Training in progress, step 1800, checkpoint
Browse files- checkpoint-1800/README.md +207 -0
- checkpoint-1800/adapter_config.json +53 -0
- checkpoint-1800/adapter_model.safetensors +3 -0
- checkpoint-1800/optimizer.pt +3 -0
- checkpoint-1800/rng_state.pth +3 -0
- checkpoint-1800/scheduler.pt +3 -0
- checkpoint-1800/trainer_state.json +2698 -0
- checkpoint-1800/training_args.bin +3 -0
checkpoint-1800/README.md
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3.6-27B
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen3.6-27B
|
| 7 |
+
- lora
|
| 8 |
+
- transformers
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Model Card for Model ID
|
| 12 |
+
|
| 13 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
## Model Details
|
| 18 |
+
|
| 19 |
+
### Model Description
|
| 20 |
+
|
| 21 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
- **Developed by:** [More Information Needed]
|
| 26 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 27 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 28 |
+
- **Model type:** [More Information Needed]
|
| 29 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 30 |
+
- **License:** [More Information Needed]
|
| 31 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 32 |
+
|
| 33 |
+
### Model Sources [optional]
|
| 34 |
+
|
| 35 |
+
<!-- Provide the basic links for the model. -->
|
| 36 |
+
|
| 37 |
+
- **Repository:** [More Information Needed]
|
| 38 |
+
- **Paper [optional]:** [More Information Needed]
|
| 39 |
+
- **Demo [optional]:** [More Information Needed]
|
| 40 |
+
|
| 41 |
+
## Uses
|
| 42 |
+
|
| 43 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 44 |
+
|
| 45 |
+
### Direct Use
|
| 46 |
+
|
| 47 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 48 |
+
|
| 49 |
+
[More Information Needed]
|
| 50 |
+
|
| 51 |
+
### Downstream Use [optional]
|
| 52 |
+
|
| 53 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 54 |
+
|
| 55 |
+
[More Information Needed]
|
| 56 |
+
|
| 57 |
+
### Out-of-Scope Use
|
| 58 |
+
|
| 59 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 60 |
+
|
| 61 |
+
[More Information Needed]
|
| 62 |
+
|
| 63 |
+
## Bias, Risks, and Limitations
|
| 64 |
+
|
| 65 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 66 |
+
|
| 67 |
+
[More Information Needed]
|
| 68 |
+
|
| 69 |
+
### Recommendations
|
| 70 |
+
|
| 71 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 72 |
+
|
| 73 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 74 |
+
|
| 75 |
+
## How to Get Started with the Model
|
| 76 |
+
|
| 77 |
+
Use the code below to get started with the model.
|
| 78 |
+
|
| 79 |
+
[More Information Needed]
|
| 80 |
+
|
| 81 |
+
## Training Details
|
| 82 |
+
|
| 83 |
+
### Training Data
|
| 84 |
+
|
| 85 |
+
<!-- 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. -->
|
| 86 |
+
|
| 87 |
+
[More Information Needed]
|
| 88 |
+
|
| 89 |
+
### Training Procedure
|
| 90 |
+
|
| 91 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 92 |
+
|
| 93 |
+
#### Preprocessing [optional]
|
| 94 |
+
|
| 95 |
+
[More Information Needed]
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
#### Training Hyperparameters
|
| 99 |
+
|
| 100 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 101 |
+
|
| 102 |
+
#### Speeds, Sizes, Times [optional]
|
| 103 |
+
|
| 104 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 105 |
+
|
| 106 |
+
[More Information Needed]
|
| 107 |
+
|
| 108 |
+
## Evaluation
|
| 109 |
+
|
| 110 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 111 |
+
|
| 112 |
+
### Testing Data, Factors & Metrics
|
| 113 |
+
|
| 114 |
+
#### Testing Data
|
| 115 |
+
|
| 116 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 117 |
+
|
| 118 |
+
[More Information Needed]
|
| 119 |
+
|
| 120 |
+
#### Factors
|
| 121 |
+
|
| 122 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 123 |
+
|
| 124 |
+
[More Information Needed]
|
| 125 |
+
|
| 126 |
+
#### Metrics
|
| 127 |
+
|
| 128 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 129 |
+
|
| 130 |
+
[More Information Needed]
|
| 131 |
+
|
| 132 |
+
### Results
|
| 133 |
+
|
| 134 |
+
[More Information Needed]
|
| 135 |
+
|
| 136 |
+
#### Summary
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
## Model Examination [optional]
|
| 141 |
+
|
| 142 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 143 |
+
|
| 144 |
+
[More Information Needed]
|
| 145 |
+
|
| 146 |
+
## Environmental Impact
|
| 147 |
+
|
| 148 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 149 |
+
|
| 150 |
+
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).
|
| 151 |
+
|
| 152 |
+
- **Hardware Type:** [More Information Needed]
|
| 153 |
+
- **Hours used:** [More Information Needed]
|
| 154 |
+
- **Cloud Provider:** [More Information Needed]
|
| 155 |
+
- **Compute Region:** [More Information Needed]
|
| 156 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 157 |
+
|
| 158 |
+
## Technical Specifications [optional]
|
| 159 |
+
|
| 160 |
+
### Model Architecture and Objective
|
| 161 |
+
|
| 162 |
+
[More Information Needed]
|
| 163 |
+
|
| 164 |
+
### Compute Infrastructure
|
| 165 |
+
|
| 166 |
+
[More Information Needed]
|
| 167 |
+
|
| 168 |
+
#### Hardware
|
| 169 |
+
|
| 170 |
+
[More Information Needed]
|
| 171 |
+
|
| 172 |
+
#### Software
|
| 173 |
+
|
| 174 |
+
[More Information Needed]
|
| 175 |
+
|
| 176 |
+
## Citation [optional]
|
| 177 |
+
|
| 178 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 179 |
+
|
| 180 |
+
**BibTeX:**
|
| 181 |
+
|
| 182 |
+
[More Information Needed]
|
| 183 |
+
|
| 184 |
+
**APA:**
|
| 185 |
+
|
| 186 |
+
[More Information Needed]
|
| 187 |
+
|
| 188 |
+
## Glossary [optional]
|
| 189 |
+
|
| 190 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 191 |
+
|
| 192 |
+
[More Information Needed]
|
| 193 |
+
|
| 194 |
+
## More Information [optional]
|
| 195 |
+
|
| 196 |
+
[More Information Needed]
|
| 197 |
+
|
| 198 |
+
## Model Card Authors [optional]
|
| 199 |
+
|
| 200 |
+
[More Information Needed]
|
| 201 |
+
|
| 202 |
+
## Model Card Contact
|
| 203 |
+
|
| 204 |
+
[More Information Needed]
|
| 205 |
+
### Framework versions
|
| 206 |
+
|
| 207 |
+
- PEFT 0.20.0
|
checkpoint-1800/adapter_config.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen3.6-27B",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 64,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.0,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"monteclora_config": null,
|
| 27 |
+
"peft_type": "LORA",
|
| 28 |
+
"peft_version": "0.20.0",
|
| 29 |
+
"qalora_group_size": 16,
|
| 30 |
+
"r": 64,
|
| 31 |
+
"rank_pattern": {},
|
| 32 |
+
"revision": null,
|
| 33 |
+
"target_modules": [
|
| 34 |
+
"in_proj_qkv",
|
| 35 |
+
"down_proj",
|
| 36 |
+
"k_proj",
|
| 37 |
+
"v_proj",
|
| 38 |
+
"q_proj",
|
| 39 |
+
"in_proj_z",
|
| 40 |
+
"o_proj",
|
| 41 |
+
"up_proj",
|
| 42 |
+
"gate_proj",
|
| 43 |
+
"out_proj"
|
| 44 |
+
],
|
| 45 |
+
"target_parameters": null,
|
| 46 |
+
"task_type": "CAUSAL_LM",
|
| 47 |
+
"trainable_token_indices": null,
|
| 48 |
+
"use_bdlora": null,
|
| 49 |
+
"use_dora": false,
|
| 50 |
+
"use_qalora": false,
|
| 51 |
+
"use_rslora": true,
|
| 52 |
+
"velora_config": null
|
| 53 |
+
}
|
checkpoint-1800/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fb292122002e5bd7e5a6ecdb68426b594fbac609731b40b138177432f1e5f66
|
| 3 |
+
size 1740746640
|
checkpoint-1800/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:305d4b8e04d488752041e7e8811ff506ab1d24cb3f4227be9839c659b591853d
|
| 3 |
+
size 3481950275
|
checkpoint-1800/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed3753ab7977739b8eda494dd72defae5750f7283141b11a8f562160ba4c1a23
|
| 3 |
+
size 14645
|
checkpoint-1800/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b5119be380ac0b8ec72d232a9b923fc4f1ec1119d7f1125cdbc9a523d944ce8
|
| 3 |
+
size 1529
|
checkpoint-1800/trainer_state.json
ADDED
|
@@ -0,0 +1,2698 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.8716681835912103,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 1800,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.005200884150305552,
|
| 14 |
+
"grad_norm": 4.82585334777832,
|
| 15 |
+
"learning_rate": 5.6140350877192985e-06,
|
| 16 |
+
"loss": 0.7676299571990967,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.010401768300611104,
|
| 21 |
+
"grad_norm": 3.292309522628784,
|
| 22 |
+
"learning_rate": 1.263157894736842e-05,
|
| 23 |
+
"loss": 0.631245470046997,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.015602652450916656,
|
| 28 |
+
"grad_norm": 3.0301995277404785,
|
| 29 |
+
"learning_rate": 1.9649122807017544e-05,
|
| 30 |
+
"loss": 0.6749040126800537,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.02080353660122221,
|
| 35 |
+
"grad_norm": 2.853067398071289,
|
| 36 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 37 |
+
"loss": 0.7889204978942871,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.02600442075152776,
|
| 42 |
+
"grad_norm": 2.4595491886138916,
|
| 43 |
+
"learning_rate": 3.368421052631579e-05,
|
| 44 |
+
"loss": 0.8261689186096192,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.031205304901833313,
|
| 49 |
+
"grad_norm": 3.285839319229126,
|
| 50 |
+
"learning_rate": 4.070175438596492e-05,
|
| 51 |
+
"loss": 0.8855669021606445,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.03640618905213886,
|
| 56 |
+
"grad_norm": 2.9381635189056396,
|
| 57 |
+
"learning_rate": 4.771929824561404e-05,
|
| 58 |
+
"loss": 0.8640634536743164,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.04160707320244442,
|
| 63 |
+
"grad_norm": 2.142974376678467,
|
| 64 |
+
"learning_rate": 5.4736842105263165e-05,
|
| 65 |
+
"loss": 0.8938538551330566,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.046807957352749965,
|
| 70 |
+
"grad_norm": 3.4374115467071533,
|
| 71 |
+
"learning_rate": 6.175438596491228e-05,
|
| 72 |
+
"loss": 0.9762144088745117,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.05200884150305552,
|
| 77 |
+
"grad_norm": 2.2888057231903076,
|
| 78 |
+
"learning_rate": 6.87719298245614e-05,
|
| 79 |
+
"loss": 1.0100465774536134,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.05720972565336107,
|
| 84 |
+
"grad_norm": 2.101193428039551,
|
| 85 |
+
"learning_rate": 7.578947368421052e-05,
|
| 86 |
+
"loss": 1.0064237594604493,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.062410609803666625,
|
| 91 |
+
"grad_norm": 2.3019754886627197,
|
| 92 |
+
"learning_rate": 7.999977348305978e-05,
|
| 93 |
+
"loss": 1.0382986068725586,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.06761149395397217,
|
| 98 |
+
"grad_norm": 2.0822298526763916,
|
| 99 |
+
"learning_rate": 7.999722519694521e-05,
|
| 100 |
+
"loss": 1.1403823852539063,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.07281237810427772,
|
| 105 |
+
"grad_norm": 2.109672784805298,
|
| 106 |
+
"learning_rate": 7.999184565952555e-05,
|
| 107 |
+
"loss": 1.0954228401184083,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.07801326225458328,
|
| 112 |
+
"grad_norm": 1.9484328031539917,
|
| 113 |
+
"learning_rate": 7.998363525159777e-05,
|
| 114 |
+
"loss": 1.125577735900879,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.08321414640488883,
|
| 119 |
+
"grad_norm": 2.0304486751556396,
|
| 120 |
+
"learning_rate": 7.997259455434539e-05,
|
| 121 |
+
"loss": 1.078431987762451,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.08841503055519438,
|
| 126 |
+
"grad_norm": 1.8764644861221313,
|
| 127 |
+
"learning_rate": 7.995872434929734e-05,
|
| 128 |
+
"loss": 1.0825774192810058,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.09361591470549993,
|
| 133 |
+
"grad_norm": 2.521047353744507,
|
| 134 |
+
"learning_rate": 7.994202561827263e-05,
|
| 135 |
+
"loss": 1.0628202438354493,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.0988167988558055,
|
| 140 |
+
"grad_norm": 1.7737245559692383,
|
| 141 |
+
"learning_rate": 7.992249954331088e-05,
|
| 142 |
+
"loss": 1.0672310829162597,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.10401768300611104,
|
| 147 |
+
"grad_norm": 2.0016262531280518,
|
| 148 |
+
"learning_rate": 7.990014750658856e-05,
|
| 149 |
+
"loss": 1.0844260215759278,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.10401768300611104,
|
| 154 |
+
"eval_loss": 1.090377688407898,
|
| 155 |
+
"eval_runtime": 131.495,
|
| 156 |
+
"eval_samples_per_second": 1.947,
|
| 157 |
+
"eval_steps_per_second": 1.947,
|
| 158 |
+
"step": 100
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.10921856715641659,
|
| 162 |
+
"grad_norm": 2.2041330337524414,
|
| 163 |
+
"learning_rate": 7.987497109032128e-05,
|
| 164 |
+
"loss": 1.095380973815918,
|
| 165 |
+
"step": 105
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.11441945130672214,
|
| 169 |
+
"grad_norm": 1.7770912647247314,
|
| 170 |
+
"learning_rate": 7.98469720766517e-05,
|
| 171 |
+
"loss": 1.076313304901123,
|
| 172 |
+
"step": 110
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.11962033545702769,
|
| 176 |
+
"grad_norm": 2.0055956840515137,
|
| 177 |
+
"learning_rate": 7.98161524475234e-05,
|
| 178 |
+
"loss": 1.069803810119629,
|
| 179 |
+
"step": 115
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.12482121960733325,
|
| 183 |
+
"grad_norm": 1.9808892011642456,
|
| 184 |
+
"learning_rate": 7.978251438454063e-05,
|
| 185 |
+
"loss": 1.062901496887207,
|
| 186 |
+
"step": 120
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.13002210375763879,
|
| 190 |
+
"grad_norm": 1.7519869804382324,
|
| 191 |
+
"learning_rate": 7.974606026881378e-05,
|
| 192 |
+
"loss": 1.03425931930542,
|
| 193 |
+
"step": 125
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.13522298790794435,
|
| 197 |
+
"grad_norm": 1.8879916667938232,
|
| 198 |
+
"learning_rate": 7.970679268079092e-05,
|
| 199 |
+
"loss": 1.085061264038086,
|
| 200 |
+
"step": 130
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.1404238720582499,
|
| 204 |
+
"grad_norm": 1.855212926864624,
|
| 205 |
+
"learning_rate": 7.966471440007514e-05,
|
| 206 |
+
"loss": 1.0653216361999511,
|
| 207 |
+
"step": 135
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.14562475620855544,
|
| 211 |
+
"grad_norm": 1.9829131364822388,
|
| 212 |
+
"learning_rate": 7.961982840522773e-05,
|
| 213 |
+
"loss": 1.0679091453552245,
|
| 214 |
+
"step": 140
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.150825640358861,
|
| 218 |
+
"grad_norm": 1.8631235361099243,
|
| 219 |
+
"learning_rate": 7.957213787355738e-05,
|
| 220 |
+
"loss": 1.0336699485778809,
|
| 221 |
+
"step": 145
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.15602652450916657,
|
| 225 |
+
"grad_norm": 1.7199710607528687,
|
| 226 |
+
"learning_rate": 7.95216461808953e-05,
|
| 227 |
+
"loss": 1.085853385925293,
|
| 228 |
+
"step": 150
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.1612274086594721,
|
| 232 |
+
"grad_norm": 1.8429338932037354,
|
| 233 |
+
"learning_rate": 7.946835690135617e-05,
|
| 234 |
+
"loss": 1.039409065246582,
|
| 235 |
+
"step": 155
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.16642829280977767,
|
| 239 |
+
"grad_norm": 1.9319918155670166,
|
| 240 |
+
"learning_rate": 7.941227380708522e-05,
|
| 241 |
+
"loss": 1.0467087745666503,
|
| 242 |
+
"step": 160
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.1716291769600832,
|
| 246 |
+
"grad_norm": 2.0441744327545166,
|
| 247 |
+
"learning_rate": 7.93534008679912e-05,
|
| 248 |
+
"loss": 1.0675994873046875,
|
| 249 |
+
"step": 165
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.17683006111038876,
|
| 253 |
+
"grad_norm": 1.847270131111145,
|
| 254 |
+
"learning_rate": 7.929174225146534e-05,
|
| 255 |
+
"loss": 1.0682602882385255,
|
| 256 |
+
"step": 170
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.18203094526069433,
|
| 260 |
+
"grad_norm": 1.8770182132720947,
|
| 261 |
+
"learning_rate": 7.922730232208637e-05,
|
| 262 |
+
"loss": 1.0655933380126954,
|
| 263 |
+
"step": 175
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.18723182941099986,
|
| 267 |
+
"grad_norm": 1.9199661016464233,
|
| 268 |
+
"learning_rate": 7.916008564131158e-05,
|
| 269 |
+
"loss": 1.0514616012573241,
|
| 270 |
+
"step": 180
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.19243271356130542,
|
| 274 |
+
"grad_norm": 1.7040131092071533,
|
| 275 |
+
"learning_rate": 7.909009696715391e-05,
|
| 276 |
+
"loss": 1.0357669830322265,
|
| 277 |
+
"step": 185
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.197633597711611,
|
| 281 |
+
"grad_norm": 1.7878484725952148,
|
| 282 |
+
"learning_rate": 7.901734125384515e-05,
|
| 283 |
+
"loss": 1.034726905822754,
|
| 284 |
+
"step": 190
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.20283448186191652,
|
| 288 |
+
"grad_norm": 1.7647621631622314,
|
| 289 |
+
"learning_rate": 7.89418236514853e-05,
|
| 290 |
+
"loss": 1.0258402824401855,
|
| 291 |
+
"step": 195
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.20803536601222208,
|
| 295 |
+
"grad_norm": 1.7211089134216309,
|
| 296 |
+
"learning_rate": 7.886354950567789e-05,
|
| 297 |
+
"loss": 1.0237075805664062,
|
| 298 |
+
"step": 200
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.20803536601222208,
|
| 302 |
+
"eval_loss": 1.0211308002471924,
|
| 303 |
+
"eval_runtime": 130.7508,
|
| 304 |
+
"eval_samples_per_second": 1.958,
|
| 305 |
+
"eval_steps_per_second": 1.958,
|
| 306 |
+
"step": 200
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.21323625016252762,
|
| 310 |
+
"grad_norm": 1.9167125225067139,
|
| 311 |
+
"learning_rate": 7.878252435715178e-05,
|
| 312 |
+
"loss": 1.0424039840698243,
|
| 313 |
+
"step": 205
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.21843713431283318,
|
| 317 |
+
"grad_norm": 1.6589795351028442,
|
| 318 |
+
"learning_rate": 7.869875394136873e-05,
|
| 319 |
+
"loss": 0.985629940032959,
|
| 320 |
+
"step": 210
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.22363801846313874,
|
| 324 |
+
"grad_norm": 1.7960469722747803,
|
| 325 |
+
"learning_rate": 7.861224418811757e-05,
|
| 326 |
+
"loss": 1.0503170013427734,
|
| 327 |
+
"step": 215
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.22883890261344428,
|
| 331 |
+
"grad_norm": 1.876910924911499,
|
| 332 |
+
"learning_rate": 7.852300122109443e-05,
|
| 333 |
+
"loss": 1.0263469696044922,
|
| 334 |
+
"step": 220
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 0.23403978676374984,
|
| 338 |
+
"grad_norm": 1.7034902572631836,
|
| 339 |
+
"learning_rate": 7.843103135746916e-05,
|
| 340 |
+
"loss": 1.0396705627441407,
|
| 341 |
+
"step": 225
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 0.23924067091405538,
|
| 345 |
+
"grad_norm": 1.7886664867401123,
|
| 346 |
+
"learning_rate": 7.833634110743832e-05,
|
| 347 |
+
"loss": 1.0125335693359374,
|
| 348 |
+
"step": 230
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.24444155506436094,
|
| 352 |
+
"grad_norm": 1.7878754138946533,
|
| 353 |
+
"learning_rate": 7.823893717376422e-05,
|
| 354 |
+
"loss": 0.9978487968444825,
|
| 355 |
+
"step": 235
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.2496424392146665,
|
| 359 |
+
"grad_norm": 1.6163357496261597,
|
| 360 |
+
"learning_rate": 7.813882645130049e-05,
|
| 361 |
+
"loss": 1.0093013763427734,
|
| 362 |
+
"step": 240
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.25484332336497206,
|
| 366 |
+
"grad_norm": 1.7179474830627441,
|
| 367 |
+
"learning_rate": 7.80360160265041e-05,
|
| 368 |
+
"loss": 0.9946321487426758,
|
| 369 |
+
"step": 245
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.26004420751527757,
|
| 373 |
+
"grad_norm": 1.828262209892273,
|
| 374 |
+
"learning_rate": 7.793051317693359e-05,
|
| 375 |
+
"loss": 1.0461179733276367,
|
| 376 |
+
"step": 250
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.26524509166558313,
|
| 380 |
+
"grad_norm": 1.837222933769226,
|
| 381 |
+
"learning_rate": 7.782232537073406e-05,
|
| 382 |
+
"loss": 1.0099411964416505,
|
| 383 |
+
"step": 255
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.2704459758158887,
|
| 387 |
+
"grad_norm": 1.9459391832351685,
|
| 388 |
+
"learning_rate": 7.771146026610844e-05,
|
| 389 |
+
"loss": 0.9811776161193848,
|
| 390 |
+
"step": 260
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.27564685996619426,
|
| 394 |
+
"grad_norm": 1.8060634136199951,
|
| 395 |
+
"learning_rate": 7.759792571077545e-05,
|
| 396 |
+
"loss": 0.9858491897583008,
|
| 397 |
+
"step": 265
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.2808477441164998,
|
| 401 |
+
"grad_norm": 1.8257906436920166,
|
| 402 |
+
"learning_rate": 7.748172974141401e-05,
|
| 403 |
+
"loss": 1.0260663032531738,
|
| 404 |
+
"step": 270
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.2860486282668054,
|
| 408 |
+
"grad_norm": 1.7271229028701782,
|
| 409 |
+
"learning_rate": 7.736288058309448e-05,
|
| 410 |
+
"loss": 1.0253376007080077,
|
| 411 |
+
"step": 275
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.2912495124171109,
|
| 415 |
+
"grad_norm": 1.6389424800872803,
|
| 416 |
+
"learning_rate": 7.724138664869628e-05,
|
| 417 |
+
"loss": 0.9872174263000488,
|
| 418 |
+
"step": 280
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.29645039656741645,
|
| 422 |
+
"grad_norm": 1.7230466604232788,
|
| 423 |
+
"learning_rate": 7.711725653831255e-05,
|
| 424 |
+
"loss": 1.0354929924011231,
|
| 425 |
+
"step": 285
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.301651280717722,
|
| 429 |
+
"grad_norm": 1.7749247550964355,
|
| 430 |
+
"learning_rate": 7.699049903864125e-05,
|
| 431 |
+
"loss": 0.9916903495788574,
|
| 432 |
+
"step": 290
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.3068521648680276,
|
| 436 |
+
"grad_norm": 1.7340270280838013,
|
| 437 |
+
"learning_rate": 7.68611231223632e-05,
|
| 438 |
+
"loss": 1.0025782585144043,
|
| 439 |
+
"step": 295
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.31205304901833314,
|
| 443 |
+
"grad_norm": 1.5753134489059448,
|
| 444 |
+
"learning_rate": 7.672913794750699e-05,
|
| 445 |
+
"loss": 0.9782845497131347,
|
| 446 |
+
"step": 300
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.31205304901833314,
|
| 450 |
+
"eval_loss": 1.01508629322052,
|
| 451 |
+
"eval_runtime": 130.89,
|
| 452 |
+
"eval_samples_per_second": 1.956,
|
| 453 |
+
"eval_steps_per_second": 1.956,
|
| 454 |
+
"step": 300
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 0.31725393316863865,
|
| 458 |
+
"grad_norm": 1.6529031991958618,
|
| 459 |
+
"learning_rate": 7.659455285680071e-05,
|
| 460 |
+
"loss": 0.9918001174926758,
|
| 461 |
+
"step": 305
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 0.3224548173189442,
|
| 465 |
+
"grad_norm": 1.6655994653701782,
|
| 466 |
+
"learning_rate": 7.645737737701054e-05,
|
| 467 |
+
"loss": 0.9847027778625488,
|
| 468 |
+
"step": 310
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 0.32765570146924977,
|
| 472 |
+
"grad_norm": 1.7864056825637817,
|
| 473 |
+
"learning_rate": 7.631762121826653e-05,
|
| 474 |
+
"loss": 0.9591518402099609,
|
| 475 |
+
"step": 315
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 0.33285658561955533,
|
| 479 |
+
"grad_norm": 1.7958587408065796,
|
| 480 |
+
"learning_rate": 7.617529427337507e-05,
|
| 481 |
+
"loss": 0.9712434768676758,
|
| 482 |
+
"step": 320
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.3380574697698609,
|
| 486 |
+
"grad_norm": 1.7462350130081177,
|
| 487 |
+
"learning_rate": 7.603040661711879e-05,
|
| 488 |
+
"loss": 1.0182976722717285,
|
| 489 |
+
"step": 325
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.3432583539201664,
|
| 493 |
+
"grad_norm": 1.73703932762146,
|
| 494 |
+
"learning_rate": 7.588296850554326e-05,
|
| 495 |
+
"loss": 0.978699779510498,
|
| 496 |
+
"step": 330
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.34845923807047197,
|
| 500 |
+
"grad_norm": 1.781213402748108,
|
| 501 |
+
"learning_rate": 7.573299037523115e-05,
|
| 502 |
+
"loss": 1.0263344764709472,
|
| 503 |
+
"step": 335
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.35366012222077753,
|
| 507 |
+
"grad_norm": 1.7940926551818848,
|
| 508 |
+
"learning_rate": 7.558048284256334e-05,
|
| 509 |
+
"loss": 1.039241409301758,
|
| 510 |
+
"step": 340
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.3588610063710831,
|
| 514 |
+
"grad_norm": 1.725530982017517,
|
| 515 |
+
"learning_rate": 7.542545670296747e-05,
|
| 516 |
+
"loss": 0.9716745376586914,
|
| 517 |
+
"step": 345
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 0.36406189052138865,
|
| 521 |
+
"grad_norm": 1.665209174156189,
|
| 522 |
+
"learning_rate": 7.526792293015382e-05,
|
| 523 |
+
"loss": 0.9396204948425293,
|
| 524 |
+
"step": 350
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.36926277467169416,
|
| 528 |
+
"grad_norm": 1.8031824827194214,
|
| 529 |
+
"learning_rate": 7.51078926753384e-05,
|
| 530 |
+
"loss": 0.9682992935180664,
|
| 531 |
+
"step": 355
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.3744636588219997,
|
| 535 |
+
"grad_norm": 1.7742233276367188,
|
| 536 |
+
"learning_rate": 7.494537726645375e-05,
|
| 537 |
+
"loss": 0.9833150863647461,
|
| 538 |
+
"step": 360
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.3796645429723053,
|
| 542 |
+
"grad_norm": 1.7864766120910645,
|
| 543 |
+
"learning_rate": 7.478038820734698e-05,
|
| 544 |
+
"loss": 0.9690051078796387,
|
| 545 |
+
"step": 365
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.38486542712261085,
|
| 549 |
+
"grad_norm": 1.7735403776168823,
|
| 550 |
+
"learning_rate": 7.461293717696549e-05,
|
| 551 |
+
"loss": 0.9864785194396972,
|
| 552 |
+
"step": 370
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 0.3900663112729164,
|
| 556 |
+
"grad_norm": 1.6049963235855103,
|
| 557 |
+
"learning_rate": 7.444303602853024e-05,
|
| 558 |
+
"loss": 0.9804511070251465,
|
| 559 |
+
"step": 375
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 0.395267195423222,
|
| 563 |
+
"grad_norm": 1.6558054685592651,
|
| 564 |
+
"learning_rate": 7.427069678869672e-05,
|
| 565 |
+
"loss": 0.9362913131713867,
|
| 566 |
+
"step": 380
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.4004680795735275,
|
| 570 |
+
"grad_norm": 1.6555157899856567,
|
| 571 |
+
"learning_rate": 7.409593165670364e-05,
|
| 572 |
+
"loss": 0.948128604888916,
|
| 573 |
+
"step": 385
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.40566896372383304,
|
| 577 |
+
"grad_norm": 1.812888741493225,
|
| 578 |
+
"learning_rate": 7.391875300350937e-05,
|
| 579 |
+
"loss": 0.9553811073303222,
|
| 580 |
+
"step": 390
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.4108698478741386,
|
| 584 |
+
"grad_norm": 1.6602718830108643,
|
| 585 |
+
"learning_rate": 7.373917337091626e-05,
|
| 586 |
+
"loss": 0.940127944946289,
|
| 587 |
+
"step": 395
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.41607073202444417,
|
| 591 |
+
"grad_norm": 1.7474323511123657,
|
| 592 |
+
"learning_rate": 7.355720547068288e-05,
|
| 593 |
+
"loss": 0.9683933258056641,
|
| 594 |
+
"step": 400
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.41607073202444417,
|
| 598 |
+
"eval_loss": 0.9856516122817993,
|
| 599 |
+
"eval_runtime": 130.2348,
|
| 600 |
+
"eval_samples_per_second": 1.966,
|
| 601 |
+
"eval_steps_per_second": 1.966,
|
| 602 |
+
"step": 400
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.42127161617474973,
|
| 606 |
+
"grad_norm": 1.7211471796035767,
|
| 607 |
+
"learning_rate": 7.337286218362413e-05,
|
| 608 |
+
"loss": 0.9713785171508789,
|
| 609 |
+
"step": 405
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.42647250032505524,
|
| 613 |
+
"grad_norm": 1.839705467224121,
|
| 614 |
+
"learning_rate": 7.31861565586995e-05,
|
| 615 |
+
"loss": 0.9828580856323242,
|
| 616 |
+
"step": 410
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.4316733844753608,
|
| 620 |
+
"grad_norm": 1.6094111204147339,
|
| 621 |
+
"learning_rate": 7.299710181208943e-05,
|
| 622 |
+
"loss": 0.9652169227600098,
|
| 623 |
+
"step": 415
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 0.43687426862566636,
|
| 627 |
+
"grad_norm": 1.8238450288772583,
|
| 628 |
+
"learning_rate": 7.280571132625971e-05,
|
| 629 |
+
"loss": 0.9175550460815429,
|
| 630 |
+
"step": 420
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 0.4420751527759719,
|
| 634 |
+
"grad_norm": 1.7738935947418213,
|
| 635 |
+
"learning_rate": 7.261199864901423e-05,
|
| 636 |
+
"loss": 0.959293270111084,
|
| 637 |
+
"step": 425
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 0.4472760369262775,
|
| 641 |
+
"grad_norm": 1.7823359966278076,
|
| 642 |
+
"learning_rate": 7.241597749253593e-05,
|
| 643 |
+
"loss": 0.9460945129394531,
|
| 644 |
+
"step": 430
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.452476921076583,
|
| 648 |
+
"grad_norm": 1.852073073387146,
|
| 649 |
+
"learning_rate": 7.221766173241629e-05,
|
| 650 |
+
"loss": 0.9572076797485352,
|
| 651 |
+
"step": 435
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.45767780522688856,
|
| 655 |
+
"grad_norm": 1.7884498834609985,
|
| 656 |
+
"learning_rate": 7.201706540667293e-05,
|
| 657 |
+
"loss": 0.980253028869629,
|
| 658 |
+
"step": 440
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 0.4628786893771941,
|
| 662 |
+
"grad_norm": 1.6045715808868408,
|
| 663 |
+
"learning_rate": 7.181420271475616e-05,
|
| 664 |
+
"loss": 0.9448029518127441,
|
| 665 |
+
"step": 445
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 0.4680795735274997,
|
| 669 |
+
"grad_norm": 1.703908920288086,
|
| 670 |
+
"learning_rate": 7.160908801654358e-05,
|
| 671 |
+
"loss": 0.9464167594909668,
|
| 672 |
+
"step": 450
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 0.47328045767780524,
|
| 676 |
+
"grad_norm": 1.5748329162597656,
|
| 677 |
+
"learning_rate": 7.14017358313239e-05,
|
| 678 |
+
"loss": 0.9481819152832032,
|
| 679 |
+
"step": 455
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 0.47848134182811075,
|
| 683 |
+
"grad_norm": 1.62021803855896,
|
| 684 |
+
"learning_rate": 7.11921608367689e-05,
|
| 685 |
+
"loss": 0.9535123825073242,
|
| 686 |
+
"step": 460
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.4836822259784163,
|
| 690 |
+
"grad_norm": 1.6786726713180542,
|
| 691 |
+
"learning_rate": 7.09803778678946e-05,
|
| 692 |
+
"loss": 0.9362807273864746,
|
| 693 |
+
"step": 465
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.4888831101287219,
|
| 697 |
+
"grad_norm": 1.602408528327942,
|
| 698 |
+
"learning_rate": 7.076640191601113e-05,
|
| 699 |
+
"loss": 0.9352068901062012,
|
| 700 |
+
"step": 470
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 0.49408399427902744,
|
| 704 |
+
"grad_norm": 1.710305094718933,
|
| 705 |
+
"learning_rate": 7.055024812766153e-05,
|
| 706 |
+
"loss": 0.9479847908020019,
|
| 707 |
+
"step": 475
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 0.499284878429333,
|
| 711 |
+
"grad_norm": 1.7393652200698853,
|
| 712 |
+
"learning_rate": 7.03319318035496e-05,
|
| 713 |
+
"loss": 0.9210905075073242,
|
| 714 |
+
"step": 480
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.5044857625796385,
|
| 718 |
+
"grad_norm": 1.6267069578170776,
|
| 719 |
+
"learning_rate": 7.011146839745681e-05,
|
| 720 |
+
"loss": 0.935267448425293,
|
| 721 |
+
"step": 485
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 0.5096866467299441,
|
| 725 |
+
"grad_norm": 1.5649526119232178,
|
| 726 |
+
"learning_rate": 6.98888735151484e-05,
|
| 727 |
+
"loss": 0.950043773651123,
|
| 728 |
+
"step": 490
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 0.5148875308802496,
|
| 732 |
+
"grad_norm": 1.7210514545440674,
|
| 733 |
+
"learning_rate": 6.966416291326867e-05,
|
| 734 |
+
"loss": 0.9338683128356934,
|
| 735 |
+
"step": 495
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.5200884150305551,
|
| 739 |
+
"grad_norm": 1.7836523056030273,
|
| 740 |
+
"learning_rate": 6.943735249822567e-05,
|
| 741 |
+
"loss": 0.9206833839416504,
|
| 742 |
+
"step": 500
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 0.5200884150305551,
|
| 746 |
+
"eval_loss": 0.9551063776016235,
|
| 747 |
+
"eval_runtime": 130.2472,
|
| 748 |
+
"eval_samples_per_second": 1.965,
|
| 749 |
+
"eval_steps_per_second": 1.965,
|
| 750 |
+
"step": 500
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 0.5252892991808608,
|
| 754 |
+
"grad_norm": 1.6640737056732178,
|
| 755 |
+
"learning_rate": 6.920845832506523e-05,
|
| 756 |
+
"loss": 0.9343124389648437,
|
| 757 |
+
"step": 505
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.5304901833311663,
|
| 761 |
+
"grad_norm": 1.5780658721923828,
|
| 762 |
+
"learning_rate": 6.897749659633448e-05,
|
| 763 |
+
"loss": 0.9712604522705078,
|
| 764 |
+
"step": 510
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.5356910674814719,
|
| 768 |
+
"grad_norm": 1.6826986074447632,
|
| 769 |
+
"learning_rate": 6.874448366093497e-05,
|
| 770 |
+
"loss": 0.9570392608642578,
|
| 771 |
+
"step": 515
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.5408919516317774,
|
| 775 |
+
"grad_norm": 1.6517504453659058,
|
| 776 |
+
"learning_rate": 6.850943601296529e-05,
|
| 777 |
+
"loss": 0.9325905799865722,
|
| 778 |
+
"step": 520
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 0.546092835782083,
|
| 782 |
+
"grad_norm": 1.8107248544692993,
|
| 783 |
+
"learning_rate": 6.827237029055364e-05,
|
| 784 |
+
"loss": 0.9377958297729492,
|
| 785 |
+
"step": 525
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.5512937199323885,
|
| 789 |
+
"grad_norm": 1.6924495697021484,
|
| 790 |
+
"learning_rate": 6.803330327468006e-05,
|
| 791 |
+
"loss": 0.9227448463439941,
|
| 792 |
+
"step": 530
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 0.556494604082694,
|
| 796 |
+
"grad_norm": 1.6941320896148682,
|
| 797 |
+
"learning_rate": 6.779225188798846e-05,
|
| 798 |
+
"loss": 0.9221724510192871,
|
| 799 |
+
"step": 535
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 0.5616954882329996,
|
| 803 |
+
"grad_norm": 1.605466604232788,
|
| 804 |
+
"learning_rate": 6.754923319358883e-05,
|
| 805 |
+
"loss": 0.9474879264831543,
|
| 806 |
+
"step": 540
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.5668963723833051,
|
| 810 |
+
"grad_norm": 1.6994117498397827,
|
| 811 |
+
"learning_rate": 6.730426439384939e-05,
|
| 812 |
+
"loss": 0.9544130325317383,
|
| 813 |
+
"step": 545
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.5720972565336108,
|
| 817 |
+
"grad_norm": 1.6269444227218628,
|
| 818 |
+
"learning_rate": 6.705736282917892e-05,
|
| 819 |
+
"loss": 0.8944686889648438,
|
| 820 |
+
"step": 550
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 0.5772981406839163,
|
| 824 |
+
"grad_norm": 1.7221931219100952,
|
| 825 |
+
"learning_rate": 6.680854597679924e-05,
|
| 826 |
+
"loss": 0.9075075149536133,
|
| 827 |
+
"step": 555
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.5824990248342218,
|
| 831 |
+
"grad_norm": 1.7379156351089478,
|
| 832 |
+
"learning_rate": 6.655783144950809e-05,
|
| 833 |
+
"loss": 0.9554330825805664,
|
| 834 |
+
"step": 560
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.5876999089845274,
|
| 838 |
+
"grad_norm": 1.7438715696334839,
|
| 839 |
+
"learning_rate": 6.63052369944324e-05,
|
| 840 |
+
"loss": 0.9195778846740723,
|
| 841 |
+
"step": 565
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.5929007931348329,
|
| 845 |
+
"grad_norm": 1.6393606662750244,
|
| 846 |
+
"learning_rate": 6.605078049177205e-05,
|
| 847 |
+
"loss": 0.915708065032959,
|
| 848 |
+
"step": 570
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.5981016772851385,
|
| 852 |
+
"grad_norm": 1.7054882049560547,
|
| 853 |
+
"learning_rate": 6.579447995353416e-05,
|
| 854 |
+
"loss": 0.9384199142456054,
|
| 855 |
+
"step": 575
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.603302561435444,
|
| 859 |
+
"grad_norm": 1.5726091861724854,
|
| 860 |
+
"learning_rate": 6.553635352225812e-05,
|
| 861 |
+
"loss": 0.9182180404663086,
|
| 862 |
+
"step": 580
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 0.6085034455857495,
|
| 866 |
+
"grad_norm": 1.827543020248413,
|
| 867 |
+
"learning_rate": 6.52764194697313e-05,
|
| 868 |
+
"loss": 0.9172782897949219,
|
| 869 |
+
"step": 585
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.6137043297360552,
|
| 873 |
+
"grad_norm": 1.541303038597107,
|
| 874 |
+
"learning_rate": 6.501469619569579e-05,
|
| 875 |
+
"loss": 0.9366864204406739,
|
| 876 |
+
"step": 590
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 0.6189052138863607,
|
| 880 |
+
"grad_norm": 1.6896532773971558,
|
| 881 |
+
"learning_rate": 6.475120222654573e-05,
|
| 882 |
+
"loss": 0.91693115234375,
|
| 883 |
+
"step": 595
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 0.6241060980366663,
|
| 887 |
+
"grad_norm": 1.8263614177703857,
|
| 888 |
+
"learning_rate": 6.448595621401615e-05,
|
| 889 |
+
"loss": 0.9207332611083985,
|
| 890 |
+
"step": 600
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.6241060980366663,
|
| 894 |
+
"eval_loss": 0.9301373958587646,
|
| 895 |
+
"eval_runtime": 129.9867,
|
| 896 |
+
"eval_samples_per_second": 1.969,
|
| 897 |
+
"eval_steps_per_second": 1.969,
|
| 898 |
+
"step": 600
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.6293069821869718,
|
| 902 |
+
"grad_norm": 2.5737788677215576,
|
| 903 |
+
"learning_rate": 6.421897693386245e-05,
|
| 904 |
+
"loss": 1.8008251190185547,
|
| 905 |
+
"step": 605
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.6345078663372773,
|
| 909 |
+
"grad_norm": 2.3786563873291016,
|
| 910 |
+
"learning_rate": 6.395028328453154e-05,
|
| 911 |
+
"loss": 1.0148398399353027,
|
| 912 |
+
"step": 610
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.6397087504875829,
|
| 916 |
+
"grad_norm": 2.1619725227355957,
|
| 917 |
+
"learning_rate": 6.367989428582395e-05,
|
| 918 |
+
"loss": 0.9035258293151855,
|
| 919 |
+
"step": 615
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.6449096346378884,
|
| 923 |
+
"grad_norm": 1.8177882432937622,
|
| 924 |
+
"learning_rate": 6.340782907754754e-05,
|
| 925 |
+
"loss": 0.9431497573852539,
|
| 926 |
+
"step": 620
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.650110518788194,
|
| 930 |
+
"grad_norm": 2.0389435291290283,
|
| 931 |
+
"learning_rate": 6.313410691816269e-05,
|
| 932 |
+
"loss": 0.9617778778076171,
|
| 933 |
+
"step": 625
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.6553114029384995,
|
| 937 |
+
"grad_norm": 1.8454713821411133,
|
| 938 |
+
"learning_rate": 6.285874718341898e-05,
|
| 939 |
+
"loss": 0.9618912696838379,
|
| 940 |
+
"step": 630
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.660512287088805,
|
| 944 |
+
"grad_norm": 1.9317169189453125,
|
| 945 |
+
"learning_rate": 6.25817693649838e-05,
|
| 946 |
+
"loss": 1.020989227294922,
|
| 947 |
+
"step": 635
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.6657131712391107,
|
| 951 |
+
"grad_norm": 2.249952554702759,
|
| 952 |
+
"learning_rate": 6.230319306906246e-05,
|
| 953 |
+
"loss": 1.0368837356567382,
|
| 954 |
+
"step": 640
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.6709140553894162,
|
| 958 |
+
"grad_norm": 1.8525416851043701,
|
| 959 |
+
"learning_rate": 6.202303801501045e-05,
|
| 960 |
+
"loss": 0.9958114624023438,
|
| 961 |
+
"step": 645
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.6761149395397218,
|
| 965 |
+
"grad_norm": 1.99785578250885,
|
| 966 |
+
"learning_rate": 6.174132403393749e-05,
|
| 967 |
+
"loss": 1.0103933334350585,
|
| 968 |
+
"step": 650
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.6813158236900273,
|
| 972 |
+
"grad_norm": 2.1036858558654785,
|
| 973 |
+
"learning_rate": 6.145807106730384e-05,
|
| 974 |
+
"loss": 1.009110927581787,
|
| 975 |
+
"step": 655
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.6865167078403328,
|
| 979 |
+
"grad_norm": 1.8276114463806152,
|
| 980 |
+
"learning_rate": 6.11732991655087e-05,
|
| 981 |
+
"loss": 1.0265812873840332,
|
| 982 |
+
"step": 660
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.6917175919906384,
|
| 986 |
+
"grad_norm": 1.8524454832077026,
|
| 987 |
+
"learning_rate": 6.088702848647087e-05,
|
| 988 |
+
"loss": 1.0076023101806642,
|
| 989 |
+
"step": 665
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.6969184761409439,
|
| 993 |
+
"grad_norm": 2.044529914855957,
|
| 994 |
+
"learning_rate": 6.059927929420191e-05,
|
| 995 |
+
"loss": 1.0623496055603028,
|
| 996 |
+
"step": 670
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.7021193602912496,
|
| 1000 |
+
"grad_norm": 1.9014661312103271,
|
| 1001 |
+
"learning_rate": 6.031007195737173e-05,
|
| 1002 |
+
"loss": 1.0505518913269043,
|
| 1003 |
+
"step": 675
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.7073202444415551,
|
| 1007 |
+
"grad_norm": 1.7579931020736694,
|
| 1008 |
+
"learning_rate": 6.0019426947866685e-05,
|
| 1009 |
+
"loss": 1.0260109901428223,
|
| 1010 |
+
"step": 680
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.7125211285918606,
|
| 1014 |
+
"grad_norm": 1.9789166450500488,
|
| 1015 |
+
"learning_rate": 5.972736483934053e-05,
|
| 1016 |
+
"loss": 1.0057721138000488,
|
| 1017 |
+
"step": 685
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.7177220127421662,
|
| 1021 |
+
"grad_norm": 1.7603486776351929,
|
| 1022 |
+
"learning_rate": 5.943390630575808e-05,
|
| 1023 |
+
"loss": 0.9560928344726562,
|
| 1024 |
+
"step": 690
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.7229228968924717,
|
| 1028 |
+
"grad_norm": 1.723509669303894,
|
| 1029 |
+
"learning_rate": 5.9139072119931735e-05,
|
| 1030 |
+
"loss": 1.0287532806396484,
|
| 1031 |
+
"step": 695
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.7281237810427773,
|
| 1035 |
+
"grad_norm": 1.880836844444275,
|
| 1036 |
+
"learning_rate": 5.884288315205113e-05,
|
| 1037 |
+
"loss": 1.0159936904907227,
|
| 1038 |
+
"step": 700
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.7281237810427773,
|
| 1042 |
+
"eval_loss": 1.0172600746154785,
|
| 1043 |
+
"eval_runtime": 130.5328,
|
| 1044 |
+
"eval_samples_per_second": 1.961,
|
| 1045 |
+
"eval_steps_per_second": 1.961,
|
| 1046 |
+
"step": 700
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.7333246651930828,
|
| 1050 |
+
"grad_norm": 1.7332347631454468,
|
| 1051 |
+
"learning_rate": 5.8545360368205704e-05,
|
| 1052 |
+
"loss": 0.9914582252502442,
|
| 1053 |
+
"step": 705
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.7385255493433883,
|
| 1057 |
+
"grad_norm": 1.6425188779830933,
|
| 1058 |
+
"learning_rate": 5.824652482890067e-05,
|
| 1059 |
+
"loss": 0.9969341278076171,
|
| 1060 |
+
"step": 710
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.7437264334936939,
|
| 1064 |
+
"grad_norm": 1.868652105331421,
|
| 1065 |
+
"learning_rate": 5.794639768756625e-05,
|
| 1066 |
+
"loss": 0.9733437538146973,
|
| 1067 |
+
"step": 715
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.7489273176439994,
|
| 1071 |
+
"grad_norm": 1.7285988330841064,
|
| 1072 |
+
"learning_rate": 5.764500018906019e-05,
|
| 1073 |
+
"loss": 0.992225170135498,
|
| 1074 |
+
"step": 720
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.7541282017943051,
|
| 1078 |
+
"grad_norm": 1.7920562028884888,
|
| 1079 |
+
"learning_rate": 5.734235366816398e-05,
|
| 1080 |
+
"loss": 0.9502806663513184,
|
| 1081 |
+
"step": 725
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.7593290859446106,
|
| 1085 |
+
"grad_norm": 1.7255525588989258,
|
| 1086 |
+
"learning_rate": 5.703847954807273e-05,
|
| 1087 |
+
"loss": 0.9720046997070313,
|
| 1088 |
+
"step": 730
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.7645299700949162,
|
| 1092 |
+
"grad_norm": 1.8702120780944824,
|
| 1093 |
+
"learning_rate": 5.673339933887854e-05,
|
| 1094 |
+
"loss": 1.0045533180236816,
|
| 1095 |
+
"step": 735
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.7697308542452217,
|
| 1099 |
+
"grad_norm": 1.7282917499542236,
|
| 1100 |
+
"learning_rate": 5.642713463604804e-05,
|
| 1101 |
+
"loss": 0.998747444152832,
|
| 1102 |
+
"step": 740
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.7749317383955272,
|
| 1106 |
+
"grad_norm": 1.6850981712341309,
|
| 1107 |
+
"learning_rate": 5.6119707118893566e-05,
|
| 1108 |
+
"loss": 0.9491232872009278,
|
| 1109 |
+
"step": 745
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.7801326225458328,
|
| 1113 |
+
"grad_norm": 1.8323360681533813,
|
| 1114 |
+
"learning_rate": 5.581113854903873e-05,
|
| 1115 |
+
"loss": 0.9483734130859375,
|
| 1116 |
+
"step": 750
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.7853335066961383,
|
| 1120 |
+
"grad_norm": 1.7287927865982056,
|
| 1121 |
+
"learning_rate": 5.5501450768877895e-05,
|
| 1122 |
+
"loss": 0.9630053520202637,
|
| 1123 |
+
"step": 755
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.790534390846444,
|
| 1127 |
+
"grad_norm": 1.8735415935516357,
|
| 1128 |
+
"learning_rate": 5.519066570003006e-05,
|
| 1129 |
+
"loss": 0.9625276565551758,
|
| 1130 |
+
"step": 760
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.7957352749967495,
|
| 1134 |
+
"grad_norm": 1.7333344221115112,
|
| 1135 |
+
"learning_rate": 5.4878805341787106e-05,
|
| 1136 |
+
"loss": 0.956482982635498,
|
| 1137 |
+
"step": 765
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.800936159147055,
|
| 1141 |
+
"grad_norm": 1.7283087968826294,
|
| 1142 |
+
"learning_rate": 5.456589176955656e-05,
|
| 1143 |
+
"loss": 0.9767995834350586,
|
| 1144 |
+
"step": 770
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.8061370432973606,
|
| 1148 |
+
"grad_norm": 1.6415756940841675,
|
| 1149 |
+
"learning_rate": 5.4251947133298954e-05,
|
| 1150 |
+
"loss": 0.9446447372436524,
|
| 1151 |
+
"step": 775
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.8113379274476661,
|
| 1155 |
+
"grad_norm": 1.6519927978515625,
|
| 1156 |
+
"learning_rate": 5.393699365595995e-05,
|
| 1157 |
+
"loss": 0.9424878120422363,
|
| 1158 |
+
"step": 780
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.8165388115979717,
|
| 1162 |
+
"grad_norm": 1.647696852684021,
|
| 1163 |
+
"learning_rate": 5.3621053631897175e-05,
|
| 1164 |
+
"loss": 0.9464174270629883,
|
| 1165 |
+
"step": 785
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.8217396957482772,
|
| 1169 |
+
"grad_norm": 1.8417209386825562,
|
| 1170 |
+
"learning_rate": 5.330414942530217e-05,
|
| 1171 |
+
"loss": 0.9534976959228516,
|
| 1172 |
+
"step": 790
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.8269405798985827,
|
| 1176 |
+
"grad_norm": 1.8787815570831299,
|
| 1177 |
+
"learning_rate": 5.298630346861732e-05,
|
| 1178 |
+
"loss": 0.902367115020752,
|
| 1179 |
+
"step": 795
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.8321414640488883,
|
| 1183 |
+
"grad_norm": 1.68453848361969,
|
| 1184 |
+
"learning_rate": 5.266753826094787e-05,
|
| 1185 |
+
"loss": 0.9392575263977051,
|
| 1186 |
+
"step": 800
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.8321414640488883,
|
| 1190 |
+
"eval_loss": 0.9664498567581177,
|
| 1191 |
+
"eval_runtime": 129.775,
|
| 1192 |
+
"eval_samples_per_second": 1.973,
|
| 1193 |
+
"eval_steps_per_second": 1.973,
|
| 1194 |
+
"step": 800
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.8373423481991938,
|
| 1198 |
+
"grad_norm": 1.501584529876709,
|
| 1199 |
+
"learning_rate": 5.234787636646932e-05,
|
| 1200 |
+
"loss": 0.9557664871215821,
|
| 1201 |
+
"step": 805
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 0.8425432323494995,
|
| 1205 |
+
"grad_norm": 1.5360844135284424,
|
| 1206 |
+
"learning_rate": 5.202734041283029e-05,
|
| 1207 |
+
"loss": 0.9075163841247559,
|
| 1208 |
+
"step": 810
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 0.847744116499805,
|
| 1212 |
+
"grad_norm": 1.65811288356781,
|
| 1213 |
+
"learning_rate": 5.1705953089550675e-05,
|
| 1214 |
+
"loss": 0.9179675102233886,
|
| 1215 |
+
"step": 815
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.8529450006501105,
|
| 1219 |
+
"grad_norm": 1.61856210231781,
|
| 1220 |
+
"learning_rate": 5.138373714641558e-05,
|
| 1221 |
+
"loss": 0.9237114906311035,
|
| 1222 |
+
"step": 820
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 0.8581458848004161,
|
| 1226 |
+
"grad_norm": 1.7458878755569458,
|
| 1227 |
+
"learning_rate": 5.1060715391864965e-05,
|
| 1228 |
+
"loss": 0.8636340141296387,
|
| 1229 |
+
"step": 825
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 0.8633467689507216,
|
| 1233 |
+
"grad_norm": 1.6920363903045654,
|
| 1234 |
+
"learning_rate": 5.073691069137912e-05,
|
| 1235 |
+
"loss": 0.9312037467956543,
|
| 1236 |
+
"step": 830
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 0.8685476531010272,
|
| 1240 |
+
"grad_norm": 1.714153528213501,
|
| 1241 |
+
"learning_rate": 5.041234596586009e-05,
|
| 1242 |
+
"loss": 0.9352224349975586,
|
| 1243 |
+
"step": 835
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 0.8737485372513327,
|
| 1247 |
+
"grad_norm": 1.6470508575439453,
|
| 1248 |
+
"learning_rate": 5.0087044190009206e-05,
|
| 1249 |
+
"loss": 0.8943827629089356,
|
| 1250 |
+
"step": 840
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 0.8789494214016382,
|
| 1254 |
+
"grad_norm": 1.622175693511963,
|
| 1255 |
+
"learning_rate": 4.9761028390700754e-05,
|
| 1256 |
+
"loss": 0.9128511428833008,
|
| 1257 |
+
"step": 845
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 0.8841503055519438,
|
| 1261 |
+
"grad_norm": 1.6196850538253784,
|
| 1262 |
+
"learning_rate": 4.9434321645352084e-05,
|
| 1263 |
+
"loss": 0.9311873435974121,
|
| 1264 |
+
"step": 850
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 0.8893511897022494,
|
| 1268 |
+
"grad_norm": 1.7249358892440796,
|
| 1269 |
+
"learning_rate": 4.9106947080289925e-05,
|
| 1270 |
+
"loss": 0.9176848411560059,
|
| 1271 |
+
"step": 855
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 0.894552073852555,
|
| 1275 |
+
"grad_norm": 1.6511820554733276,
|
| 1276 |
+
"learning_rate": 4.8778927869113445e-05,
|
| 1277 |
+
"loss": 0.9112163543701172,
|
| 1278 |
+
"step": 860
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 0.8997529580028605,
|
| 1282 |
+
"grad_norm": 1.5577549934387207,
|
| 1283 |
+
"learning_rate": 4.845028723105389e-05,
|
| 1284 |
+
"loss": 0.8965622901916503,
|
| 1285 |
+
"step": 865
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 0.904953842153166,
|
| 1289 |
+
"grad_norm": 1.6360331773757935,
|
| 1290 |
+
"learning_rate": 4.812104842933087e-05,
|
| 1291 |
+
"loss": 0.913609504699707,
|
| 1292 |
+
"step": 870
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 0.9101547263034716,
|
| 1296 |
+
"grad_norm": 1.451485276222229,
|
| 1297 |
+
"learning_rate": 4.779123476950581e-05,
|
| 1298 |
+
"loss": 0.8944340705871582,
|
| 1299 |
+
"step": 875
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.9153556104537771,
|
| 1303 |
+
"grad_norm": 1.5654209852218628,
|
| 1304 |
+
"learning_rate": 4.746086959783209e-05,
|
| 1305 |
+
"loss": 0.8596482276916504,
|
| 1306 |
+
"step": 880
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.9205564946040827,
|
| 1310 |
+
"grad_norm": 1.5695706605911255,
|
| 1311 |
+
"learning_rate": 4.712997629960253e-05,
|
| 1312 |
+
"loss": 0.8860456466674804,
|
| 1313 |
+
"step": 885
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 0.9257573787543882,
|
| 1317 |
+
"grad_norm": 1.7602401971817017,
|
| 1318 |
+
"learning_rate": 4.679857829749404e-05,
|
| 1319 |
+
"loss": 0.8744911193847656,
|
| 1320 |
+
"step": 890
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 0.9309582629046937,
|
| 1324 |
+
"grad_norm": 1.6938329935073853,
|
| 1325 |
+
"learning_rate": 4.6466699049909584e-05,
|
| 1326 |
+
"loss": 0.9156827926635742,
|
| 1327 |
+
"step": 895
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 0.9361591470549994,
|
| 1331 |
+
"grad_norm": 1.4965558052062988,
|
| 1332 |
+
"learning_rate": 4.6134362049317625e-05,
|
| 1333 |
+
"loss": 0.9088706016540528,
|
| 1334 |
+
"step": 900
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 0.9361591470549994,
|
| 1338 |
+
"eval_loss": 0.9005925059318542,
|
| 1339 |
+
"eval_runtime": 129.9874,
|
| 1340 |
+
"eval_samples_per_second": 1.969,
|
| 1341 |
+
"eval_steps_per_second": 1.969,
|
| 1342 |
+
"step": 900
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 0.9413600312053049,
|
| 1346 |
+
"grad_norm": 1.5755003690719604,
|
| 1347 |
+
"learning_rate": 4.58015908205893e-05,
|
| 1348 |
+
"loss": 0.8684419631958008,
|
| 1349 |
+
"step": 905
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 0.9465609153556105,
|
| 1353 |
+
"grad_norm": 1.5753810405731201,
|
| 1354 |
+
"learning_rate": 4.5468408919333025e-05,
|
| 1355 |
+
"loss": 0.8938017845153808,
|
| 1356 |
+
"step": 910
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 0.951761799505916,
|
| 1360 |
+
"grad_norm": 1.5218995809555054,
|
| 1361 |
+
"learning_rate": 4.513483993022719e-05,
|
| 1362 |
+
"loss": 0.851717185974121,
|
| 1363 |
+
"step": 915
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 0.9569626836562215,
|
| 1367 |
+
"grad_norm": 1.6325594186782837,
|
| 1368 |
+
"learning_rate": 4.4800907465350664e-05,
|
| 1369 |
+
"loss": 0.8885617256164551,
|
| 1370 |
+
"step": 920
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 0.9621635678065271,
|
| 1374 |
+
"grad_norm": 1.4952536821365356,
|
| 1375 |
+
"learning_rate": 4.446663516251138e-05,
|
| 1376 |
+
"loss": 0.8511702537536621,
|
| 1377 |
+
"step": 925
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.9673644519568326,
|
| 1381 |
+
"grad_norm": 1.5268827676773071,
|
| 1382 |
+
"learning_rate": 4.413204668357312e-05,
|
| 1383 |
+
"loss": 0.8577158927917481,
|
| 1384 |
+
"step": 930
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 0.9725653361071382,
|
| 1388 |
+
"grad_norm": 1.4323556423187256,
|
| 1389 |
+
"learning_rate": 4.379716571278054e-05,
|
| 1390 |
+
"loss": 0.8342367172241211,
|
| 1391 |
+
"step": 935
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 0.9777662202574438,
|
| 1395 |
+
"grad_norm": 1.5065745115280151,
|
| 1396 |
+
"learning_rate": 4.3462015955082665e-05,
|
| 1397 |
+
"loss": 0.894658374786377,
|
| 1398 |
+
"step": 940
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 0.9829671044077494,
|
| 1402 |
+
"grad_norm": 1.4767268896102905,
|
| 1403 |
+
"learning_rate": 4.3126621134455e-05,
|
| 1404 |
+
"loss": 0.8451394081115723,
|
| 1405 |
+
"step": 945
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 0.9881679885580549,
|
| 1409 |
+
"grad_norm": 1.5763777494430542,
|
| 1410 |
+
"learning_rate": 4.279100499222004e-05,
|
| 1411 |
+
"loss": 0.8588390350341797,
|
| 1412 |
+
"step": 950
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 0.9933688727083604,
|
| 1416 |
+
"grad_norm": 1.5762237310409546,
|
| 1417 |
+
"learning_rate": 4.2455191285366845e-05,
|
| 1418 |
+
"loss": 0.8754203796386719,
|
| 1419 |
+
"step": 955
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 0.998569756858666,
|
| 1423 |
+
"grad_norm": 1.5145306587219238,
|
| 1424 |
+
"learning_rate": 4.2119203784869304e-05,
|
| 1425 |
+
"loss": 0.8561000823974609,
|
| 1426 |
+
"step": 960
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 1.0031205304901833,
|
| 1430 |
+
"grad_norm": 1.470058798789978,
|
| 1431 |
+
"learning_rate": 4.178306627400347e-05,
|
| 1432 |
+
"loss": 0.7531153202056885,
|
| 1433 |
+
"step": 965
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 1.0083214146404889,
|
| 1437 |
+
"grad_norm": 1.6469708681106567,
|
| 1438 |
+
"learning_rate": 4.144680254666413e-05,
|
| 1439 |
+
"loss": 0.7166049003601074,
|
| 1440 |
+
"step": 970
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 1.0135222987907944,
|
| 1444 |
+
"grad_norm": 1.5783348083496094,
|
| 1445 |
+
"learning_rate": 4.1110436405680376e-05,
|
| 1446 |
+
"loss": 0.6519159317016602,
|
| 1447 |
+
"step": 975
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 1.0187231829411,
|
| 1451 |
+
"grad_norm": 1.494524598121643,
|
| 1452 |
+
"learning_rate": 4.0773991661130806e-05,
|
| 1453 |
+
"loss": 0.6752121925354004,
|
| 1454 |
+
"step": 980
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 1.0239240670914056,
|
| 1458 |
+
"grad_norm": 1.523681640625,
|
| 1459 |
+
"learning_rate": 4.043749212865811e-05,
|
| 1460 |
+
"loss": 0.6791035175323487,
|
| 1461 |
+
"step": 985
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 1.029124951241711,
|
| 1465 |
+
"grad_norm": 1.4255659580230713,
|
| 1466 |
+
"learning_rate": 4.010096162778309e-05,
|
| 1467 |
+
"loss": 0.7047647476196289,
|
| 1468 |
+
"step": 990
|
| 1469 |
+
},
|
| 1470 |
+
{
|
| 1471 |
+
"epoch": 1.0343258353920166,
|
| 1472 |
+
"grad_norm": 1.512510061264038,
|
| 1473 |
+
"learning_rate": 3.97644239802188e-05,
|
| 1474 |
+
"loss": 0.6946704387664795,
|
| 1475 |
+
"step": 995
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 1.0395267195423221,
|
| 1479 |
+
"grad_norm": 1.4743566513061523,
|
| 1480 |
+
"learning_rate": 3.942790300818415e-05,
|
| 1481 |
+
"loss": 0.676310396194458,
|
| 1482 |
+
"step": 1000
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 1.0395267195423221,
|
| 1486 |
+
"eval_loss": 0.8658661246299744,
|
| 1487 |
+
"eval_runtime": 130.1356,
|
| 1488 |
+
"eval_samples_per_second": 1.967,
|
| 1489 |
+
"eval_steps_per_second": 1.967,
|
| 1490 |
+
"step": 1000
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 1.0447276036926278,
|
| 1494 |
+
"grad_norm": 1.5579502582550049,
|
| 1495 |
+
"learning_rate": 3.90914225327176e-05,
|
| 1496 |
+
"loss": 0.6901298522949219,
|
| 1497 |
+
"step": 1005
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 1.0499284878429334,
|
| 1501 |
+
"grad_norm": 1.5494235754013062,
|
| 1502 |
+
"learning_rate": 3.875500637199108e-05,
|
| 1503 |
+
"loss": 0.6718050003051758,
|
| 1504 |
+
"step": 1010
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 1.0551293719932389,
|
| 1508 |
+
"grad_norm": 1.5289891958236694,
|
| 1509 |
+
"learning_rate": 3.8418678339623876e-05,
|
| 1510 |
+
"loss": 0.6892761707305908,
|
| 1511 |
+
"step": 1015
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 1.0603302561435444,
|
| 1515 |
+
"grad_norm": 1.4304561614990234,
|
| 1516 |
+
"learning_rate": 3.8082462242997025e-05,
|
| 1517 |
+
"loss": 0.6954478263854981,
|
| 1518 |
+
"step": 1020
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 1.0655311402938499,
|
| 1522 |
+
"grad_norm": 1.4161802530288696,
|
| 1523 |
+
"learning_rate": 3.774638188156808e-05,
|
| 1524 |
+
"loss": 0.6717328548431396,
|
| 1525 |
+
"step": 1025
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"epoch": 1.0707320244441556,
|
| 1529 |
+
"grad_norm": 1.438629150390625,
|
| 1530 |
+
"learning_rate": 3.741046104518636e-05,
|
| 1531 |
+
"loss": 0.6766324043273926,
|
| 1532 |
+
"step": 1030
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 1.0759329085944611,
|
| 1536 |
+
"grad_norm": 1.5406919717788696,
|
| 1537 |
+
"learning_rate": 3.707472351240907e-05,
|
| 1538 |
+
"loss": 0.7088249206542969,
|
| 1539 |
+
"step": 1035
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 1.0811337927447666,
|
| 1543 |
+
"grad_norm": 1.3865864276885986,
|
| 1544 |
+
"learning_rate": 3.6739193048818e-05,
|
| 1545 |
+
"loss": 0.6776373386383057,
|
| 1546 |
+
"step": 1040
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 1.0863346768950721,
|
| 1550 |
+
"grad_norm": 1.5101228952407837,
|
| 1551 |
+
"learning_rate": 3.640389340533736e-05,
|
| 1552 |
+
"loss": 0.660363245010376,
|
| 1553 |
+
"step": 1045
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 1.0915355610453776,
|
| 1557 |
+
"grad_norm": 1.4708372354507446,
|
| 1558 |
+
"learning_rate": 3.6068848316552415e-05,
|
| 1559 |
+
"loss": 0.6472445487976074,
|
| 1560 |
+
"step": 1050
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 1.0967364451956834,
|
| 1564 |
+
"grad_norm": 1.5044161081314087,
|
| 1565 |
+
"learning_rate": 3.573408149902955e-05,
|
| 1566 |
+
"loss": 0.7127279758453369,
|
| 1567 |
+
"step": 1055
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 1.1019373293459889,
|
| 1571 |
+
"grad_norm": 1.4291512966156006,
|
| 1572 |
+
"learning_rate": 3.53996166496373e-05,
|
| 1573 |
+
"loss": 0.6595888614654541,
|
| 1574 |
+
"step": 1060
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 1.1071382134962944,
|
| 1578 |
+
"grad_norm": 1.5285484790802002,
|
| 1579 |
+
"learning_rate": 3.506547744386911e-05,
|
| 1580 |
+
"loss": 0.6698886394500733,
|
| 1581 |
+
"step": 1065
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 1.1123390976465999,
|
| 1585 |
+
"grad_norm": 1.3300918340682983,
|
| 1586 |
+
"learning_rate": 3.473168753416728e-05,
|
| 1587 |
+
"loss": 0.6541372776031494,
|
| 1588 |
+
"step": 1070
|
| 1589 |
+
},
|
| 1590 |
+
{
|
| 1591 |
+
"epoch": 1.1175399817969054,
|
| 1592 |
+
"grad_norm": 1.329465389251709,
|
| 1593 |
+
"learning_rate": 3.439827054824881e-05,
|
| 1594 |
+
"loss": 0.6664098739624024,
|
| 1595 |
+
"step": 1075
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 1.1227408659472111,
|
| 1599 |
+
"grad_norm": 1.3707212209701538,
|
| 1600 |
+
"learning_rate": 3.406525008743285e-05,
|
| 1601 |
+
"loss": 0.6693881034851075,
|
| 1602 |
+
"step": 1080
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 1.1279417500975166,
|
| 1606 |
+
"grad_norm": 1.474888563156128,
|
| 1607 |
+
"learning_rate": 3.373264972497002e-05,
|
| 1608 |
+
"loss": 0.6865148067474365,
|
| 1609 |
+
"step": 1085
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 1.1331426342478221,
|
| 1613 |
+
"grad_norm": 1.370944857597351,
|
| 1614 |
+
"learning_rate": 3.3400493004373815e-05,
|
| 1615 |
+
"loss": 0.6525755405426026,
|
| 1616 |
+
"step": 1090
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 1.1383435183981276,
|
| 1620 |
+
"grad_norm": 1.5666426420211792,
|
| 1621 |
+
"learning_rate": 3.306880343775396e-05,
|
| 1622 |
+
"loss": 0.6941968917846679,
|
| 1623 |
+
"step": 1095
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 1.1435444025484331,
|
| 1627 |
+
"grad_norm": 1.3775230646133423,
|
| 1628 |
+
"learning_rate": 3.273760450415218e-05,
|
| 1629 |
+
"loss": 0.6021693706512451,
|
| 1630 |
+
"step": 1100
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"epoch": 1.1435444025484331,
|
| 1634 |
+
"eval_loss": 0.8314206600189209,
|
| 1635 |
+
"eval_runtime": 130.5631,
|
| 1636 |
+
"eval_samples_per_second": 1.961,
|
| 1637 |
+
"eval_steps_per_second": 1.961,
|
| 1638 |
+
"step": 1100
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 1.1487452866987389,
|
| 1642 |
+
"grad_norm": 1.4845924377441406,
|
| 1643 |
+
"learning_rate": 3.240691964788012e-05,
|
| 1644 |
+
"loss": 0.6344992160797119,
|
| 1645 |
+
"step": 1105
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 1.1539461708490444,
|
| 1649 |
+
"grad_norm": 1.515212059020996,
|
| 1650 |
+
"learning_rate": 3.207677227685989e-05,
|
| 1651 |
+
"loss": 0.6564799785614014,
|
| 1652 |
+
"step": 1110
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 1.15914705499935,
|
| 1656 |
+
"grad_norm": 1.382857084274292,
|
| 1657 |
+
"learning_rate": 3.1747185760966985e-05,
|
| 1658 |
+
"loss": 0.6568068981170654,
|
| 1659 |
+
"step": 1115
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 1.1643479391496554,
|
| 1663 |
+
"grad_norm": 1.4786866903305054,
|
| 1664 |
+
"learning_rate": 3.141818343037621e-05,
|
| 1665 |
+
"loss": 0.6519091129302979,
|
| 1666 |
+
"step": 1120
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 1.169548823299961,
|
| 1670 |
+
"grad_norm": 1.5029971599578857,
|
| 1671 |
+
"learning_rate": 3.108978857391002e-05,
|
| 1672 |
+
"loss": 0.6406647682189941,
|
| 1673 |
+
"step": 1125
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 1.1747497074502666,
|
| 1677 |
+
"grad_norm": 1.4615740776062012,
|
| 1678 |
+
"learning_rate": 3.076202443739014e-05,
|
| 1679 |
+
"loss": 0.6860923290252685,
|
| 1680 |
+
"step": 1130
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 1.1799505916005721,
|
| 1684 |
+
"grad_norm": 1.4388511180877686,
|
| 1685 |
+
"learning_rate": 3.0434914221992032e-05,
|
| 1686 |
+
"loss": 0.6385154724121094,
|
| 1687 |
+
"step": 1135
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 1.1851514757508776,
|
| 1691 |
+
"grad_norm": 1.4187670946121216,
|
| 1692 |
+
"learning_rate": 3.0108481082602517e-05,
|
| 1693 |
+
"loss": 0.6268198013305664,
|
| 1694 |
+
"step": 1140
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 1.1903523599011832,
|
| 1698 |
+
"grad_norm": 1.5264593362808228,
|
| 1699 |
+
"learning_rate": 2.9782748126180885e-05,
|
| 1700 |
+
"loss": 0.6531328678131103,
|
| 1701 |
+
"step": 1145
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 1.1955532440514887,
|
| 1705 |
+
"grad_norm": 1.4612548351287842,
|
| 1706 |
+
"learning_rate": 2.945773841012303e-05,
|
| 1707 |
+
"loss": 0.669494915008545,
|
| 1708 |
+
"step": 1150
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 1.2007541282017944,
|
| 1712 |
+
"grad_norm": 1.267225742340088,
|
| 1713 |
+
"learning_rate": 2.913347494062949e-05,
|
| 1714 |
+
"loss": 0.6084520816802979,
|
| 1715 |
+
"step": 1155
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 1.2059550123521,
|
| 1719 |
+
"grad_norm": 1.449588418006897,
|
| 1720 |
+
"learning_rate": 2.8809980671076803e-05,
|
| 1721 |
+
"loss": 0.6461035728454589,
|
| 1722 |
+
"step": 1160
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 1.2111558965024054,
|
| 1726 |
+
"grad_norm": 1.3878182172775269,
|
| 1727 |
+
"learning_rate": 2.848727850039281e-05,
|
| 1728 |
+
"loss": 0.6444483280181885,
|
| 1729 |
+
"step": 1165
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 1.216356780652711,
|
| 1733 |
+
"grad_norm": 1.510225772857666,
|
| 1734 |
+
"learning_rate": 2.8165391271435667e-05,
|
| 1735 |
+
"loss": 0.6362089157104492,
|
| 1736 |
+
"step": 1170
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 1.2215576648030164,
|
| 1740 |
+
"grad_norm": 1.3843779563903809,
|
| 1741 |
+
"learning_rate": 2.7844341769376888e-05,
|
| 1742 |
+
"loss": 0.6338253974914551,
|
| 1743 |
+
"step": 1175
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 1.2267585489533221,
|
| 1747 |
+
"grad_norm": 1.414486289024353,
|
| 1748 |
+
"learning_rate": 2.752415272008853e-05,
|
| 1749 |
+
"loss": 0.6381827354431152,
|
| 1750 |
+
"step": 1180
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 1.2319594331036277,
|
| 1754 |
+
"grad_norm": 1.3414344787597656,
|
| 1755 |
+
"learning_rate": 2.720484678853445e-05,
|
| 1756 |
+
"loss": 0.6552750587463378,
|
| 1757 |
+
"step": 1185
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 1.2371603172539332,
|
| 1761 |
+
"grad_norm": 1.470218539237976,
|
| 1762 |
+
"learning_rate": 2.6886446577165987e-05,
|
| 1763 |
+
"loss": 0.6548665523529053,
|
| 1764 |
+
"step": 1190
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 1.2423612014042387,
|
| 1768 |
+
"grad_norm": 1.4118874073028564,
|
| 1769 |
+
"learning_rate": 2.656897462432193e-05,
|
| 1770 |
+
"loss": 0.6231658935546875,
|
| 1771 |
+
"step": 1195
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 1.2475620855545442,
|
| 1775 |
+
"grad_norm": 1.407113790512085,
|
| 1776 |
+
"learning_rate": 2.6252453402633284e-05,
|
| 1777 |
+
"loss": 0.5831446647644043,
|
| 1778 |
+
"step": 1200
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 1.2475620855545442,
|
| 1782 |
+
"eval_loss": 0.7889392971992493,
|
| 1783 |
+
"eval_runtime": 130.1098,
|
| 1784 |
+
"eval_samples_per_second": 1.968,
|
| 1785 |
+
"eval_steps_per_second": 1.968,
|
| 1786 |
+
"step": 1200
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 1.25276296970485,
|
| 1790 |
+
"grad_norm": 1.5195738077163696,
|
| 1791 |
+
"learning_rate": 2.593690531743231e-05,
|
| 1792 |
+
"loss": 0.6311056613922119,
|
| 1793 |
+
"step": 1205
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 1.2579638538551554,
|
| 1797 |
+
"grad_norm": 1.4188272953033447,
|
| 1798 |
+
"learning_rate": 2.5622352705166725e-05,
|
| 1799 |
+
"loss": 0.6084880352020263,
|
| 1800 |
+
"step": 1210
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 1.263164738005461,
|
| 1804 |
+
"grad_norm": 1.3883174657821655,
|
| 1805 |
+
"learning_rate": 2.5308817831818447e-05,
|
| 1806 |
+
"loss": 0.6124576568603516,
|
| 1807 |
+
"step": 1215
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 1.2683656221557664,
|
| 1811 |
+
"grad_norm": 1.4531702995300293,
|
| 1812 |
+
"learning_rate": 2.4996322891327576e-05,
|
| 1813 |
+
"loss": 0.6091352462768554,
|
| 1814 |
+
"step": 1220
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 1.273566506306072,
|
| 1818 |
+
"grad_norm": 1.4332900047302246,
|
| 1819 |
+
"learning_rate": 2.46848900040213e-05,
|
| 1820 |
+
"loss": 0.6466999053955078,
|
| 1821 |
+
"step": 1225
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 1.2787673904563777,
|
| 1825 |
+
"grad_norm": 1.4958285093307495,
|
| 1826 |
+
"learning_rate": 2.437454121504809e-05,
|
| 1827 |
+
"loss": 0.616027545928955,
|
| 1828 |
+
"step": 1230
|
| 1829 |
+
},
|
| 1830 |
+
{
|
| 1831 |
+
"epoch": 1.2839682746066832,
|
| 1832 |
+
"grad_norm": 1.4578135013580322,
|
| 1833 |
+
"learning_rate": 2.406529849281726e-05,
|
| 1834 |
+
"loss": 0.6332333087921143,
|
| 1835 |
+
"step": 1235
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 1.2891691587569887,
|
| 1839 |
+
"grad_norm": 1.4748591184616089,
|
| 1840 |
+
"learning_rate": 2.375718372744384e-05,
|
| 1841 |
+
"loss": 0.6314262866973877,
|
| 1842 |
+
"step": 1240
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 1.2943700429072942,
|
| 1846 |
+
"grad_norm": 1.4996991157531738,
|
| 1847 |
+
"learning_rate": 2.3450218729199108e-05,
|
| 1848 |
+
"loss": 0.6231923580169678,
|
| 1849 |
+
"step": 1245
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 1.2995709270575997,
|
| 1853 |
+
"grad_norm": 1.4916212558746338,
|
| 1854 |
+
"learning_rate": 2.314442522696669e-05,
|
| 1855 |
+
"loss": 0.6058928966522217,
|
| 1856 |
+
"step": 1250
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 1.3047718112079054,
|
| 1860 |
+
"grad_norm": 1.3732458353042603,
|
| 1861 |
+
"learning_rate": 2.283982486670449e-05,
|
| 1862 |
+
"loss": 0.5989131450653076,
|
| 1863 |
+
"step": 1255
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 1.309972695358211,
|
| 1867 |
+
"grad_norm": 1.3525115251541138,
|
| 1868 |
+
"learning_rate": 2.2536439209912393e-05,
|
| 1869 |
+
"loss": 0.6314842700958252,
|
| 1870 |
+
"step": 1260
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 1.3151735795085164,
|
| 1874 |
+
"grad_norm": 1.4011585712432861,
|
| 1875 |
+
"learning_rate": 2.2234289732106102e-05,
|
| 1876 |
+
"loss": 0.6161143779754639,
|
| 1877 |
+
"step": 1265
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 1.320374463658822,
|
| 1881 |
+
"grad_norm": 1.2732415199279785,
|
| 1882 |
+
"learning_rate": 2.193339782129685e-05,
|
| 1883 |
+
"loss": 0.5840548515319824,
|
| 1884 |
+
"step": 1270
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 1.3255753478091274,
|
| 1888 |
+
"grad_norm": 1.5150249004364014,
|
| 1889 |
+
"learning_rate": 2.1633784776477585e-05,
|
| 1890 |
+
"loss": 0.625645112991333,
|
| 1891 |
+
"step": 1275
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 1.3307762319594332,
|
| 1895 |
+
"grad_norm": 1.4052765369415283,
|
| 1896 |
+
"learning_rate": 2.1335471806115117e-05,
|
| 1897 |
+
"loss": 0.599894666671753,
|
| 1898 |
+
"step": 1280
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 1.3359771161097387,
|
| 1902 |
+
"grad_norm": 1.4317781925201416,
|
| 1903 |
+
"learning_rate": 2.1038480026648945e-05,
|
| 1904 |
+
"loss": 0.584019947052002,
|
| 1905 |
+
"step": 1285
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 1.3411780002600442,
|
| 1909 |
+
"grad_norm": 1.4249917268753052,
|
| 1910 |
+
"learning_rate": 2.074283046099654e-05,
|
| 1911 |
+
"loss": 0.6218175411224365,
|
| 1912 |
+
"step": 1290
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 1.3463788844103497,
|
| 1916 |
+
"grad_norm": 1.450347661972046,
|
| 1917 |
+
"learning_rate": 2.044854403706509e-05,
|
| 1918 |
+
"loss": 0.6018783569335937,
|
| 1919 |
+
"step": 1295
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 1.3515797685606552,
|
| 1923 |
+
"grad_norm": 1.3482204675674438,
|
| 1924 |
+
"learning_rate": 2.0155641586270286e-05,
|
| 1925 |
+
"loss": 0.5710643291473388,
|
| 1926 |
+
"step": 1300
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 1.3515797685606552,
|
| 1930 |
+
"eval_loss": 0.7516965270042419,
|
| 1931 |
+
"eval_runtime": 129.9408,
|
| 1932 |
+
"eval_samples_per_second": 1.97,
|
| 1933 |
+
"eval_steps_per_second": 1.97,
|
| 1934 |
+
"step": 1300
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 1.356780652710961,
|
| 1938 |
+
"grad_norm": 1.4780831336975098,
|
| 1939 |
+
"learning_rate": 1.9864143842061504e-05,
|
| 1940 |
+
"loss": 0.6006845951080322,
|
| 1941 |
+
"step": 1305
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 1.3619815368612664,
|
| 1945 |
+
"grad_norm": 1.6098695993423462,
|
| 1946 |
+
"learning_rate": 1.9574071438454388e-05,
|
| 1947 |
+
"loss": 0.5974199295043945,
|
| 1948 |
+
"step": 1310
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 1.367182421011572,
|
| 1952 |
+
"grad_norm": 1.4274905920028687,
|
| 1953 |
+
"learning_rate": 1.9285444908570064e-05,
|
| 1954 |
+
"loss": 0.5996578216552735,
|
| 1955 |
+
"step": 1315
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 1.3723833051618775,
|
| 1959 |
+
"grad_norm": 1.4278326034545898,
|
| 1960 |
+
"learning_rate": 1.8998284683181824e-05,
|
| 1961 |
+
"loss": 0.6217168807983399,
|
| 1962 |
+
"step": 1320
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 1.377584189312183,
|
| 1966 |
+
"grad_norm": 1.3714914321899414,
|
| 1967 |
+
"learning_rate": 1.871261108926882e-05,
|
| 1968 |
+
"loss": 0.6057654857635498,
|
| 1969 |
+
"step": 1325
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 1.3827850734624887,
|
| 1973 |
+
"grad_norm": 1.468660831451416,
|
| 1974 |
+
"learning_rate": 1.842844434857724e-05,
|
| 1975 |
+
"loss": 0.6053857803344727,
|
| 1976 |
+
"step": 1330
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 1.3879859576127942,
|
| 1980 |
+
"grad_norm": 1.3222684860229492,
|
| 1981 |
+
"learning_rate": 1.814580457618885e-05,
|
| 1982 |
+
"loss": 0.5948523044586181,
|
| 1983 |
+
"step": 1335
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 1.3931868417630997,
|
| 1987 |
+
"grad_norm": 1.3946906328201294,
|
| 1988 |
+
"learning_rate": 1.7864711779097122e-05,
|
| 1989 |
+
"loss": 0.5642759323120117,
|
| 1990 |
+
"step": 1340
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 1.3983877259134052,
|
| 1994 |
+
"grad_norm": 1.404165506362915,
|
| 1995 |
+
"learning_rate": 1.7585185854791076e-05,
|
| 1996 |
+
"loss": 0.5775787353515625,
|
| 1997 |
+
"step": 1345
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 1.4035886100637107,
|
| 2001 |
+
"grad_norm": 1.370401382446289,
|
| 2002 |
+
"learning_rate": 1.7307246589846767e-05,
|
| 2003 |
+
"loss": 0.5661319732666016,
|
| 2004 |
+
"step": 1350
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 1.4087894942140164,
|
| 2008 |
+
"grad_norm": 1.3934425115585327,
|
| 2009 |
+
"learning_rate": 1.7030913658526675e-05,
|
| 2010 |
+
"loss": 0.5760215282440185,
|
| 2011 |
+
"step": 1355
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 1.413990378364322,
|
| 2015 |
+
"grad_norm": 1.389297366142273,
|
| 2016 |
+
"learning_rate": 1.6756206621387e-05,
|
| 2017 |
+
"loss": 0.5774462699890137,
|
| 2018 |
+
"step": 1360
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 1.4191912625146275,
|
| 2022 |
+
"grad_norm": 1.511326789855957,
|
| 2023 |
+
"learning_rate": 1.6483144923893135e-05,
|
| 2024 |
+
"loss": 0.585289192199707,
|
| 2025 |
+
"step": 1365
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 1.424392146664933,
|
| 2029 |
+
"grad_norm": 1.4418237209320068,
|
| 2030 |
+
"learning_rate": 1.62117478950431e-05,
|
| 2031 |
+
"loss": 0.5913166999816895,
|
| 2032 |
+
"step": 1370
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 1.4295930308152385,
|
| 2036 |
+
"grad_norm": 1.46451997756958,
|
| 2037 |
+
"learning_rate": 1.5942034745999383e-05,
|
| 2038 |
+
"loss": 0.5850035667419433,
|
| 2039 |
+
"step": 1375
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 1.4347939149655442,
|
| 2043 |
+
"grad_norm": 1.308406114578247,
|
| 2044 |
+
"learning_rate": 1.5674024568729036e-05,
|
| 2045 |
+
"loss": 0.5444441795349121,
|
| 2046 |
+
"step": 1380
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 1.4399947991158497,
|
| 2050 |
+
"grad_norm": 1.340357780456543,
|
| 2051 |
+
"learning_rate": 1.5407736334652214e-05,
|
| 2052 |
+
"loss": 0.5663641929626465,
|
| 2053 |
+
"step": 1385
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 1.4451956832661552,
|
| 2057 |
+
"grad_norm": 1.3704862594604492,
|
| 2058 |
+
"learning_rate": 1.5143188893299266e-05,
|
| 2059 |
+
"loss": 0.579612398147583,
|
| 2060 |
+
"step": 1390
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 1.4503965674164607,
|
| 2064 |
+
"grad_norm": 1.418916940689087,
|
| 2065 |
+
"learning_rate": 1.4880400970976428e-05,
|
| 2066 |
+
"loss": 0.5483696460723877,
|
| 2067 |
+
"step": 1395
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 1.4555974515667662,
|
| 2071 |
+
"grad_norm": 1.4289562702178955,
|
| 2072 |
+
"learning_rate": 1.461939116944032e-05,
|
| 2073 |
+
"loss": 0.5578598976135254,
|
| 2074 |
+
"step": 1400
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 1.4555974515667662,
|
| 2078 |
+
"eval_loss": 0.7209516763687134,
|
| 2079 |
+
"eval_runtime": 129.7511,
|
| 2080 |
+
"eval_samples_per_second": 1.973,
|
| 2081 |
+
"eval_steps_per_second": 1.973,
|
| 2082 |
+
"step": 1400
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 1.460798335717072,
|
| 2086 |
+
"grad_norm": 1.397242546081543,
|
| 2087 |
+
"learning_rate": 1.4360177964581156e-05,
|
| 2088 |
+
"loss": 0.5415009498596192,
|
| 2089 |
+
"step": 1405
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 1.4659992198673775,
|
| 2093 |
+
"grad_norm": 1.3476572036743164,
|
| 2094 |
+
"learning_rate": 1.4102779705114907e-05,
|
| 2095 |
+
"loss": 0.5409503936767578,
|
| 2096 |
+
"step": 1410
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 1.471200104017683,
|
| 2100 |
+
"grad_norm": 1.4320838451385498,
|
| 2101 |
+
"learning_rate": 1.3847214611284439e-05,
|
| 2102 |
+
"loss": 0.5809547424316406,
|
| 2103 |
+
"step": 1415
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 1.4764009881679885,
|
| 2107 |
+
"grad_norm": 1.4180504083633423,
|
| 2108 |
+
"learning_rate": 1.3593500773569854e-05,
|
| 2109 |
+
"loss": 0.5446939945220948,
|
| 2110 |
+
"step": 1420
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 1.481601872318294,
|
| 2114 |
+
"grad_norm": 1.4159796237945557,
|
| 2115 |
+
"learning_rate": 1.334165615140783e-05,
|
| 2116 |
+
"loss": 0.5414989471435547,
|
| 2117 |
+
"step": 1425
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 1.4868027564685997,
|
| 2121 |
+
"grad_norm": 1.3080824613571167,
|
| 2122 |
+
"learning_rate": 1.3091698571920422e-05,
|
| 2123 |
+
"loss": 0.5712019443511963,
|
| 2124 |
+
"step": 1430
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 1.4920036406189052,
|
| 2128 |
+
"grad_norm": 1.2765617370605469,
|
| 2129 |
+
"learning_rate": 1.284364572865311e-05,
|
| 2130 |
+
"loss": 0.5223927974700928,
|
| 2131 |
+
"step": 1435
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 1.4972045247692107,
|
| 2135 |
+
"grad_norm": 1.459304928779602,
|
| 2136 |
+
"learning_rate": 1.2597515180322368e-05,
|
| 2137 |
+
"loss": 0.5872461318969726,
|
| 2138 |
+
"step": 1440
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 1.5024054089195165,
|
| 2142 |
+
"grad_norm": 1.3618521690368652,
|
| 2143 |
+
"learning_rate": 1.23533243495727e-05,
|
| 2144 |
+
"loss": 0.5361846446990967,
|
| 2145 |
+
"step": 1445
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 1.5076062930698217,
|
| 2149 |
+
"grad_norm": 1.3767704963684082,
|
| 2150 |
+
"learning_rate": 1.2111090521743374e-05,
|
| 2151 |
+
"loss": 0.5445142269134522,
|
| 2152 |
+
"step": 1450
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 1.5128071772201275,
|
| 2156 |
+
"grad_norm": 1.2690768241882324,
|
| 2157 |
+
"learning_rate": 1.1870830843644917e-05,
|
| 2158 |
+
"loss": 0.5451547622680664,
|
| 2159 |
+
"step": 1455
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 1.518008061370433,
|
| 2163 |
+
"grad_norm": 1.356768012046814,
|
| 2164 |
+
"learning_rate": 1.1632562322345292e-05,
|
| 2165 |
+
"loss": 0.5559448719024658,
|
| 2166 |
+
"step": 1460
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 1.5232089455207385,
|
| 2170 |
+
"grad_norm": 1.4047377109527588,
|
| 2171 |
+
"learning_rate": 1.1396301823966054e-05,
|
| 2172 |
+
"loss": 0.5453744888305664,
|
| 2173 |
+
"step": 1465
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 1.5284098296710442,
|
| 2177 |
+
"grad_norm": 1.4262696504592896,
|
| 2178 |
+
"learning_rate": 1.1162066072488434e-05,
|
| 2179 |
+
"loss": 0.5406304359436035,
|
| 2180 |
+
"step": 1470
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 1.5336107138213495,
|
| 2184 |
+
"grad_norm": 1.4099568128585815,
|
| 2185 |
+
"learning_rate": 1.0929871648569591e-05,
|
| 2186 |
+
"loss": 0.5617681980133057,
|
| 2187 |
+
"step": 1475
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 1.5388115979716552,
|
| 2191 |
+
"grad_norm": 1.317654013633728,
|
| 2192 |
+
"learning_rate": 1.0699734988368817e-05,
|
| 2193 |
+
"loss": 0.5236352443695068,
|
| 2194 |
+
"step": 1480
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 1.5440124821219607,
|
| 2198 |
+
"grad_norm": 1.3843480348587036,
|
| 2199 |
+
"learning_rate": 1.0471672382384185e-05,
|
| 2200 |
+
"loss": 0.5739215850830078,
|
| 2201 |
+
"step": 1485
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 1.5492133662722662,
|
| 2205 |
+
"grad_norm": 1.4144139289855957,
|
| 2206 |
+
"learning_rate": 1.0245699974299356e-05,
|
| 2207 |
+
"loss": 0.5243452548980713,
|
| 2208 |
+
"step": 1490
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 1.554414250422572,
|
| 2212 |
+
"grad_norm": 1.4148069620132446,
|
| 2213 |
+
"learning_rate": 1.002183375984085e-05,
|
| 2214 |
+
"loss": 0.5655048847198486,
|
| 2215 |
+
"step": 1495
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 1.5596151345728773,
|
| 2219 |
+
"grad_norm": 1.4749091863632202,
|
| 2220 |
+
"learning_rate": 9.800089585645733e-06,
|
| 2221 |
+
"loss": 0.5409163951873779,
|
| 2222 |
+
"step": 1500
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 1.5596151345728773,
|
| 2226 |
+
"eval_loss": 0.6939327120780945,
|
| 2227 |
+
"eval_runtime": 129.7422,
|
| 2228 |
+
"eval_samples_per_second": 1.973,
|
| 2229 |
+
"eval_steps_per_second": 1.973,
|
| 2230 |
+
"step": 1500
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 1.564816018723183,
|
| 2234 |
+
"grad_norm": 1.397222876548767,
|
| 2235 |
+
"learning_rate": 9.58048314813992e-06,
|
| 2236 |
+
"loss": 0.5466369152069092,
|
| 2237 |
+
"step": 1505
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 1.5700169028734885,
|
| 2241 |
+
"grad_norm": 1.4299346208572388,
|
| 2242 |
+
"learning_rate": 9.363029992427112e-06,
|
| 2243 |
+
"loss": 0.5456615447998047,
|
| 2244 |
+
"step": 1510
|
| 2245 |
+
},
|
| 2246 |
+
{
|
| 2247 |
+
"epoch": 1.575217787023794,
|
| 2248 |
+
"grad_norm": 1.4388434886932373,
|
| 2249 |
+
"learning_rate": 9.147745511188363e-06,
|
| 2250 |
+
"loss": 0.5131537914276123,
|
| 2251 |
+
"step": 1515
|
| 2252 |
+
},
|
| 2253 |
+
{
|
| 2254 |
+
"epoch": 1.5804186711740997,
|
| 2255 |
+
"grad_norm": 1.3658560514450073,
|
| 2256 |
+
"learning_rate": 8.934644943592551e-06,
|
| 2257 |
+
"loss": 0.5328524112701416,
|
| 2258 |
+
"step": 1520
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 1.585619555324405,
|
| 2262 |
+
"grad_norm": 1.4248464107513428,
|
| 2263 |
+
"learning_rate": 8.723743374217566e-06,
|
| 2264 |
+
"loss": 0.5406161785125733,
|
| 2265 |
+
"step": 1525
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 1.5908204394747107,
|
| 2269 |
+
"grad_norm": 1.2822633981704712,
|
| 2270 |
+
"learning_rate": 8.51505573198264e-06,
|
| 2271 |
+
"loss": 0.5242678642272949,
|
| 2272 |
+
"step": 1530
|
| 2273 |
+
},
|
| 2274 |
+
{
|
| 2275 |
+
"epoch": 1.5960213236250163,
|
| 2276 |
+
"grad_norm": 1.3976045846939087,
|
| 2277 |
+
"learning_rate": 8.308596789091492e-06,
|
| 2278 |
+
"loss": 0.5548820495605469,
|
| 2279 |
+
"step": 1535
|
| 2280 |
+
},
|
| 2281 |
+
{
|
| 2282 |
+
"epoch": 1.6012222077753218,
|
| 2283 |
+
"grad_norm": 1.3557575941085815,
|
| 2284 |
+
"learning_rate": 8.104381159986717e-06,
|
| 2285 |
+
"loss": 0.5298625946044921,
|
| 2286 |
+
"step": 1540
|
| 2287 |
+
},
|
| 2288 |
+
{
|
| 2289 |
+
"epoch": 1.6064230919256275,
|
| 2290 |
+
"grad_norm": 1.343584656715393,
|
| 2291 |
+
"learning_rate": 7.902423300315271e-06,
|
| 2292 |
+
"loss": 0.5180022239685058,
|
| 2293 |
+
"step": 1545
|
| 2294 |
+
},
|
| 2295 |
+
{
|
| 2296 |
+
"epoch": 1.6116239760759328,
|
| 2297 |
+
"grad_norm": 1.4940485954284668,
|
| 2298 |
+
"learning_rate": 7.70273750590521e-06,
|
| 2299 |
+
"loss": 0.5428160667419434,
|
| 2300 |
+
"step": 1550
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 1.6168248602262385,
|
| 2304 |
+
"grad_norm": 1.3675767183303833,
|
| 2305 |
+
"learning_rate": 7.5053379117537136e-06,
|
| 2306 |
+
"loss": 0.516777229309082,
|
| 2307 |
+
"step": 1555
|
| 2308 |
+
},
|
| 2309 |
+
{
|
| 2310 |
+
"epoch": 1.622025744376544,
|
| 2311 |
+
"grad_norm": 1.4647380113601685,
|
| 2312 |
+
"learning_rate": 7.310238491026567e-06,
|
| 2313 |
+
"loss": 0.5383810043334961,
|
| 2314 |
+
"step": 1560
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 1.6272266285268495,
|
| 2318 |
+
"grad_norm": 1.482635736465454,
|
| 2319 |
+
"learning_rate": 7.117453054069039e-06,
|
| 2320 |
+
"loss": 0.5144073009490967,
|
| 2321 |
+
"step": 1565
|
| 2322 |
+
},
|
| 2323 |
+
{
|
| 2324 |
+
"epoch": 1.6324275126771552,
|
| 2325 |
+
"grad_norm": 1.5026439428329468,
|
| 2326 |
+
"learning_rate": 6.926995247428285e-06,
|
| 2327 |
+
"loss": 0.5365920066833496,
|
| 2328 |
+
"step": 1570
|
| 2329 |
+
},
|
| 2330 |
+
{
|
| 2331 |
+
"epoch": 1.6376283968274605,
|
| 2332 |
+
"grad_norm": 1.4037001132965088,
|
| 2333 |
+
"learning_rate": 6.7388785528874e-06,
|
| 2334 |
+
"loss": 0.539414644241333,
|
| 2335 |
+
"step": 1575
|
| 2336 |
+
},
|
| 2337 |
+
{
|
| 2338 |
+
"epoch": 1.6428292809777663,
|
| 2339 |
+
"grad_norm": 1.3790786266326904,
|
| 2340 |
+
"learning_rate": 6.553116286511012e-06,
|
| 2341 |
+
"loss": 0.5314173221588134,
|
| 2342 |
+
"step": 1580
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 1.6480301651280718,
|
| 2346 |
+
"grad_norm": 1.3834137916564941,
|
| 2347 |
+
"learning_rate": 6.369721597702802e-06,
|
| 2348 |
+
"loss": 0.5361592292785644,
|
| 2349 |
+
"step": 1585
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 1.6532310492783773,
|
| 2353 |
+
"grad_norm": 1.3719836473464966,
|
| 2354 |
+
"learning_rate": 6.188707468274597e-06,
|
| 2355 |
+
"loss": 0.5356816291809082,
|
| 2356 |
+
"step": 1590
|
| 2357 |
+
},
|
| 2358 |
+
{
|
| 2359 |
+
"epoch": 1.658431933428683,
|
| 2360 |
+
"grad_norm": 1.5612096786499023,
|
| 2361 |
+
"learning_rate": 6.010086711527519e-06,
|
| 2362 |
+
"loss": 0.522746467590332,
|
| 2363 |
+
"step": 1595
|
| 2364 |
+
},
|
| 2365 |
+
{
|
| 2366 |
+
"epoch": 1.6636328175789883,
|
| 2367 |
+
"grad_norm": 1.3957282304763794,
|
| 2368 |
+
"learning_rate": 5.833871971344947e-06,
|
| 2369 |
+
"loss": 0.5154781341552734,
|
| 2370 |
+
"step": 1600
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"epoch": 1.6636328175789883,
|
| 2374 |
+
"eval_loss": 0.6775081157684326,
|
| 2375 |
+
"eval_runtime": 129.5251,
|
| 2376 |
+
"eval_samples_per_second": 1.976,
|
| 2377 |
+
"eval_steps_per_second": 1.976,
|
| 2378 |
+
"step": 1600
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 1.668833701729294,
|
| 2382 |
+
"grad_norm": 1.3207283020019531,
|
| 2383 |
+
"learning_rate": 5.6600757212975065e-06,
|
| 2384 |
+
"loss": 0.5063146591186524,
|
| 2385 |
+
"step": 1605
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 1.6740345858795995,
|
| 2389 |
+
"grad_norm": 1.4711432456970215,
|
| 2390 |
+
"learning_rate": 5.4887102637600995e-06,
|
| 2391 |
+
"loss": 0.5405515193939209,
|
| 2392 |
+
"step": 1610
|
| 2393 |
+
},
|
| 2394 |
+
{
|
| 2395 |
+
"epoch": 1.679235470029905,
|
| 2396 |
+
"grad_norm": 1.4866151809692383,
|
| 2397 |
+
"learning_rate": 5.319787729041084e-06,
|
| 2398 |
+
"loss": 0.5130389213562012,
|
| 2399 |
+
"step": 1615
|
| 2400 |
+
},
|
| 2401 |
+
{
|
| 2402 |
+
"epoch": 1.6844363541802108,
|
| 2403 |
+
"grad_norm": 1.3158960342407227,
|
| 2404 |
+
"learning_rate": 5.153320074523618e-06,
|
| 2405 |
+
"loss": 0.5351908206939697,
|
| 2406 |
+
"step": 1620
|
| 2407 |
+
},
|
| 2408 |
+
{
|
| 2409 |
+
"epoch": 1.689637238330516,
|
| 2410 |
+
"grad_norm": 1.3680565357208252,
|
| 2411 |
+
"learning_rate": 4.9893190838192415e-06,
|
| 2412 |
+
"loss": 0.4998152256011963,
|
| 2413 |
+
"step": 1625
|
| 2414 |
+
},
|
| 2415 |
+
{
|
| 2416 |
+
"epoch": 1.6948381224808218,
|
| 2417 |
+
"grad_norm": 1.4631091356277466,
|
| 2418 |
+
"learning_rate": 4.827796365933752e-06,
|
| 2419 |
+
"loss": 0.5004712104797363,
|
| 2420 |
+
"step": 1630
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 1.7000390066311273,
|
| 2424 |
+
"grad_norm": 1.3971714973449707,
|
| 2425 |
+
"learning_rate": 4.668763354445425e-06,
|
| 2426 |
+
"loss": 0.5030968666076661,
|
| 2427 |
+
"step": 1635
|
| 2428 |
+
},
|
| 2429 |
+
{
|
| 2430 |
+
"epoch": 1.7052398907814328,
|
| 2431 |
+
"grad_norm": 1.2639859914779663,
|
| 2432 |
+
"learning_rate": 4.5122313066957355e-06,
|
| 2433 |
+
"loss": 0.5040280818939209,
|
| 2434 |
+
"step": 1640
|
| 2435 |
+
},
|
| 2436 |
+
{
|
| 2437 |
+
"epoch": 1.7104407749317385,
|
| 2438 |
+
"grad_norm": 1.3765854835510254,
|
| 2439 |
+
"learning_rate": 4.358211302992414e-06,
|
| 2440 |
+
"loss": 0.503818941116333,
|
| 2441 |
+
"step": 1645
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 1.7156416590820438,
|
| 2445 |
+
"grad_norm": 1.3985488414764404,
|
| 2446 |
+
"learning_rate": 4.206714245825207e-06,
|
| 2447 |
+
"loss": 0.5131355285644531,
|
| 2448 |
+
"step": 1650
|
| 2449 |
+
},
|
| 2450 |
+
{
|
| 2451 |
+
"epoch": 1.7208425432323495,
|
| 2452 |
+
"grad_norm": 1.3251243829727173,
|
| 2453 |
+
"learning_rate": 4.057750859094029e-06,
|
| 2454 |
+
"loss": 0.5185832500457763,
|
| 2455 |
+
"step": 1655
|
| 2456 |
+
},
|
| 2457 |
+
{
|
| 2458 |
+
"epoch": 1.726043427382655,
|
| 2459 |
+
"grad_norm": 1.3081040382385254,
|
| 2460 |
+
"learning_rate": 3.911331687349957e-06,
|
| 2461 |
+
"loss": 0.5041447639465332,
|
| 2462 |
+
"step": 1660
|
| 2463 |
+
},
|
| 2464 |
+
{
|
| 2465 |
+
"epoch": 1.7312443115329605,
|
| 2466 |
+
"grad_norm": 1.2962945699691772,
|
| 2467 |
+
"learning_rate": 3.7674670950487337e-06,
|
| 2468 |
+
"loss": 0.49753355979919434,
|
| 2469 |
+
"step": 1665
|
| 2470 |
+
},
|
| 2471 |
+
{
|
| 2472 |
+
"epoch": 1.7364451956832663,
|
| 2473 |
+
"grad_norm": 1.4440361261367798,
|
| 2474 |
+
"learning_rate": 3.626167265817162e-06,
|
| 2475 |
+
"loss": 0.5241962432861328,
|
| 2476 |
+
"step": 1670
|
| 2477 |
+
},
|
| 2478 |
+
{
|
| 2479 |
+
"epoch": 1.7416460798335716,
|
| 2480 |
+
"grad_norm": 1.3910887241363525,
|
| 2481 |
+
"learning_rate": 3.487442201732245e-06,
|
| 2482 |
+
"loss": 0.5163005352020263,
|
| 2483 |
+
"step": 1675
|
| 2484 |
+
},
|
| 2485 |
+
{
|
| 2486 |
+
"epoch": 1.7468469639838773,
|
| 2487 |
+
"grad_norm": 1.4579485654830933,
|
| 2488 |
+
"learning_rate": 3.3513017226131537e-06,
|
| 2489 |
+
"loss": 0.5024435520172119,
|
| 2490 |
+
"step": 1680
|
| 2491 |
+
},
|
| 2492 |
+
{
|
| 2493 |
+
"epoch": 1.7520478481341828,
|
| 2494 |
+
"grad_norm": 1.3572936058044434,
|
| 2495 |
+
"learning_rate": 3.217755465326127e-06,
|
| 2496 |
+
"loss": 0.5091588020324707,
|
| 2497 |
+
"step": 1685
|
| 2498 |
+
},
|
| 2499 |
+
{
|
| 2500 |
+
"epoch": 1.7572487322844883,
|
| 2501 |
+
"grad_norm": 1.3362730741500854,
|
| 2502 |
+
"learning_rate": 3.0868128831023123e-06,
|
| 2503 |
+
"loss": 0.4787764549255371,
|
| 2504 |
+
"step": 1690
|
| 2505 |
+
},
|
| 2506 |
+
{
|
| 2507 |
+
"epoch": 1.762449616434794,
|
| 2508 |
+
"grad_norm": 1.5451667308807373,
|
| 2509 |
+
"learning_rate": 2.9584832448686216e-06,
|
| 2510 |
+
"loss": 0.5192002773284912,
|
| 2511 |
+
"step": 1695
|
| 2512 |
+
},
|
| 2513 |
+
{
|
| 2514 |
+
"epoch": 1.7676505005850993,
|
| 2515 |
+
"grad_norm": 1.3013676404953003,
|
| 2516 |
+
"learning_rate": 2.832775634591589e-06,
|
| 2517 |
+
"loss": 0.4944888114929199,
|
| 2518 |
+
"step": 1700
|
| 2519 |
+
},
|
| 2520 |
+
{
|
| 2521 |
+
"epoch": 1.7676505005850993,
|
| 2522 |
+
"eval_loss": 0.6653155088424683,
|
| 2523 |
+
"eval_runtime": 129.5395,
|
| 2524 |
+
"eval_samples_per_second": 1.976,
|
| 2525 |
+
"eval_steps_per_second": 1.976,
|
| 2526 |
+
"step": 1700
|
| 2527 |
+
},
|
| 2528 |
+
{
|
| 2529 |
+
"epoch": 1.772851384735405,
|
| 2530 |
+
"grad_norm": 1.4618582725524902,
|
| 2531 |
+
"learning_rate": 2.709698950634412e-06,
|
| 2532 |
+
"loss": 0.5045624732971191,
|
| 2533 |
+
"step": 1705
|
| 2534 |
+
},
|
| 2535 |
+
{
|
| 2536 |
+
"epoch": 1.7780522688857106,
|
| 2537 |
+
"grad_norm": 1.4680557250976562,
|
| 2538 |
+
"learning_rate": 2.5892619051269873e-06,
|
| 2539 |
+
"loss": 0.5313224792480469,
|
| 2540 |
+
"step": 1710
|
| 2541 |
+
},
|
| 2542 |
+
{
|
| 2543 |
+
"epoch": 1.783253153036016,
|
| 2544 |
+
"grad_norm": 1.441771149635315,
|
| 2545 |
+
"learning_rate": 2.471473023349269e-06,
|
| 2546 |
+
"loss": 0.5317369937896729,
|
| 2547 |
+
"step": 1715
|
| 2548 |
+
},
|
| 2549 |
+
{
|
| 2550 |
+
"epoch": 1.7884540371863218,
|
| 2551 |
+
"grad_norm": 1.377977728843689,
|
| 2552 |
+
"learning_rate": 2.356340643127797e-06,
|
| 2553 |
+
"loss": 0.49757208824157717,
|
| 2554 |
+
"step": 1720
|
| 2555 |
+
},
|
| 2556 |
+
{
|
| 2557 |
+
"epoch": 1.793654921336627,
|
| 2558 |
+
"grad_norm": 1.376712679862976,
|
| 2559 |
+
"learning_rate": 2.243872914245442e-06,
|
| 2560 |
+
"loss": 0.5022801399230957,
|
| 2561 |
+
"step": 1725
|
| 2562 |
+
},
|
| 2563 |
+
{
|
| 2564 |
+
"epoch": 1.7988558054869328,
|
| 2565 |
+
"grad_norm": 1.5128220319747925,
|
| 2566 |
+
"learning_rate": 2.1340777978646045e-06,
|
| 2567 |
+
"loss": 0.5198845863342285,
|
| 2568 |
+
"step": 1730
|
| 2569 |
+
},
|
| 2570 |
+
{
|
| 2571 |
+
"epoch": 1.8040566896372383,
|
| 2572 |
+
"grad_norm": 1.3930203914642334,
|
| 2573 |
+
"learning_rate": 2.026963065963572e-06,
|
| 2574 |
+
"loss": 0.502904748916626,
|
| 2575 |
+
"step": 1735
|
| 2576 |
+
},
|
| 2577 |
+
{
|
| 2578 |
+
"epoch": 1.8092575737875438,
|
| 2579 |
+
"grad_norm": 1.3942198753356934,
|
| 2580 |
+
"learning_rate": 1.9225363007864483e-06,
|
| 2581 |
+
"loss": 0.48986196517944336,
|
| 2582 |
+
"step": 1740
|
| 2583 |
+
},
|
| 2584 |
+
{
|
| 2585 |
+
"epoch": 1.8144584579378495,
|
| 2586 |
+
"grad_norm": 1.238763689994812,
|
| 2587 |
+
"learning_rate": 1.8208048943063872e-06,
|
| 2588 |
+
"loss": 0.48829169273376466,
|
| 2589 |
+
"step": 1745
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 1.8196593420881548,
|
| 2593 |
+
"grad_norm": 1.3654608726501465,
|
| 2594 |
+
"learning_rate": 1.7217760477023659e-06,
|
| 2595 |
+
"loss": 0.5089236259460449,
|
| 2596 |
+
"step": 1750
|
| 2597 |
+
},
|
| 2598 |
+
{
|
| 2599 |
+
"epoch": 1.8248602262384606,
|
| 2600 |
+
"grad_norm": 1.3893874883651733,
|
| 2601 |
+
"learning_rate": 1.6254567708494517e-06,
|
| 2602 |
+
"loss": 0.5198930740356446,
|
| 2603 |
+
"step": 1755
|
| 2604 |
+
},
|
| 2605 |
+
{
|
| 2606 |
+
"epoch": 1.830061110388766,
|
| 2607 |
+
"grad_norm": 1.4330559968948364,
|
| 2608 |
+
"learning_rate": 1.531853881822567e-06,
|
| 2609 |
+
"loss": 0.5197700500488281,
|
| 2610 |
+
"step": 1760
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"epoch": 1.8352619945390716,
|
| 2614 |
+
"grad_norm": 1.4249515533447266,
|
| 2615 |
+
"learning_rate": 1.4409740064138844e-06,
|
| 2616 |
+
"loss": 0.502013874053955,
|
| 2617 |
+
"step": 1765
|
| 2618 |
+
},
|
| 2619 |
+
{
|
| 2620 |
+
"epoch": 1.8404628786893773,
|
| 2621 |
+
"grad_norm": 1.3588781356811523,
|
| 2622 |
+
"learning_rate": 1.3528235776638111e-06,
|
| 2623 |
+
"loss": 0.48603029251098634,
|
| 2624 |
+
"step": 1770
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 1.8456637628396826,
|
| 2628 |
+
"grad_norm": 1.3336181640625,
|
| 2629 |
+
"learning_rate": 1.2674088354056148e-06,
|
| 2630 |
+
"loss": 0.5047059059143066,
|
| 2631 |
+
"step": 1775
|
| 2632 |
+
},
|
| 2633 |
+
{
|
| 2634 |
+
"epoch": 1.8508646469899883,
|
| 2635 |
+
"grad_norm": 1.3933433294296265,
|
| 2636 |
+
"learning_rate": 1.1847358258237329e-06,
|
| 2637 |
+
"loss": 0.5210882663726807,
|
| 2638 |
+
"step": 1780
|
| 2639 |
+
},
|
| 2640 |
+
{
|
| 2641 |
+
"epoch": 1.8560655311402938,
|
| 2642 |
+
"grad_norm": 1.4772483110427856,
|
| 2643 |
+
"learning_rate": 1.104810401025791e-06,
|
| 2644 |
+
"loss": 0.512470006942749,
|
| 2645 |
+
"step": 1785
|
| 2646 |
+
},
|
| 2647 |
+
{
|
| 2648 |
+
"epoch": 1.8612664152905993,
|
| 2649 |
+
"grad_norm": 1.2868046760559082,
|
| 2650 |
+
"learning_rate": 1.0276382186283285e-06,
|
| 2651 |
+
"loss": 0.4919888973236084,
|
| 2652 |
+
"step": 1790
|
| 2653 |
+
},
|
| 2654 |
+
{
|
| 2655 |
+
"epoch": 1.866467299440905,
|
| 2656 |
+
"grad_norm": 1.4422026872634888,
|
| 2657 |
+
"learning_rate": 9.532247413563555e-07,
|
| 2658 |
+
"loss": 0.5298680782318115,
|
| 2659 |
+
"step": 1795
|
| 2660 |
+
},
|
| 2661 |
+
{
|
| 2662 |
+
"epoch": 1.8716681835912103,
|
| 2663 |
+
"grad_norm": 1.4196135997772217,
|
| 2664 |
+
"learning_rate": 8.815752366566399e-07,
|
| 2665 |
+
"loss": 0.5006773948669434,
|
| 2666 |
+
"step": 1800
|
| 2667 |
+
},
|
| 2668 |
+
{
|
| 2669 |
+
"epoch": 1.8716681835912103,
|
| 2670 |
+
"eval_loss": 0.6575887203216553,
|
| 2671 |
+
"eval_runtime": 130.8561,
|
| 2672 |
+
"eval_samples_per_second": 1.956,
|
| 2673 |
+
"eval_steps_per_second": 1.956,
|
| 2674 |
+
"step": 1800
|
| 2675 |
+
}
|
| 2676 |
+
],
|
| 2677 |
+
"logging_steps": 5,
|
| 2678 |
+
"max_steps": 1924,
|
| 2679 |
+
"num_input_tokens_seen": 0,
|
| 2680 |
+
"num_train_epochs": 2,
|
| 2681 |
+
"save_steps": 100,
|
| 2682 |
+
"stateful_callbacks": {
|
| 2683 |
+
"TrainerControl": {
|
| 2684 |
+
"args": {
|
| 2685 |
+
"should_epoch_stop": false,
|
| 2686 |
+
"should_evaluate": false,
|
| 2687 |
+
"should_log": false,
|
| 2688 |
+
"should_save": true,
|
| 2689 |
+
"should_training_stop": false
|
| 2690 |
+
},
|
| 2691 |
+
"attributes": {}
|
| 2692 |
+
}
|
| 2693 |
+
},
|
| 2694 |
+
"total_flos": 4.897885910540295e+18,
|
| 2695 |
+
"train_batch_size": 1,
|
| 2696 |
+
"trial_name": null,
|
| 2697 |
+
"trial_params": null
|
| 2698 |
+
}
|
checkpoint-1800/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14fd1411109c0eee6413d22d6af96a8f8643991c4f44679b65cf8291ea6222b1
|
| 3 |
+
size 5201
|