Upload folder using huggingface_hub
Browse files- README.md +206 -0
- adapter_config.json +46 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1539 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,206 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: GritLM/GritLM-7B
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- base_model:adapter:GritLM/GritLM-7B
|
| 6 |
+
- lora
|
| 7 |
+
- transformers
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# Model Card for Model ID
|
| 11 |
+
|
| 12 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
## Model Details
|
| 17 |
+
|
| 18 |
+
### Model Description
|
| 19 |
+
|
| 20 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
- **Developed by:** [More Information Needed]
|
| 25 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 26 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 27 |
+
- **Model type:** [More Information Needed]
|
| 28 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 29 |
+
- **License:** [More Information Needed]
|
| 30 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 31 |
+
|
| 32 |
+
### Model Sources [optional]
|
| 33 |
+
|
| 34 |
+
<!-- Provide the basic links for the model. -->
|
| 35 |
+
|
| 36 |
+
- **Repository:** [More Information Needed]
|
| 37 |
+
- **Paper [optional]:** [More Information Needed]
|
| 38 |
+
- **Demo [optional]:** [More Information Needed]
|
| 39 |
+
|
| 40 |
+
## Uses
|
| 41 |
+
|
| 42 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 43 |
+
|
| 44 |
+
### Direct Use
|
| 45 |
+
|
| 46 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 47 |
+
|
| 48 |
+
[More Information Needed]
|
| 49 |
+
|
| 50 |
+
### Downstream Use [optional]
|
| 51 |
+
|
| 52 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 53 |
+
|
| 54 |
+
[More Information Needed]
|
| 55 |
+
|
| 56 |
+
### Out-of-Scope Use
|
| 57 |
+
|
| 58 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 59 |
+
|
| 60 |
+
[More Information Needed]
|
| 61 |
+
|
| 62 |
+
## Bias, Risks, and Limitations
|
| 63 |
+
|
| 64 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 65 |
+
|
| 66 |
+
[More Information Needed]
|
| 67 |
+
|
| 68 |
+
### Recommendations
|
| 69 |
+
|
| 70 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 71 |
+
|
| 72 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 73 |
+
|
| 74 |
+
## How to Get Started with the Model
|
| 75 |
+
|
| 76 |
+
Use the code below to get started with the model.
|
| 77 |
+
|
| 78 |
+
[More Information Needed]
|
| 79 |
+
|
| 80 |
+
## Training Details
|
| 81 |
+
|
| 82 |
+
### Training Data
|
| 83 |
+
|
| 84 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 85 |
+
|
| 86 |
+
[More Information Needed]
|
| 87 |
+
|
| 88 |
+
### Training Procedure
|
| 89 |
+
|
| 90 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 91 |
+
|
| 92 |
+
#### Preprocessing [optional]
|
| 93 |
+
|
| 94 |
+
[More Information Needed]
|
| 95 |
+
|
| 96 |
+
|
| 97 |
+
#### Training Hyperparameters
|
| 98 |
+
|
| 99 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 100 |
+
|
| 101 |
+
#### Speeds, Sizes, Times [optional]
|
| 102 |
+
|
| 103 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 104 |
+
|
| 105 |
+
[More Information Needed]
|
| 106 |
+
|
| 107 |
+
## Evaluation
|
| 108 |
+
|
| 109 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 110 |
+
|
| 111 |
+
### Testing Data, Factors & Metrics
|
| 112 |
+
|
| 113 |
+
#### Testing Data
|
| 114 |
+
|
| 115 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 116 |
+
|
| 117 |
+
[More Information Needed]
|
| 118 |
+
|
| 119 |
+
#### Factors
|
| 120 |
+
|
| 121 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 122 |
+
|
| 123 |
+
[More Information Needed]
|
| 124 |
+
|
| 125 |
+
#### Metrics
|
| 126 |
+
|
| 127 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
### Results
|
| 132 |
+
|
| 133 |
+
[More Information Needed]
|
| 134 |
+
|
| 135 |
+
#### Summary
|
| 136 |
+
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
## Model Examination [optional]
|
| 140 |
+
|
| 141 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 142 |
+
|
| 143 |
+
[More Information Needed]
|
| 144 |
+
|
| 145 |
+
## Environmental Impact
|
| 146 |
+
|
| 147 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 148 |
+
|
| 149 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 150 |
+
|
| 151 |
+
- **Hardware Type:** [More Information Needed]
|
| 152 |
+
- **Hours used:** [More Information Needed]
|
| 153 |
+
- **Cloud Provider:** [More Information Needed]
|
| 154 |
+
- **Compute Region:** [More Information Needed]
|
| 155 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 156 |
+
|
| 157 |
+
## Technical Specifications [optional]
|
| 158 |
+
|
| 159 |
+
### Model Architecture and Objective
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
### Compute Infrastructure
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Hardware
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
#### Software
|
| 172 |
+
|
| 173 |
+
[More Information Needed]
|
| 174 |
+
|
| 175 |
+
## Citation [optional]
|
| 176 |
+
|
| 177 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 178 |
+
|
| 179 |
+
**BibTeX:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
**APA:**
|
| 184 |
+
|
| 185 |
+
[More Information Needed]
|
| 186 |
+
|
| 187 |
+
## Glossary [optional]
|
| 188 |
+
|
| 189 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## More Information [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Authors [optional]
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
## Model Card Contact
|
| 202 |
+
|
| 203 |
+
[More Information Needed]
|
| 204 |
+
### Framework versions
|
| 205 |
+
|
| 206 |
+
- PEFT 0.18.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "GritLM/GritLM-7B",
|
| 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": 0.1,
|
| 22 |
+
"megatron_config": null,
|
| 23 |
+
"megatron_core": "megatron.core",
|
| 24 |
+
"modules_to_save": null,
|
| 25 |
+
"peft_type": "LORA",
|
| 26 |
+
"peft_version": "0.18.0",
|
| 27 |
+
"qalora_group_size": 16,
|
| 28 |
+
"r": 16,
|
| 29 |
+
"rank_pattern": {},
|
| 30 |
+
"revision": null,
|
| 31 |
+
"target_modules": [
|
| 32 |
+
"q_proj",
|
| 33 |
+
"gate_proj",
|
| 34 |
+
"v_proj",
|
| 35 |
+
"o_proj",
|
| 36 |
+
"down_proj",
|
| 37 |
+
"up_proj",
|
| 38 |
+
"k_proj"
|
| 39 |
+
],
|
| 40 |
+
"target_parameters": null,
|
| 41 |
+
"task_type": "FEATURE_EXTRACTION",
|
| 42 |
+
"trainable_token_indices": null,
|
| 43 |
+
"use_dora": false,
|
| 44 |
+
"use_qalora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d15f57313a3c82fe89c0c48dc591a2b656a399294e817ff4f7799dde6a8f4e1
|
| 3 |
+
size 167829552
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1626fde439e9d6b8a7a2b3ceb5ef6a3ea465f4f222be046a9c90af16e352df37
|
| 3 |
+
size 335929123
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7d937aa7c9372bc7eaee67e21e3bd46354719c75fed56633c28912fa3bea55c
|
| 3 |
+
size 15429
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a58b8f93c476fd5b68bf7a1cb71dba339962af71e8b291b3fbf4160fe65e941a
|
| 3 |
+
size 15429
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:512417ea00dd4fd97d28215f3836dfe48b613244d70307cb0c81034c2782ced0
|
| 3 |
+
size 15429
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:590dcc33c75446dac475616a6cf1a9d7759e01b9b1b624bde6440e0486e04ab7
|
| 3 |
+
size 15429
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef532fe642b0fbba9874c76a4247414897630ace094b1ab155215ac20a987d63
|
| 3 |
+
size 1465
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1539 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 10797,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0046311304589450285,
|
| 14 |
+
"grad_norm": 45311.37890625,
|
| 15 |
+
"learning_rate": 4.537037037037038e-07,
|
| 16 |
+
"loss": 5.1101,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.009262260917890057,
|
| 21 |
+
"grad_norm": 24385.150390625,
|
| 22 |
+
"learning_rate": 9.166666666666666e-07,
|
| 23 |
+
"loss": 5.4531,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.013893391376835085,
|
| 28 |
+
"grad_norm": 17766.69921875,
|
| 29 |
+
"learning_rate": 1.3796296296296296e-06,
|
| 30 |
+
"loss": 6.8544,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.018524521835780114,
|
| 35 |
+
"grad_norm": 24810.97265625,
|
| 36 |
+
"learning_rate": 1.8425925925925927e-06,
|
| 37 |
+
"loss": 8.9807,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.023155652294725142,
|
| 42 |
+
"grad_norm": 20551.3984375,
|
| 43 |
+
"learning_rate": 2.305555555555556e-06,
|
| 44 |
+
"loss": 14.0074,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.02778678275367017,
|
| 49 |
+
"grad_norm": 35652.94921875,
|
| 50 |
+
"learning_rate": 2.7685185185185187e-06,
|
| 51 |
+
"loss": 20.0341,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0324179132126152,
|
| 56 |
+
"grad_norm": 43745.55859375,
|
| 57 |
+
"learning_rate": 3.2314814814814814e-06,
|
| 58 |
+
"loss": 22.4377,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.03704904367156023,
|
| 63 |
+
"grad_norm": 170773.203125,
|
| 64 |
+
"learning_rate": 3.694444444444445e-06,
|
| 65 |
+
"loss": 26.4996,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.04168017413050526,
|
| 70 |
+
"grad_norm": 158025.984375,
|
| 71 |
+
"learning_rate": 4.157407407407408e-06,
|
| 72 |
+
"loss": 36.6171,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.046311304589450285,
|
| 77 |
+
"grad_norm": 34478.3203125,
|
| 78 |
+
"learning_rate": 4.620370370370371e-06,
|
| 79 |
+
"loss": 30.4798,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.05094243504839532,
|
| 84 |
+
"grad_norm": 136783.609375,
|
| 85 |
+
"learning_rate": 5.0833333333333335e-06,
|
| 86 |
+
"loss": 34.9235,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.05557356550734034,
|
| 91 |
+
"grad_norm": 74166.8984375,
|
| 92 |
+
"learning_rate": 5.546296296296296e-06,
|
| 93 |
+
"loss": 36.3313,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.060204695966285374,
|
| 98 |
+
"grad_norm": 81349.1015625,
|
| 99 |
+
"learning_rate": 6.009259259259261e-06,
|
| 100 |
+
"loss": 35.7238,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.0648358264252304,
|
| 105 |
+
"grad_norm": 131790.796875,
|
| 106 |
+
"learning_rate": 6.472222222222223e-06,
|
| 107 |
+
"loss": 37.7356,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.06946695688417542,
|
| 112 |
+
"grad_norm": 104120.3359375,
|
| 113 |
+
"learning_rate": 6.935185185185186e-06,
|
| 114 |
+
"loss": 39.6583,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.07409808734312046,
|
| 119 |
+
"grad_norm": 20184.501953125,
|
| 120 |
+
"learning_rate": 7.398148148148149e-06,
|
| 121 |
+
"loss": 43.7877,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.07872921780206549,
|
| 126 |
+
"grad_norm": 28208.6328125,
|
| 127 |
+
"learning_rate": 7.861111111111112e-06,
|
| 128 |
+
"loss": 56.835,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.08336034826101052,
|
| 133 |
+
"grad_norm": 41647.78515625,
|
| 134 |
+
"learning_rate": 8.324074074074074e-06,
|
| 135 |
+
"loss": 52.439,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.08799147871995554,
|
| 140 |
+
"grad_norm": 44205.96875,
|
| 141 |
+
"learning_rate": 8.787037037037038e-06,
|
| 142 |
+
"loss": 51.0145,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.09262260917890057,
|
| 147 |
+
"grad_norm": 32592.4609375,
|
| 148 |
+
"learning_rate": 9.250000000000001e-06,
|
| 149 |
+
"loss": 48.7292,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.0972537396378456,
|
| 154 |
+
"grad_norm": 18587.83984375,
|
| 155 |
+
"learning_rate": 9.712962962962965e-06,
|
| 156 |
+
"loss": 55.1206,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.10188487009679063,
|
| 161 |
+
"grad_norm": 54501.23828125,
|
| 162 |
+
"learning_rate": 9.980446639909439e-06,
|
| 163 |
+
"loss": 55.8502,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.10651600055573565,
|
| 168 |
+
"grad_norm": 31179.115234375,
|
| 169 |
+
"learning_rate": 9.928990429144798e-06,
|
| 170 |
+
"loss": 56.1253,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.11114713101468068,
|
| 175 |
+
"grad_norm": 19028.408203125,
|
| 176 |
+
"learning_rate": 9.877534218380159e-06,
|
| 177 |
+
"loss": 51.6047,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.11577826147362572,
|
| 182 |
+
"grad_norm": 23272.919921875,
|
| 183 |
+
"learning_rate": 9.826078007615521e-06,
|
| 184 |
+
"loss": 48.5006,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.12040939193257075,
|
| 189 |
+
"grad_norm": 20129.248046875,
|
| 190 |
+
"learning_rate": 9.77462179685088e-06,
|
| 191 |
+
"loss": 47.4703,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.12504052239151578,
|
| 196 |
+
"grad_norm": 20898.05859375,
|
| 197 |
+
"learning_rate": 9.723165586086241e-06,
|
| 198 |
+
"loss": 47.1912,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.1296716528504608,
|
| 203 |
+
"grad_norm": 30558.55859375,
|
| 204 |
+
"learning_rate": 9.671709375321602e-06,
|
| 205 |
+
"loss": 41.2223,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.13430278330940582,
|
| 210 |
+
"grad_norm": 25856.19140625,
|
| 211 |
+
"learning_rate": 9.620253164556963e-06,
|
| 212 |
+
"loss": 39.0084,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.13893391376835085,
|
| 217 |
+
"grad_norm": 16568.400390625,
|
| 218 |
+
"learning_rate": 9.568796953792322e-06,
|
| 219 |
+
"loss": 41.6975,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.14356504422729588,
|
| 224 |
+
"grad_norm": 14717.109375,
|
| 225 |
+
"learning_rate": 9.517340743027685e-06,
|
| 226 |
+
"loss": 34.7697,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.1481961746862409,
|
| 231 |
+
"grad_norm": 16112.0263671875,
|
| 232 |
+
"learning_rate": 9.465884532263044e-06,
|
| 233 |
+
"loss": 32.84,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.15282730514518594,
|
| 238 |
+
"grad_norm": 28320.36328125,
|
| 239 |
+
"learning_rate": 9.414428321498405e-06,
|
| 240 |
+
"loss": 30.6541,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.15745843560413098,
|
| 245 |
+
"grad_norm": 14664.193359375,
|
| 246 |
+
"learning_rate": 9.362972110733768e-06,
|
| 247 |
+
"loss": 24.7009,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.162089566063076,
|
| 252 |
+
"grad_norm": 5361.5087890625,
|
| 253 |
+
"learning_rate": 9.311515899969127e-06,
|
| 254 |
+
"loss": 18.9679,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.16672069652202104,
|
| 259 |
+
"grad_norm": 3825.643798828125,
|
| 260 |
+
"learning_rate": 9.260059689204488e-06,
|
| 261 |
+
"loss": 14.1527,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.17135182698096604,
|
| 266 |
+
"grad_norm": 687.0768432617188,
|
| 267 |
+
"learning_rate": 9.208603478439848e-06,
|
| 268 |
+
"loss": 8.0994,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.17598295743991108,
|
| 273 |
+
"grad_norm": 161.3083038330078,
|
| 274 |
+
"learning_rate": 9.15714726767521e-06,
|
| 275 |
+
"loss": 5.4372,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.1806140878988561,
|
| 280 |
+
"grad_norm": 111.15824890136719,
|
| 281 |
+
"learning_rate": 9.10569105691057e-06,
|
| 282 |
+
"loss": 5.0239,
|
| 283 |
+
"step": 1950
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.18524521835780114,
|
| 287 |
+
"grad_norm": 62.675636291503906,
|
| 288 |
+
"learning_rate": 9.054234846145931e-06,
|
| 289 |
+
"loss": 4.9312,
|
| 290 |
+
"step": 2000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.18987634881674617,
|
| 294 |
+
"grad_norm": 40.70977020263672,
|
| 295 |
+
"learning_rate": 9.00277863538129e-06,
|
| 296 |
+
"loss": 4.8934,
|
| 297 |
+
"step": 2050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.1945074792756912,
|
| 301 |
+
"grad_norm": 31.48650550842285,
|
| 302 |
+
"learning_rate": 8.951322424616651e-06,
|
| 303 |
+
"loss": 4.8852,
|
| 304 |
+
"step": 2100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.19913860973463623,
|
| 308 |
+
"grad_norm": 28.155406951904297,
|
| 309 |
+
"learning_rate": 8.899866213852014e-06,
|
| 310 |
+
"loss": 4.8705,
|
| 311 |
+
"step": 2150
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.20376974019358127,
|
| 315 |
+
"grad_norm": 30.841955184936523,
|
| 316 |
+
"learning_rate": 8.848410003087373e-06,
|
| 317 |
+
"loss": 4.8821,
|
| 318 |
+
"step": 2200
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.20840087065252627,
|
| 322 |
+
"grad_norm": 17.3418025970459,
|
| 323 |
+
"learning_rate": 8.796953792322734e-06,
|
| 324 |
+
"loss": 4.8662,
|
| 325 |
+
"step": 2250
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.2130320011114713,
|
| 329 |
+
"grad_norm": 15.722943305969238,
|
| 330 |
+
"learning_rate": 8.745497581558095e-06,
|
| 331 |
+
"loss": 4.8593,
|
| 332 |
+
"step": 2300
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.21766313157041633,
|
| 336 |
+
"grad_norm": 12.287271499633789,
|
| 337 |
+
"learning_rate": 8.694041370793456e-06,
|
| 338 |
+
"loss": 4.8663,
|
| 339 |
+
"step": 2350
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.22229426202936137,
|
| 343 |
+
"grad_norm": 8.732343673706055,
|
| 344 |
+
"learning_rate": 8.642585160028816e-06,
|
| 345 |
+
"loss": 4.861,
|
| 346 |
+
"step": 2400
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.2269253924883064,
|
| 350 |
+
"grad_norm": 18.63037872314453,
|
| 351 |
+
"learning_rate": 8.591128949264177e-06,
|
| 352 |
+
"loss": 4.8586,
|
| 353 |
+
"step": 2450
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.23155652294725143,
|
| 357 |
+
"grad_norm": 10.168179512023926,
|
| 358 |
+
"learning_rate": 8.539672738499537e-06,
|
| 359 |
+
"loss": 4.8613,
|
| 360 |
+
"step": 2500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.23618765340619646,
|
| 364 |
+
"grad_norm": 8.444642066955566,
|
| 365 |
+
"learning_rate": 8.488216527734897e-06,
|
| 366 |
+
"loss": 4.8552,
|
| 367 |
+
"step": 2550
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.2408187838651415,
|
| 371 |
+
"grad_norm": 6.634263038635254,
|
| 372 |
+
"learning_rate": 8.43676031697026e-06,
|
| 373 |
+
"loss": 4.8612,
|
| 374 |
+
"step": 2600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.2454499143240865,
|
| 378 |
+
"grad_norm": 9.856132507324219,
|
| 379 |
+
"learning_rate": 8.38530410620562e-06,
|
| 380 |
+
"loss": 4.8555,
|
| 381 |
+
"step": 2650
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.25008104478303156,
|
| 385 |
+
"grad_norm": 6.173237323760986,
|
| 386 |
+
"learning_rate": 8.33384789544098e-06,
|
| 387 |
+
"loss": 4.854,
|
| 388 |
+
"step": 2700
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.2547121752419766,
|
| 392 |
+
"grad_norm": 8.70698356628418,
|
| 393 |
+
"learning_rate": 8.282391684676341e-06,
|
| 394 |
+
"loss": 4.8522,
|
| 395 |
+
"step": 2750
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.2593433057009216,
|
| 399 |
+
"grad_norm": 4.96877908706665,
|
| 400 |
+
"learning_rate": 8.230935473911702e-06,
|
| 401 |
+
"loss": 4.8563,
|
| 402 |
+
"step": 2800
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.2639744361598666,
|
| 406 |
+
"grad_norm": 6.604714393615723,
|
| 407 |
+
"learning_rate": 8.179479263147063e-06,
|
| 408 |
+
"loss": 4.8491,
|
| 409 |
+
"step": 2850
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.26860556661881163,
|
| 413 |
+
"grad_norm": 7.707324981689453,
|
| 414 |
+
"learning_rate": 8.128023052382424e-06,
|
| 415 |
+
"loss": 4.8559,
|
| 416 |
+
"step": 2900
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.27323669707775666,
|
| 420 |
+
"grad_norm": 6.189296245574951,
|
| 421 |
+
"learning_rate": 8.076566841617785e-06,
|
| 422 |
+
"loss": 4.8549,
|
| 423 |
+
"step": 2950
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.2778678275367017,
|
| 427 |
+
"grad_norm": 4.309783935546875,
|
| 428 |
+
"learning_rate": 8.025110630853145e-06,
|
| 429 |
+
"loss": 4.8547,
|
| 430 |
+
"step": 3000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.2824989579956467,
|
| 434 |
+
"grad_norm": 5.0381999015808105,
|
| 435 |
+
"learning_rate": 7.973654420088506e-06,
|
| 436 |
+
"loss": 4.8552,
|
| 437 |
+
"step": 3050
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.28713008845459176,
|
| 441 |
+
"grad_norm": 10.880996704101562,
|
| 442 |
+
"learning_rate": 7.922198209323865e-06,
|
| 443 |
+
"loss": 4.8581,
|
| 444 |
+
"step": 3100
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.2917612189135368,
|
| 448 |
+
"grad_norm": 4.348069190979004,
|
| 449 |
+
"learning_rate": 7.870741998559226e-06,
|
| 450 |
+
"loss": 4.8557,
|
| 451 |
+
"step": 3150
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.2963923493724818,
|
| 455 |
+
"grad_norm": 11.774301528930664,
|
| 456 |
+
"learning_rate": 7.819285787794587e-06,
|
| 457 |
+
"loss": 4.8533,
|
| 458 |
+
"step": 3200
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.30102347983142685,
|
| 462 |
+
"grad_norm": 12.425819396972656,
|
| 463 |
+
"learning_rate": 7.767829577029948e-06,
|
| 464 |
+
"loss": 4.8567,
|
| 465 |
+
"step": 3250
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.3056546102903719,
|
| 469 |
+
"grad_norm": 4.84695291519165,
|
| 470 |
+
"learning_rate": 7.716373366265309e-06,
|
| 471 |
+
"loss": 4.8513,
|
| 472 |
+
"step": 3300
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.3102857407493169,
|
| 476 |
+
"grad_norm": 5.18828010559082,
|
| 477 |
+
"learning_rate": 7.66491715550067e-06,
|
| 478 |
+
"loss": 4.8538,
|
| 479 |
+
"step": 3350
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.31491687120826195,
|
| 483 |
+
"grad_norm": 10.579144477844238,
|
| 484 |
+
"learning_rate": 7.613460944736031e-06,
|
| 485 |
+
"loss": 4.8549,
|
| 486 |
+
"step": 3400
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.319548001667207,
|
| 490 |
+
"grad_norm": 3.7520084381103516,
|
| 491 |
+
"learning_rate": 7.562004733971391e-06,
|
| 492 |
+
"loss": 4.8546,
|
| 493 |
+
"step": 3450
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.324179132126152,
|
| 497 |
+
"grad_norm": 5.303626537322998,
|
| 498 |
+
"learning_rate": 7.510548523206752e-06,
|
| 499 |
+
"loss": 4.8527,
|
| 500 |
+
"step": 3500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.32881026258509705,
|
| 504 |
+
"grad_norm": 3.4561500549316406,
|
| 505 |
+
"learning_rate": 7.459092312442113e-06,
|
| 506 |
+
"loss": 4.8547,
|
| 507 |
+
"step": 3550
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.3334413930440421,
|
| 511 |
+
"grad_norm": 4.276394367218018,
|
| 512 |
+
"learning_rate": 7.4076361016774735e-06,
|
| 513 |
+
"loss": 4.854,
|
| 514 |
+
"step": 3600
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.33807252350298705,
|
| 518 |
+
"grad_norm": 6.949066162109375,
|
| 519 |
+
"learning_rate": 7.3561798909128335e-06,
|
| 520 |
+
"loss": 4.8526,
|
| 521 |
+
"step": 3650
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.3427036539619321,
|
| 525 |
+
"grad_norm": 3.7716352939605713,
|
| 526 |
+
"learning_rate": 7.304723680148194e-06,
|
| 527 |
+
"loss": 4.8529,
|
| 528 |
+
"step": 3700
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.3473347844208771,
|
| 532 |
+
"grad_norm": 3.8829033374786377,
|
| 533 |
+
"learning_rate": 7.2532674693835544e-06,
|
| 534 |
+
"loss": 4.8516,
|
| 535 |
+
"step": 3750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.35196591487982215,
|
| 539 |
+
"grad_norm": 7.156257629394531,
|
| 540 |
+
"learning_rate": 7.201811258618916e-06,
|
| 541 |
+
"loss": 4.8566,
|
| 542 |
+
"step": 3800
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.3565970453387672,
|
| 546 |
+
"grad_norm": 3.4680042266845703,
|
| 547 |
+
"learning_rate": 7.150355047854277e-06,
|
| 548 |
+
"loss": 4.8521,
|
| 549 |
+
"step": 3850
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.3612281757977122,
|
| 553 |
+
"grad_norm": 6.309057712554932,
|
| 554 |
+
"learning_rate": 7.098898837089637e-06,
|
| 555 |
+
"loss": 4.852,
|
| 556 |
+
"step": 3900
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.36585930625665725,
|
| 560 |
+
"grad_norm": 3.311298131942749,
|
| 561 |
+
"learning_rate": 7.047442626324999e-06,
|
| 562 |
+
"loss": 4.8532,
|
| 563 |
+
"step": 3950
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.3704904367156023,
|
| 567 |
+
"grad_norm": 4.21369743347168,
|
| 568 |
+
"learning_rate": 6.995986415560359e-06,
|
| 569 |
+
"loss": 4.8541,
|
| 570 |
+
"step": 4000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.3751215671745473,
|
| 574 |
+
"grad_norm": 3.184129238128662,
|
| 575 |
+
"learning_rate": 6.94453020479572e-06,
|
| 576 |
+
"loss": 4.8545,
|
| 577 |
+
"step": 4050
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.37975269763349234,
|
| 581 |
+
"grad_norm": 7.411576747894287,
|
| 582 |
+
"learning_rate": 6.89307399403108e-06,
|
| 583 |
+
"loss": 4.8561,
|
| 584 |
+
"step": 4100
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.3843838280924374,
|
| 588 |
+
"grad_norm": 7.5306878089904785,
|
| 589 |
+
"learning_rate": 6.841617783266441e-06,
|
| 590 |
+
"loss": 4.8524,
|
| 591 |
+
"step": 4150
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.3890149585513824,
|
| 595 |
+
"grad_norm": 6.128129005432129,
|
| 596 |
+
"learning_rate": 6.790161572501801e-06,
|
| 597 |
+
"loss": 4.8531,
|
| 598 |
+
"step": 4200
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.39364608901032744,
|
| 602 |
+
"grad_norm": 5.687031269073486,
|
| 603 |
+
"learning_rate": 6.7387053617371624e-06,
|
| 604 |
+
"loss": 4.8514,
|
| 605 |
+
"step": 4250
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.39827721946927247,
|
| 609 |
+
"grad_norm": 3.1113038063049316,
|
| 610 |
+
"learning_rate": 6.687249150972523e-06,
|
| 611 |
+
"loss": 4.8537,
|
| 612 |
+
"step": 4300
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.4029083499282175,
|
| 616 |
+
"grad_norm": 8.376502990722656,
|
| 617 |
+
"learning_rate": 6.635792940207883e-06,
|
| 618 |
+
"loss": 4.8534,
|
| 619 |
+
"step": 4350
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.40753948038716253,
|
| 623 |
+
"grad_norm": 7.945234775543213,
|
| 624 |
+
"learning_rate": 6.584336729443245e-06,
|
| 625 |
+
"loss": 4.8529,
|
| 626 |
+
"step": 4400
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.4121706108461075,
|
| 630 |
+
"grad_norm": 3.565673351287842,
|
| 631 |
+
"learning_rate": 6.532880518678605e-06,
|
| 632 |
+
"loss": 4.8543,
|
| 633 |
+
"step": 4450
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.41680174130505254,
|
| 637 |
+
"grad_norm": 3.2953274250030518,
|
| 638 |
+
"learning_rate": 6.481424307913966e-06,
|
| 639 |
+
"loss": 4.8503,
|
| 640 |
+
"step": 4500
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.4214328717639976,
|
| 644 |
+
"grad_norm": 2.9050490856170654,
|
| 645 |
+
"learning_rate": 6.429968097149326e-06,
|
| 646 |
+
"loss": 4.8533,
|
| 647 |
+
"step": 4550
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.4260640022229426,
|
| 651 |
+
"grad_norm": 7.26942777633667,
|
| 652 |
+
"learning_rate": 6.378511886384687e-06,
|
| 653 |
+
"loss": 4.854,
|
| 654 |
+
"step": 4600
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.43069513268188764,
|
| 658 |
+
"grad_norm": 4.875161647796631,
|
| 659 |
+
"learning_rate": 6.327055675620048e-06,
|
| 660 |
+
"loss": 4.8547,
|
| 661 |
+
"step": 4650
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.43532626314083267,
|
| 665 |
+
"grad_norm": 3.538259267807007,
|
| 666 |
+
"learning_rate": 6.275599464855409e-06,
|
| 667 |
+
"loss": 4.8524,
|
| 668 |
+
"step": 4700
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.4399573935997777,
|
| 672 |
+
"grad_norm": 7.06084680557251,
|
| 673 |
+
"learning_rate": 6.2241432540907696e-06,
|
| 674 |
+
"loss": 4.8519,
|
| 675 |
+
"step": 4750
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.44458852405872273,
|
| 679 |
+
"grad_norm": 3.635225534439087,
|
| 680 |
+
"learning_rate": 6.17268704332613e-06,
|
| 681 |
+
"loss": 4.8525,
|
| 682 |
+
"step": 4800
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.44921965451766777,
|
| 686 |
+
"grad_norm": 4.0461835861206055,
|
| 687 |
+
"learning_rate": 6.121230832561491e-06,
|
| 688 |
+
"loss": 4.8534,
|
| 689 |
+
"step": 4850
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.4538507849766128,
|
| 693 |
+
"grad_norm": 4.653171539306641,
|
| 694 |
+
"learning_rate": 6.069774621796851e-06,
|
| 695 |
+
"loss": 4.8505,
|
| 696 |
+
"step": 4900
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.45848191543555783,
|
| 700 |
+
"grad_norm": 4.088388442993164,
|
| 701 |
+
"learning_rate": 6.018318411032212e-06,
|
| 702 |
+
"loss": 4.8543,
|
| 703 |
+
"step": 4950
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.46311304589450286,
|
| 707 |
+
"grad_norm": 2.659907817840576,
|
| 708 |
+
"learning_rate": 5.966862200267572e-06,
|
| 709 |
+
"loss": 4.8551,
|
| 710 |
+
"step": 5000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.4677441763534479,
|
| 714 |
+
"grad_norm": 2.58552885055542,
|
| 715 |
+
"learning_rate": 5.915405989502934e-06,
|
| 716 |
+
"loss": 4.8521,
|
| 717 |
+
"step": 5050
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.4723753068123929,
|
| 721 |
+
"grad_norm": 2.699875593185425,
|
| 722 |
+
"learning_rate": 5.863949778738294e-06,
|
| 723 |
+
"loss": 4.8543,
|
| 724 |
+
"step": 5100
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.47700643727133796,
|
| 728 |
+
"grad_norm": 2.67714786529541,
|
| 729 |
+
"learning_rate": 5.812493567973655e-06,
|
| 730 |
+
"loss": 4.8525,
|
| 731 |
+
"step": 5150
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.481637567730283,
|
| 735 |
+
"grad_norm": 4.694529056549072,
|
| 736 |
+
"learning_rate": 5.761037357209016e-06,
|
| 737 |
+
"loss": 4.8547,
|
| 738 |
+
"step": 5200
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.48626869818922797,
|
| 742 |
+
"grad_norm": 2.6322555541992188,
|
| 743 |
+
"learning_rate": 5.709581146444376e-06,
|
| 744 |
+
"loss": 4.8512,
|
| 745 |
+
"step": 5250
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.490899828648173,
|
| 749 |
+
"grad_norm": 3.097139835357666,
|
| 750 |
+
"learning_rate": 5.658124935679738e-06,
|
| 751 |
+
"loss": 4.853,
|
| 752 |
+
"step": 5300
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.49553095910711803,
|
| 756 |
+
"grad_norm": 4.2281575202941895,
|
| 757 |
+
"learning_rate": 5.606668724915098e-06,
|
| 758 |
+
"loss": 4.8516,
|
| 759 |
+
"step": 5350
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.5001620895660631,
|
| 763 |
+
"grad_norm": 4.780153274536133,
|
| 764 |
+
"learning_rate": 5.5552125141504585e-06,
|
| 765 |
+
"loss": 4.853,
|
| 766 |
+
"step": 5400
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.5047932200250081,
|
| 770 |
+
"grad_norm": 4.7001051902771,
|
| 771 |
+
"learning_rate": 5.5037563033858186e-06,
|
| 772 |
+
"loss": 4.8519,
|
| 773 |
+
"step": 5450
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.5094243504839532,
|
| 777 |
+
"grad_norm": 2.692204475402832,
|
| 778 |
+
"learning_rate": 5.45230009262118e-06,
|
| 779 |
+
"loss": 4.8527,
|
| 780 |
+
"step": 5500
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.5140554809428982,
|
| 784 |
+
"grad_norm": 4.267179489135742,
|
| 785 |
+
"learning_rate": 5.40084388185654e-06,
|
| 786 |
+
"loss": 4.8527,
|
| 787 |
+
"step": 5550
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.5186866114018432,
|
| 791 |
+
"grad_norm": 4.3875532150268555,
|
| 792 |
+
"learning_rate": 5.349387671091901e-06,
|
| 793 |
+
"loss": 4.8531,
|
| 794 |
+
"step": 5600
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.5233177418607882,
|
| 798 |
+
"grad_norm": 4.2535223960876465,
|
| 799 |
+
"learning_rate": 5.297931460327262e-06,
|
| 800 |
+
"loss": 4.8529,
|
| 801 |
+
"step": 5650
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.5279488723197332,
|
| 805 |
+
"grad_norm": 4.176506042480469,
|
| 806 |
+
"learning_rate": 5.246475249562622e-06,
|
| 807 |
+
"loss": 4.8527,
|
| 808 |
+
"step": 5700
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.5325800027786782,
|
| 812 |
+
"grad_norm": 5.777888298034668,
|
| 813 |
+
"learning_rate": 5.195019038797984e-06,
|
| 814 |
+
"loss": 4.851,
|
| 815 |
+
"step": 5750
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.5372111332376233,
|
| 819 |
+
"grad_norm": 2.5011487007141113,
|
| 820 |
+
"learning_rate": 5.143562828033344e-06,
|
| 821 |
+
"loss": 4.8525,
|
| 822 |
+
"step": 5800
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.5418422636965683,
|
| 826 |
+
"grad_norm": 2.296004056930542,
|
| 827 |
+
"learning_rate": 5.092106617268705e-06,
|
| 828 |
+
"loss": 4.8537,
|
| 829 |
+
"step": 5850
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.5464733941555133,
|
| 833 |
+
"grad_norm": 3.866945266723633,
|
| 834 |
+
"learning_rate": 5.040650406504065e-06,
|
| 835 |
+
"loss": 4.8507,
|
| 836 |
+
"step": 5900
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.5511045246144584,
|
| 840 |
+
"grad_norm": 4.017833232879639,
|
| 841 |
+
"learning_rate": 4.9891941957394266e-06,
|
| 842 |
+
"loss": 4.8535,
|
| 843 |
+
"step": 5950
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.5557356550734034,
|
| 847 |
+
"grad_norm": 2.5634918212890625,
|
| 848 |
+
"learning_rate": 4.937737984974787e-06,
|
| 849 |
+
"loss": 4.8522,
|
| 850 |
+
"step": 6000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.5603667855323484,
|
| 854 |
+
"grad_norm": 2.3562004566192627,
|
| 855 |
+
"learning_rate": 4.8862817742101475e-06,
|
| 856 |
+
"loss": 4.8537,
|
| 857 |
+
"step": 6050
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.5649979159912935,
|
| 861 |
+
"grad_norm": 2.573345899581909,
|
| 862 |
+
"learning_rate": 4.834825563445508e-06,
|
| 863 |
+
"loss": 4.8525,
|
| 864 |
+
"step": 6100
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.5696290464502385,
|
| 868 |
+
"grad_norm": 2.818164825439453,
|
| 869 |
+
"learning_rate": 4.783369352680869e-06,
|
| 870 |
+
"loss": 4.8537,
|
| 871 |
+
"step": 6150
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.5742601769091835,
|
| 875 |
+
"grad_norm": 2.9981884956359863,
|
| 876 |
+
"learning_rate": 4.731913141916229e-06,
|
| 877 |
+
"loss": 4.8532,
|
| 878 |
+
"step": 6200
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.5788913073681285,
|
| 882 |
+
"grad_norm": 3.1095032691955566,
|
| 883 |
+
"learning_rate": 4.68045693115159e-06,
|
| 884 |
+
"loss": 4.8512,
|
| 885 |
+
"step": 6250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.5835224378270736,
|
| 889 |
+
"grad_norm": 2.8659579753875732,
|
| 890 |
+
"learning_rate": 4.629000720386951e-06,
|
| 891 |
+
"loss": 4.8531,
|
| 892 |
+
"step": 6300
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.5881535682860186,
|
| 896 |
+
"grad_norm": 4.299989700317383,
|
| 897 |
+
"learning_rate": 4.577544509622312e-06,
|
| 898 |
+
"loss": 4.8522,
|
| 899 |
+
"step": 6350
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.5927846987449636,
|
| 903 |
+
"grad_norm": 1.9564199447631836,
|
| 904 |
+
"learning_rate": 4.526088298857673e-06,
|
| 905 |
+
"loss": 4.853,
|
| 906 |
+
"step": 6400
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.5974158292039087,
|
| 910 |
+
"grad_norm": 2.792586326599121,
|
| 911 |
+
"learning_rate": 4.474632088093034e-06,
|
| 912 |
+
"loss": 4.8524,
|
| 913 |
+
"step": 6450
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.6020469596628537,
|
| 917 |
+
"grad_norm": 2.5155632495880127,
|
| 918 |
+
"learning_rate": 4.423175877328394e-06,
|
| 919 |
+
"loss": 4.8535,
|
| 920 |
+
"step": 6500
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.6066780901217987,
|
| 924 |
+
"grad_norm": 3.115560293197632,
|
| 925 |
+
"learning_rate": 4.371719666563755e-06,
|
| 926 |
+
"loss": 4.8523,
|
| 927 |
+
"step": 6550
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.6113092205807438,
|
| 931 |
+
"grad_norm": 2.115840196609497,
|
| 932 |
+
"learning_rate": 4.3202634557991155e-06,
|
| 933 |
+
"loss": 4.8536,
|
| 934 |
+
"step": 6600
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.6159403510396888,
|
| 938 |
+
"grad_norm": 1.9011411666870117,
|
| 939 |
+
"learning_rate": 4.2688072450344755e-06,
|
| 940 |
+
"loss": 4.8516,
|
| 941 |
+
"step": 6650
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.6205714814986338,
|
| 945 |
+
"grad_norm": 4.708501815795898,
|
| 946 |
+
"learning_rate": 4.217351034269836e-06,
|
| 947 |
+
"loss": 4.8526,
|
| 948 |
+
"step": 6700
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.6252026119575789,
|
| 952 |
+
"grad_norm": 1.7983591556549072,
|
| 953 |
+
"learning_rate": 4.165894823505197e-06,
|
| 954 |
+
"loss": 4.8545,
|
| 955 |
+
"step": 6750
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.6298337424165239,
|
| 959 |
+
"grad_norm": 2.4441957473754883,
|
| 960 |
+
"learning_rate": 4.114438612740558e-06,
|
| 961 |
+
"loss": 4.8515,
|
| 962 |
+
"step": 6800
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.6344648728754689,
|
| 966 |
+
"grad_norm": 4.444235324859619,
|
| 967 |
+
"learning_rate": 4.062982401975919e-06,
|
| 968 |
+
"loss": 4.8521,
|
| 969 |
+
"step": 6850
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.639096003334414,
|
| 973 |
+
"grad_norm": 2.260263442993164,
|
| 974 |
+
"learning_rate": 4.01152619121128e-06,
|
| 975 |
+
"loss": 4.8527,
|
| 976 |
+
"step": 6900
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.643727133793359,
|
| 980 |
+
"grad_norm": 3.5399653911590576,
|
| 981 |
+
"learning_rate": 3.96006998044664e-06,
|
| 982 |
+
"loss": 4.8527,
|
| 983 |
+
"step": 6950
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.648358264252304,
|
| 987 |
+
"grad_norm": 3.3484957218170166,
|
| 988 |
+
"learning_rate": 3.908613769682001e-06,
|
| 989 |
+
"loss": 4.8526,
|
| 990 |
+
"step": 7000
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.6529893947112491,
|
| 994 |
+
"grad_norm": 2.836869955062866,
|
| 995 |
+
"learning_rate": 3.857157558917362e-06,
|
| 996 |
+
"loss": 4.8517,
|
| 997 |
+
"step": 7050
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.6576205251701941,
|
| 1001 |
+
"grad_norm": 5.348451137542725,
|
| 1002 |
+
"learning_rate": 3.8057013481527222e-06,
|
| 1003 |
+
"loss": 4.8531,
|
| 1004 |
+
"step": 7100
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.6622516556291391,
|
| 1008 |
+
"grad_norm": 1.7368900775909424,
|
| 1009 |
+
"learning_rate": 3.7542451373880827e-06,
|
| 1010 |
+
"loss": 4.851,
|
| 1011 |
+
"step": 7150
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.6668827860880842,
|
| 1015 |
+
"grad_norm": 2.110898733139038,
|
| 1016 |
+
"learning_rate": 3.702788926623444e-06,
|
| 1017 |
+
"loss": 4.8519,
|
| 1018 |
+
"step": 7200
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.6715139165470291,
|
| 1022 |
+
"grad_norm": 3.1552112102508545,
|
| 1023 |
+
"learning_rate": 3.651332715858805e-06,
|
| 1024 |
+
"loss": 4.852,
|
| 1025 |
+
"step": 7250
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.6761450470059741,
|
| 1029 |
+
"grad_norm": 2.895655632019043,
|
| 1030 |
+
"learning_rate": 3.5998765050941653e-06,
|
| 1031 |
+
"loss": 4.8525,
|
| 1032 |
+
"step": 7300
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.6807761774649191,
|
| 1036 |
+
"grad_norm": 2.147881269454956,
|
| 1037 |
+
"learning_rate": 3.548420294329526e-06,
|
| 1038 |
+
"loss": 4.8536,
|
| 1039 |
+
"step": 7350
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.6854073079238642,
|
| 1043 |
+
"grad_norm": 3.5029313564300537,
|
| 1044 |
+
"learning_rate": 3.4969640835648867e-06,
|
| 1045 |
+
"loss": 4.8519,
|
| 1046 |
+
"step": 7400
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.6900384383828092,
|
| 1050 |
+
"grad_norm": 7.018946170806885,
|
| 1051 |
+
"learning_rate": 3.445507872800247e-06,
|
| 1052 |
+
"loss": 4.8529,
|
| 1053 |
+
"step": 7450
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.6946695688417542,
|
| 1057 |
+
"grad_norm": 2.3654017448425293,
|
| 1058 |
+
"learning_rate": 3.394051662035608e-06,
|
| 1059 |
+
"loss": 4.8515,
|
| 1060 |
+
"step": 7500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.6993006993006993,
|
| 1064 |
+
"grad_norm": 4.802801609039307,
|
| 1065 |
+
"learning_rate": 3.3425954512709685e-06,
|
| 1066 |
+
"loss": 4.852,
|
| 1067 |
+
"step": 7550
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.7039318297596443,
|
| 1071 |
+
"grad_norm": 3.281493663787842,
|
| 1072 |
+
"learning_rate": 3.2911392405063294e-06,
|
| 1073 |
+
"loss": 4.8526,
|
| 1074 |
+
"step": 7600
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.7085629602185893,
|
| 1078 |
+
"grad_norm": 5.945383548736572,
|
| 1079 |
+
"learning_rate": 3.2396830297416903e-06,
|
| 1080 |
+
"loss": 4.8526,
|
| 1081 |
+
"step": 7650
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.7131940906775344,
|
| 1085 |
+
"grad_norm": 3.7236597537994385,
|
| 1086 |
+
"learning_rate": 3.188226818977051e-06,
|
| 1087 |
+
"loss": 4.8527,
|
| 1088 |
+
"step": 7700
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.7178252211364794,
|
| 1092 |
+
"grad_norm": 3.1034650802612305,
|
| 1093 |
+
"learning_rate": 3.1367706082124116e-06,
|
| 1094 |
+
"loss": 4.8519,
|
| 1095 |
+
"step": 7750
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.7224563515954244,
|
| 1099 |
+
"grad_norm": 1.2914083003997803,
|
| 1100 |
+
"learning_rate": 3.0853143974477725e-06,
|
| 1101 |
+
"loss": 4.8521,
|
| 1102 |
+
"step": 7800
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.7270874820543695,
|
| 1106 |
+
"grad_norm": 3.742281436920166,
|
| 1107 |
+
"learning_rate": 3.033858186683133e-06,
|
| 1108 |
+
"loss": 4.8526,
|
| 1109 |
+
"step": 7850
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.7317186125133145,
|
| 1113 |
+
"grad_norm": 1.8345437049865723,
|
| 1114 |
+
"learning_rate": 2.9824019759184934e-06,
|
| 1115 |
+
"loss": 4.8526,
|
| 1116 |
+
"step": 7900
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.7363497429722595,
|
| 1120 |
+
"grad_norm": 2.8292195796966553,
|
| 1121 |
+
"learning_rate": 2.9309457651538543e-06,
|
| 1122 |
+
"loss": 4.8528,
|
| 1123 |
+
"step": 7950
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.7409808734312046,
|
| 1127 |
+
"grad_norm": 8.58931827545166,
|
| 1128 |
+
"learning_rate": 2.8794895543892147e-06,
|
| 1129 |
+
"loss": 4.853,
|
| 1130 |
+
"step": 8000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.7456120038901496,
|
| 1134 |
+
"grad_norm": 3.2066941261291504,
|
| 1135 |
+
"learning_rate": 2.8280333436245756e-06,
|
| 1136 |
+
"loss": 4.8526,
|
| 1137 |
+
"step": 8050
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.7502431343490946,
|
| 1141 |
+
"grad_norm": 5.162906646728516,
|
| 1142 |
+
"learning_rate": 2.7765771328599365e-06,
|
| 1143 |
+
"loss": 4.8529,
|
| 1144 |
+
"step": 8100
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.7548742648080397,
|
| 1148 |
+
"grad_norm": 2.4766018390655518,
|
| 1149 |
+
"learning_rate": 2.7251209220952974e-06,
|
| 1150 |
+
"loss": 4.8519,
|
| 1151 |
+
"step": 8150
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.7595053952669847,
|
| 1155 |
+
"grad_norm": 2.510815382003784,
|
| 1156 |
+
"learning_rate": 2.673664711330658e-06,
|
| 1157 |
+
"loss": 4.8519,
|
| 1158 |
+
"step": 8200
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.7641365257259297,
|
| 1162 |
+
"grad_norm": 2.531654119491577,
|
| 1163 |
+
"learning_rate": 2.6222085005660187e-06,
|
| 1164 |
+
"loss": 4.8531,
|
| 1165 |
+
"step": 8250
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.7687676561848747,
|
| 1169 |
+
"grad_norm": 2.691474437713623,
|
| 1170 |
+
"learning_rate": 2.570752289801379e-06,
|
| 1171 |
+
"loss": 4.8529,
|
| 1172 |
+
"step": 8300
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.7733987866438198,
|
| 1176 |
+
"grad_norm": 2.490870475769043,
|
| 1177 |
+
"learning_rate": 2.51929607903674e-06,
|
| 1178 |
+
"loss": 4.8523,
|
| 1179 |
+
"step": 8350
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.7780299171027648,
|
| 1183 |
+
"grad_norm": 3.6683449745178223,
|
| 1184 |
+
"learning_rate": 2.4678398682721005e-06,
|
| 1185 |
+
"loss": 4.8517,
|
| 1186 |
+
"step": 8400
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.7826610475617098,
|
| 1190 |
+
"grad_norm": 1.9419876337051392,
|
| 1191 |
+
"learning_rate": 2.4163836575074614e-06,
|
| 1192 |
+
"loss": 4.8524,
|
| 1193 |
+
"step": 8450
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.7872921780206549,
|
| 1197 |
+
"grad_norm": 3.776477575302124,
|
| 1198 |
+
"learning_rate": 2.364927446742822e-06,
|
| 1199 |
+
"loss": 4.8527,
|
| 1200 |
+
"step": 8500
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.7919233084795999,
|
| 1204 |
+
"grad_norm": 5.972130298614502,
|
| 1205 |
+
"learning_rate": 2.3134712359781828e-06,
|
| 1206 |
+
"loss": 4.8522,
|
| 1207 |
+
"step": 8550
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.7965544389385449,
|
| 1211 |
+
"grad_norm": 2.1102585792541504,
|
| 1212 |
+
"learning_rate": 2.2620150252135432e-06,
|
| 1213 |
+
"loss": 4.8527,
|
| 1214 |
+
"step": 8600
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.80118556939749,
|
| 1218 |
+
"grad_norm": 3.494260549545288,
|
| 1219 |
+
"learning_rate": 2.210558814448904e-06,
|
| 1220 |
+
"loss": 4.8526,
|
| 1221 |
+
"step": 8650
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.805816699856435,
|
| 1225 |
+
"grad_norm": 1.6491005420684814,
|
| 1226 |
+
"learning_rate": 2.159102603684265e-06,
|
| 1227 |
+
"loss": 4.853,
|
| 1228 |
+
"step": 8700
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.81044783031538,
|
| 1232 |
+
"grad_norm": 3.104100227355957,
|
| 1233 |
+
"learning_rate": 2.1076463929196255e-06,
|
| 1234 |
+
"loss": 4.8522,
|
| 1235 |
+
"step": 8750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.8150789607743251,
|
| 1239 |
+
"grad_norm": 3.840959072113037,
|
| 1240 |
+
"learning_rate": 2.0561901821549863e-06,
|
| 1241 |
+
"loss": 4.8515,
|
| 1242 |
+
"step": 8800
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.81971009123327,
|
| 1246 |
+
"grad_norm": 2.8900058269500732,
|
| 1247 |
+
"learning_rate": 2.004733971390347e-06,
|
| 1248 |
+
"loss": 4.8527,
|
| 1249 |
+
"step": 8850
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.824341221692215,
|
| 1253 |
+
"grad_norm": 4.004197120666504,
|
| 1254 |
+
"learning_rate": 1.9532777606257077e-06,
|
| 1255 |
+
"loss": 4.8525,
|
| 1256 |
+
"step": 8900
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.82897235215116,
|
| 1260 |
+
"grad_norm": 3.287238359451294,
|
| 1261 |
+
"learning_rate": 1.9018215498610684e-06,
|
| 1262 |
+
"loss": 4.8537,
|
| 1263 |
+
"step": 8950
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.8336034826101051,
|
| 1267 |
+
"grad_norm": 1.3281551599502563,
|
| 1268 |
+
"learning_rate": 1.850365339096429e-06,
|
| 1269 |
+
"loss": 4.8526,
|
| 1270 |
+
"step": 9000
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.8382346130690501,
|
| 1274 |
+
"grad_norm": 1.9539192914962769,
|
| 1275 |
+
"learning_rate": 1.7989091283317897e-06,
|
| 1276 |
+
"loss": 4.8516,
|
| 1277 |
+
"step": 9050
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.8428657435279951,
|
| 1281 |
+
"grad_norm": 1.8044812679290771,
|
| 1282 |
+
"learning_rate": 1.7474529175671506e-06,
|
| 1283 |
+
"loss": 4.852,
|
| 1284 |
+
"step": 9100
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.8474968739869402,
|
| 1288 |
+
"grad_norm": 2.2323732376098633,
|
| 1289 |
+
"learning_rate": 1.6959967068025113e-06,
|
| 1290 |
+
"loss": 4.8525,
|
| 1291 |
+
"step": 9150
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.8521280044458852,
|
| 1295 |
+
"grad_norm": 6.444853782653809,
|
| 1296 |
+
"learning_rate": 1.644540496037872e-06,
|
| 1297 |
+
"loss": 4.8525,
|
| 1298 |
+
"step": 9200
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.8567591349048302,
|
| 1302 |
+
"grad_norm": 2.432457447052002,
|
| 1303 |
+
"learning_rate": 1.5930842852732326e-06,
|
| 1304 |
+
"loss": 4.8532,
|
| 1305 |
+
"step": 9250
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.8613902653637753,
|
| 1309 |
+
"grad_norm": 9.460570335388184,
|
| 1310 |
+
"learning_rate": 1.5416280745085933e-06,
|
| 1311 |
+
"loss": 4.8529,
|
| 1312 |
+
"step": 9300
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.8660213958227203,
|
| 1316 |
+
"grad_norm": 1.7130793333053589,
|
| 1317 |
+
"learning_rate": 1.4901718637439542e-06,
|
| 1318 |
+
"loss": 4.8519,
|
| 1319 |
+
"step": 9350
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.8706525262816653,
|
| 1323 |
+
"grad_norm": 1.7794573307037354,
|
| 1324 |
+
"learning_rate": 1.4387156529793148e-06,
|
| 1325 |
+
"loss": 4.8528,
|
| 1326 |
+
"step": 9400
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.8752836567406104,
|
| 1330 |
+
"grad_norm": 2.324021816253662,
|
| 1331 |
+
"learning_rate": 1.3872594422146753e-06,
|
| 1332 |
+
"loss": 4.8515,
|
| 1333 |
+
"step": 9450
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.8799147871995554,
|
| 1337 |
+
"grad_norm": 2.8876137733459473,
|
| 1338 |
+
"learning_rate": 1.335803231450036e-06,
|
| 1339 |
+
"loss": 4.8529,
|
| 1340 |
+
"step": 9500
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.8845459176585004,
|
| 1344 |
+
"grad_norm": 1.5305650234222412,
|
| 1345 |
+
"learning_rate": 1.284347020685397e-06,
|
| 1346 |
+
"loss": 4.8528,
|
| 1347 |
+
"step": 9550
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.8891770481174455,
|
| 1351 |
+
"grad_norm": 1.89708411693573,
|
| 1352 |
+
"learning_rate": 1.2328908099207575e-06,
|
| 1353 |
+
"loss": 4.8523,
|
| 1354 |
+
"step": 9600
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.8938081785763905,
|
| 1358 |
+
"grad_norm": 1.8456463813781738,
|
| 1359 |
+
"learning_rate": 1.1814345991561182e-06,
|
| 1360 |
+
"loss": 4.8523,
|
| 1361 |
+
"step": 9650
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.8984393090353355,
|
| 1365 |
+
"grad_norm": 3.4749717712402344,
|
| 1366 |
+
"learning_rate": 1.1299783883914789e-06,
|
| 1367 |
+
"loss": 4.8524,
|
| 1368 |
+
"step": 9700
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.9030704394942806,
|
| 1372 |
+
"grad_norm": 2.6961116790771484,
|
| 1373 |
+
"learning_rate": 1.0785221776268398e-06,
|
| 1374 |
+
"loss": 4.8521,
|
| 1375 |
+
"step": 9750
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.9077015699532256,
|
| 1379 |
+
"grad_norm": 4.795749187469482,
|
| 1380 |
+
"learning_rate": 1.0270659668622002e-06,
|
| 1381 |
+
"loss": 4.8518,
|
| 1382 |
+
"step": 9800
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.9123327004121706,
|
| 1386 |
+
"grad_norm": 5.0294904708862305,
|
| 1387 |
+
"learning_rate": 9.75609756097561e-07,
|
| 1388 |
+
"loss": 4.8519,
|
| 1389 |
+
"step": 9850
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.9169638308711157,
|
| 1393 |
+
"grad_norm": 2.320612668991089,
|
| 1394 |
+
"learning_rate": 9.241535453329218e-07,
|
| 1395 |
+
"loss": 4.8519,
|
| 1396 |
+
"step": 9900
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.9215949613300607,
|
| 1400 |
+
"grad_norm": 1.5690840482711792,
|
| 1401 |
+
"learning_rate": 8.726973345682825e-07,
|
| 1402 |
+
"loss": 4.8525,
|
| 1403 |
+
"step": 9950
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.9262260917890057,
|
| 1407 |
+
"grad_norm": 3.0287981033325195,
|
| 1408 |
+
"learning_rate": 8.212411238036431e-07,
|
| 1409 |
+
"loss": 4.8527,
|
| 1410 |
+
"step": 10000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.9308572222479508,
|
| 1414 |
+
"grad_norm": 4.888521194458008,
|
| 1415 |
+
"learning_rate": 7.697849130390039e-07,
|
| 1416 |
+
"loss": 4.8526,
|
| 1417 |
+
"step": 10050
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.9354883527068958,
|
| 1421 |
+
"grad_norm": 8.247330665588379,
|
| 1422 |
+
"learning_rate": 7.183287022743646e-07,
|
| 1423 |
+
"loss": 4.8525,
|
| 1424 |
+
"step": 10100
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.9401194831658408,
|
| 1428 |
+
"grad_norm": 4.7511982917785645,
|
| 1429 |
+
"learning_rate": 6.668724915097252e-07,
|
| 1430 |
+
"loss": 4.8515,
|
| 1431 |
+
"step": 10150
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.9447506136247859,
|
| 1435 |
+
"grad_norm": 3.2248997688293457,
|
| 1436 |
+
"learning_rate": 6.15416280745086e-07,
|
| 1437 |
+
"loss": 4.8532,
|
| 1438 |
+
"step": 10200
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.9493817440837309,
|
| 1442 |
+
"grad_norm": 3.083930730819702,
|
| 1443 |
+
"learning_rate": 5.639600699804467e-07,
|
| 1444 |
+
"loss": 4.8528,
|
| 1445 |
+
"step": 10250
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.9540128745426759,
|
| 1449 |
+
"grad_norm": 6.262050151824951,
|
| 1450 |
+
"learning_rate": 5.125038592158075e-07,
|
| 1451 |
+
"loss": 4.8514,
|
| 1452 |
+
"step": 10300
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.958644005001621,
|
| 1456 |
+
"grad_norm": 1.9046210050582886,
|
| 1457 |
+
"learning_rate": 4.610476484511681e-07,
|
| 1458 |
+
"loss": 4.8525,
|
| 1459 |
+
"step": 10350
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.963275135460566,
|
| 1463 |
+
"grad_norm": 4.532755374908447,
|
| 1464 |
+
"learning_rate": 4.0959143768652876e-07,
|
| 1465 |
+
"loss": 4.8519,
|
| 1466 |
+
"step": 10400
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.9679062659195109,
|
| 1470 |
+
"grad_norm": 1.4820815324783325,
|
| 1471 |
+
"learning_rate": 3.581352269218895e-07,
|
| 1472 |
+
"loss": 4.8527,
|
| 1473 |
+
"step": 10450
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.9725373963784559,
|
| 1477 |
+
"grad_norm": 1.89457106590271,
|
| 1478 |
+
"learning_rate": 3.066790161572502e-07,
|
| 1479 |
+
"loss": 4.8516,
|
| 1480 |
+
"step": 10500
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.977168526837401,
|
| 1484 |
+
"grad_norm": 1.8384500741958618,
|
| 1485 |
+
"learning_rate": 2.5522280539261093e-07,
|
| 1486 |
+
"loss": 4.8523,
|
| 1487 |
+
"step": 10550
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.981799657296346,
|
| 1491 |
+
"grad_norm": 2.7351698875427246,
|
| 1492 |
+
"learning_rate": 2.0376659462797163e-07,
|
| 1493 |
+
"loss": 4.8524,
|
| 1494 |
+
"step": 10600
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.986430787755291,
|
| 1498 |
+
"grad_norm": 3.5502257347106934,
|
| 1499 |
+
"learning_rate": 1.523103838633323e-07,
|
| 1500 |
+
"loss": 4.8523,
|
| 1501 |
+
"step": 10650
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.9910619182142361,
|
| 1505 |
+
"grad_norm": 2.255584478378296,
|
| 1506 |
+
"learning_rate": 1.0085417309869303e-07,
|
| 1507 |
+
"loss": 4.8518,
|
| 1508 |
+
"step": 10700
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.9956930486731811,
|
| 1512 |
+
"grad_norm": 1.546319842338562,
|
| 1513 |
+
"learning_rate": 4.9397962334053725e-08,
|
| 1514 |
+
"loss": 4.8524,
|
| 1515 |
+
"step": 10750
|
| 1516 |
+
}
|
| 1517 |
+
],
|
| 1518 |
+
"logging_steps": 50,
|
| 1519 |
+
"max_steps": 10797,
|
| 1520 |
+
"num_input_tokens_seen": 0,
|
| 1521 |
+
"num_train_epochs": 1,
|
| 1522 |
+
"save_steps": 5000,
|
| 1523 |
+
"stateful_callbacks": {
|
| 1524 |
+
"TrainerControl": {
|
| 1525 |
+
"args": {
|
| 1526 |
+
"should_epoch_stop": false,
|
| 1527 |
+
"should_evaluate": false,
|
| 1528 |
+
"should_log": false,
|
| 1529 |
+
"should_save": true,
|
| 1530 |
+
"should_training_stop": true
|
| 1531 |
+
},
|
| 1532 |
+
"attributes": {}
|
| 1533 |
+
}
|
| 1534 |
+
},
|
| 1535 |
+
"total_flos": 0.0,
|
| 1536 |
+
"train_batch_size": 4,
|
| 1537 |
+
"trial_name": null,
|
| 1538 |
+
"trial_params": null
|
| 1539 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef6a514a916232def37a982c0c2afa66792ff69fbb3aa77602e36d62415abbcc
|
| 3 |
+
size 5969
|