Training in progress, step 117000, checkpoint
Browse files- last-checkpoint/README.md +202 -0
- last-checkpoint/adapter_config.json +72 -0
- last-checkpoint/adapter_model.safetensors +3 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/special_tokens_map.json +30 -0
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +43 -0
- last-checkpoint/trainer_state.json +2595 -0
- last-checkpoint/training_args.bin +3 -0
last-checkpoint/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: rank_lstm_full_trained_depth3_n2
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.10.0
|
last-checkpoint/adapter_config.json
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "rank_lstm_full_trained_depth3_n2",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"model.layers.1.mlp.router.layer",
|
| 24 |
+
"model.layers.21.self_attention.experts.router.layer",
|
| 25 |
+
"model.layers.20.self_attention.experts.router.layer",
|
| 26 |
+
"model.layers.12.self_attention.kv_proj",
|
| 27 |
+
"model.layers.20.self_attention.kv_proj",
|
| 28 |
+
"model.layers.15.self_attention.kv_proj",
|
| 29 |
+
"model.layers.18.self_attention.kv_proj",
|
| 30 |
+
"model.lstm_gates.0.transform",
|
| 31 |
+
"model.lstm_gates.1.transform",
|
| 32 |
+
"model.layers.6.self_attention.kv_proj",
|
| 33 |
+
"model.layers.10.self_attention.kv_proj",
|
| 34 |
+
"model.layers.7.self_attention.kv_proj",
|
| 35 |
+
"model.lstm_gates.2.transform",
|
| 36 |
+
"model.lstm_gates.0.input_gate",
|
| 37 |
+
"model.layers.2.self_attention.kv_proj",
|
| 38 |
+
"model.layers.20.mlp.router.layer",
|
| 39 |
+
"model.layers.23.self_attention.kv_proj",
|
| 40 |
+
"model.layers.19.mlp.router.layer",
|
| 41 |
+
"model.layers.16.self_attention.kv_proj",
|
| 42 |
+
"model.layers.4.self_attention.kv_proj",
|
| 43 |
+
"model.layers.1.mlp.router.perturbation",
|
| 44 |
+
"model.layers.19.self_attention.kv_proj",
|
| 45 |
+
"model.lstm_gates.0.forget_gate",
|
| 46 |
+
"model.layers.1.self_attention.experts.router.layer",
|
| 47 |
+
"model.layers.21.mlp.router.layer",
|
| 48 |
+
"model.layers.9.self_attention.kv_proj",
|
| 49 |
+
"model.lstm_gates.1.input_gate",
|
| 50 |
+
"model.layers.21.self_attention.kv_proj",
|
| 51 |
+
"model.layers.22.self_attention.kv_proj",
|
| 52 |
+
"model.lstm_gates.1.output_gate",
|
| 53 |
+
"model.layers.5.self_attention.kv_proj",
|
| 54 |
+
"model.layers.8.self_attention.kv_proj",
|
| 55 |
+
"model.layers.17.self_attention.kv_proj",
|
| 56 |
+
"model.layers.3.self_attention.kv_proj",
|
| 57 |
+
"model.layers.11.self_attention.kv_proj",
|
| 58 |
+
"model.lstm_gates.0.output_gate",
|
| 59 |
+
"model.lstm_gates.2.forget_gate",
|
| 60 |
+
"model.layers.0.self_attention.kv_proj",
|
| 61 |
+
"model.lstm_gates.1.forget_gate",
|
| 62 |
+
"model.layers.13.self_attention.kv_proj",
|
| 63 |
+
"model.lstm_gates.2.output_gate",
|
| 64 |
+
"model.layers.1.self_attention.kv_proj",
|
| 65 |
+
"model.layers.19.self_attention.experts.router.layer",
|
| 66 |
+
"model.layers.14.self_attention.kv_proj",
|
| 67 |
+
"model.lstm_gates.2.input_gate"
|
| 68 |
+
],
|
| 69 |
+
"task_type": "CAUSAL_LM",
|
| 70 |
+
"use_dora": false,
|
| 71 |
+
"use_rslora": false
|
| 72 |
+
}
|
last-checkpoint/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2482c4383c4fcf70f17d5fc82ff290a43376fc65ce81e14fd7624acc1e34e5b4
|
| 3 |
+
size 6961088
|
last-checkpoint/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7f22cff26e6869048fca1948e3a8f6c884dab45ebd886cf517329af324446af
|
| 3 |
+
size 3583418
|
last-checkpoint/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b0bbd11e01d72127f9b367e4226d634850af6672b46d740c5e59481f283296c
|
| 3 |
+
size 14244
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2db0670077b034d76b77e7a25e641a336a29ca0ef1e035c75d5f9798b8a22878
|
| 3 |
+
size 1064
|
last-checkpoint/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
last-checkpoint/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last-checkpoint/tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"additional_special_tokens": [],
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"clean_up_tokenization_spaces": false,
|
| 33 |
+
"eos_token": "</s>",
|
| 34 |
+
"legacy": true,
|
| 35 |
+
"model_max_length": 4096,
|
| 36 |
+
"pad_token": "</s>",
|
| 37 |
+
"padding_side": "right",
|
| 38 |
+
"sp_model_kwargs": {},
|
| 39 |
+
"spaces_between_special_tokens": false,
|
| 40 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 41 |
+
"unk_token": "<unk>",
|
| 42 |
+
"use_default_system_prompt": false
|
| 43 |
+
}
|
last-checkpoint/trainer_state.json
ADDED
|
@@ -0,0 +1,2595 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9669421487603306,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 117000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"grad_norm": 53.65376281738281,
|
| 14 |
+
"learning_rate": 1.9917355371900827e-05,
|
| 15 |
+
"loss": 9.7879,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01,
|
| 20 |
+
"grad_norm": 92.14137268066406,
|
| 21 |
+
"learning_rate": 1.9834710743801656e-05,
|
| 22 |
+
"loss": 7.9084,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"eval_loss": 7.1100754737854,
|
| 28 |
+
"eval_runtime": 137.7524,
|
| 29 |
+
"eval_samples_per_second": 6.984,
|
| 30 |
+
"eval_steps_per_second": 6.984,
|
| 31 |
+
"step": 1000
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.01,
|
| 35 |
+
"grad_norm": 116.5856704711914,
|
| 36 |
+
"learning_rate": 1.9752066115702482e-05,
|
| 37 |
+
"loss": 7.3127,
|
| 38 |
+
"step": 1500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.02,
|
| 42 |
+
"grad_norm": 31.839763641357422,
|
| 43 |
+
"learning_rate": 1.9669421487603307e-05,
|
| 44 |
+
"loss": 7.1385,
|
| 45 |
+
"step": 2000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.02,
|
| 49 |
+
"eval_loss": 6.323878765106201,
|
| 50 |
+
"eval_runtime": 139.7775,
|
| 51 |
+
"eval_samples_per_second": 6.882,
|
| 52 |
+
"eval_steps_per_second": 6.882,
|
| 53 |
+
"step": 2000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.02,
|
| 57 |
+
"grad_norm": 81.93315887451172,
|
| 58 |
+
"learning_rate": 1.9586776859504133e-05,
|
| 59 |
+
"loss": 6.5815,
|
| 60 |
+
"step": 2500
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.02,
|
| 64 |
+
"grad_norm": 91.25088500976562,
|
| 65 |
+
"learning_rate": 1.950413223140496e-05,
|
| 66 |
+
"loss": 6.3278,
|
| 67 |
+
"step": 3000
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.02,
|
| 71 |
+
"eval_loss": 5.6174092292785645,
|
| 72 |
+
"eval_runtime": 137.9688,
|
| 73 |
+
"eval_samples_per_second": 6.973,
|
| 74 |
+
"eval_steps_per_second": 6.973,
|
| 75 |
+
"step": 3000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.03,
|
| 79 |
+
"grad_norm": 42.85502243041992,
|
| 80 |
+
"learning_rate": 1.9421487603305788e-05,
|
| 81 |
+
"loss": 5.9866,
|
| 82 |
+
"step": 3500
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.03,
|
| 86 |
+
"grad_norm": 128.11082458496094,
|
| 87 |
+
"learning_rate": 1.9338842975206613e-05,
|
| 88 |
+
"loss": 5.6448,
|
| 89 |
+
"step": 4000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.03,
|
| 93 |
+
"eval_loss": 5.013957977294922,
|
| 94 |
+
"eval_runtime": 141.6906,
|
| 95 |
+
"eval_samples_per_second": 6.789,
|
| 96 |
+
"eval_steps_per_second": 6.789,
|
| 97 |
+
"step": 4000
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.04,
|
| 101 |
+
"grad_norm": 94.7215576171875,
|
| 102 |
+
"learning_rate": 1.925619834710744e-05,
|
| 103 |
+
"loss": 5.2837,
|
| 104 |
+
"step": 4500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.04,
|
| 108 |
+
"grad_norm": 109.5147705078125,
|
| 109 |
+
"learning_rate": 1.9173553719008268e-05,
|
| 110 |
+
"loss": 5.0691,
|
| 111 |
+
"step": 5000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.04,
|
| 115 |
+
"eval_loss": 4.529860973358154,
|
| 116 |
+
"eval_runtime": 139.3388,
|
| 117 |
+
"eval_samples_per_second": 6.904,
|
| 118 |
+
"eval_steps_per_second": 6.904,
|
| 119 |
+
"step": 5000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.05,
|
| 123 |
+
"grad_norm": 136.12649536132812,
|
| 124 |
+
"learning_rate": 1.9090909090909094e-05,
|
| 125 |
+
"loss": 4.8339,
|
| 126 |
+
"step": 5500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.05,
|
| 130 |
+
"grad_norm": 118.48357391357422,
|
| 131 |
+
"learning_rate": 1.900826446280992e-05,
|
| 132 |
+
"loss": 4.6329,
|
| 133 |
+
"step": 6000
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.05,
|
| 137 |
+
"eval_loss": 4.244248390197754,
|
| 138 |
+
"eval_runtime": 141.3143,
|
| 139 |
+
"eval_samples_per_second": 6.808,
|
| 140 |
+
"eval_steps_per_second": 6.808,
|
| 141 |
+
"step": 6000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.05,
|
| 145 |
+
"grad_norm": 297.8464660644531,
|
| 146 |
+
"learning_rate": 1.8925619834710745e-05,
|
| 147 |
+
"loss": 4.5749,
|
| 148 |
+
"step": 6500
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.06,
|
| 152 |
+
"grad_norm": 155.1725311279297,
|
| 153 |
+
"learning_rate": 1.884297520661157e-05,
|
| 154 |
+
"loss": 4.6391,
|
| 155 |
+
"step": 7000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.06,
|
| 159 |
+
"eval_loss": 4.004535675048828,
|
| 160 |
+
"eval_runtime": 142.1183,
|
| 161 |
+
"eval_samples_per_second": 6.769,
|
| 162 |
+
"eval_steps_per_second": 6.769,
|
| 163 |
+
"step": 7000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.06,
|
| 167 |
+
"grad_norm": 82.23986053466797,
|
| 168 |
+
"learning_rate": 1.87603305785124e-05,
|
| 169 |
+
"loss": 4.299,
|
| 170 |
+
"step": 7500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.07,
|
| 174 |
+
"grad_norm": 83.66497039794922,
|
| 175 |
+
"learning_rate": 1.8677685950413225e-05,
|
| 176 |
+
"loss": 4.1757,
|
| 177 |
+
"step": 8000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.07,
|
| 181 |
+
"eval_loss": 3.7286927700042725,
|
| 182 |
+
"eval_runtime": 141.6853,
|
| 183 |
+
"eval_samples_per_second": 6.79,
|
| 184 |
+
"eval_steps_per_second": 6.79,
|
| 185 |
+
"step": 8000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.07,
|
| 189 |
+
"grad_norm": 185.3876190185547,
|
| 190 |
+
"learning_rate": 1.859504132231405e-05,
|
| 191 |
+
"loss": 4.1474,
|
| 192 |
+
"step": 8500
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.07,
|
| 196 |
+
"grad_norm": 26.485153198242188,
|
| 197 |
+
"learning_rate": 1.851239669421488e-05,
|
| 198 |
+
"loss": 4.3622,
|
| 199 |
+
"step": 9000
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.07,
|
| 203 |
+
"eval_loss": 3.6635849475860596,
|
| 204 |
+
"eval_runtime": 138.132,
|
| 205 |
+
"eval_samples_per_second": 6.964,
|
| 206 |
+
"eval_steps_per_second": 6.964,
|
| 207 |
+
"step": 9000
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.08,
|
| 211 |
+
"grad_norm": 158.5999755859375,
|
| 212 |
+
"learning_rate": 1.8429752066115705e-05,
|
| 213 |
+
"loss": 4.0511,
|
| 214 |
+
"step": 9500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.08,
|
| 218 |
+
"grad_norm": 48.88996505737305,
|
| 219 |
+
"learning_rate": 1.834710743801653e-05,
|
| 220 |
+
"loss": 4.0734,
|
| 221 |
+
"step": 10000
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.08,
|
| 225 |
+
"eval_loss": 3.5613434314727783,
|
| 226 |
+
"eval_runtime": 141.6568,
|
| 227 |
+
"eval_samples_per_second": 6.791,
|
| 228 |
+
"eval_steps_per_second": 6.791,
|
| 229 |
+
"step": 10000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.09,
|
| 233 |
+
"grad_norm": 46.01389694213867,
|
| 234 |
+
"learning_rate": 1.8264462809917356e-05,
|
| 235 |
+
"loss": 3.9621,
|
| 236 |
+
"step": 10500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.09,
|
| 240 |
+
"grad_norm": 311.6304016113281,
|
| 241 |
+
"learning_rate": 1.8181818181818182e-05,
|
| 242 |
+
"loss": 3.8738,
|
| 243 |
+
"step": 11000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.09,
|
| 247 |
+
"eval_loss": 3.4829487800598145,
|
| 248 |
+
"eval_runtime": 137.0137,
|
| 249 |
+
"eval_samples_per_second": 7.021,
|
| 250 |
+
"eval_steps_per_second": 7.021,
|
| 251 |
+
"step": 11000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.1,
|
| 255 |
+
"grad_norm": 148.29006958007812,
|
| 256 |
+
"learning_rate": 1.809917355371901e-05,
|
| 257 |
+
"loss": 3.7787,
|
| 258 |
+
"step": 11500
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.1,
|
| 262 |
+
"grad_norm": 87.70325469970703,
|
| 263 |
+
"learning_rate": 1.8016528925619837e-05,
|
| 264 |
+
"loss": 3.8316,
|
| 265 |
+
"step": 12000
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.1,
|
| 269 |
+
"eval_loss": 3.322986364364624,
|
| 270 |
+
"eval_runtime": 140.8967,
|
| 271 |
+
"eval_samples_per_second": 6.828,
|
| 272 |
+
"eval_steps_per_second": 6.828,
|
| 273 |
+
"step": 12000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.1,
|
| 277 |
+
"grad_norm": 87.01234436035156,
|
| 278 |
+
"learning_rate": 1.7933884297520662e-05,
|
| 279 |
+
"loss": 3.9134,
|
| 280 |
+
"step": 12500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.11,
|
| 284 |
+
"grad_norm": 308.3322448730469,
|
| 285 |
+
"learning_rate": 1.7851239669421488e-05,
|
| 286 |
+
"loss": 3.7965,
|
| 287 |
+
"step": 13000
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.11,
|
| 291 |
+
"eval_loss": 3.3614585399627686,
|
| 292 |
+
"eval_runtime": 141.5793,
|
| 293 |
+
"eval_samples_per_second": 6.795,
|
| 294 |
+
"eval_steps_per_second": 6.795,
|
| 295 |
+
"step": 13000
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.11,
|
| 299 |
+
"grad_norm": 142.58859252929688,
|
| 300 |
+
"learning_rate": 1.7768595041322317e-05,
|
| 301 |
+
"loss": 3.7439,
|
| 302 |
+
"step": 13500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.12,
|
| 306 |
+
"grad_norm": 134.673828125,
|
| 307 |
+
"learning_rate": 1.7685950413223143e-05,
|
| 308 |
+
"loss": 3.7948,
|
| 309 |
+
"step": 14000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.12,
|
| 313 |
+
"eval_loss": 3.228428363800049,
|
| 314 |
+
"eval_runtime": 136.8867,
|
| 315 |
+
"eval_samples_per_second": 7.028,
|
| 316 |
+
"eval_steps_per_second": 7.028,
|
| 317 |
+
"step": 14000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.12,
|
| 321 |
+
"grad_norm": 69.1788330078125,
|
| 322 |
+
"learning_rate": 1.7603305785123968e-05,
|
| 323 |
+
"loss": 3.5873,
|
| 324 |
+
"step": 14500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.12,
|
| 328 |
+
"grad_norm": 161.53973388671875,
|
| 329 |
+
"learning_rate": 1.7520661157024794e-05,
|
| 330 |
+
"loss": 3.8479,
|
| 331 |
+
"step": 15000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.12,
|
| 335 |
+
"eval_loss": 3.2672481536865234,
|
| 336 |
+
"eval_runtime": 138.7625,
|
| 337 |
+
"eval_samples_per_second": 6.933,
|
| 338 |
+
"eval_steps_per_second": 6.933,
|
| 339 |
+
"step": 15000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.13,
|
| 343 |
+
"grad_norm": 128.98785400390625,
|
| 344 |
+
"learning_rate": 1.743801652892562e-05,
|
| 345 |
+
"loss": 3.6716,
|
| 346 |
+
"step": 15500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.13,
|
| 350 |
+
"grad_norm": 170.5436553955078,
|
| 351 |
+
"learning_rate": 1.735537190082645e-05,
|
| 352 |
+
"loss": 3.7273,
|
| 353 |
+
"step": 16000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.13,
|
| 357 |
+
"eval_loss": 3.1376287937164307,
|
| 358 |
+
"eval_runtime": 136.1603,
|
| 359 |
+
"eval_samples_per_second": 7.065,
|
| 360 |
+
"eval_steps_per_second": 7.065,
|
| 361 |
+
"step": 16000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.14,
|
| 365 |
+
"grad_norm": 129.81439208984375,
|
| 366 |
+
"learning_rate": 1.7272727272727274e-05,
|
| 367 |
+
"loss": 3.5567,
|
| 368 |
+
"step": 16500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.14,
|
| 372 |
+
"grad_norm": 135.2463836669922,
|
| 373 |
+
"learning_rate": 1.71900826446281e-05,
|
| 374 |
+
"loss": 3.6128,
|
| 375 |
+
"step": 17000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.14,
|
| 379 |
+
"eval_loss": 3.1712100505828857,
|
| 380 |
+
"eval_runtime": 140.5239,
|
| 381 |
+
"eval_samples_per_second": 6.846,
|
| 382 |
+
"eval_steps_per_second": 6.846,
|
| 383 |
+
"step": 17000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.14,
|
| 387 |
+
"grad_norm": 99.10409545898438,
|
| 388 |
+
"learning_rate": 1.710743801652893e-05,
|
| 389 |
+
"loss": 3.5886,
|
| 390 |
+
"step": 17500
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.15,
|
| 394 |
+
"grad_norm": 42.10710144042969,
|
| 395 |
+
"learning_rate": 1.7024793388429754e-05,
|
| 396 |
+
"loss": 3.4751,
|
| 397 |
+
"step": 18000
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.15,
|
| 401 |
+
"eval_loss": 3.1437861919403076,
|
| 402 |
+
"eval_runtime": 141.4419,
|
| 403 |
+
"eval_samples_per_second": 6.801,
|
| 404 |
+
"eval_steps_per_second": 6.801,
|
| 405 |
+
"step": 18000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.15,
|
| 409 |
+
"grad_norm": 60.31798553466797,
|
| 410 |
+
"learning_rate": 1.694214876033058e-05,
|
| 411 |
+
"loss": 3.3902,
|
| 412 |
+
"step": 18500
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 0.16,
|
| 416 |
+
"grad_norm": 446.0960388183594,
|
| 417 |
+
"learning_rate": 1.6859504132231405e-05,
|
| 418 |
+
"loss": 3.5544,
|
| 419 |
+
"step": 19000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.16,
|
| 423 |
+
"eval_loss": 3.0222690105438232,
|
| 424 |
+
"eval_runtime": 140.8408,
|
| 425 |
+
"eval_samples_per_second": 6.83,
|
| 426 |
+
"eval_steps_per_second": 6.83,
|
| 427 |
+
"step": 19000
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 0.16,
|
| 431 |
+
"grad_norm": 125.9988784790039,
|
| 432 |
+
"learning_rate": 1.677685950413223e-05,
|
| 433 |
+
"loss": 3.4624,
|
| 434 |
+
"step": 19500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.17,
|
| 438 |
+
"grad_norm": 41.044036865234375,
|
| 439 |
+
"learning_rate": 1.669421487603306e-05,
|
| 440 |
+
"loss": 3.3734,
|
| 441 |
+
"step": 20000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.17,
|
| 445 |
+
"eval_loss": 2.9934887886047363,
|
| 446 |
+
"eval_runtime": 140.0157,
|
| 447 |
+
"eval_samples_per_second": 6.871,
|
| 448 |
+
"eval_steps_per_second": 6.871,
|
| 449 |
+
"step": 20000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.17,
|
| 453 |
+
"grad_norm": 98.76380157470703,
|
| 454 |
+
"learning_rate": 1.6611570247933886e-05,
|
| 455 |
+
"loss": 3.4481,
|
| 456 |
+
"step": 20500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.17,
|
| 460 |
+
"grad_norm": 96.16433715820312,
|
| 461 |
+
"learning_rate": 1.652892561983471e-05,
|
| 462 |
+
"loss": 3.6288,
|
| 463 |
+
"step": 21000
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.17,
|
| 467 |
+
"eval_loss": 2.9670004844665527,
|
| 468 |
+
"eval_runtime": 141.8861,
|
| 469 |
+
"eval_samples_per_second": 6.78,
|
| 470 |
+
"eval_steps_per_second": 6.78,
|
| 471 |
+
"step": 21000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.18,
|
| 475 |
+
"grad_norm": 147.28933715820312,
|
| 476 |
+
"learning_rate": 1.644628099173554e-05,
|
| 477 |
+
"loss": 3.622,
|
| 478 |
+
"step": 21500
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.18,
|
| 482 |
+
"grad_norm": 85.05192565917969,
|
| 483 |
+
"learning_rate": 1.6363636363636366e-05,
|
| 484 |
+
"loss": 3.194,
|
| 485 |
+
"step": 22000
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.18,
|
| 489 |
+
"eval_loss": 2.9449918270111084,
|
| 490 |
+
"eval_runtime": 140.4537,
|
| 491 |
+
"eval_samples_per_second": 6.849,
|
| 492 |
+
"eval_steps_per_second": 6.849,
|
| 493 |
+
"step": 22000
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.19,
|
| 497 |
+
"grad_norm": 231.34249877929688,
|
| 498 |
+
"learning_rate": 1.628099173553719e-05,
|
| 499 |
+
"loss": 3.3939,
|
| 500 |
+
"step": 22500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.19,
|
| 504 |
+
"grad_norm": 17.25453758239746,
|
| 505 |
+
"learning_rate": 1.6198347107438017e-05,
|
| 506 |
+
"loss": 3.4362,
|
| 507 |
+
"step": 23000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.19,
|
| 511 |
+
"eval_loss": 2.9837887287139893,
|
| 512 |
+
"eval_runtime": 140.5356,
|
| 513 |
+
"eval_samples_per_second": 6.845,
|
| 514 |
+
"eval_steps_per_second": 6.845,
|
| 515 |
+
"step": 23000
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.19,
|
| 519 |
+
"grad_norm": 209.98016357421875,
|
| 520 |
+
"learning_rate": 1.6115702479338843e-05,
|
| 521 |
+
"loss": 3.5168,
|
| 522 |
+
"step": 23500
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.2,
|
| 526 |
+
"grad_norm": 94.24089050292969,
|
| 527 |
+
"learning_rate": 1.6033057851239672e-05,
|
| 528 |
+
"loss": 3.2853,
|
| 529 |
+
"step": 24000
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.2,
|
| 533 |
+
"eval_loss": 2.9006521701812744,
|
| 534 |
+
"eval_runtime": 139.8116,
|
| 535 |
+
"eval_samples_per_second": 6.881,
|
| 536 |
+
"eval_steps_per_second": 6.881,
|
| 537 |
+
"step": 24000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.2,
|
| 541 |
+
"grad_norm": 59.02330780029297,
|
| 542 |
+
"learning_rate": 1.5950413223140497e-05,
|
| 543 |
+
"loss": 3.2102,
|
| 544 |
+
"step": 24500
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.21,
|
| 548 |
+
"grad_norm": 114.82744598388672,
|
| 549 |
+
"learning_rate": 1.5867768595041323e-05,
|
| 550 |
+
"loss": 3.3839,
|
| 551 |
+
"step": 25000
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.21,
|
| 555 |
+
"eval_loss": 2.8425700664520264,
|
| 556 |
+
"eval_runtime": 135.9965,
|
| 557 |
+
"eval_samples_per_second": 7.074,
|
| 558 |
+
"eval_steps_per_second": 7.074,
|
| 559 |
+
"step": 25000
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 0.21,
|
| 563 |
+
"grad_norm": 151.8341064453125,
|
| 564 |
+
"learning_rate": 1.5785123966942152e-05,
|
| 565 |
+
"loss": 3.3901,
|
| 566 |
+
"step": 25500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.21,
|
| 570 |
+
"grad_norm": 69.12097930908203,
|
| 571 |
+
"learning_rate": 1.5702479338842978e-05,
|
| 572 |
+
"loss": 3.4662,
|
| 573 |
+
"step": 26000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.21,
|
| 577 |
+
"eval_loss": 2.8814632892608643,
|
| 578 |
+
"eval_runtime": 139.0607,
|
| 579 |
+
"eval_samples_per_second": 6.918,
|
| 580 |
+
"eval_steps_per_second": 6.918,
|
| 581 |
+
"step": 26000
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.22,
|
| 585 |
+
"grad_norm": 81.52751159667969,
|
| 586 |
+
"learning_rate": 1.5619834710743803e-05,
|
| 587 |
+
"loss": 3.325,
|
| 588 |
+
"step": 26500
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 0.22,
|
| 592 |
+
"grad_norm": 206.8463592529297,
|
| 593 |
+
"learning_rate": 1.553719008264463e-05,
|
| 594 |
+
"loss": 3.3232,
|
| 595 |
+
"step": 27000
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 0.22,
|
| 599 |
+
"eval_loss": 2.836251735687256,
|
| 600 |
+
"eval_runtime": 138.3679,
|
| 601 |
+
"eval_samples_per_second": 6.952,
|
| 602 |
+
"eval_steps_per_second": 6.952,
|
| 603 |
+
"step": 27000
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.23,
|
| 607 |
+
"grad_norm": 82.50727844238281,
|
| 608 |
+
"learning_rate": 1.5454545454545454e-05,
|
| 609 |
+
"loss": 3.2616,
|
| 610 |
+
"step": 27500
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.23,
|
| 614 |
+
"grad_norm": 131.51040649414062,
|
| 615 |
+
"learning_rate": 1.5371900826446283e-05,
|
| 616 |
+
"loss": 3.3857,
|
| 617 |
+
"step": 28000
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.23,
|
| 621 |
+
"eval_loss": 2.780090093612671,
|
| 622 |
+
"eval_runtime": 140.6306,
|
| 623 |
+
"eval_samples_per_second": 6.841,
|
| 624 |
+
"eval_steps_per_second": 6.841,
|
| 625 |
+
"step": 28000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.24,
|
| 629 |
+
"grad_norm": 66.1187515258789,
|
| 630 |
+
"learning_rate": 1.528925619834711e-05,
|
| 631 |
+
"loss": 3.2072,
|
| 632 |
+
"step": 28500
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.24,
|
| 636 |
+
"grad_norm": 131.09405517578125,
|
| 637 |
+
"learning_rate": 1.5206611570247936e-05,
|
| 638 |
+
"loss": 3.0476,
|
| 639 |
+
"step": 29000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.24,
|
| 643 |
+
"eval_loss": 2.8148860931396484,
|
| 644 |
+
"eval_runtime": 141.206,
|
| 645 |
+
"eval_samples_per_second": 6.813,
|
| 646 |
+
"eval_steps_per_second": 6.813,
|
| 647 |
+
"step": 29000
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.24,
|
| 651 |
+
"grad_norm": 51.353572845458984,
|
| 652 |
+
"learning_rate": 1.5123966942148762e-05,
|
| 653 |
+
"loss": 3.3377,
|
| 654 |
+
"step": 29500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.25,
|
| 658 |
+
"grad_norm": 66.42013549804688,
|
| 659 |
+
"learning_rate": 1.504132231404959e-05,
|
| 660 |
+
"loss": 3.0664,
|
| 661 |
+
"step": 30000
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.25,
|
| 665 |
+
"eval_loss": 2.776242971420288,
|
| 666 |
+
"eval_runtime": 141.6364,
|
| 667 |
+
"eval_samples_per_second": 6.792,
|
| 668 |
+
"eval_steps_per_second": 6.792,
|
| 669 |
+
"step": 30000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.25,
|
| 673 |
+
"grad_norm": 170.49464416503906,
|
| 674 |
+
"learning_rate": 1.4958677685950413e-05,
|
| 675 |
+
"loss": 3.0958,
|
| 676 |
+
"step": 30500
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.26,
|
| 680 |
+
"grad_norm": 137.87022399902344,
|
| 681 |
+
"learning_rate": 1.487603305785124e-05,
|
| 682 |
+
"loss": 3.2919,
|
| 683 |
+
"step": 31000
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.26,
|
| 687 |
+
"eval_loss": 2.8100545406341553,
|
| 688 |
+
"eval_runtime": 141.0359,
|
| 689 |
+
"eval_samples_per_second": 6.821,
|
| 690 |
+
"eval_steps_per_second": 6.821,
|
| 691 |
+
"step": 31000
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.26,
|
| 695 |
+
"grad_norm": 211.2021942138672,
|
| 696 |
+
"learning_rate": 1.4793388429752066e-05,
|
| 697 |
+
"loss": 3.4836,
|
| 698 |
+
"step": 31500
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.26,
|
| 702 |
+
"grad_norm": 113.34933471679688,
|
| 703 |
+
"learning_rate": 1.4710743801652893e-05,
|
| 704 |
+
"loss": 3.334,
|
| 705 |
+
"step": 32000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.26,
|
| 709 |
+
"eval_loss": 2.754260301589966,
|
| 710 |
+
"eval_runtime": 140.5105,
|
| 711 |
+
"eval_samples_per_second": 6.846,
|
| 712 |
+
"eval_steps_per_second": 6.846,
|
| 713 |
+
"step": 32000
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.27,
|
| 717 |
+
"grad_norm": 114.3346939086914,
|
| 718 |
+
"learning_rate": 1.462809917355372e-05,
|
| 719 |
+
"loss": 3.0715,
|
| 720 |
+
"step": 32500
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.27,
|
| 724 |
+
"grad_norm": 91.6365966796875,
|
| 725 |
+
"learning_rate": 1.4545454545454546e-05,
|
| 726 |
+
"loss": 3.2307,
|
| 727 |
+
"step": 33000
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.27,
|
| 731 |
+
"eval_loss": 2.7607641220092773,
|
| 732 |
+
"eval_runtime": 139.2517,
|
| 733 |
+
"eval_samples_per_second": 6.908,
|
| 734 |
+
"eval_steps_per_second": 6.908,
|
| 735 |
+
"step": 33000
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.28,
|
| 739 |
+
"grad_norm": 6.1861701011657715,
|
| 740 |
+
"learning_rate": 1.4462809917355374e-05,
|
| 741 |
+
"loss": 2.9537,
|
| 742 |
+
"step": 33500
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 0.28,
|
| 746 |
+
"grad_norm": 97.13253021240234,
|
| 747 |
+
"learning_rate": 1.4380165289256201e-05,
|
| 748 |
+
"loss": 2.9517,
|
| 749 |
+
"step": 34000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.28,
|
| 753 |
+
"eval_loss": 2.805582046508789,
|
| 754 |
+
"eval_runtime": 138.7882,
|
| 755 |
+
"eval_samples_per_second": 6.931,
|
| 756 |
+
"eval_steps_per_second": 6.931,
|
| 757 |
+
"step": 34000
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.29,
|
| 761 |
+
"grad_norm": 55.73282241821289,
|
| 762 |
+
"learning_rate": 1.4297520661157025e-05,
|
| 763 |
+
"loss": 3.5026,
|
| 764 |
+
"step": 34500
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.29,
|
| 768 |
+
"grad_norm": 105.15763854980469,
|
| 769 |
+
"learning_rate": 1.4214876033057852e-05,
|
| 770 |
+
"loss": 3.3557,
|
| 771 |
+
"step": 35000
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.29,
|
| 775 |
+
"eval_loss": 2.7643611431121826,
|
| 776 |
+
"eval_runtime": 140.4066,
|
| 777 |
+
"eval_samples_per_second": 6.852,
|
| 778 |
+
"eval_steps_per_second": 6.852,
|
| 779 |
+
"step": 35000
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.29,
|
| 783 |
+
"grad_norm": 34.19166564941406,
|
| 784 |
+
"learning_rate": 1.4132231404958678e-05,
|
| 785 |
+
"loss": 3.1291,
|
| 786 |
+
"step": 35500
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.3,
|
| 790 |
+
"grad_norm": 129.49188232421875,
|
| 791 |
+
"learning_rate": 1.4049586776859505e-05,
|
| 792 |
+
"loss": 3.2801,
|
| 793 |
+
"step": 36000
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.3,
|
| 797 |
+
"eval_loss": 2.7544772624969482,
|
| 798 |
+
"eval_runtime": 138.7006,
|
| 799 |
+
"eval_samples_per_second": 6.936,
|
| 800 |
+
"eval_steps_per_second": 6.936,
|
| 801 |
+
"step": 36000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.3,
|
| 805 |
+
"grad_norm": 36.190162658691406,
|
| 806 |
+
"learning_rate": 1.3966942148760332e-05,
|
| 807 |
+
"loss": 3.1862,
|
| 808 |
+
"step": 36500
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.31,
|
| 812 |
+
"grad_norm": 126.45512390136719,
|
| 813 |
+
"learning_rate": 1.3884297520661158e-05,
|
| 814 |
+
"loss": 3.1573,
|
| 815 |
+
"step": 37000
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.31,
|
| 819 |
+
"eval_loss": 2.7139012813568115,
|
| 820 |
+
"eval_runtime": 139.7912,
|
| 821 |
+
"eval_samples_per_second": 6.882,
|
| 822 |
+
"eval_steps_per_second": 6.882,
|
| 823 |
+
"step": 37000
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 0.31,
|
| 827 |
+
"grad_norm": 168.74777221679688,
|
| 828 |
+
"learning_rate": 1.3801652892561985e-05,
|
| 829 |
+
"loss": 3.1524,
|
| 830 |
+
"step": 37500
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.31,
|
| 834 |
+
"grad_norm": 64.23265075683594,
|
| 835 |
+
"learning_rate": 1.3719008264462813e-05,
|
| 836 |
+
"loss": 3.2022,
|
| 837 |
+
"step": 38000
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.31,
|
| 841 |
+
"eval_loss": 2.726412773132324,
|
| 842 |
+
"eval_runtime": 137.2349,
|
| 843 |
+
"eval_samples_per_second": 7.01,
|
| 844 |
+
"eval_steps_per_second": 7.01,
|
| 845 |
+
"step": 38000
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.32,
|
| 849 |
+
"grad_norm": 143.0786895751953,
|
| 850 |
+
"learning_rate": 1.3636363636363637e-05,
|
| 851 |
+
"loss": 3.3005,
|
| 852 |
+
"step": 38500
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.32,
|
| 856 |
+
"grad_norm": 0.35411542654037476,
|
| 857 |
+
"learning_rate": 1.3553719008264464e-05,
|
| 858 |
+
"loss": 3.1852,
|
| 859 |
+
"step": 39000
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.32,
|
| 863 |
+
"eval_loss": 2.7224111557006836,
|
| 864 |
+
"eval_runtime": 140.911,
|
| 865 |
+
"eval_samples_per_second": 6.827,
|
| 866 |
+
"eval_steps_per_second": 6.827,
|
| 867 |
+
"step": 39000
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.33,
|
| 871 |
+
"grad_norm": 56.73325729370117,
|
| 872 |
+
"learning_rate": 1.347107438016529e-05,
|
| 873 |
+
"loss": 3.0389,
|
| 874 |
+
"step": 39500
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 0.33,
|
| 878 |
+
"grad_norm": 182.5022430419922,
|
| 879 |
+
"learning_rate": 1.3388429752066117e-05,
|
| 880 |
+
"loss": 2.9861,
|
| 881 |
+
"step": 40000
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 0.33,
|
| 885 |
+
"eval_loss": 2.7215094566345215,
|
| 886 |
+
"eval_runtime": 142.3112,
|
| 887 |
+
"eval_samples_per_second": 6.76,
|
| 888 |
+
"eval_steps_per_second": 6.76,
|
| 889 |
+
"step": 40000
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.33,
|
| 893 |
+
"grad_norm": 129.25076293945312,
|
| 894 |
+
"learning_rate": 1.3305785123966944e-05,
|
| 895 |
+
"loss": 3.2484,
|
| 896 |
+
"step": 40500
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.34,
|
| 900 |
+
"grad_norm": 28.573749542236328,
|
| 901 |
+
"learning_rate": 1.322314049586777e-05,
|
| 902 |
+
"loss": 3.176,
|
| 903 |
+
"step": 41000
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.34,
|
| 907 |
+
"eval_loss": 2.678982973098755,
|
| 908 |
+
"eval_runtime": 140.2555,
|
| 909 |
+
"eval_samples_per_second": 6.859,
|
| 910 |
+
"eval_steps_per_second": 6.859,
|
| 911 |
+
"step": 41000
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 0.34,
|
| 915 |
+
"grad_norm": 29.228971481323242,
|
| 916 |
+
"learning_rate": 1.3140495867768597e-05,
|
| 917 |
+
"loss": 2.898,
|
| 918 |
+
"step": 41500
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 0.35,
|
| 922 |
+
"grad_norm": 2.7074639797210693,
|
| 923 |
+
"learning_rate": 1.3057851239669424e-05,
|
| 924 |
+
"loss": 2.9024,
|
| 925 |
+
"step": 42000
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 0.35,
|
| 929 |
+
"eval_loss": 2.7119204998016357,
|
| 930 |
+
"eval_runtime": 141.0803,
|
| 931 |
+
"eval_samples_per_second": 6.819,
|
| 932 |
+
"eval_steps_per_second": 6.819,
|
| 933 |
+
"step": 42000
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.35,
|
| 937 |
+
"grad_norm": 122.27530670166016,
|
| 938 |
+
"learning_rate": 1.2975206611570248e-05,
|
| 939 |
+
"loss": 3.024,
|
| 940 |
+
"step": 42500
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.36,
|
| 944 |
+
"grad_norm": 19.63726806640625,
|
| 945 |
+
"learning_rate": 1.2892561983471074e-05,
|
| 946 |
+
"loss": 3.2979,
|
| 947 |
+
"step": 43000
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.36,
|
| 951 |
+
"eval_loss": 2.6496329307556152,
|
| 952 |
+
"eval_runtime": 141.7782,
|
| 953 |
+
"eval_samples_per_second": 6.785,
|
| 954 |
+
"eval_steps_per_second": 6.785,
|
| 955 |
+
"step": 43000
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.36,
|
| 959 |
+
"grad_norm": 220.49954223632812,
|
| 960 |
+
"learning_rate": 1.2809917355371901e-05,
|
| 961 |
+
"loss": 3.0016,
|
| 962 |
+
"step": 43500
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.36,
|
| 966 |
+
"grad_norm": 77.60582733154297,
|
| 967 |
+
"learning_rate": 1.2727272727272728e-05,
|
| 968 |
+
"loss": 3.0776,
|
| 969 |
+
"step": 44000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.36,
|
| 973 |
+
"eval_loss": 2.6587836742401123,
|
| 974 |
+
"eval_runtime": 139.8192,
|
| 975 |
+
"eval_samples_per_second": 6.88,
|
| 976 |
+
"eval_steps_per_second": 6.88,
|
| 977 |
+
"step": 44000
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.37,
|
| 981 |
+
"grad_norm": 94.2193832397461,
|
| 982 |
+
"learning_rate": 1.2644628099173554e-05,
|
| 983 |
+
"loss": 3.0418,
|
| 984 |
+
"step": 44500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.37,
|
| 988 |
+
"grad_norm": 30.321847915649414,
|
| 989 |
+
"learning_rate": 1.2561983471074381e-05,
|
| 990 |
+
"loss": 3.2145,
|
| 991 |
+
"step": 45000
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 0.37,
|
| 995 |
+
"eval_loss": 2.7039036750793457,
|
| 996 |
+
"eval_runtime": 138.137,
|
| 997 |
+
"eval_samples_per_second": 6.964,
|
| 998 |
+
"eval_steps_per_second": 6.964,
|
| 999 |
+
"step": 45000
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.38,
|
| 1003 |
+
"grad_norm": 102.64441680908203,
|
| 1004 |
+
"learning_rate": 1.2479338842975209e-05,
|
| 1005 |
+
"loss": 2.9082,
|
| 1006 |
+
"step": 45500
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.38,
|
| 1010 |
+
"grad_norm": 95.51321411132812,
|
| 1011 |
+
"learning_rate": 1.2396694214876034e-05,
|
| 1012 |
+
"loss": 3.2535,
|
| 1013 |
+
"step": 46000
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.38,
|
| 1017 |
+
"eval_loss": 2.648103952407837,
|
| 1018 |
+
"eval_runtime": 139.7372,
|
| 1019 |
+
"eval_samples_per_second": 6.884,
|
| 1020 |
+
"eval_steps_per_second": 6.884,
|
| 1021 |
+
"step": 46000
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 0.38,
|
| 1025 |
+
"grad_norm": 90.64472961425781,
|
| 1026 |
+
"learning_rate": 1.231404958677686e-05,
|
| 1027 |
+
"loss": 3.1841,
|
| 1028 |
+
"step": 46500
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 0.39,
|
| 1032 |
+
"grad_norm": 128.23159790039062,
|
| 1033 |
+
"learning_rate": 1.2231404958677686e-05,
|
| 1034 |
+
"loss": 3.0074,
|
| 1035 |
+
"step": 47000
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.39,
|
| 1039 |
+
"eval_loss": 2.6026036739349365,
|
| 1040 |
+
"eval_runtime": 139.947,
|
| 1041 |
+
"eval_samples_per_second": 6.874,
|
| 1042 |
+
"eval_steps_per_second": 6.874,
|
| 1043 |
+
"step": 47000
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 0.39,
|
| 1047 |
+
"grad_norm": 254.29718017578125,
|
| 1048 |
+
"learning_rate": 1.2148760330578513e-05,
|
| 1049 |
+
"loss": 3.3493,
|
| 1050 |
+
"step": 47500
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.4,
|
| 1054 |
+
"grad_norm": 33.48649215698242,
|
| 1055 |
+
"learning_rate": 1.206611570247934e-05,
|
| 1056 |
+
"loss": 3.007,
|
| 1057 |
+
"step": 48000
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 0.4,
|
| 1061 |
+
"eval_loss": 2.6409358978271484,
|
| 1062 |
+
"eval_runtime": 140.003,
|
| 1063 |
+
"eval_samples_per_second": 6.871,
|
| 1064 |
+
"eval_steps_per_second": 6.871,
|
| 1065 |
+
"step": 48000
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.4,
|
| 1069 |
+
"grad_norm": 165.1754608154297,
|
| 1070 |
+
"learning_rate": 1.1983471074380166e-05,
|
| 1071 |
+
"loss": 3.0267,
|
| 1072 |
+
"step": 48500
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 0.4,
|
| 1076 |
+
"grad_norm": 57.49995803833008,
|
| 1077 |
+
"learning_rate": 1.1900826446280993e-05,
|
| 1078 |
+
"loss": 3.0913,
|
| 1079 |
+
"step": 49000
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 0.4,
|
| 1083 |
+
"eval_loss": 2.676673412322998,
|
| 1084 |
+
"eval_runtime": 139.7897,
|
| 1085 |
+
"eval_samples_per_second": 6.882,
|
| 1086 |
+
"eval_steps_per_second": 6.882,
|
| 1087 |
+
"step": 49000
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.41,
|
| 1091 |
+
"grad_norm": 269.28326416015625,
|
| 1092 |
+
"learning_rate": 1.181818181818182e-05,
|
| 1093 |
+
"loss": 3.0674,
|
| 1094 |
+
"step": 49500
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.41,
|
| 1098 |
+
"grad_norm": 81.5179672241211,
|
| 1099 |
+
"learning_rate": 1.1735537190082646e-05,
|
| 1100 |
+
"loss": 3.1847,
|
| 1101 |
+
"step": 50000
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.41,
|
| 1105 |
+
"eval_loss": 2.6336779594421387,
|
| 1106 |
+
"eval_runtime": 140.9712,
|
| 1107 |
+
"eval_samples_per_second": 6.824,
|
| 1108 |
+
"eval_steps_per_second": 6.824,
|
| 1109 |
+
"step": 50000
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.42,
|
| 1113 |
+
"grad_norm": 81.88212585449219,
|
| 1114 |
+
"learning_rate": 1.1652892561983472e-05,
|
| 1115 |
+
"loss": 2.7742,
|
| 1116 |
+
"step": 50500
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.42,
|
| 1120 |
+
"grad_norm": 34.32734298706055,
|
| 1121 |
+
"learning_rate": 1.1570247933884297e-05,
|
| 1122 |
+
"loss": 2.9359,
|
| 1123 |
+
"step": 51000
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.42,
|
| 1127 |
+
"eval_loss": 2.649772882461548,
|
| 1128 |
+
"eval_runtime": 139.5432,
|
| 1129 |
+
"eval_samples_per_second": 6.894,
|
| 1130 |
+
"eval_steps_per_second": 6.894,
|
| 1131 |
+
"step": 51000
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 0.43,
|
| 1135 |
+
"grad_norm": 44.86323165893555,
|
| 1136 |
+
"learning_rate": 1.1487603305785125e-05,
|
| 1137 |
+
"loss": 3.1545,
|
| 1138 |
+
"step": 51500
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 0.43,
|
| 1142 |
+
"grad_norm": 70.11674499511719,
|
| 1143 |
+
"learning_rate": 1.1404958677685952e-05,
|
| 1144 |
+
"loss": 2.9488,
|
| 1145 |
+
"step": 52000
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 0.43,
|
| 1149 |
+
"eval_loss": 2.5968177318573,
|
| 1150 |
+
"eval_runtime": 142.9712,
|
| 1151 |
+
"eval_samples_per_second": 6.729,
|
| 1152 |
+
"eval_steps_per_second": 6.729,
|
| 1153 |
+
"step": 52000
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 0.43,
|
| 1157 |
+
"grad_norm": 43.42722702026367,
|
| 1158 |
+
"learning_rate": 1.1322314049586777e-05,
|
| 1159 |
+
"loss": 3.02,
|
| 1160 |
+
"step": 52500
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 0.44,
|
| 1164 |
+
"grad_norm": 178.18666076660156,
|
| 1165 |
+
"learning_rate": 1.1239669421487605e-05,
|
| 1166 |
+
"loss": 3.0279,
|
| 1167 |
+
"step": 53000
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.44,
|
| 1171 |
+
"eval_loss": 2.625840425491333,
|
| 1172 |
+
"eval_runtime": 142.8837,
|
| 1173 |
+
"eval_samples_per_second": 6.733,
|
| 1174 |
+
"eval_steps_per_second": 6.733,
|
| 1175 |
+
"step": 53000
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.44,
|
| 1179 |
+
"grad_norm": 33.83938217163086,
|
| 1180 |
+
"learning_rate": 1.1157024793388432e-05,
|
| 1181 |
+
"loss": 2.9362,
|
| 1182 |
+
"step": 53500
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.45,
|
| 1186 |
+
"grad_norm": 24.059724807739258,
|
| 1187 |
+
"learning_rate": 1.1074380165289258e-05,
|
| 1188 |
+
"loss": 2.9282,
|
| 1189 |
+
"step": 54000
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.45,
|
| 1193 |
+
"eval_loss": 2.671956777572632,
|
| 1194 |
+
"eval_runtime": 141.943,
|
| 1195 |
+
"eval_samples_per_second": 6.777,
|
| 1196 |
+
"eval_steps_per_second": 6.777,
|
| 1197 |
+
"step": 54000
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 0.45,
|
| 1201 |
+
"grad_norm": 150.78285217285156,
|
| 1202 |
+
"learning_rate": 1.0991735537190083e-05,
|
| 1203 |
+
"loss": 3.1242,
|
| 1204 |
+
"step": 54500
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 0.45,
|
| 1208 |
+
"grad_norm": 129.85336303710938,
|
| 1209 |
+
"learning_rate": 1.0909090909090909e-05,
|
| 1210 |
+
"loss": 2.9939,
|
| 1211 |
+
"step": 55000
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 0.45,
|
| 1215 |
+
"eval_loss": 2.6020476818084717,
|
| 1216 |
+
"eval_runtime": 137.1321,
|
| 1217 |
+
"eval_samples_per_second": 7.015,
|
| 1218 |
+
"eval_steps_per_second": 7.015,
|
| 1219 |
+
"step": 55000
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 0.46,
|
| 1223 |
+
"grad_norm": 97.6047134399414,
|
| 1224 |
+
"learning_rate": 1.0826446280991736e-05,
|
| 1225 |
+
"loss": 3.2276,
|
| 1226 |
+
"step": 55500
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 0.46,
|
| 1230 |
+
"grad_norm": 54.10629653930664,
|
| 1231 |
+
"learning_rate": 1.0743801652892562e-05,
|
| 1232 |
+
"loss": 3.1815,
|
| 1233 |
+
"step": 56000
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 0.46,
|
| 1237 |
+
"eval_loss": 2.6137943267822266,
|
| 1238 |
+
"eval_runtime": 140.5161,
|
| 1239 |
+
"eval_samples_per_second": 6.846,
|
| 1240 |
+
"eval_steps_per_second": 6.846,
|
| 1241 |
+
"step": 56000
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.47,
|
| 1245 |
+
"grad_norm": 116.71500396728516,
|
| 1246 |
+
"learning_rate": 1.0661157024793389e-05,
|
| 1247 |
+
"loss": 2.7576,
|
| 1248 |
+
"step": 56500
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.47,
|
| 1252 |
+
"grad_norm": 132.3123016357422,
|
| 1253 |
+
"learning_rate": 1.0578512396694216e-05,
|
| 1254 |
+
"loss": 2.8927,
|
| 1255 |
+
"step": 57000
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.47,
|
| 1259 |
+
"eval_loss": 2.58026385307312,
|
| 1260 |
+
"eval_runtime": 137.5438,
|
| 1261 |
+
"eval_samples_per_second": 6.994,
|
| 1262 |
+
"eval_steps_per_second": 6.994,
|
| 1263 |
+
"step": 57000
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.48,
|
| 1267 |
+
"grad_norm": 1.3877036571502686,
|
| 1268 |
+
"learning_rate": 1.0495867768595042e-05,
|
| 1269 |
+
"loss": 3.1726,
|
| 1270 |
+
"step": 57500
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.48,
|
| 1274 |
+
"grad_norm": 23.99924659729004,
|
| 1275 |
+
"learning_rate": 1.041322314049587e-05,
|
| 1276 |
+
"loss": 3.0603,
|
| 1277 |
+
"step": 58000
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.48,
|
| 1281 |
+
"eval_loss": 2.5942938327789307,
|
| 1282 |
+
"eval_runtime": 139.9432,
|
| 1283 |
+
"eval_samples_per_second": 6.874,
|
| 1284 |
+
"eval_steps_per_second": 6.874,
|
| 1285 |
+
"step": 58000
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 0.48,
|
| 1289 |
+
"grad_norm": 89.54573059082031,
|
| 1290 |
+
"learning_rate": 1.0330578512396693e-05,
|
| 1291 |
+
"loss": 2.9213,
|
| 1292 |
+
"step": 58500
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 0.49,
|
| 1296 |
+
"grad_norm": 117.28192138671875,
|
| 1297 |
+
"learning_rate": 1.024793388429752e-05,
|
| 1298 |
+
"loss": 2.9974,
|
| 1299 |
+
"step": 59000
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.49,
|
| 1303 |
+
"eval_loss": 2.574179172515869,
|
| 1304 |
+
"eval_runtime": 137.8963,
|
| 1305 |
+
"eval_samples_per_second": 6.976,
|
| 1306 |
+
"eval_steps_per_second": 6.976,
|
| 1307 |
+
"step": 59000
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 0.49,
|
| 1311 |
+
"grad_norm": 230.2947540283203,
|
| 1312 |
+
"learning_rate": 1.0165289256198348e-05,
|
| 1313 |
+
"loss": 2.9884,
|
| 1314 |
+
"step": 59500
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.5,
|
| 1318 |
+
"grad_norm": 114.89617156982422,
|
| 1319 |
+
"learning_rate": 1.0082644628099174e-05,
|
| 1320 |
+
"loss": 3.1789,
|
| 1321 |
+
"step": 60000
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.5,
|
| 1325 |
+
"eval_loss": 2.551656723022461,
|
| 1326 |
+
"eval_runtime": 139.8913,
|
| 1327 |
+
"eval_samples_per_second": 6.877,
|
| 1328 |
+
"eval_steps_per_second": 6.877,
|
| 1329 |
+
"step": 60000
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.5,
|
| 1333 |
+
"grad_norm": 19.36899185180664,
|
| 1334 |
+
"learning_rate": 1e-05,
|
| 1335 |
+
"loss": 3.2153,
|
| 1336 |
+
"step": 60500
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.5,
|
| 1340 |
+
"grad_norm": 95.15733337402344,
|
| 1341 |
+
"learning_rate": 9.917355371900828e-06,
|
| 1342 |
+
"loss": 3.0478,
|
| 1343 |
+
"step": 61000
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.5,
|
| 1347 |
+
"eval_loss": 2.5420753955841064,
|
| 1348 |
+
"eval_runtime": 138.826,
|
| 1349 |
+
"eval_samples_per_second": 6.93,
|
| 1350 |
+
"eval_steps_per_second": 6.93,
|
| 1351 |
+
"step": 61000
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 0.51,
|
| 1355 |
+
"grad_norm": 164.1331329345703,
|
| 1356 |
+
"learning_rate": 9.834710743801654e-06,
|
| 1357 |
+
"loss": 3.0467,
|
| 1358 |
+
"step": 61500
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 0.51,
|
| 1362 |
+
"grad_norm": 120.298828125,
|
| 1363 |
+
"learning_rate": 9.75206611570248e-06,
|
| 1364 |
+
"loss": 3.0664,
|
| 1365 |
+
"step": 62000
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 0.51,
|
| 1369 |
+
"eval_loss": 2.561354875564575,
|
| 1370 |
+
"eval_runtime": 138.2294,
|
| 1371 |
+
"eval_samples_per_second": 6.959,
|
| 1372 |
+
"eval_steps_per_second": 6.959,
|
| 1373 |
+
"step": 62000
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 0.52,
|
| 1377 |
+
"grad_norm": 67.15013122558594,
|
| 1378 |
+
"learning_rate": 9.669421487603307e-06,
|
| 1379 |
+
"loss": 3.0473,
|
| 1380 |
+
"step": 62500
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 0.52,
|
| 1384 |
+
"grad_norm": 116.40657043457031,
|
| 1385 |
+
"learning_rate": 9.586776859504134e-06,
|
| 1386 |
+
"loss": 2.8695,
|
| 1387 |
+
"step": 63000
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 0.52,
|
| 1391 |
+
"eval_loss": 2.559004783630371,
|
| 1392 |
+
"eval_runtime": 139.5498,
|
| 1393 |
+
"eval_samples_per_second": 6.894,
|
| 1394 |
+
"eval_steps_per_second": 6.894,
|
| 1395 |
+
"step": 63000
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.52,
|
| 1399 |
+
"grad_norm": 16.178442001342773,
|
| 1400 |
+
"learning_rate": 9.50413223140496e-06,
|
| 1401 |
+
"loss": 3.1084,
|
| 1402 |
+
"step": 63500
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.53,
|
| 1406 |
+
"grad_norm": 9.640996932983398,
|
| 1407 |
+
"learning_rate": 9.421487603305785e-06,
|
| 1408 |
+
"loss": 3.0757,
|
| 1409 |
+
"step": 64000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.53,
|
| 1413 |
+
"eval_loss": 2.553495407104492,
|
| 1414 |
+
"eval_runtime": 140.0088,
|
| 1415 |
+
"eval_samples_per_second": 6.871,
|
| 1416 |
+
"eval_steps_per_second": 6.871,
|
| 1417 |
+
"step": 64000
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.53,
|
| 1421 |
+
"grad_norm": 5.591582775115967,
|
| 1422 |
+
"learning_rate": 9.338842975206613e-06,
|
| 1423 |
+
"loss": 2.9386,
|
| 1424 |
+
"step": 64500
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.54,
|
| 1428 |
+
"grad_norm": 62.728607177734375,
|
| 1429 |
+
"learning_rate": 9.25619834710744e-06,
|
| 1430 |
+
"loss": 2.9709,
|
| 1431 |
+
"step": 65000
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.54,
|
| 1435 |
+
"eval_loss": 2.530237913131714,
|
| 1436 |
+
"eval_runtime": 139.6525,
|
| 1437 |
+
"eval_samples_per_second": 6.889,
|
| 1438 |
+
"eval_steps_per_second": 6.889,
|
| 1439 |
+
"step": 65000
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 0.54,
|
| 1443 |
+
"grad_norm": 27.372655868530273,
|
| 1444 |
+
"learning_rate": 9.173553719008265e-06,
|
| 1445 |
+
"loss": 2.976,
|
| 1446 |
+
"step": 65500
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 0.55,
|
| 1450 |
+
"grad_norm": 89.07634735107422,
|
| 1451 |
+
"learning_rate": 9.090909090909091e-06,
|
| 1452 |
+
"loss": 2.8215,
|
| 1453 |
+
"step": 66000
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 0.55,
|
| 1457 |
+
"eval_loss": 2.565800905227661,
|
| 1458 |
+
"eval_runtime": 140.4523,
|
| 1459 |
+
"eval_samples_per_second": 6.849,
|
| 1460 |
+
"eval_steps_per_second": 6.849,
|
| 1461 |
+
"step": 66000
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 0.55,
|
| 1465 |
+
"grad_norm": 20.640071868896484,
|
| 1466 |
+
"learning_rate": 9.008264462809918e-06,
|
| 1467 |
+
"loss": 3.0081,
|
| 1468 |
+
"step": 66500
|
| 1469 |
+
},
|
| 1470 |
+
{
|
| 1471 |
+
"epoch": 0.55,
|
| 1472 |
+
"grad_norm": 69.5301284790039,
|
| 1473 |
+
"learning_rate": 8.925619834710744e-06,
|
| 1474 |
+
"loss": 3.077,
|
| 1475 |
+
"step": 67000
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 0.55,
|
| 1479 |
+
"eval_loss": 2.5604488849639893,
|
| 1480 |
+
"eval_runtime": 140.6864,
|
| 1481 |
+
"eval_samples_per_second": 6.838,
|
| 1482 |
+
"eval_steps_per_second": 6.838,
|
| 1483 |
+
"step": 67000
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 0.56,
|
| 1487 |
+
"grad_norm": 46.04232406616211,
|
| 1488 |
+
"learning_rate": 8.842975206611571e-06,
|
| 1489 |
+
"loss": 3.0368,
|
| 1490 |
+
"step": 67500
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 0.56,
|
| 1494 |
+
"grad_norm": 142.82720947265625,
|
| 1495 |
+
"learning_rate": 8.760330578512397e-06,
|
| 1496 |
+
"loss": 2.9914,
|
| 1497 |
+
"step": 68000
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 0.56,
|
| 1501 |
+
"eval_loss": 2.561345100402832,
|
| 1502 |
+
"eval_runtime": 139.7552,
|
| 1503 |
+
"eval_samples_per_second": 6.883,
|
| 1504 |
+
"eval_steps_per_second": 6.883,
|
| 1505 |
+
"step": 68000
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 0.57,
|
| 1509 |
+
"grad_norm": 12.521268844604492,
|
| 1510 |
+
"learning_rate": 8.677685950413224e-06,
|
| 1511 |
+
"loss": 2.8843,
|
| 1512 |
+
"step": 68500
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 0.57,
|
| 1516 |
+
"grad_norm": 2.718876600265503,
|
| 1517 |
+
"learning_rate": 8.59504132231405e-06,
|
| 1518 |
+
"loss": 2.8383,
|
| 1519 |
+
"step": 69000
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 0.57,
|
| 1523 |
+
"eval_loss": 2.55441951751709,
|
| 1524 |
+
"eval_runtime": 140.0164,
|
| 1525 |
+
"eval_samples_per_second": 6.871,
|
| 1526 |
+
"eval_steps_per_second": 6.871,
|
| 1527 |
+
"step": 69000
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 0.57,
|
| 1531 |
+
"grad_norm": 68.07179260253906,
|
| 1532 |
+
"learning_rate": 8.512396694214877e-06,
|
| 1533 |
+
"loss": 2.9206,
|
| 1534 |
+
"step": 69500
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 0.58,
|
| 1538 |
+
"grad_norm": 53.18625259399414,
|
| 1539 |
+
"learning_rate": 8.429752066115703e-06,
|
| 1540 |
+
"loss": 3.0139,
|
| 1541 |
+
"step": 70000
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 0.58,
|
| 1545 |
+
"eval_loss": 2.539428234100342,
|
| 1546 |
+
"eval_runtime": 141.3662,
|
| 1547 |
+
"eval_samples_per_second": 6.805,
|
| 1548 |
+
"eval_steps_per_second": 6.805,
|
| 1549 |
+
"step": 70000
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.58,
|
| 1553 |
+
"grad_norm": 38.117530822753906,
|
| 1554 |
+
"learning_rate": 8.34710743801653e-06,
|
| 1555 |
+
"loss": 2.9579,
|
| 1556 |
+
"step": 70500
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.59,
|
| 1560 |
+
"grad_norm": 11.0903902053833,
|
| 1561 |
+
"learning_rate": 8.264462809917356e-06,
|
| 1562 |
+
"loss": 2.9588,
|
| 1563 |
+
"step": 71000
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.59,
|
| 1567 |
+
"eval_loss": 2.5550858974456787,
|
| 1568 |
+
"eval_runtime": 140.3679,
|
| 1569 |
+
"eval_samples_per_second": 6.853,
|
| 1570 |
+
"eval_steps_per_second": 6.853,
|
| 1571 |
+
"step": 71000
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.59,
|
| 1575 |
+
"grad_norm": 136.44300842285156,
|
| 1576 |
+
"learning_rate": 8.181818181818183e-06,
|
| 1577 |
+
"loss": 2.9754,
|
| 1578 |
+
"step": 71500
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.6,
|
| 1582 |
+
"grad_norm": 118.072265625,
|
| 1583 |
+
"learning_rate": 8.099173553719009e-06,
|
| 1584 |
+
"loss": 3.1051,
|
| 1585 |
+
"step": 72000
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.6,
|
| 1589 |
+
"eval_loss": 2.5240180492401123,
|
| 1590 |
+
"eval_runtime": 140.2239,
|
| 1591 |
+
"eval_samples_per_second": 6.86,
|
| 1592 |
+
"eval_steps_per_second": 6.86,
|
| 1593 |
+
"step": 72000
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 0.6,
|
| 1597 |
+
"grad_norm": 124.3985824584961,
|
| 1598 |
+
"learning_rate": 8.016528925619836e-06,
|
| 1599 |
+
"loss": 2.9229,
|
| 1600 |
+
"step": 72500
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 0.6,
|
| 1604 |
+
"grad_norm": 39.26608657836914,
|
| 1605 |
+
"learning_rate": 7.933884297520661e-06,
|
| 1606 |
+
"loss": 2.9566,
|
| 1607 |
+
"step": 73000
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 0.6,
|
| 1611 |
+
"eval_loss": 2.5205495357513428,
|
| 1612 |
+
"eval_runtime": 140.8561,
|
| 1613 |
+
"eval_samples_per_second": 6.83,
|
| 1614 |
+
"eval_steps_per_second": 6.83,
|
| 1615 |
+
"step": 73000
|
| 1616 |
+
},
|
| 1617 |
+
{
|
| 1618 |
+
"epoch": 0.61,
|
| 1619 |
+
"grad_norm": 101.39036560058594,
|
| 1620 |
+
"learning_rate": 7.851239669421489e-06,
|
| 1621 |
+
"loss": 3.1112,
|
| 1622 |
+
"step": 73500
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 0.61,
|
| 1626 |
+
"grad_norm": 66.84815216064453,
|
| 1627 |
+
"learning_rate": 7.768595041322314e-06,
|
| 1628 |
+
"loss": 2.8258,
|
| 1629 |
+
"step": 74000
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 0.61,
|
| 1633 |
+
"eval_loss": 2.53057599067688,
|
| 1634 |
+
"eval_runtime": 138.4074,
|
| 1635 |
+
"eval_samples_per_second": 6.95,
|
| 1636 |
+
"eval_steps_per_second": 6.95,
|
| 1637 |
+
"step": 74000
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 0.62,
|
| 1641 |
+
"grad_norm": 27.408185958862305,
|
| 1642 |
+
"learning_rate": 7.685950413223142e-06,
|
| 1643 |
+
"loss": 3.0526,
|
| 1644 |
+
"step": 74500
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 0.62,
|
| 1648 |
+
"grad_norm": 51.945796966552734,
|
| 1649 |
+
"learning_rate": 7.603305785123968e-06,
|
| 1650 |
+
"loss": 3.1191,
|
| 1651 |
+
"step": 75000
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 0.62,
|
| 1655 |
+
"eval_loss": 2.5579235553741455,
|
| 1656 |
+
"eval_runtime": 140.5154,
|
| 1657 |
+
"eval_samples_per_second": 6.846,
|
| 1658 |
+
"eval_steps_per_second": 6.846,
|
| 1659 |
+
"step": 75000
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 0.62,
|
| 1663 |
+
"grad_norm": 54.32289123535156,
|
| 1664 |
+
"learning_rate": 7.520661157024795e-06,
|
| 1665 |
+
"loss": 2.6603,
|
| 1666 |
+
"step": 75500
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 0.63,
|
| 1670 |
+
"grad_norm": 68.38690185546875,
|
| 1671 |
+
"learning_rate": 7.43801652892562e-06,
|
| 1672 |
+
"loss": 2.9808,
|
| 1673 |
+
"step": 76000
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 0.63,
|
| 1677 |
+
"eval_loss": 2.4875569343566895,
|
| 1678 |
+
"eval_runtime": 139.4265,
|
| 1679 |
+
"eval_samples_per_second": 6.9,
|
| 1680 |
+
"eval_steps_per_second": 6.9,
|
| 1681 |
+
"step": 76000
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 0.63,
|
| 1685 |
+
"grad_norm": 13.368736267089844,
|
| 1686 |
+
"learning_rate": 7.355371900826447e-06,
|
| 1687 |
+
"loss": 2.9716,
|
| 1688 |
+
"step": 76500
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 0.64,
|
| 1692 |
+
"grad_norm": 223.064208984375,
|
| 1693 |
+
"learning_rate": 7.272727272727273e-06,
|
| 1694 |
+
"loss": 2.866,
|
| 1695 |
+
"step": 77000
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 0.64,
|
| 1699 |
+
"eval_loss": 2.4790120124816895,
|
| 1700 |
+
"eval_runtime": 138.7203,
|
| 1701 |
+
"eval_samples_per_second": 6.935,
|
| 1702 |
+
"eval_steps_per_second": 6.935,
|
| 1703 |
+
"step": 77000
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.64,
|
| 1707 |
+
"grad_norm": 45.701168060302734,
|
| 1708 |
+
"learning_rate": 7.1900826446281005e-06,
|
| 1709 |
+
"loss": 2.8411,
|
| 1710 |
+
"step": 77500
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.64,
|
| 1714 |
+
"grad_norm": 45.346946716308594,
|
| 1715 |
+
"learning_rate": 7.107438016528926e-06,
|
| 1716 |
+
"loss": 3.0315,
|
| 1717 |
+
"step": 78000
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.64,
|
| 1721 |
+
"eval_loss": 2.4591948986053467,
|
| 1722 |
+
"eval_runtime": 136.0903,
|
| 1723 |
+
"eval_samples_per_second": 7.069,
|
| 1724 |
+
"eval_steps_per_second": 7.069,
|
| 1725 |
+
"step": 78000
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.65,
|
| 1729 |
+
"grad_norm": 110.85874938964844,
|
| 1730 |
+
"learning_rate": 7.0247933884297525e-06,
|
| 1731 |
+
"loss": 2.9017,
|
| 1732 |
+
"step": 78500
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.65,
|
| 1736 |
+
"grad_norm": 38.339019775390625,
|
| 1737 |
+
"learning_rate": 6.942148760330579e-06,
|
| 1738 |
+
"loss": 2.9615,
|
| 1739 |
+
"step": 79000
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.65,
|
| 1743 |
+
"eval_loss": 2.519632339477539,
|
| 1744 |
+
"eval_runtime": 136.2766,
|
| 1745 |
+
"eval_samples_per_second": 7.059,
|
| 1746 |
+
"eval_steps_per_second": 7.059,
|
| 1747 |
+
"step": 79000
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 0.66,
|
| 1751 |
+
"grad_norm": 136.72471618652344,
|
| 1752 |
+
"learning_rate": 6.859504132231406e-06,
|
| 1753 |
+
"loss": 2.7923,
|
| 1754 |
+
"step": 79500
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 0.66,
|
| 1758 |
+
"grad_norm": 177.0449676513672,
|
| 1759 |
+
"learning_rate": 6.776859504132232e-06,
|
| 1760 |
+
"loss": 2.894,
|
| 1761 |
+
"step": 80000
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 0.66,
|
| 1765 |
+
"eval_loss": 2.4873228073120117,
|
| 1766 |
+
"eval_runtime": 140.1936,
|
| 1767 |
+
"eval_samples_per_second": 6.862,
|
| 1768 |
+
"eval_steps_per_second": 6.862,
|
| 1769 |
+
"step": 80000
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 0.67,
|
| 1773 |
+
"grad_norm": 52.91669464111328,
|
| 1774 |
+
"learning_rate": 6.694214876033058e-06,
|
| 1775 |
+
"loss": 2.9347,
|
| 1776 |
+
"step": 80500
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 0.67,
|
| 1780 |
+
"grad_norm": 29.3709716796875,
|
| 1781 |
+
"learning_rate": 6.611570247933885e-06,
|
| 1782 |
+
"loss": 3.0159,
|
| 1783 |
+
"step": 81000
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 0.67,
|
| 1787 |
+
"eval_loss": 2.5049378871917725,
|
| 1788 |
+
"eval_runtime": 136.3273,
|
| 1789 |
+
"eval_samples_per_second": 7.057,
|
| 1790 |
+
"eval_steps_per_second": 7.057,
|
| 1791 |
+
"step": 81000
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 0.67,
|
| 1795 |
+
"grad_norm": 39.67999267578125,
|
| 1796 |
+
"learning_rate": 6.528925619834712e-06,
|
| 1797 |
+
"loss": 2.7904,
|
| 1798 |
+
"step": 81500
|
| 1799 |
+
},
|
| 1800 |
+
{
|
| 1801 |
+
"epoch": 0.68,
|
| 1802 |
+
"grad_norm": 67.77261352539062,
|
| 1803 |
+
"learning_rate": 6.446280991735537e-06,
|
| 1804 |
+
"loss": 2.8427,
|
| 1805 |
+
"step": 82000
|
| 1806 |
+
},
|
| 1807 |
+
{
|
| 1808 |
+
"epoch": 0.68,
|
| 1809 |
+
"eval_loss": 2.483983039855957,
|
| 1810 |
+
"eval_runtime": 140.506,
|
| 1811 |
+
"eval_samples_per_second": 6.847,
|
| 1812 |
+
"eval_steps_per_second": 6.847,
|
| 1813 |
+
"step": 82000
|
| 1814 |
+
},
|
| 1815 |
+
{
|
| 1816 |
+
"epoch": 0.68,
|
| 1817 |
+
"grad_norm": 31.837095260620117,
|
| 1818 |
+
"learning_rate": 6.363636363636364e-06,
|
| 1819 |
+
"loss": 2.9611,
|
| 1820 |
+
"step": 82500
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 0.69,
|
| 1824 |
+
"grad_norm": 90.8124008178711,
|
| 1825 |
+
"learning_rate": 6.280991735537191e-06,
|
| 1826 |
+
"loss": 3.0876,
|
| 1827 |
+
"step": 83000
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 0.69,
|
| 1831 |
+
"eval_loss": 2.4686708450317383,
|
| 1832 |
+
"eval_runtime": 140.2415,
|
| 1833 |
+
"eval_samples_per_second": 6.86,
|
| 1834 |
+
"eval_steps_per_second": 6.86,
|
| 1835 |
+
"step": 83000
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 0.69,
|
| 1839 |
+
"grad_norm": 203.96783447265625,
|
| 1840 |
+
"learning_rate": 6.198347107438017e-06,
|
| 1841 |
+
"loss": 2.8774,
|
| 1842 |
+
"step": 83500
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 0.69,
|
| 1846 |
+
"grad_norm": 68.90469360351562,
|
| 1847 |
+
"learning_rate": 6.115702479338843e-06,
|
| 1848 |
+
"loss": 2.9447,
|
| 1849 |
+
"step": 84000
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 0.69,
|
| 1853 |
+
"eval_loss": 2.4458138942718506,
|
| 1854 |
+
"eval_runtime": 140.8702,
|
| 1855 |
+
"eval_samples_per_second": 6.829,
|
| 1856 |
+
"eval_steps_per_second": 6.829,
|
| 1857 |
+
"step": 84000
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.7,
|
| 1861 |
+
"grad_norm": 96.91522979736328,
|
| 1862 |
+
"learning_rate": 6.03305785123967e-06,
|
| 1863 |
+
"loss": 3.1052,
|
| 1864 |
+
"step": 84500
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.7,
|
| 1868 |
+
"grad_norm": 54.14280319213867,
|
| 1869 |
+
"learning_rate": 5.9504132231404965e-06,
|
| 1870 |
+
"loss": 3.133,
|
| 1871 |
+
"step": 85000
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.7,
|
| 1875 |
+
"eval_loss": 2.498807668685913,
|
| 1876 |
+
"eval_runtime": 140.2236,
|
| 1877 |
+
"eval_samples_per_second": 6.86,
|
| 1878 |
+
"eval_steps_per_second": 6.86,
|
| 1879 |
+
"step": 85000
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.71,
|
| 1883 |
+
"grad_norm": 32.362709045410156,
|
| 1884 |
+
"learning_rate": 5.867768595041323e-06,
|
| 1885 |
+
"loss": 3.0148,
|
| 1886 |
+
"step": 85500
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.71,
|
| 1890 |
+
"grad_norm": 89.885009765625,
|
| 1891 |
+
"learning_rate": 5.785123966942149e-06,
|
| 1892 |
+
"loss": 2.8195,
|
| 1893 |
+
"step": 86000
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.71,
|
| 1897 |
+
"eval_loss": 2.465299606323242,
|
| 1898 |
+
"eval_runtime": 138.3234,
|
| 1899 |
+
"eval_samples_per_second": 6.955,
|
| 1900 |
+
"eval_steps_per_second": 6.955,
|
| 1901 |
+
"step": 86000
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 0.71,
|
| 1905 |
+
"grad_norm": 0.9571592211723328,
|
| 1906 |
+
"learning_rate": 5.702479338842976e-06,
|
| 1907 |
+
"loss": 2.896,
|
| 1908 |
+
"step": 86500
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 0.72,
|
| 1912 |
+
"grad_norm": 76.42816162109375,
|
| 1913 |
+
"learning_rate": 5.619834710743802e-06,
|
| 1914 |
+
"loss": 3.0033,
|
| 1915 |
+
"step": 87000
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 0.72,
|
| 1919 |
+
"eval_loss": 2.4510247707366943,
|
| 1920 |
+
"eval_runtime": 137.4476,
|
| 1921 |
+
"eval_samples_per_second": 6.999,
|
| 1922 |
+
"eval_steps_per_second": 6.999,
|
| 1923 |
+
"step": 87000
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 0.72,
|
| 1927 |
+
"grad_norm": 31.637996673583984,
|
| 1928 |
+
"learning_rate": 5.537190082644629e-06,
|
| 1929 |
+
"loss": 3.0171,
|
| 1930 |
+
"step": 87500
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"epoch": 0.73,
|
| 1934 |
+
"grad_norm": 276.10009765625,
|
| 1935 |
+
"learning_rate": 5.4545454545454545e-06,
|
| 1936 |
+
"loss": 2.7309,
|
| 1937 |
+
"step": 88000
|
| 1938 |
+
},
|
| 1939 |
+
{
|
| 1940 |
+
"epoch": 0.73,
|
| 1941 |
+
"eval_loss": 2.4777259826660156,
|
| 1942 |
+
"eval_runtime": 138.3526,
|
| 1943 |
+
"eval_samples_per_second": 6.953,
|
| 1944 |
+
"eval_steps_per_second": 6.953,
|
| 1945 |
+
"step": 88000
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 0.73,
|
| 1949 |
+
"grad_norm": 64.81793212890625,
|
| 1950 |
+
"learning_rate": 5.371900826446281e-06,
|
| 1951 |
+
"loss": 3.035,
|
| 1952 |
+
"step": 88500
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 0.74,
|
| 1956 |
+
"grad_norm": 74.73489379882812,
|
| 1957 |
+
"learning_rate": 5.289256198347108e-06,
|
| 1958 |
+
"loss": 2.778,
|
| 1959 |
+
"step": 89000
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 0.74,
|
| 1963 |
+
"eval_loss": 2.4714279174804688,
|
| 1964 |
+
"eval_runtime": 135.884,
|
| 1965 |
+
"eval_samples_per_second": 7.08,
|
| 1966 |
+
"eval_steps_per_second": 7.08,
|
| 1967 |
+
"step": 89000
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 0.74,
|
| 1971 |
+
"grad_norm": 423.29888916015625,
|
| 1972 |
+
"learning_rate": 5.206611570247935e-06,
|
| 1973 |
+
"loss": 3.1729,
|
| 1974 |
+
"step": 89500
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 0.74,
|
| 1978 |
+
"grad_norm": 68.26463317871094,
|
| 1979 |
+
"learning_rate": 5.12396694214876e-06,
|
| 1980 |
+
"loss": 2.6937,
|
| 1981 |
+
"step": 90000
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 0.74,
|
| 1985 |
+
"eval_loss": 2.511780023574829,
|
| 1986 |
+
"eval_runtime": 139.7573,
|
| 1987 |
+
"eval_samples_per_second": 6.883,
|
| 1988 |
+
"eval_steps_per_second": 6.883,
|
| 1989 |
+
"step": 90000
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 0.75,
|
| 1993 |
+
"grad_norm": 63.75825500488281,
|
| 1994 |
+
"learning_rate": 5.041322314049587e-06,
|
| 1995 |
+
"loss": 2.8172,
|
| 1996 |
+
"step": 90500
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 0.75,
|
| 2000 |
+
"grad_norm": 95.2588882446289,
|
| 2001 |
+
"learning_rate": 4.958677685950414e-06,
|
| 2002 |
+
"loss": 2.6397,
|
| 2003 |
+
"step": 91000
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 0.75,
|
| 2007 |
+
"eval_loss": 2.4570491313934326,
|
| 2008 |
+
"eval_runtime": 139.6678,
|
| 2009 |
+
"eval_samples_per_second": 6.888,
|
| 2010 |
+
"eval_steps_per_second": 6.888,
|
| 2011 |
+
"step": 91000
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.76,
|
| 2015 |
+
"grad_norm": 146.0210418701172,
|
| 2016 |
+
"learning_rate": 4.87603305785124e-06,
|
| 2017 |
+
"loss": 2.7785,
|
| 2018 |
+
"step": 91500
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.76,
|
| 2022 |
+
"grad_norm": 4.548470973968506,
|
| 2023 |
+
"learning_rate": 4.793388429752067e-06,
|
| 2024 |
+
"loss": 2.8252,
|
| 2025 |
+
"step": 92000
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.76,
|
| 2029 |
+
"eval_loss": 2.455515146255493,
|
| 2030 |
+
"eval_runtime": 140.0032,
|
| 2031 |
+
"eval_samples_per_second": 6.871,
|
| 2032 |
+
"eval_steps_per_second": 6.871,
|
| 2033 |
+
"step": 92000
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 0.76,
|
| 2037 |
+
"grad_norm": 1.6395989656448364,
|
| 2038 |
+
"learning_rate": 4.710743801652893e-06,
|
| 2039 |
+
"loss": 2.8768,
|
| 2040 |
+
"step": 92500
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 0.77,
|
| 2044 |
+
"grad_norm": 127.5672607421875,
|
| 2045 |
+
"learning_rate": 4.62809917355372e-06,
|
| 2046 |
+
"loss": 2.8688,
|
| 2047 |
+
"step": 93000
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 0.77,
|
| 2051 |
+
"eval_loss": 2.456037998199463,
|
| 2052 |
+
"eval_runtime": 140.078,
|
| 2053 |
+
"eval_samples_per_second": 6.868,
|
| 2054 |
+
"eval_steps_per_second": 6.868,
|
| 2055 |
+
"step": 93000
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 0.77,
|
| 2059 |
+
"grad_norm": 76.23936462402344,
|
| 2060 |
+
"learning_rate": 4.5454545454545455e-06,
|
| 2061 |
+
"loss": 2.8035,
|
| 2062 |
+
"step": 93500
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 0.78,
|
| 2066 |
+
"grad_norm": 1.9954880475997925,
|
| 2067 |
+
"learning_rate": 4.462809917355372e-06,
|
| 2068 |
+
"loss": 2.8295,
|
| 2069 |
+
"step": 94000
|
| 2070 |
+
},
|
| 2071 |
+
{
|
| 2072 |
+
"epoch": 0.78,
|
| 2073 |
+
"eval_loss": 2.470505714416504,
|
| 2074 |
+
"eval_runtime": 140.8327,
|
| 2075 |
+
"eval_samples_per_second": 6.831,
|
| 2076 |
+
"eval_steps_per_second": 6.831,
|
| 2077 |
+
"step": 94000
|
| 2078 |
+
},
|
| 2079 |
+
{
|
| 2080 |
+
"epoch": 0.78,
|
| 2081 |
+
"grad_norm": 121.44882202148438,
|
| 2082 |
+
"learning_rate": 4.3801652892561984e-06,
|
| 2083 |
+
"loss": 2.7538,
|
| 2084 |
+
"step": 94500
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 0.79,
|
| 2088 |
+
"grad_norm": 222.09165954589844,
|
| 2089 |
+
"learning_rate": 4.297520661157025e-06,
|
| 2090 |
+
"loss": 2.885,
|
| 2091 |
+
"step": 95000
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"epoch": 0.79,
|
| 2095 |
+
"eval_loss": 2.462240695953369,
|
| 2096 |
+
"eval_runtime": 140.1637,
|
| 2097 |
+
"eval_samples_per_second": 6.863,
|
| 2098 |
+
"eval_steps_per_second": 6.863,
|
| 2099 |
+
"step": 95000
|
| 2100 |
+
},
|
| 2101 |
+
{
|
| 2102 |
+
"epoch": 0.79,
|
| 2103 |
+
"grad_norm": 54.475791931152344,
|
| 2104 |
+
"learning_rate": 4.214876033057851e-06,
|
| 2105 |
+
"loss": 2.9929,
|
| 2106 |
+
"step": 95500
|
| 2107 |
+
},
|
| 2108 |
+
{
|
| 2109 |
+
"epoch": 0.79,
|
| 2110 |
+
"grad_norm": 132.60020446777344,
|
| 2111 |
+
"learning_rate": 4.132231404958678e-06,
|
| 2112 |
+
"loss": 2.9288,
|
| 2113 |
+
"step": 96000
|
| 2114 |
+
},
|
| 2115 |
+
{
|
| 2116 |
+
"epoch": 0.79,
|
| 2117 |
+
"eval_loss": 2.461066484451294,
|
| 2118 |
+
"eval_runtime": 137.924,
|
| 2119 |
+
"eval_samples_per_second": 6.975,
|
| 2120 |
+
"eval_steps_per_second": 6.975,
|
| 2121 |
+
"step": 96000
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 0.8,
|
| 2125 |
+
"grad_norm": 43.78097915649414,
|
| 2126 |
+
"learning_rate": 4.049586776859504e-06,
|
| 2127 |
+
"loss": 2.8568,
|
| 2128 |
+
"step": 96500
|
| 2129 |
+
},
|
| 2130 |
+
{
|
| 2131 |
+
"epoch": 0.8,
|
| 2132 |
+
"grad_norm": 29.313560485839844,
|
| 2133 |
+
"learning_rate": 3.966942148760331e-06,
|
| 2134 |
+
"loss": 2.8473,
|
| 2135 |
+
"step": 97000
|
| 2136 |
+
},
|
| 2137 |
+
{
|
| 2138 |
+
"epoch": 0.8,
|
| 2139 |
+
"eval_loss": 2.4508566856384277,
|
| 2140 |
+
"eval_runtime": 139.8571,
|
| 2141 |
+
"eval_samples_per_second": 6.878,
|
| 2142 |
+
"eval_steps_per_second": 6.878,
|
| 2143 |
+
"step": 97000
|
| 2144 |
+
},
|
| 2145 |
+
{
|
| 2146 |
+
"epoch": 0.81,
|
| 2147 |
+
"grad_norm": 32.94176483154297,
|
| 2148 |
+
"learning_rate": 3.884297520661157e-06,
|
| 2149 |
+
"loss": 3.0909,
|
| 2150 |
+
"step": 97500
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 0.81,
|
| 2154 |
+
"grad_norm": 26.41152000427246,
|
| 2155 |
+
"learning_rate": 3.801652892561984e-06,
|
| 2156 |
+
"loss": 2.8863,
|
| 2157 |
+
"step": 98000
|
| 2158 |
+
},
|
| 2159 |
+
{
|
| 2160 |
+
"epoch": 0.81,
|
| 2161 |
+
"eval_loss": 2.4427459239959717,
|
| 2162 |
+
"eval_runtime": 139.5787,
|
| 2163 |
+
"eval_samples_per_second": 6.892,
|
| 2164 |
+
"eval_steps_per_second": 6.892,
|
| 2165 |
+
"step": 98000
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.81,
|
| 2169 |
+
"grad_norm": 75.68090057373047,
|
| 2170 |
+
"learning_rate": 3.71900826446281e-06,
|
| 2171 |
+
"loss": 2.8636,
|
| 2172 |
+
"step": 98500
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.82,
|
| 2176 |
+
"grad_norm": 30.334091186523438,
|
| 2177 |
+
"learning_rate": 3.6363636363636366e-06,
|
| 2178 |
+
"loss": 2.7238,
|
| 2179 |
+
"step": 99000
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.82,
|
| 2183 |
+
"eval_loss": 2.4287164211273193,
|
| 2184 |
+
"eval_runtime": 140.5273,
|
| 2185 |
+
"eval_samples_per_second": 6.846,
|
| 2186 |
+
"eval_steps_per_second": 6.846,
|
| 2187 |
+
"step": 99000
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 0.82,
|
| 2191 |
+
"grad_norm": 191.05506896972656,
|
| 2192 |
+
"learning_rate": 3.553719008264463e-06,
|
| 2193 |
+
"loss": 3.0945,
|
| 2194 |
+
"step": 99500
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 0.83,
|
| 2198 |
+
"grad_norm": 30.880615234375,
|
| 2199 |
+
"learning_rate": 3.4710743801652895e-06,
|
| 2200 |
+
"loss": 2.842,
|
| 2201 |
+
"step": 100000
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 0.83,
|
| 2205 |
+
"eval_loss": 2.418543815612793,
|
| 2206 |
+
"eval_runtime": 137.122,
|
| 2207 |
+
"eval_samples_per_second": 7.016,
|
| 2208 |
+
"eval_steps_per_second": 7.016,
|
| 2209 |
+
"step": 100000
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 0.83,
|
| 2213 |
+
"grad_norm": 169.966796875,
|
| 2214 |
+
"learning_rate": 3.388429752066116e-06,
|
| 2215 |
+
"loss": 2.6592,
|
| 2216 |
+
"step": 100500
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 0.83,
|
| 2220 |
+
"grad_norm": 31.075923919677734,
|
| 2221 |
+
"learning_rate": 3.3057851239669424e-06,
|
| 2222 |
+
"loss": 2.947,
|
| 2223 |
+
"step": 101000
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 0.83,
|
| 2227 |
+
"eval_loss": 2.415428400039673,
|
| 2228 |
+
"eval_runtime": 137.232,
|
| 2229 |
+
"eval_samples_per_second": 7.01,
|
| 2230 |
+
"eval_steps_per_second": 7.01,
|
| 2231 |
+
"step": 101000
|
| 2232 |
+
},
|
| 2233 |
+
{
|
| 2234 |
+
"epoch": 0.84,
|
| 2235 |
+
"grad_norm": 2.725558280944824,
|
| 2236 |
+
"learning_rate": 3.2231404958677685e-06,
|
| 2237 |
+
"loss": 2.7334,
|
| 2238 |
+
"step": 101500
|
| 2239 |
+
},
|
| 2240 |
+
{
|
| 2241 |
+
"epoch": 0.84,
|
| 2242 |
+
"grad_norm": 96.62724304199219,
|
| 2243 |
+
"learning_rate": 3.1404958677685953e-06,
|
| 2244 |
+
"loss": 2.9315,
|
| 2245 |
+
"step": 102000
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 0.84,
|
| 2249 |
+
"eval_loss": 2.4265284538269043,
|
| 2250 |
+
"eval_runtime": 139.3641,
|
| 2251 |
+
"eval_samples_per_second": 6.903,
|
| 2252 |
+
"eval_steps_per_second": 6.903,
|
| 2253 |
+
"step": 102000
|
| 2254 |
+
},
|
| 2255 |
+
{
|
| 2256 |
+
"epoch": 0.85,
|
| 2257 |
+
"grad_norm": 245.8263702392578,
|
| 2258 |
+
"learning_rate": 3.0578512396694214e-06,
|
| 2259 |
+
"loss": 2.7418,
|
| 2260 |
+
"step": 102500
|
| 2261 |
+
},
|
| 2262 |
+
{
|
| 2263 |
+
"epoch": 0.85,
|
| 2264 |
+
"grad_norm": 166.16859436035156,
|
| 2265 |
+
"learning_rate": 2.9752066115702483e-06,
|
| 2266 |
+
"loss": 2.8382,
|
| 2267 |
+
"step": 103000
|
| 2268 |
+
},
|
| 2269 |
+
{
|
| 2270 |
+
"epoch": 0.85,
|
| 2271 |
+
"eval_loss": 2.4436089992523193,
|
| 2272 |
+
"eval_runtime": 138.7814,
|
| 2273 |
+
"eval_samples_per_second": 6.932,
|
| 2274 |
+
"eval_steps_per_second": 6.932,
|
| 2275 |
+
"step": 103000
|
| 2276 |
+
},
|
| 2277 |
+
{
|
| 2278 |
+
"epoch": 0.86,
|
| 2279 |
+
"grad_norm": 155.92645263671875,
|
| 2280 |
+
"learning_rate": 2.8925619834710743e-06,
|
| 2281 |
+
"loss": 2.8438,
|
| 2282 |
+
"step": 103500
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"epoch": 0.86,
|
| 2286 |
+
"grad_norm": 229.83657836914062,
|
| 2287 |
+
"learning_rate": 2.809917355371901e-06,
|
| 2288 |
+
"loss": 2.8605,
|
| 2289 |
+
"step": 104000
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 0.86,
|
| 2293 |
+
"eval_loss": 2.4522359371185303,
|
| 2294 |
+
"eval_runtime": 140.2918,
|
| 2295 |
+
"eval_samples_per_second": 6.857,
|
| 2296 |
+
"eval_steps_per_second": 6.857,
|
| 2297 |
+
"step": 104000
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 0.86,
|
| 2301 |
+
"grad_norm": 114.02568817138672,
|
| 2302 |
+
"learning_rate": 2.7272727272727272e-06,
|
| 2303 |
+
"loss": 2.7917,
|
| 2304 |
+
"step": 104500
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 0.87,
|
| 2308 |
+
"grad_norm": 0.14724546670913696,
|
| 2309 |
+
"learning_rate": 2.644628099173554e-06,
|
| 2310 |
+
"loss": 2.8771,
|
| 2311 |
+
"step": 105000
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"epoch": 0.87,
|
| 2315 |
+
"eval_loss": 2.4402596950531006,
|
| 2316 |
+
"eval_runtime": 137.5715,
|
| 2317 |
+
"eval_samples_per_second": 6.993,
|
| 2318 |
+
"eval_steps_per_second": 6.993,
|
| 2319 |
+
"step": 105000
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.87,
|
| 2323 |
+
"grad_norm": 62.19240188598633,
|
| 2324 |
+
"learning_rate": 2.56198347107438e-06,
|
| 2325 |
+
"loss": 2.8352,
|
| 2326 |
+
"step": 105500
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.88,
|
| 2330 |
+
"grad_norm": 285.7218017578125,
|
| 2331 |
+
"learning_rate": 2.479338842975207e-06,
|
| 2332 |
+
"loss": 2.9687,
|
| 2333 |
+
"step": 106000
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.88,
|
| 2337 |
+
"eval_loss": 2.443941116333008,
|
| 2338 |
+
"eval_runtime": 138.5628,
|
| 2339 |
+
"eval_samples_per_second": 6.943,
|
| 2340 |
+
"eval_steps_per_second": 6.943,
|
| 2341 |
+
"step": 106000
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 0.88,
|
| 2345 |
+
"grad_norm": 7.110346794128418,
|
| 2346 |
+
"learning_rate": 2.3966942148760335e-06,
|
| 2347 |
+
"loss": 2.7594,
|
| 2348 |
+
"step": 106500
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 0.88,
|
| 2352 |
+
"grad_norm": 55.28038787841797,
|
| 2353 |
+
"learning_rate": 2.31404958677686e-06,
|
| 2354 |
+
"loss": 2.8578,
|
| 2355 |
+
"step": 107000
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 0.88,
|
| 2359 |
+
"eval_loss": 2.435091257095337,
|
| 2360 |
+
"eval_runtime": 141.2615,
|
| 2361 |
+
"eval_samples_per_second": 6.81,
|
| 2362 |
+
"eval_steps_per_second": 6.81,
|
| 2363 |
+
"step": 107000
|
| 2364 |
+
},
|
| 2365 |
+
{
|
| 2366 |
+
"epoch": 0.89,
|
| 2367 |
+
"grad_norm": 89.96186828613281,
|
| 2368 |
+
"learning_rate": 2.231404958677686e-06,
|
| 2369 |
+
"loss": 2.6923,
|
| 2370 |
+
"step": 107500
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"epoch": 0.89,
|
| 2374 |
+
"grad_norm": 65.65628051757812,
|
| 2375 |
+
"learning_rate": 2.1487603305785124e-06,
|
| 2376 |
+
"loss": 2.8386,
|
| 2377 |
+
"step": 108000
|
| 2378 |
+
},
|
| 2379 |
+
{
|
| 2380 |
+
"epoch": 0.89,
|
| 2381 |
+
"eval_loss": 2.4371442794799805,
|
| 2382 |
+
"eval_runtime": 138.8387,
|
| 2383 |
+
"eval_samples_per_second": 6.929,
|
| 2384 |
+
"eval_steps_per_second": 6.929,
|
| 2385 |
+
"step": 108000
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 0.9,
|
| 2389 |
+
"grad_norm": 235.8939971923828,
|
| 2390 |
+
"learning_rate": 2.066115702479339e-06,
|
| 2391 |
+
"loss": 2.8686,
|
| 2392 |
+
"step": 108500
|
| 2393 |
+
},
|
| 2394 |
+
{
|
| 2395 |
+
"epoch": 0.9,
|
| 2396 |
+
"grad_norm": 66.96907806396484,
|
| 2397 |
+
"learning_rate": 1.9834710743801654e-06,
|
| 2398 |
+
"loss": 2.9078,
|
| 2399 |
+
"step": 109000
|
| 2400 |
+
},
|
| 2401 |
+
{
|
| 2402 |
+
"epoch": 0.9,
|
| 2403 |
+
"eval_loss": 2.4459149837493896,
|
| 2404 |
+
"eval_runtime": 140.0398,
|
| 2405 |
+
"eval_samples_per_second": 6.869,
|
| 2406 |
+
"eval_steps_per_second": 6.869,
|
| 2407 |
+
"step": 109000
|
| 2408 |
+
},
|
| 2409 |
+
{
|
| 2410 |
+
"epoch": 0.9,
|
| 2411 |
+
"grad_norm": 204.19281005859375,
|
| 2412 |
+
"learning_rate": 1.900826446280992e-06,
|
| 2413 |
+
"loss": 2.8531,
|
| 2414 |
+
"step": 109500
|
| 2415 |
+
},
|
| 2416 |
+
{
|
| 2417 |
+
"epoch": 0.91,
|
| 2418 |
+
"grad_norm": 121.73772430419922,
|
| 2419 |
+
"learning_rate": 1.8181818181818183e-06,
|
| 2420 |
+
"loss": 2.9152,
|
| 2421 |
+
"step": 110000
|
| 2422 |
+
},
|
| 2423 |
+
{
|
| 2424 |
+
"epoch": 0.91,
|
| 2425 |
+
"eval_loss": 2.436737060546875,
|
| 2426 |
+
"eval_runtime": 140.5818,
|
| 2427 |
+
"eval_samples_per_second": 6.843,
|
| 2428 |
+
"eval_steps_per_second": 6.843,
|
| 2429 |
+
"step": 110000
|
| 2430 |
+
},
|
| 2431 |
+
{
|
| 2432 |
+
"epoch": 0.91,
|
| 2433 |
+
"grad_norm": 555.6137084960938,
|
| 2434 |
+
"learning_rate": 1.7355371900826448e-06,
|
| 2435 |
+
"loss": 2.8121,
|
| 2436 |
+
"step": 110500
|
| 2437 |
+
},
|
| 2438 |
+
{
|
| 2439 |
+
"epoch": 0.92,
|
| 2440 |
+
"grad_norm": 75.70996856689453,
|
| 2441 |
+
"learning_rate": 1.6528925619834712e-06,
|
| 2442 |
+
"loss": 2.8674,
|
| 2443 |
+
"step": 111000
|
| 2444 |
+
},
|
| 2445 |
+
{
|
| 2446 |
+
"epoch": 0.92,
|
| 2447 |
+
"eval_loss": 2.4294447898864746,
|
| 2448 |
+
"eval_runtime": 140.7437,
|
| 2449 |
+
"eval_samples_per_second": 6.835,
|
| 2450 |
+
"eval_steps_per_second": 6.835,
|
| 2451 |
+
"step": 111000
|
| 2452 |
+
},
|
| 2453 |
+
{
|
| 2454 |
+
"epoch": 0.92,
|
| 2455 |
+
"grad_norm": 64.46011352539062,
|
| 2456 |
+
"learning_rate": 1.5702479338842977e-06,
|
| 2457 |
+
"loss": 2.7017,
|
| 2458 |
+
"step": 111500
|
| 2459 |
+
},
|
| 2460 |
+
{
|
| 2461 |
+
"epoch": 0.93,
|
| 2462 |
+
"grad_norm": 7.751842975616455,
|
| 2463 |
+
"learning_rate": 1.4876033057851241e-06,
|
| 2464 |
+
"loss": 3.2391,
|
| 2465 |
+
"step": 112000
|
| 2466 |
+
},
|
| 2467 |
+
{
|
| 2468 |
+
"epoch": 0.93,
|
| 2469 |
+
"eval_loss": 2.433881998062134,
|
| 2470 |
+
"eval_runtime": 138.8671,
|
| 2471 |
+
"eval_samples_per_second": 6.927,
|
| 2472 |
+
"eval_steps_per_second": 6.927,
|
| 2473 |
+
"step": 112000
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.93,
|
| 2477 |
+
"grad_norm": 81.50652313232422,
|
| 2478 |
+
"learning_rate": 1.4049586776859506e-06,
|
| 2479 |
+
"loss": 2.9904,
|
| 2480 |
+
"step": 112500
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.93,
|
| 2484 |
+
"grad_norm": 57.682987213134766,
|
| 2485 |
+
"learning_rate": 1.322314049586777e-06,
|
| 2486 |
+
"loss": 2.8742,
|
| 2487 |
+
"step": 113000
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.93,
|
| 2491 |
+
"eval_loss": 2.4209775924682617,
|
| 2492 |
+
"eval_runtime": 138.7625,
|
| 2493 |
+
"eval_samples_per_second": 6.933,
|
| 2494 |
+
"eval_steps_per_second": 6.933,
|
| 2495 |
+
"step": 113000
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 0.94,
|
| 2499 |
+
"grad_norm": 52.617713928222656,
|
| 2500 |
+
"learning_rate": 1.2396694214876035e-06,
|
| 2501 |
+
"loss": 2.9336,
|
| 2502 |
+
"step": 113500
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 0.94,
|
| 2506 |
+
"grad_norm": 123.95398712158203,
|
| 2507 |
+
"learning_rate": 1.15702479338843e-06,
|
| 2508 |
+
"loss": 2.7248,
|
| 2509 |
+
"step": 114000
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 0.94,
|
| 2513 |
+
"eval_loss": 2.4292454719543457,
|
| 2514 |
+
"eval_runtime": 138.6689,
|
| 2515 |
+
"eval_samples_per_second": 6.937,
|
| 2516 |
+
"eval_steps_per_second": 6.937,
|
| 2517 |
+
"step": 114000
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 0.95,
|
| 2521 |
+
"grad_norm": 122.3961410522461,
|
| 2522 |
+
"learning_rate": 1.0743801652892562e-06,
|
| 2523 |
+
"loss": 2.9363,
|
| 2524 |
+
"step": 114500
|
| 2525 |
+
},
|
| 2526 |
+
{
|
| 2527 |
+
"epoch": 0.95,
|
| 2528 |
+
"grad_norm": 1.238726258277893,
|
| 2529 |
+
"learning_rate": 9.917355371900827e-07,
|
| 2530 |
+
"loss": 3.0417,
|
| 2531 |
+
"step": 115000
|
| 2532 |
+
},
|
| 2533 |
+
{
|
| 2534 |
+
"epoch": 0.95,
|
| 2535 |
+
"eval_loss": 2.4144928455352783,
|
| 2536 |
+
"eval_runtime": 139.5698,
|
| 2537 |
+
"eval_samples_per_second": 6.893,
|
| 2538 |
+
"eval_steps_per_second": 6.893,
|
| 2539 |
+
"step": 115000
|
| 2540 |
+
},
|
| 2541 |
+
{
|
| 2542 |
+
"epoch": 0.95,
|
| 2543 |
+
"grad_norm": 29.5744571685791,
|
| 2544 |
+
"learning_rate": 9.090909090909091e-07,
|
| 2545 |
+
"loss": 2.7703,
|
| 2546 |
+
"step": 115500
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 0.96,
|
| 2550 |
+
"grad_norm": 57.384883880615234,
|
| 2551 |
+
"learning_rate": 8.264462809917356e-07,
|
| 2552 |
+
"loss": 3.0549,
|
| 2553 |
+
"step": 116000
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 0.96,
|
| 2557 |
+
"eval_loss": 2.4143543243408203,
|
| 2558 |
+
"eval_runtime": 139.2695,
|
| 2559 |
+
"eval_samples_per_second": 6.907,
|
| 2560 |
+
"eval_steps_per_second": 6.907,
|
| 2561 |
+
"step": 116000
|
| 2562 |
+
},
|
| 2563 |
+
{
|
| 2564 |
+
"epoch": 0.96,
|
| 2565 |
+
"grad_norm": 108.1037826538086,
|
| 2566 |
+
"learning_rate": 7.438016528925621e-07,
|
| 2567 |
+
"loss": 2.9309,
|
| 2568 |
+
"step": 116500
|
| 2569 |
+
},
|
| 2570 |
+
{
|
| 2571 |
+
"epoch": 0.97,
|
| 2572 |
+
"grad_norm": 68.91290283203125,
|
| 2573 |
+
"learning_rate": 6.611570247933885e-07,
|
| 2574 |
+
"loss": 2.8769,
|
| 2575 |
+
"step": 117000
|
| 2576 |
+
},
|
| 2577 |
+
{
|
| 2578 |
+
"epoch": 0.97,
|
| 2579 |
+
"eval_loss": 2.4317731857299805,
|
| 2580 |
+
"eval_runtime": 139.2728,
|
| 2581 |
+
"eval_samples_per_second": 6.907,
|
| 2582 |
+
"eval_steps_per_second": 6.907,
|
| 2583 |
+
"step": 117000
|
| 2584 |
+
}
|
| 2585 |
+
],
|
| 2586 |
+
"logging_steps": 500,
|
| 2587 |
+
"max_steps": 121000,
|
| 2588 |
+
"num_input_tokens_seen": 0,
|
| 2589 |
+
"num_train_epochs": 1,
|
| 2590 |
+
"save_steps": 1000,
|
| 2591 |
+
"total_flos": 2.975715266349957e+18,
|
| 2592 |
+
"train_batch_size": 1,
|
| 2593 |
+
"trial_name": null,
|
| 2594 |
+
"trial_params": null
|
| 2595 |
+
}
|
last-checkpoint/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76ebb30abafb6539f25921a315acd0e5bba747b74cb94aaf246e64bc74ec71f8
|
| 3 |
+
size 5176
|