992168031328,
|
| 1985 |
+
"eval_loss": 0.7888354063034058,
|
| 1986 |
+
"eval_runtime": 48.652,
|
| 1987 |
+
"eval_samples_per_second": 97.221,
|
| 1988 |
+
"eval_steps_per_second": 12.168,
|
| 1989 |
+
"step": 11000
|
| 1990 |
+
}
|
| 1991 |
+
],
|
| 1992 |
+
"logging_steps": 50,
|
| 1993 |
+
"max_steps": 16854,
|
| 1994 |
+
"num_input_tokens_seen": 0,
|
| 1995 |
+
"num_train_epochs": 3,
|
| 1996 |
+
"save_steps": 200,
|
| 1997 |
+
"stateful_callbacks": {
|
| 1998 |
+
"TrainerControl": {
|
| 1999 |
+
"args": {
|
| 2000 |
+
"should_epoch_stop": false,
|
| 2001 |
+
"should_evaluate": false,
|
| 2002 |
+
"should_log": false,
|
| 2003 |
+
"should_save": true,
|
| 2004 |
+
"should_training_stop": false
|
| 2005 |
+
},
|
| 2006 |
+
"attributes": {}
|
| 2007 |
+
}
|
| 2008 |
+
},
|
| 2009 |
+
"total_flos": 1.1927863315888128e+16,
|
| 2010 |
+
"train_batch_size": 8,
|
| 2011 |
+
"trial_name": null,
|
| 2012 |
+
"trial_params": null
|
| 2013 |
+
}
|
checkpoint-11000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10485f64019cbab11a104b6cddaccbfd3dfd757a8f8549a1bdb15583c0c14040
|
| 3 |
+
size 5969
|
checkpoint-11000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|