Upload full trainer checkpoint step=2196 (profile=llama3_1_8b_base_lessdata, run_type=sft)
Browse files- .gitattributes +1 -0
- meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2196/README.md +210 -0
- meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2196/adapter_config.json +50 -0
- meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2196/adapter_model.safetensors +3 -0
- meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2196/chat_template.jinja +12 -0
- meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2196/optimizer.pt +3 -0
- meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2196/rng_state.pth +3 -0
- meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2196/scheduler.pt +3 -0
- meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2196/tokenizer.json +3 -0
- meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2196/tokenizer_config.json +18 -0
- meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2196/trainer_state.json +3203 -0
- meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2196/training_args.bin +3 -0
- meta-llama__meta-llama-3.1-8b/sft/run_manifest.json +8 -2
.gitattributes
CHANGED
|
@@ -153,3 +153,4 @@ meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-732/tokenizer.json filt
|
|
| 153 |
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-1098/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 154 |
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-1464/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 155 |
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-1830/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 153 |
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-1098/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 154 |
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-1464/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 155 |
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-1830/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 156 |
+
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2196/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2196/README.md
ADDED
|
@@ -0,0 +1,210 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: unsloth/Meta-Llama-3.1-8B
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:unsloth/Meta-Llama-3.1-8B
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
- unsloth
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# Model Card for Model ID
|
| 15 |
+
|
| 16 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
## Model Details
|
| 21 |
+
|
| 22 |
+
### Model Description
|
| 23 |
+
|
| 24 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
|
| 28 |
+
- **Developed by:** [More Information Needed]
|
| 29 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 30 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 31 |
+
- **Model type:** [More Information Needed]
|
| 32 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 33 |
+
- **License:** [More Information Needed]
|
| 34 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
### Model Sources [optional]
|
| 37 |
+
|
| 38 |
+
<!-- Provide the basic links for the model. -->
|
| 39 |
+
|
| 40 |
+
- **Repository:** [More Information Needed]
|
| 41 |
+
- **Paper [optional]:** [More Information Needed]
|
| 42 |
+
- **Demo [optional]:** [More Information Needed]
|
| 43 |
+
|
| 44 |
+
## Uses
|
| 45 |
+
|
| 46 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 47 |
+
|
| 48 |
+
### Direct Use
|
| 49 |
+
|
| 50 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 51 |
+
|
| 52 |
+
[More Information Needed]
|
| 53 |
+
|
| 54 |
+
### Downstream Use [optional]
|
| 55 |
+
|
| 56 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 57 |
+
|
| 58 |
+
[More Information Needed]
|
| 59 |
+
|
| 60 |
+
### Out-of-Scope Use
|
| 61 |
+
|
| 62 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 63 |
+
|
| 64 |
+
[More Information Needed]
|
| 65 |
+
|
| 66 |
+
## Bias, Risks, and Limitations
|
| 67 |
+
|
| 68 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 69 |
+
|
| 70 |
+
[More Information Needed]
|
| 71 |
+
|
| 72 |
+
### Recommendations
|
| 73 |
+
|
| 74 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 75 |
+
|
| 76 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 77 |
+
|
| 78 |
+
## How to Get Started with the Model
|
| 79 |
+
|
| 80 |
+
Use the code below to get started with the model.
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
## Training Details
|
| 85 |
+
|
| 86 |
+
### Training Data
|
| 87 |
+
|
| 88 |
+
<!-- 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. -->
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
### Training Procedure
|
| 93 |
+
|
| 94 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 95 |
+
|
| 96 |
+
#### Preprocessing [optional]
|
| 97 |
+
|
| 98 |
+
[More Information Needed]
|
| 99 |
+
|
| 100 |
+
|
| 101 |
+
#### Training Hyperparameters
|
| 102 |
+
|
| 103 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 104 |
+
|
| 105 |
+
#### Speeds, Sizes, Times [optional]
|
| 106 |
+
|
| 107 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 108 |
+
|
| 109 |
+
[More Information Needed]
|
| 110 |
+
|
| 111 |
+
## Evaluation
|
| 112 |
+
|
| 113 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 114 |
+
|
| 115 |
+
### Testing Data, Factors & Metrics
|
| 116 |
+
|
| 117 |
+
#### Testing Data
|
| 118 |
+
|
| 119 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 120 |
+
|
| 121 |
+
[More Information Needed]
|
| 122 |
+
|
| 123 |
+
#### Factors
|
| 124 |
+
|
| 125 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 126 |
+
|
| 127 |
+
[More Information Needed]
|
| 128 |
+
|
| 129 |
+
#### Metrics
|
| 130 |
+
|
| 131 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 132 |
+
|
| 133 |
+
[More Information Needed]
|
| 134 |
+
|
| 135 |
+
### Results
|
| 136 |
+
|
| 137 |
+
[More Information Needed]
|
| 138 |
+
|
| 139 |
+
#### Summary
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
|
| 143 |
+
## Model Examination [optional]
|
| 144 |
+
|
| 145 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 146 |
+
|
| 147 |
+
[More Information Needed]
|
| 148 |
+
|
| 149 |
+
## Environmental Impact
|
| 150 |
+
|
| 151 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 152 |
+
|
| 153 |
+
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).
|
| 154 |
+
|
| 155 |
+
- **Hardware Type:** [More Information Needed]
|
| 156 |
+
- **Hours used:** [More Information Needed]
|
| 157 |
+
- **Cloud Provider:** [More Information Needed]
|
| 158 |
+
- **Compute Region:** [More Information Needed]
|
| 159 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 160 |
+
|
| 161 |
+
## Technical Specifications [optional]
|
| 162 |
+
|
| 163 |
+
### Model Architecture and Objective
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
### Compute Infrastructure
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
#### Hardware
|
| 172 |
+
|
| 173 |
+
[More Information Needed]
|
| 174 |
+
|
| 175 |
+
#### Software
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
## Citation [optional]
|
| 180 |
+
|
| 181 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 182 |
+
|
| 183 |
+
**BibTeX:**
|
| 184 |
+
|
| 185 |
+
[More Information Needed]
|
| 186 |
+
|
| 187 |
+
**APA:**
|
| 188 |
+
|
| 189 |
+
[More Information Needed]
|
| 190 |
+
|
| 191 |
+
## Glossary [optional]
|
| 192 |
+
|
| 193 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## More Information [optional]
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
## Model Card Authors [optional]
|
| 202 |
+
|
| 203 |
+
[More Information Needed]
|
| 204 |
+
|
| 205 |
+
## Model Card Contact
|
| 206 |
+
|
| 207 |
+
[More Information Needed]
|
| 208 |
+
### Framework versions
|
| 209 |
+
|
| 210 |
+
- PEFT 0.18.1
|
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2196/adapter_config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": {
|
| 6 |
+
"base_model_class": "LlamaForCausalLM",
|
| 7 |
+
"parent_library": "transformers.models.llama.modeling_llama",
|
| 8 |
+
"unsloth_fixed": true
|
| 9 |
+
},
|
| 10 |
+
"base_model_name_or_path": "unsloth/Meta-Llama-3.1-8B",
|
| 11 |
+
"bias": "none",
|
| 12 |
+
"corda_config": null,
|
| 13 |
+
"ensure_weight_tying": false,
|
| 14 |
+
"eva_config": null,
|
| 15 |
+
"exclude_modules": null,
|
| 16 |
+
"fan_in_fan_out": false,
|
| 17 |
+
"inference_mode": true,
|
| 18 |
+
"init_lora_weights": true,
|
| 19 |
+
"layer_replication": null,
|
| 20 |
+
"layers_pattern": null,
|
| 21 |
+
"layers_to_transform": null,
|
| 22 |
+
"loftq_config": {},
|
| 23 |
+
"lora_alpha": 16,
|
| 24 |
+
"lora_bias": false,
|
| 25 |
+
"lora_dropout": 0.0,
|
| 26 |
+
"megatron_config": null,
|
| 27 |
+
"megatron_core": "megatron.core",
|
| 28 |
+
"modules_to_save": null,
|
| 29 |
+
"peft_type": "LORA",
|
| 30 |
+
"peft_version": "0.18.1",
|
| 31 |
+
"qalora_group_size": 16,
|
| 32 |
+
"r": 8,
|
| 33 |
+
"rank_pattern": {},
|
| 34 |
+
"revision": null,
|
| 35 |
+
"target_modules": [
|
| 36 |
+
"q_proj",
|
| 37 |
+
"k_proj",
|
| 38 |
+
"up_proj",
|
| 39 |
+
"gate_proj",
|
| 40 |
+
"down_proj",
|
| 41 |
+
"o_proj",
|
| 42 |
+
"v_proj"
|
| 43 |
+
],
|
| 44 |
+
"target_parameters": null,
|
| 45 |
+
"task_type": "CAUSAL_LM",
|
| 46 |
+
"trainable_token_indices": null,
|
| 47 |
+
"use_dora": false,
|
| 48 |
+
"use_qalora": false,
|
| 49 |
+
"use_rslora": false
|
| 50 |
+
}
|
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2196/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec5e15b419b88b556f172661495d05db5612e44c5f5e491069a0834105412c13
|
| 3 |
+
size 83945296
|
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2196/chat_template.jinja
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ messages[0]['content'] + '
|
| 2 |
+
|
| 3 |
+
' }}{% set loop_messages = messages[1:] %}{% else %}{{ '' + '
|
| 4 |
+
|
| 5 |
+
' }}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['role'] == 'user' %}{{ '### Instruction:
|
| 6 |
+
' + message['content'] + '
|
| 7 |
+
|
| 8 |
+
' }}{% elif message['role'] == 'assistant' %}{{ '### Response:
|
| 9 |
+
' + message['content'] + eos_token + '
|
| 10 |
+
|
| 11 |
+
' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '### Response:
|
| 12 |
+
' }}{% endif %}
|
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2196/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0201b217b6318169c41b80cf856170c5dce4cab09c31c16e4febadcf621d33c5
|
| 3 |
+
size 43127973
|
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2196/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:827270dbeb2e04c837d1c35958cd7372837c48e711d15c2963ea3917cc5c7b4a
|
| 3 |
+
size 14645
|
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2196/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:018241c2f6214dfcf645e2e92db9ca7ae590dc70f41f5123b6979b3d5694c51a
|
| 3 |
+
size 1465
|
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2196/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
| 3 |
+
size 17209920
|
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2196/tokenizer_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<|begin_of_text|>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "<|end_of_text|>",
|
| 6 |
+
"from_slow": true,
|
| 7 |
+
"is_local": false,
|
| 8 |
+
"legacy": false,
|
| 9 |
+
"model_input_names": [
|
| 10 |
+
"input_ids",
|
| 11 |
+
"attention_mask"
|
| 12 |
+
],
|
| 13 |
+
"model_max_length": 131072,
|
| 14 |
+
"pad_token": "<|finetune_right_pad_id|>",
|
| 15 |
+
"padding_side": "right",
|
| 16 |
+
"tokenizer_class": "TokenizersBackend",
|
| 17 |
+
"unk_token": null
|
| 18 |
+
}
|
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2196/trainer_state.json
ADDED
|
@@ -0,0 +1,3203 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.4979536152796726,
|
| 6 |
+
"eval_steps": 366,
|
| 7 |
+
"global_step": 2196,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0034106412005457027,
|
| 14 |
+
"grad_norm": 3.1571648120880127,
|
| 15 |
+
"learning_rate": 2.542372881355932e-06,
|
| 16 |
+
"loss": 1.6981744766235352,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0068212824010914054,
|
| 21 |
+
"grad_norm": 9.80073070526123,
|
| 22 |
+
"learning_rate": 5.720338983050847e-06,
|
| 23 |
+
"loss": 1.5801130294799806,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.010231923601637109,
|
| 28 |
+
"grad_norm": 4.481558799743652,
|
| 29 |
+
"learning_rate": 8.898305084745763e-06,
|
| 30 |
+
"loss": 2.1718717575073243,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.013642564802182811,
|
| 35 |
+
"grad_norm": 7.221553802490234,
|
| 36 |
+
"learning_rate": 1.2076271186440677e-05,
|
| 37 |
+
"loss": 1.5270480155944823,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.017053206002728513,
|
| 42 |
+
"grad_norm": 5.330269813537598,
|
| 43 |
+
"learning_rate": 1.5254237288135592e-05,
|
| 44 |
+
"loss": 0.9586630821228027,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.020463847203274217,
|
| 49 |
+
"grad_norm": 1.7404323816299438,
|
| 50 |
+
"learning_rate": 1.8432203389830506e-05,
|
| 51 |
+
"loss": 0.48505802154541017,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.023874488403819918,
|
| 56 |
+
"grad_norm": 1.2418887615203857,
|
| 57 |
+
"learning_rate": 2.1610169491525424e-05,
|
| 58 |
+
"loss": 0.24452033042907714,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.027285129604365622,
|
| 63 |
+
"grad_norm": 1.5928819179534912,
|
| 64 |
+
"learning_rate": 2.4788135593220338e-05,
|
| 65 |
+
"loss": 0.25337533950805663,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.030695770804911322,
|
| 70 |
+
"grad_norm": 2.0335769653320312,
|
| 71 |
+
"learning_rate": 2.796610169491525e-05,
|
| 72 |
+
"loss": 0.1938886046409607,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.034106412005457026,
|
| 77 |
+
"grad_norm": 0.18029411137104034,
|
| 78 |
+
"learning_rate": 3.114406779661017e-05,
|
| 79 |
+
"loss": 0.1834133505821228,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.03751705320600273,
|
| 84 |
+
"grad_norm": 1.7757192850112915,
|
| 85 |
+
"learning_rate": 3.432203389830508e-05,
|
| 86 |
+
"loss": 0.15151114463806153,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.040927694406548434,
|
| 91 |
+
"grad_norm": 2.1376893520355225,
|
| 92 |
+
"learning_rate": 3.75e-05,
|
| 93 |
+
"loss": 0.21634674072265625,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.04433833560709413,
|
| 98 |
+
"grad_norm": 2.196387767791748,
|
| 99 |
+
"learning_rate": 4.067796610169491e-05,
|
| 100 |
+
"loss": 0.11320395469665527,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.047748976807639835,
|
| 105 |
+
"grad_norm": 1.5888807773590088,
|
| 106 |
+
"learning_rate": 4.3855932203389825e-05,
|
| 107 |
+
"loss": 0.11050152778625488,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.05115961800818554,
|
| 112 |
+
"grad_norm": 4.606944561004639,
|
| 113 |
+
"learning_rate": 4.703389830508474e-05,
|
| 114 |
+
"loss": 0.23255281448364257,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.054570259208731244,
|
| 119 |
+
"grad_norm": 1.7308639287948608,
|
| 120 |
+
"learning_rate": 5.021186440677966e-05,
|
| 121 |
+
"loss": 0.08995866179466247,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.05798090040927694,
|
| 126 |
+
"grad_norm": 2.622438430786133,
|
| 127 |
+
"learning_rate": 5.338983050847457e-05,
|
| 128 |
+
"loss": 0.05715223550796509,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.061391541609822645,
|
| 133 |
+
"grad_norm": 0.34140461683273315,
|
| 134 |
+
"learning_rate": 5.656779661016949e-05,
|
| 135 |
+
"loss": 0.06703727245330811,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.06480218281036836,
|
| 140 |
+
"grad_norm": 2.7264959812164307,
|
| 141 |
+
"learning_rate": 5.97457627118644e-05,
|
| 142 |
+
"loss": 0.10092716217041016,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.06821282401091405,
|
| 147 |
+
"grad_norm": 2.0234780311584473,
|
| 148 |
+
"learning_rate": 6.292372881355932e-05,
|
| 149 |
+
"loss": 0.03579937815666199,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.07162346521145975,
|
| 154 |
+
"grad_norm": 1.3716133832931519,
|
| 155 |
+
"learning_rate": 6.610169491525423e-05,
|
| 156 |
+
"loss": 0.07851418852806091,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.07503410641200546,
|
| 161 |
+
"grad_norm": 1.2307227849960327,
|
| 162 |
+
"learning_rate": 6.927966101694914e-05,
|
| 163 |
+
"loss": 0.07370938658714295,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.07844474761255116,
|
| 168 |
+
"grad_norm": 1.7142690420150757,
|
| 169 |
+
"learning_rate": 7.245762711864406e-05,
|
| 170 |
+
"loss": 0.08064572811126709,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.08185538881309687,
|
| 175 |
+
"grad_norm": 1.343595266342163,
|
| 176 |
+
"learning_rate": 7.499999439507554e-05,
|
| 177 |
+
"loss": 0.11841402053833008,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.08526603001364257,
|
| 182 |
+
"grad_norm": 1.2511327266693115,
|
| 183 |
+
"learning_rate": 7.499979822289558e-05,
|
| 184 |
+
"loss": 0.06974860429763793,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.08867667121418826,
|
| 189 |
+
"grad_norm": 1.5642656087875366,
|
| 190 |
+
"learning_rate": 7.49993218061684e-05,
|
| 191 |
+
"loss": 0.10972714424133301,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.09208731241473397,
|
| 196 |
+
"grad_norm": 1.6669789552688599,
|
| 197 |
+
"learning_rate": 7.499856514845436e-05,
|
| 198 |
+
"loss": 0.09864612817764282,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.09549795361527967,
|
| 203 |
+
"grad_norm": 0.9789333343505859,
|
| 204 |
+
"learning_rate": 7.499752825540815e-05,
|
| 205 |
+
"loss": 0.0699621558189392,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.09890859481582538,
|
| 210 |
+
"grad_norm": 0.41792476177215576,
|
| 211 |
+
"learning_rate": 7.499621113477873e-05,
|
| 212 |
+
"loss": 0.06734349727630615,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.10231923601637108,
|
| 217 |
+
"grad_norm": 1.5968533754348755,
|
| 218 |
+
"learning_rate": 7.499461379640919e-05,
|
| 219 |
+
"loss": 0.060729533433914185,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.10572987721691678,
|
| 224 |
+
"grad_norm": 0.8512193560600281,
|
| 225 |
+
"learning_rate": 7.499273625223683e-05,
|
| 226 |
+
"loss": 0.052730172872543335,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.10914051841746249,
|
| 231 |
+
"grad_norm": 1.3257211446762085,
|
| 232 |
+
"learning_rate": 7.499057851629299e-05,
|
| 233 |
+
"loss": 0.10094538927078248,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.11255115961800818,
|
| 238 |
+
"grad_norm": 0.659118115901947,
|
| 239 |
+
"learning_rate": 7.498814060470288e-05,
|
| 240 |
+
"loss": 0.01604635864496231,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.11596180081855388,
|
| 245 |
+
"grad_norm": 2.454979181289673,
|
| 246 |
+
"learning_rate": 7.49854225356856e-05,
|
| 247 |
+
"loss": 0.13272385597229003,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.11937244201909959,
|
| 252 |
+
"grad_norm": 2.510040521621704,
|
| 253 |
+
"learning_rate": 7.498242432955388e-05,
|
| 254 |
+
"loss": 0.08396227955818177,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.12278308321964529,
|
| 259 |
+
"grad_norm": 0.2637259364128113,
|
| 260 |
+
"learning_rate": 7.4979146008714e-05,
|
| 261 |
+
"loss": 0.05852065086364746,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.126193724420191,
|
| 266 |
+
"grad_norm": 1.4320851564407349,
|
| 267 |
+
"learning_rate": 7.497558759766564e-05,
|
| 268 |
+
"loss": 0.10392802953720093,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.1296043656207367,
|
| 273 |
+
"grad_norm": 1.273027777671814,
|
| 274 |
+
"learning_rate": 7.497174912300156e-05,
|
| 275 |
+
"loss": 0.08062989711761474,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.1330150068212824,
|
| 280 |
+
"grad_norm": 0.8102871179580688,
|
| 281 |
+
"learning_rate": 7.496763061340759e-05,
|
| 282 |
+
"loss": 0.07294153571128845,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.1364256480218281,
|
| 287 |
+
"grad_norm": 1.951328992843628,
|
| 288 |
+
"learning_rate": 7.496323209966228e-05,
|
| 289 |
+
"loss": 0.07738351821899414,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.13983628922237382,
|
| 294 |
+
"grad_norm": 0.3880983889102936,
|
| 295 |
+
"learning_rate": 7.495855361463674e-05,
|
| 296 |
+
"loss": 0.07225048542022705,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.1432469304229195,
|
| 301 |
+
"grad_norm": 3.3205058574676514,
|
| 302 |
+
"learning_rate": 7.495359519329433e-05,
|
| 303 |
+
"loss": 0.05682974457740784,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.1466575716234652,
|
| 308 |
+
"grad_norm": 0.9203559160232544,
|
| 309 |
+
"learning_rate": 7.49483568726905e-05,
|
| 310 |
+
"loss": 0.08767472505569458,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.15006821282401092,
|
| 315 |
+
"grad_norm": 0.585360586643219,
|
| 316 |
+
"learning_rate": 7.494283869197239e-05,
|
| 317 |
+
"loss": 0.039227068424224854,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.1534788540245566,
|
| 322 |
+
"grad_norm": 1.7096059322357178,
|
| 323 |
+
"learning_rate": 7.493704069237862e-05,
|
| 324 |
+
"loss": 0.10281096696853638,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.15688949522510232,
|
| 329 |
+
"grad_norm": 0.4110204875469208,
|
| 330 |
+
"learning_rate": 7.493096291723898e-05,
|
| 331 |
+
"loss": 0.04346161186695099,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.16030013642564803,
|
| 336 |
+
"grad_norm": 1.3272292613983154,
|
| 337 |
+
"learning_rate": 7.492460541197404e-05,
|
| 338 |
+
"loss": 0.049719154834747314,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.16371077762619374,
|
| 343 |
+
"grad_norm": 1.1005016565322876,
|
| 344 |
+
"learning_rate": 7.491796822409494e-05,
|
| 345 |
+
"loss": 0.09335108399391175,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.16712141882673942,
|
| 350 |
+
"grad_norm": 0.7811501026153564,
|
| 351 |
+
"learning_rate": 7.491105140320285e-05,
|
| 352 |
+
"loss": 0.05943926572799683,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.17053206002728513,
|
| 357 |
+
"grad_norm": 1.4607417583465576,
|
| 358 |
+
"learning_rate": 7.490385500098879e-05,
|
| 359 |
+
"loss": 0.04385361075401306,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.17394270122783084,
|
| 364 |
+
"grad_norm": 0.394960880279541,
|
| 365 |
+
"learning_rate": 7.489637907123308e-05,
|
| 366 |
+
"loss": 0.04446137547492981,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.17735334242837653,
|
| 371 |
+
"grad_norm": 0.8768635988235474,
|
| 372 |
+
"learning_rate": 7.488862366980505e-05,
|
| 373 |
+
"loss": 0.04143576025962829,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.18076398362892224,
|
| 378 |
+
"grad_norm": 1.9996010065078735,
|
| 379 |
+
"learning_rate": 7.488058885466262e-05,
|
| 380 |
+
"loss": 0.07952215671539306,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.18417462482946795,
|
| 385 |
+
"grad_norm": 0.03770223259925842,
|
| 386 |
+
"learning_rate": 7.487227468585178e-05,
|
| 387 |
+
"loss": 0.02531362771987915,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.18758526603001363,
|
| 392 |
+
"grad_norm": 0.26082542538642883,
|
| 393 |
+
"learning_rate": 7.486368122550619e-05,
|
| 394 |
+
"loss": 0.09930967688560485,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.19099590723055934,
|
| 399 |
+
"grad_norm": 5.622270584106445,
|
| 400 |
+
"learning_rate": 7.485480853784677e-05,
|
| 401 |
+
"loss": 0.06534865498542786,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.19440654843110505,
|
| 406 |
+
"grad_norm": 0.5298851132392883,
|
| 407 |
+
"learning_rate": 7.484565668918111e-05,
|
| 408 |
+
"loss": 0.06109699010848999,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.19781718963165076,
|
| 413 |
+
"grad_norm": 1.4887421131134033,
|
| 414 |
+
"learning_rate": 7.483622574790308e-05,
|
| 415 |
+
"loss": 0.048966211080551145,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.20122783083219645,
|
| 420 |
+
"grad_norm": 0.5699282884597778,
|
| 421 |
+
"learning_rate": 7.482651578449223e-05,
|
| 422 |
+
"loss": 0.05427658557891846,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.20463847203274216,
|
| 427 |
+
"grad_norm": 1.6645292043685913,
|
| 428 |
+
"learning_rate": 7.481652687151339e-05,
|
| 429 |
+
"loss": 0.037466832995414735,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.20804911323328787,
|
| 434 |
+
"grad_norm": 0.4979431629180908,
|
| 435 |
+
"learning_rate": 7.480625908361593e-05,
|
| 436 |
+
"loss": 0.019084173440933227,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.21145975443383355,
|
| 441 |
+
"grad_norm": 2.73081636428833,
|
| 442 |
+
"learning_rate": 7.479571249753339e-05,
|
| 443 |
+
"loss": 0.07597044706344605,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.21487039563437926,
|
| 448 |
+
"grad_norm": 0.009097559377551079,
|
| 449 |
+
"learning_rate": 7.478488719208281e-05,
|
| 450 |
+
"loss": 0.017771795392036438,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.21828103683492497,
|
| 455 |
+
"grad_norm": 1.5284112691879272,
|
| 456 |
+
"learning_rate": 7.477378324816419e-05,
|
| 457 |
+
"loss": 0.07524526119232178,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.22169167803547066,
|
| 462 |
+
"grad_norm": 1.400959849357605,
|
| 463 |
+
"learning_rate": 7.47624007487598e-05,
|
| 464 |
+
"loss": 0.0357323557138443,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.22510231923601637,
|
| 469 |
+
"grad_norm": 0.5988397598266602,
|
| 470 |
+
"learning_rate": 7.47507397789337e-05,
|
| 471 |
+
"loss": 0.06072888970375061,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.22851296043656208,
|
| 476 |
+
"grad_norm": 0.18309183418750763,
|
| 477 |
+
"learning_rate": 7.473880042583092e-05,
|
| 478 |
+
"loss": 0.03904334008693695,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.23192360163710776,
|
| 483 |
+
"grad_norm": 0.7360084056854248,
|
| 484 |
+
"learning_rate": 7.472658277867702e-05,
|
| 485 |
+
"loss": 0.05045387148857117,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.23533424283765347,
|
| 490 |
+
"grad_norm": 2.315072536468506,
|
| 491 |
+
"learning_rate": 7.471408692877724e-05,
|
| 492 |
+
"loss": 0.07920202016830444,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.23874488403819918,
|
| 497 |
+
"grad_norm": 1.2811086177825928,
|
| 498 |
+
"learning_rate": 7.470131296951592e-05,
|
| 499 |
+
"loss": 0.05552580952644348,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.2421555252387449,
|
| 504 |
+
"grad_norm": 4.006563186645508,
|
| 505 |
+
"learning_rate": 7.468826099635578e-05,
|
| 506 |
+
"loss": 0.1419215679168701,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.24556616643929058,
|
| 511 |
+
"grad_norm": 1.1540688276290894,
|
| 512 |
+
"learning_rate": 7.467493110683718e-05,
|
| 513 |
+
"loss": 0.03980849981307984,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.2489768076398363,
|
| 518 |
+
"grad_norm": 1.5472272634506226,
|
| 519 |
+
"learning_rate": 7.466132340057742e-05,
|
| 520 |
+
"loss": 0.020862475037574768,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.24965893587994542,
|
| 525 |
+
"eval_loss": 0.11654457449913025,
|
| 526 |
+
"eval_runtime": 1.0333,
|
| 527 |
+
"eval_samples_per_second": 72.584,
|
| 528 |
+
"eval_steps_per_second": 1.936,
|
| 529 |
+
"step": 366
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"eval_cer_subset": 0.05232320479629377,
|
| 533 |
+
"eval_cer_subset_edit_distance": 384,
|
| 534 |
+
"eval_cer_subset_groups": 75,
|
| 535 |
+
"eval_cer_subset_items": 75,
|
| 536 |
+
"eval_cer_subset_ref_chars": 7339,
|
| 537 |
+
"step": 366
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.252387448840382,
|
| 541 |
+
"grad_norm": 1.730627417564392,
|
| 542 |
+
"learning_rate": 7.464743797927002e-05,
|
| 543 |
+
"loss": 0.11239330768585205,
|
| 544 |
+
"step": 370
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.2557980900409277,
|
| 548 |
+
"grad_norm": 0.1921682506799698,
|
| 549 |
+
"learning_rate": 7.463327494668388e-05,
|
| 550 |
+
"loss": 0.09260941743850708,
|
| 551 |
+
"step": 375
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.2592087312414734,
|
| 555 |
+
"grad_norm": 1.9259151220321655,
|
| 556 |
+
"learning_rate": 7.461883440866259e-05,
|
| 557 |
+
"loss": 0.03999299705028534,
|
| 558 |
+
"step": 380
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.2626193724420191,
|
| 562 |
+
"grad_norm": 0.0488249845802784,
|
| 563 |
+
"learning_rate": 7.460411647312358e-05,
|
| 564 |
+
"loss": 0.01459498256444931,
|
| 565 |
+
"step": 385
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 0.2660300136425648,
|
| 569 |
+
"grad_norm": 1.1967735290527344,
|
| 570 |
+
"learning_rate": 7.458912125005732e-05,
|
| 571 |
+
"loss": 0.17716412544250487,
|
| 572 |
+
"step": 390
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.2694406548431105,
|
| 576 |
+
"grad_norm": 1.0083205699920654,
|
| 577 |
+
"learning_rate": 7.457384885152655e-05,
|
| 578 |
+
"loss": 0.08738511800765991,
|
| 579 |
+
"step": 395
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.2728512960436562,
|
| 583 |
+
"grad_norm": 0.6705593466758728,
|
| 584 |
+
"learning_rate": 7.455829939166539e-05,
|
| 585 |
+
"loss": 0.026945650577545166,
|
| 586 |
+
"step": 400
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.2762619372442019,
|
| 590 |
+
"grad_norm": 1.0791361331939697,
|
| 591 |
+
"learning_rate": 7.45424729866785e-05,
|
| 592 |
+
"loss": 0.03804046213626862,
|
| 593 |
+
"step": 405
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.27967257844474763,
|
| 597 |
+
"grad_norm": 0.7377910017967224,
|
| 598 |
+
"learning_rate": 7.452636975484021e-05,
|
| 599 |
+
"loss": 0.0464675635099411,
|
| 600 |
+
"step": 410
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.2830832196452933,
|
| 604 |
+
"grad_norm": 0.8061625957489014,
|
| 605 |
+
"learning_rate": 7.450998981649365e-05,
|
| 606 |
+
"loss": 0.02737331986427307,
|
| 607 |
+
"step": 415
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 0.286493860845839,
|
| 611 |
+
"grad_norm": 0.2580685019493103,
|
| 612 |
+
"learning_rate": 7.449333329404982e-05,
|
| 613 |
+
"loss": 0.018785761296749116,
|
| 614 |
+
"step": 420
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.28990450204638474,
|
| 618 |
+
"grad_norm": 0.017052194103598595,
|
| 619 |
+
"learning_rate": 7.447640031198675e-05,
|
| 620 |
+
"loss": 0.11424320936203003,
|
| 621 |
+
"step": 425
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.2933151432469304,
|
| 625 |
+
"grad_norm": 0.2855948805809021,
|
| 626 |
+
"learning_rate": 7.445919099684845e-05,
|
| 627 |
+
"loss": 0.012821969389915467,
|
| 628 |
+
"step": 430
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 0.2967257844474761,
|
| 632 |
+
"grad_norm": 1.5070558786392212,
|
| 633 |
+
"learning_rate": 7.444170547724405e-05,
|
| 634 |
+
"loss": 0.037783479690551756,
|
| 635 |
+
"step": 435
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 0.30013642564802184,
|
| 639 |
+
"grad_norm": 0.18241967260837555,
|
| 640 |
+
"learning_rate": 7.442394388384684e-05,
|
| 641 |
+
"loss": 0.03347713351249695,
|
| 642 |
+
"step": 440
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.3035470668485675,
|
| 646 |
+
"grad_norm": 0.37319424748420715,
|
| 647 |
+
"learning_rate": 7.440590634939327e-05,
|
| 648 |
+
"loss": 0.05499382615089417,
|
| 649 |
+
"step": 445
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.3069577080491132,
|
| 653 |
+
"grad_norm": 0.11083097755908966,
|
| 654 |
+
"learning_rate": 7.438759300868193e-05,
|
| 655 |
+
"loss": 0.021977408230304717,
|
| 656 |
+
"step": 450
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.31036834924965895,
|
| 660 |
+
"grad_norm": 0.24985608458518982,
|
| 661 |
+
"learning_rate": 7.436900399857261e-05,
|
| 662 |
+
"loss": 0.07826730608940125,
|
| 663 |
+
"step": 455
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.31377899045020463,
|
| 667 |
+
"grad_norm": 2.5360186100006104,
|
| 668 |
+
"learning_rate": 7.43501394579852e-05,
|
| 669 |
+
"loss": 0.080865478515625,
|
| 670 |
+
"step": 460
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.3171896316507503,
|
| 674 |
+
"grad_norm": 0.7053658366203308,
|
| 675 |
+
"learning_rate": 7.433099952789876e-05,
|
| 676 |
+
"loss": 0.012464526295661926,
|
| 677 |
+
"step": 465
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.32060027285129605,
|
| 681 |
+
"grad_norm": 0.3297032117843628,
|
| 682 |
+
"learning_rate": 7.43115843513503e-05,
|
| 683 |
+
"loss": 0.05623521208763123,
|
| 684 |
+
"step": 470
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.32401091405184174,
|
| 688 |
+
"grad_norm": 1.3899471759796143,
|
| 689 |
+
"learning_rate": 7.42918940734339e-05,
|
| 690 |
+
"loss": 0.07306370735168458,
|
| 691 |
+
"step": 475
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.3274215552523875,
|
| 695 |
+
"grad_norm": 0.9437380433082581,
|
| 696 |
+
"learning_rate": 7.427192884129948e-05,
|
| 697 |
+
"loss": 0.058290761709213254,
|
| 698 |
+
"step": 480
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.33083219645293316,
|
| 702 |
+
"grad_norm": 1.8157323598861694,
|
| 703 |
+
"learning_rate": 7.42516888041518e-05,
|
| 704 |
+
"loss": 0.058532989025115965,
|
| 705 |
+
"step": 485
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.33424283765347884,
|
| 709 |
+
"grad_norm": 0.6275774836540222,
|
| 710 |
+
"learning_rate": 7.423117411324924e-05,
|
| 711 |
+
"loss": 0.0624964714050293,
|
| 712 |
+
"step": 490
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.3376534788540246,
|
| 716 |
+
"grad_norm": 0.6674565672874451,
|
| 717 |
+
"learning_rate": 7.421038492190278e-05,
|
| 718 |
+
"loss": 0.020014175772666933,
|
| 719 |
+
"step": 495
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.34106412005457026,
|
| 723 |
+
"grad_norm": 0.6229842901229858,
|
| 724 |
+
"learning_rate": 7.418932138547481e-05,
|
| 725 |
+
"loss": 0.03286575376987457,
|
| 726 |
+
"step": 500
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.34447476125511595,
|
| 730 |
+
"grad_norm": 1.441677212715149,
|
| 731 |
+
"learning_rate": 7.41679836613779e-05,
|
| 732 |
+
"loss": 0.04557921886444092,
|
| 733 |
+
"step": 505
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.3478854024556617,
|
| 737 |
+
"grad_norm": 0.8439592719078064,
|
| 738 |
+
"learning_rate": 7.414637190907379e-05,
|
| 739 |
+
"loss": 0.027792316675186158,
|
| 740 |
+
"step": 510
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.35129604365620737,
|
| 744 |
+
"grad_norm": 0.1357346475124359,
|
| 745 |
+
"learning_rate": 7.412448629007198e-05,
|
| 746 |
+
"loss": 0.024153730273246764,
|
| 747 |
+
"step": 515
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.35470668485675305,
|
| 751 |
+
"grad_norm": 0.11876281350851059,
|
| 752 |
+
"learning_rate": 7.41023269679287e-05,
|
| 753 |
+
"loss": 0.11651531457901002,
|
| 754 |
+
"step": 520
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.3581173260572988,
|
| 758 |
+
"grad_norm": 0.8576210737228394,
|
| 759 |
+
"learning_rate": 7.407989410824566e-05,
|
| 760 |
+
"loss": 0.045156928896903994,
|
| 761 |
+
"step": 525
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.3615279672578445,
|
| 765 |
+
"grad_norm": 0.39947113394737244,
|
| 766 |
+
"learning_rate": 7.40571878786687e-05,
|
| 767 |
+
"loss": 0.02562606930732727,
|
| 768 |
+
"step": 530
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.36493860845839016,
|
| 772 |
+
"grad_norm": 0.8822716474533081,
|
| 773 |
+
"learning_rate": 7.403420844888668e-05,
|
| 774 |
+
"loss": 0.05394383668899536,
|
| 775 |
+
"step": 535
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.3683492496589359,
|
| 779 |
+
"grad_norm": 1.8026832342147827,
|
| 780 |
+
"learning_rate": 7.40109559906301e-05,
|
| 781 |
+
"loss": 0.07706952095031738,
|
| 782 |
+
"step": 540
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.3717598908594816,
|
| 786 |
+
"grad_norm": 0.28902706503868103,
|
| 787 |
+
"learning_rate": 7.398743067766987e-05,
|
| 788 |
+
"loss": 0.0352792352437973,
|
| 789 |
+
"step": 545
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.37517053206002726,
|
| 793 |
+
"grad_norm": 0.2759908437728882,
|
| 794 |
+
"learning_rate": 7.396363268581609e-05,
|
| 795 |
+
"loss": 0.038266700506210324,
|
| 796 |
+
"step": 550
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.378581173260573,
|
| 800 |
+
"grad_norm": 1.0520153045654297,
|
| 801 |
+
"learning_rate": 7.39395621929165e-05,
|
| 802 |
+
"loss": 0.04206843376159668,
|
| 803 |
+
"step": 555
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.3819918144611187,
|
| 807 |
+
"grad_norm": 0.29290419816970825,
|
| 808 |
+
"learning_rate": 7.391521937885543e-05,
|
| 809 |
+
"loss": 0.04060278534889221,
|
| 810 |
+
"step": 560
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.38540245566166437,
|
| 814 |
+
"grad_norm": 0.11243477463722229,
|
| 815 |
+
"learning_rate": 7.389060442555228e-05,
|
| 816 |
+
"loss": 0.05412468910217285,
|
| 817 |
+
"step": 565
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.3888130968622101,
|
| 821 |
+
"grad_norm": 1.9416879415512085,
|
| 822 |
+
"learning_rate": 7.386571751696019e-05,
|
| 823 |
+
"loss": 0.02231921851634979,
|
| 824 |
+
"step": 570
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.3922237380627558,
|
| 828 |
+
"grad_norm": 0.5937671661376953,
|
| 829 |
+
"learning_rate": 7.384055883906474e-05,
|
| 830 |
+
"loss": 0.032561862468719484,
|
| 831 |
+
"step": 575
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.3956343792633015,
|
| 835 |
+
"grad_norm": 0.026148535311222076,
|
| 836 |
+
"learning_rate": 7.381512857988244e-05,
|
| 837 |
+
"loss": 0.07647547125816345,
|
| 838 |
+
"step": 580
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.3990450204638472,
|
| 842 |
+
"grad_norm": 0.7875772714614868,
|
| 843 |
+
"learning_rate": 7.378942692945944e-05,
|
| 844 |
+
"loss": 0.031203645467758178,
|
| 845 |
+
"step": 585
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.4024556616643929,
|
| 849 |
+
"grad_norm": 0.45512810349464417,
|
| 850 |
+
"learning_rate": 7.376345407987002e-05,
|
| 851 |
+
"loss": 0.04238590002059937,
|
| 852 |
+
"step": 590
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.40586630286493863,
|
| 856 |
+
"grad_norm": 1.66355299949646,
|
| 857 |
+
"learning_rate": 7.373721022521521e-05,
|
| 858 |
+
"loss": 0.052533066272735594,
|
| 859 |
+
"step": 595
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.4092769440654843,
|
| 863 |
+
"grad_norm": 0.08107655495405197,
|
| 864 |
+
"learning_rate": 7.371069556162133e-05,
|
| 865 |
+
"loss": 0.017715978622436523,
|
| 866 |
+
"step": 600
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.41268758526603,
|
| 870 |
+
"grad_norm": 0.32274800539016724,
|
| 871 |
+
"learning_rate": 7.368391028723851e-05,
|
| 872 |
+
"loss": 0.1379294991493225,
|
| 873 |
+
"step": 605
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.41609822646657574,
|
| 877 |
+
"grad_norm": 1.8197475671768188,
|
| 878 |
+
"learning_rate": 7.365685460223922e-05,
|
| 879 |
+
"loss": 0.03312918543815613,
|
| 880 |
+
"step": 610
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.4195088676671214,
|
| 884 |
+
"grad_norm": 0.1390945166349411,
|
| 885 |
+
"learning_rate": 7.362952870881677e-05,
|
| 886 |
+
"loss": 0.027584537863731384,
|
| 887 |
+
"step": 615
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.4229195088676671,
|
| 891 |
+
"grad_norm": 0.9081276655197144,
|
| 892 |
+
"learning_rate": 7.360193281118378e-05,
|
| 893 |
+
"loss": 0.06143233776092529,
|
| 894 |
+
"step": 620
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.42633015006821284,
|
| 898 |
+
"grad_norm": 0.07777975499629974,
|
| 899 |
+
"learning_rate": 7.35740671155707e-05,
|
| 900 |
+
"loss": 0.053598570823669436,
|
| 901 |
+
"step": 625
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.4297407912687585,
|
| 905 |
+
"grad_norm": 0.9314269423484802,
|
| 906 |
+
"learning_rate": 7.354593183022422e-05,
|
| 907 |
+
"loss": 0.05946495532989502,
|
| 908 |
+
"step": 630
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.4331514324693042,
|
| 912 |
+
"grad_norm": 0.5312000513076782,
|
| 913 |
+
"learning_rate": 7.351752716540575e-05,
|
| 914 |
+
"loss": 0.030707958340644836,
|
| 915 |
+
"step": 635
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.43656207366984995,
|
| 919 |
+
"grad_norm": 0.855117917060852,
|
| 920 |
+
"learning_rate": 7.348885333338984e-05,
|
| 921 |
+
"loss": 0.09321808815002441,
|
| 922 |
+
"step": 640
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.43997271487039563,
|
| 926 |
+
"grad_norm": 0.12914253771305084,
|
| 927 |
+
"learning_rate": 7.345991054846257e-05,
|
| 928 |
+
"loss": 0.010356919467449188,
|
| 929 |
+
"step": 645
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.4433833560709413,
|
| 933 |
+
"grad_norm": 0.4129096567630768,
|
| 934 |
+
"learning_rate": 7.343069902691999e-05,
|
| 935 |
+
"loss": 0.054264682531356814,
|
| 936 |
+
"step": 650
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.44679399727148705,
|
| 940 |
+
"grad_norm": 1.8499324321746826,
|
| 941 |
+
"learning_rate": 7.340121898706643e-05,
|
| 942 |
+
"loss": 0.050659948587417604,
|
| 943 |
+
"step": 655
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.45020463847203274,
|
| 947 |
+
"grad_norm": 0.5490806698799133,
|
| 948 |
+
"learning_rate": 7.337147064921299e-05,
|
| 949 |
+
"loss": 0.07158003449440002,
|
| 950 |
+
"step": 660
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.4536152796725784,
|
| 954 |
+
"grad_norm": 1.1408376693725586,
|
| 955 |
+
"learning_rate": 7.334145423567575e-05,
|
| 956 |
+
"loss": 0.08845412135124206,
|
| 957 |
+
"step": 665
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.45702592087312416,
|
| 961 |
+
"grad_norm": 1.5242546796798706,
|
| 962 |
+
"learning_rate": 7.331116997077426e-05,
|
| 963 |
+
"loss": 0.07773985266685486,
|
| 964 |
+
"step": 670
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.46043656207366984,
|
| 968 |
+
"grad_norm": 0.7061560153961182,
|
| 969 |
+
"learning_rate": 7.32806180808297e-05,
|
| 970 |
+
"loss": 0.047228410840034485,
|
| 971 |
+
"step": 675
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.4638472032742155,
|
| 975 |
+
"grad_norm": 0.8088539838790894,
|
| 976 |
+
"learning_rate": 7.324979879416333e-05,
|
| 977 |
+
"loss": 0.03726888597011566,
|
| 978 |
+
"step": 680
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.46725784447476126,
|
| 982 |
+
"grad_norm": 0.5670620799064636,
|
| 983 |
+
"learning_rate": 7.321871234109472e-05,
|
| 984 |
+
"loss": 0.02899191677570343,
|
| 985 |
+
"step": 685
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.47066848567530695,
|
| 989 |
+
"grad_norm": 2.3821427822113037,
|
| 990 |
+
"learning_rate": 7.318735895394e-05,
|
| 991 |
+
"loss": 0.033483856916427614,
|
| 992 |
+
"step": 690
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.4740791268758527,
|
| 996 |
+
"grad_norm": 0.8073883652687073,
|
| 997 |
+
"learning_rate": 7.315573886701023e-05,
|
| 998 |
+
"loss": 0.05756385326385498,
|
| 999 |
+
"step": 695
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.47748976807639837,
|
| 1003 |
+
"grad_norm": 0.09120920300483704,
|
| 1004 |
+
"learning_rate": 7.31238523166095e-05,
|
| 1005 |
+
"loss": 0.0338085800409317,
|
| 1006 |
+
"step": 700
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.48090040927694405,
|
| 1010 |
+
"grad_norm": 0.33443862199783325,
|
| 1011 |
+
"learning_rate": 7.309169954103326e-05,
|
| 1012 |
+
"loss": 0.00844155102968216,
|
| 1013 |
+
"step": 705
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.4843110504774898,
|
| 1017 |
+
"grad_norm": 0.4880702793598175,
|
| 1018 |
+
"learning_rate": 7.305928078056657e-05,
|
| 1019 |
+
"loss": 0.09532383680343628,
|
| 1020 |
+
"step": 710
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.4877216916780355,
|
| 1024 |
+
"grad_norm": 0.11862733215093613,
|
| 1025 |
+
"learning_rate": 7.302659627748221e-05,
|
| 1026 |
+
"loss": 0.01845739334821701,
|
| 1027 |
+
"step": 715
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.49113233287858116,
|
| 1031 |
+
"grad_norm": 0.03655651956796646,
|
| 1032 |
+
"learning_rate": 7.299364627603892e-05,
|
| 1033 |
+
"loss": 0.030477851629257202,
|
| 1034 |
+
"step": 720
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.4945429740791269,
|
| 1038 |
+
"grad_norm": 1.481441617012024,
|
| 1039 |
+
"learning_rate": 7.29604310224796e-05,
|
| 1040 |
+
"loss": 0.07586092352867127,
|
| 1041 |
+
"step": 725
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.4979536152796726,
|
| 1045 |
+
"grad_norm": 0.8510580658912659,
|
| 1046 |
+
"learning_rate": 7.292695076502938e-05,
|
| 1047 |
+
"loss": 0.03589251637458801,
|
| 1048 |
+
"step": 730
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.49931787175989084,
|
| 1052 |
+
"eval_loss": 0.061700768768787384,
|
| 1053 |
+
"eval_runtime": 0.8886,
|
| 1054 |
+
"eval_samples_per_second": 84.399,
|
| 1055 |
+
"eval_steps_per_second": 2.251,
|
| 1056 |
+
"step": 732
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"eval_cer_subset": 0.021256301948494344,
|
| 1060 |
+
"eval_cer_subset_edit_distance": 156,
|
| 1061 |
+
"eval_cer_subset_groups": 75,
|
| 1062 |
+
"eval_cer_subset_items": 75,
|
| 1063 |
+
"eval_cer_subset_ref_chars": 7339,
|
| 1064 |
+
"step": 732
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 0.5013642564802183,
|
| 1068 |
+
"grad_norm": 0.49610504508018494,
|
| 1069 |
+
"learning_rate": 7.28932057538939e-05,
|
| 1070 |
+
"loss": 0.06440846920013428,
|
| 1071 |
+
"step": 735
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.504774897680764,
|
| 1075 |
+
"grad_norm": 0.5659550428390503,
|
| 1076 |
+
"learning_rate": 7.285919624125732e-05,
|
| 1077 |
+
"loss": 0.08426347374916077,
|
| 1078 |
+
"step": 740
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 0.5081855388813097,
|
| 1082 |
+
"grad_norm": 0.04723689705133438,
|
| 1083 |
+
"learning_rate": 7.282492248128047e-05,
|
| 1084 |
+
"loss": 0.07788341641426086,
|
| 1085 |
+
"step": 745
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 0.5115961800818554,
|
| 1089 |
+
"grad_norm": 0.720941960811615,
|
| 1090 |
+
"learning_rate": 7.2790384730099e-05,
|
| 1091 |
+
"loss": 0.03100808262825012,
|
| 1092 |
+
"step": 750
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 0.515006821282401,
|
| 1096 |
+
"grad_norm": 0.652988851070404,
|
| 1097 |
+
"learning_rate": 7.275558324582138e-05,
|
| 1098 |
+
"loss": 0.03954651951789856,
|
| 1099 |
+
"step": 755
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 0.5184174624829468,
|
| 1103 |
+
"grad_norm": 1.2214330434799194,
|
| 1104 |
+
"learning_rate": 7.272051828852705e-05,
|
| 1105 |
+
"loss": 0.019992084801197053,
|
| 1106 |
+
"step": 760
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 0.5218281036834925,
|
| 1110 |
+
"grad_norm": 1.292953372001648,
|
| 1111 |
+
"learning_rate": 7.268519012026443e-05,
|
| 1112 |
+
"loss": 0.07394988536834717,
|
| 1113 |
+
"step": 765
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.5252387448840382,
|
| 1117 |
+
"grad_norm": 1.1823278665542603,
|
| 1118 |
+
"learning_rate": 7.264959900504901e-05,
|
| 1119 |
+
"loss": 0.037449967861175534,
|
| 1120 |
+
"step": 770
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 0.5286493860845839,
|
| 1124 |
+
"grad_norm": 1.1314970254898071,
|
| 1125 |
+
"learning_rate": 7.261374520886128e-05,
|
| 1126 |
+
"loss": 0.04381995797157288,
|
| 1127 |
+
"step": 775
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 0.5320600272851296,
|
| 1131 |
+
"grad_norm": 0.02543286792933941,
|
| 1132 |
+
"learning_rate": 7.257762899964486e-05,
|
| 1133 |
+
"loss": 0.07130052447319031,
|
| 1134 |
+
"step": 780
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 0.5354706684856753,
|
| 1138 |
+
"grad_norm": 0.37440457940101624,
|
| 1139 |
+
"learning_rate": 7.25412506473044e-05,
|
| 1140 |
+
"loss": 0.050841158628463744,
|
| 1141 |
+
"step": 785
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 0.538881309686221,
|
| 1145 |
+
"grad_norm": 0.2532084882259369,
|
| 1146 |
+
"learning_rate": 7.250461042370365e-05,
|
| 1147 |
+
"loss": 0.03486245274543762,
|
| 1148 |
+
"step": 790
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 0.5422919508867667,
|
| 1152 |
+
"grad_norm": 1.0150209665298462,
|
| 1153 |
+
"learning_rate": 7.246770860266333e-05,
|
| 1154 |
+
"loss": 0.050749993324279784,
|
| 1155 |
+
"step": 795
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 0.5457025920873124,
|
| 1159 |
+
"grad_norm": 1.108716607093811,
|
| 1160 |
+
"learning_rate": 7.24305454599592e-05,
|
| 1161 |
+
"loss": 0.03166365325450897,
|
| 1162 |
+
"step": 800
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 0.5491132332878581,
|
| 1166 |
+
"grad_norm": 0.16657976806163788,
|
| 1167 |
+
"learning_rate": 7.239312127331989e-05,
|
| 1168 |
+
"loss": 0.05016656517982483,
|
| 1169 |
+
"step": 805
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 0.5525238744884038,
|
| 1173 |
+
"grad_norm": 0.005627671722322702,
|
| 1174 |
+
"learning_rate": 7.235543632242488e-05,
|
| 1175 |
+
"loss": 0.021701858937740327,
|
| 1176 |
+
"step": 810
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 0.5559345156889495,
|
| 1180 |
+
"grad_norm": 1.8796381950378418,
|
| 1181 |
+
"learning_rate": 7.231749088890241e-05,
|
| 1182 |
+
"loss": 0.061094462871551514,
|
| 1183 |
+
"step": 815
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 0.5593451568894953,
|
| 1187 |
+
"grad_norm": 0.020010950043797493,
|
| 1188 |
+
"learning_rate": 7.227928525632737e-05,
|
| 1189 |
+
"loss": 0.0238655224442482,
|
| 1190 |
+
"step": 820
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 0.562755798090041,
|
| 1194 |
+
"grad_norm": 1.9777793884277344,
|
| 1195 |
+
"learning_rate": 7.224081971021914e-05,
|
| 1196 |
+
"loss": 0.041665592789649965,
|
| 1197 |
+
"step": 825
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 0.5661664392905866,
|
| 1201 |
+
"grad_norm": 0.06644955277442932,
|
| 1202 |
+
"learning_rate": 7.220209453803954e-05,
|
| 1203 |
+
"loss": 0.016651667654514313,
|
| 1204 |
+
"step": 830
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 0.5695770804911323,
|
| 1208 |
+
"grad_norm": 0.8203716278076172,
|
| 1209 |
+
"learning_rate": 7.216311002919064e-05,
|
| 1210 |
+
"loss": 0.03519523441791535,
|
| 1211 |
+
"step": 835
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 0.572987721691678,
|
| 1215 |
+
"grad_norm": 1.957996129989624,
|
| 1216 |
+
"learning_rate": 7.212386647501254e-05,
|
| 1217 |
+
"loss": 0.03704521656036377,
|
| 1218 |
+
"step": 840
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 0.5763983628922238,
|
| 1222 |
+
"grad_norm": 0.2386065572500229,
|
| 1223 |
+
"learning_rate": 7.208436416878125e-05,
|
| 1224 |
+
"loss": 0.02845575213432312,
|
| 1225 |
+
"step": 845
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 0.5798090040927695,
|
| 1229 |
+
"grad_norm": 0.9101418256759644,
|
| 1230 |
+
"learning_rate": 7.204460340570658e-05,
|
| 1231 |
+
"loss": 0.01103741154074669,
|
| 1232 |
+
"step": 850
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 0.5832196452933152,
|
| 1236 |
+
"grad_norm": 0.22701004147529602,
|
| 1237 |
+
"learning_rate": 7.200458448292972e-05,
|
| 1238 |
+
"loss": 0.06184377670288086,
|
| 1239 |
+
"step": 855
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 0.5866302864938608,
|
| 1243 |
+
"grad_norm": 2.3091611862182617,
|
| 1244 |
+
"learning_rate": 7.196430769952126e-05,
|
| 1245 |
+
"loss": 0.0492431253194809,
|
| 1246 |
+
"step": 860
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 0.5900409276944065,
|
| 1250 |
+
"grad_norm": 0.6630973815917969,
|
| 1251 |
+
"learning_rate": 7.192377335647876e-05,
|
| 1252 |
+
"loss": 0.027876955270767213,
|
| 1253 |
+
"step": 865
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 0.5934515688949522,
|
| 1257 |
+
"grad_norm": 1.7400578260421753,
|
| 1258 |
+
"learning_rate": 7.188298175672464e-05,
|
| 1259 |
+
"loss": 0.023742210865020753,
|
| 1260 |
+
"step": 870
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 0.596862210095498,
|
| 1264 |
+
"grad_norm": 0.7121092081069946,
|
| 1265 |
+
"learning_rate": 7.184193320510379e-05,
|
| 1266 |
+
"loss": 0.02125793993473053,
|
| 1267 |
+
"step": 875
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 0.6002728512960437,
|
| 1271 |
+
"grad_norm": 0.429611474275589,
|
| 1272 |
+
"learning_rate": 7.180062800838143e-05,
|
| 1273 |
+
"loss": 0.06682519316673279,
|
| 1274 |
+
"step": 880
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 0.6036834924965894,
|
| 1278 |
+
"grad_norm": 0.018405891954898834,
|
| 1279 |
+
"learning_rate": 7.17590664752407e-05,
|
| 1280 |
+
"loss": 0.022519922256469725,
|
| 1281 |
+
"step": 885
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 0.607094133697135,
|
| 1285 |
+
"grad_norm": 0.9797202348709106,
|
| 1286 |
+
"learning_rate": 7.171724891628046e-05,
|
| 1287 |
+
"loss": 0.10513803958892823,
|
| 1288 |
+
"step": 890
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 0.6105047748976807,
|
| 1292 |
+
"grad_norm": 0.11931606382131577,
|
| 1293 |
+
"learning_rate": 7.167517564401282e-05,
|
| 1294 |
+
"loss": 0.055521953105926516,
|
| 1295 |
+
"step": 895
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 0.6139154160982264,
|
| 1299 |
+
"grad_norm": 0.04398813843727112,
|
| 1300 |
+
"learning_rate": 7.163284697286097e-05,
|
| 1301 |
+
"loss": 0.018342888355255126,
|
| 1302 |
+
"step": 900
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 0.6173260572987722,
|
| 1306 |
+
"grad_norm": 0.11505168676376343,
|
| 1307 |
+
"learning_rate": 7.15902632191567e-05,
|
| 1308 |
+
"loss": 0.026946401596069335,
|
| 1309 |
+
"step": 905
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 0.6207366984993179,
|
| 1313 |
+
"grad_norm": 0.3042922019958496,
|
| 1314 |
+
"learning_rate": 7.154742470113816e-05,
|
| 1315 |
+
"loss": 0.02314314842224121,
|
| 1316 |
+
"step": 910
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 0.6241473396998636,
|
| 1320 |
+
"grad_norm": 0.09922346472740173,
|
| 1321 |
+
"learning_rate": 7.150433173894733e-05,
|
| 1322 |
+
"loss": 0.06378543972969056,
|
| 1323 |
+
"step": 915
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 0.6275579809004093,
|
| 1327 |
+
"grad_norm": 0.6513009667396545,
|
| 1328 |
+
"learning_rate": 7.146098465462776e-05,
|
| 1329 |
+
"loss": 0.036993378400802614,
|
| 1330 |
+
"step": 920
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 0.630968622100955,
|
| 1334 |
+
"grad_norm": 1.131602168083191,
|
| 1335 |
+
"learning_rate": 7.14173837721221e-05,
|
| 1336 |
+
"loss": 0.09491010308265686,
|
| 1337 |
+
"step": 925
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 0.6343792633015006,
|
| 1341 |
+
"grad_norm": 0.1672857254743576,
|
| 1342 |
+
"learning_rate": 7.137352941726969e-05,
|
| 1343 |
+
"loss": 0.03719751834869385,
|
| 1344 |
+
"step": 930
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 0.6377899045020464,
|
| 1348 |
+
"grad_norm": 0.7450887560844421,
|
| 1349 |
+
"learning_rate": 7.132942191780414e-05,
|
| 1350 |
+
"loss": 0.028598809242248537,
|
| 1351 |
+
"step": 935
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 0.6412005457025921,
|
| 1355 |
+
"grad_norm": 2.3537657260894775,
|
| 1356 |
+
"learning_rate": 7.128506160335084e-05,
|
| 1357 |
+
"loss": 0.06678735613822936,
|
| 1358 |
+
"step": 940
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 0.6446111869031378,
|
| 1362 |
+
"grad_norm": 0.014428210444748402,
|
| 1363 |
+
"learning_rate": 7.124044880542455e-05,
|
| 1364 |
+
"loss": 0.018354634940624236,
|
| 1365 |
+
"step": 945
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 0.6480218281036835,
|
| 1369 |
+
"grad_norm": 2.9239041805267334,
|
| 1370 |
+
"learning_rate": 7.119558385742688e-05,
|
| 1371 |
+
"loss": 0.08242651224136352,
|
| 1372 |
+
"step": 950
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 0.6514324693042292,
|
| 1376 |
+
"grad_norm": 0.39032718539237976,
|
| 1377 |
+
"learning_rate": 7.115046709464383e-05,
|
| 1378 |
+
"loss": 0.023772728443145753,
|
| 1379 |
+
"step": 955
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 0.654843110504775,
|
| 1383 |
+
"grad_norm": 0.3000798523426056,
|
| 1384 |
+
"learning_rate": 7.110509885424326e-05,
|
| 1385 |
+
"loss": 0.03464276790618896,
|
| 1386 |
+
"step": 960
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 0.6582537517053206,
|
| 1390 |
+
"grad_norm": 0.3980049192905426,
|
| 1391 |
+
"learning_rate": 7.105947947527238e-05,
|
| 1392 |
+
"loss": 0.08540127277374268,
|
| 1393 |
+
"step": 965
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 0.6616643929058663,
|
| 1397 |
+
"grad_norm": 0.9492272734642029,
|
| 1398 |
+
"learning_rate": 7.10136092986552e-05,
|
| 1399 |
+
"loss": 0.02300785481929779,
|
| 1400 |
+
"step": 970
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 0.665075034106412,
|
| 1404 |
+
"grad_norm": 1.9585710763931274,
|
| 1405 |
+
"learning_rate": 7.096748866719005e-05,
|
| 1406 |
+
"loss": 0.034704044461250305,
|
| 1407 |
+
"step": 975
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 0.6684856753069577,
|
| 1411 |
+
"grad_norm": 1.142238974571228,
|
| 1412 |
+
"learning_rate": 7.092111792554689e-05,
|
| 1413 |
+
"loss": 0.01860647052526474,
|
| 1414 |
+
"step": 980
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 0.6718963165075034,
|
| 1418 |
+
"grad_norm": 0.8443534970283508,
|
| 1419 |
+
"learning_rate": 7.087449742026488e-05,
|
| 1420 |
+
"loss": 0.03302992284297943,
|
| 1421 |
+
"step": 985
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 0.6753069577080492,
|
| 1425 |
+
"grad_norm": 1.0402863025665283,
|
| 1426 |
+
"learning_rate": 7.082762749974968e-05,
|
| 1427 |
+
"loss": 0.03963000178337097,
|
| 1428 |
+
"step": 990
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 0.6787175989085948,
|
| 1432 |
+
"grad_norm": 0.11959892511367798,
|
| 1433 |
+
"learning_rate": 7.078050851427089e-05,
|
| 1434 |
+
"loss": 0.0187692254781723,
|
| 1435 |
+
"step": 995
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 0.6821282401091405,
|
| 1439 |
+
"grad_norm": 1.495011329650879,
|
| 1440 |
+
"learning_rate": 7.073314081595945e-05,
|
| 1441 |
+
"loss": 0.050608736276626584,
|
| 1442 |
+
"step": 1000
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.6855388813096862,
|
| 1446 |
+
"grad_norm": 0.2534504234790802,
|
| 1447 |
+
"learning_rate": 7.068552475880499e-05,
|
| 1448 |
+
"loss": 0.0076520174741745,
|
| 1449 |
+
"step": 1005
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.6889495225102319,
|
| 1453 |
+
"grad_norm": 0.17387191951274872,
|
| 1454 |
+
"learning_rate": 7.063766069865314e-05,
|
| 1455 |
+
"loss": 0.028283193707466125,
|
| 1456 |
+
"step": 1010
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.6923601637107776,
|
| 1460 |
+
"grad_norm": 0.07424458116292953,
|
| 1461 |
+
"learning_rate": 7.058954899320297e-05,
|
| 1462 |
+
"loss": 0.03078552782535553,
|
| 1463 |
+
"step": 1015
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.6957708049113234,
|
| 1467 |
+
"grad_norm": 0.5854848027229309,
|
| 1468 |
+
"learning_rate": 7.05411900020042e-05,
|
| 1469 |
+
"loss": 0.02033105492591858,
|
| 1470 |
+
"step": 1020
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 0.699181446111869,
|
| 1474 |
+
"grad_norm": 0.09108871966600418,
|
| 1475 |
+
"learning_rate": 7.049258408645463e-05,
|
| 1476 |
+
"loss": 0.0510578989982605,
|
| 1477 |
+
"step": 1025
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 0.7025920873124147,
|
| 1481 |
+
"grad_norm": 0.2851751148700714,
|
| 1482 |
+
"learning_rate": 7.044373160979734e-05,
|
| 1483 |
+
"loss": 0.10413439273834228,
|
| 1484 |
+
"step": 1030
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 0.7060027285129604,
|
| 1488 |
+
"grad_norm": 0.8032590746879578,
|
| 1489 |
+
"learning_rate": 7.039463293711804e-05,
|
| 1490 |
+
"loss": 0.05853385329246521,
|
| 1491 |
+
"step": 1035
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 0.7094133697135061,
|
| 1495 |
+
"grad_norm": 0.1301775723695755,
|
| 1496 |
+
"learning_rate": 7.03452884353423e-05,
|
| 1497 |
+
"loss": 0.051472657918930055,
|
| 1498 |
+
"step": 1040
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 0.7128240109140518,
|
| 1502 |
+
"grad_norm": 0.46156957745552063,
|
| 1503 |
+
"learning_rate": 7.029569847323287e-05,
|
| 1504 |
+
"loss": 0.034115567803382874,
|
| 1505 |
+
"step": 1045
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 0.7162346521145976,
|
| 1509 |
+
"grad_norm": 1.081560730934143,
|
| 1510 |
+
"learning_rate": 7.02458634213868e-05,
|
| 1511 |
+
"loss": 0.059652507305145264,
|
| 1512 |
+
"step": 1050
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 0.7196452933151433,
|
| 1516 |
+
"grad_norm": 0.721208930015564,
|
| 1517 |
+
"learning_rate": 7.019578365223286e-05,
|
| 1518 |
+
"loss": 0.061070340871810916,
|
| 1519 |
+
"step": 1055
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 0.723055934515689,
|
| 1523 |
+
"grad_norm": 0.5738947987556458,
|
| 1524 |
+
"learning_rate": 7.014545954002855e-05,
|
| 1525 |
+
"loss": 0.03556577265262604,
|
| 1526 |
+
"step": 1060
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 0.7264665757162346,
|
| 1530 |
+
"grad_norm": 0.15053460001945496,
|
| 1531 |
+
"learning_rate": 7.009489146085744e-05,
|
| 1532 |
+
"loss": 0.03284372091293335,
|
| 1533 |
+
"step": 1065
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 0.7298772169167803,
|
| 1537 |
+
"grad_norm": 0.4496553838253021,
|
| 1538 |
+
"learning_rate": 7.004407979262635e-05,
|
| 1539 |
+
"loss": 0.07945018410682678,
|
| 1540 |
+
"step": 1070
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 0.7332878581173261,
|
| 1544 |
+
"grad_norm": 1.1821213960647583,
|
| 1545 |
+
"learning_rate": 6.999302491506245e-05,
|
| 1546 |
+
"loss": 0.033741748332977294,
|
| 1547 |
+
"step": 1075
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 0.7366984993178718,
|
| 1551 |
+
"grad_norm": 0.2809429168701172,
|
| 1552 |
+
"learning_rate": 6.994172720971047e-05,
|
| 1553 |
+
"loss": 0.023005199432373048,
|
| 1554 |
+
"step": 1080
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 0.7401091405184175,
|
| 1558 |
+
"grad_norm": 0.14925819635391235,
|
| 1559 |
+
"learning_rate": 6.989018705992991e-05,
|
| 1560 |
+
"loss": 0.01791207939386368,
|
| 1561 |
+
"step": 1085
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 0.7435197817189632,
|
| 1565 |
+
"grad_norm": 1.1947131156921387,
|
| 1566 |
+
"learning_rate": 6.983840485089203e-05,
|
| 1567 |
+
"loss": 0.03395574688911438,
|
| 1568 |
+
"step": 1090
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 0.7469304229195088,
|
| 1572 |
+
"grad_norm": 1.336547613143921,
|
| 1573 |
+
"learning_rate": 6.978638096957712e-05,
|
| 1574 |
+
"loss": 0.02712726593017578,
|
| 1575 |
+
"step": 1095
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 0.7489768076398363,
|
| 1579 |
+
"eval_loss": 0.05635881423950195,
|
| 1580 |
+
"eval_runtime": 0.8951,
|
| 1581 |
+
"eval_samples_per_second": 83.789,
|
| 1582 |
+
"eval_steps_per_second": 2.234,
|
| 1583 |
+
"step": 1098
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"eval_cer_subset": 0.023981468864967978,
|
| 1587 |
+
"eval_cer_subset_edit_distance": 176,
|
| 1588 |
+
"eval_cer_subset_groups": 75,
|
| 1589 |
+
"eval_cer_subset_items": 75,
|
| 1590 |
+
"eval_cer_subset_ref_chars": 7339,
|
| 1591 |
+
"step": 1098
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.7503410641200545,
|
| 1595 |
+
"grad_norm": 0.015995435416698456,
|
| 1596 |
+
"learning_rate": 6.973411580477149e-05,
|
| 1597 |
+
"loss": 0.018527305126190184,
|
| 1598 |
+
"step": 1100
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.7537517053206003,
|
| 1602 |
+
"grad_norm": 2.3465819358825684,
|
| 1603 |
+
"learning_rate": 6.968160974706465e-05,
|
| 1604 |
+
"loss": 0.03113352656364441,
|
| 1605 |
+
"step": 1105
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.757162346521146,
|
| 1609 |
+
"grad_norm": 8.048991203308105,
|
| 1610 |
+
"learning_rate": 6.962886318884633e-05,
|
| 1611 |
+
"loss": 0.01905607581138611,
|
| 1612 |
+
"step": 1110
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.7605729877216917,
|
| 1616 |
+
"grad_norm": 2.0705132484436035,
|
| 1617 |
+
"learning_rate": 6.957587652430363e-05,
|
| 1618 |
+
"loss": 0.08121066093444824,
|
| 1619 |
+
"step": 1115
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.7639836289222374,
|
| 1623 |
+
"grad_norm": 0.6205260157585144,
|
| 1624 |
+
"learning_rate": 6.952265014941796e-05,
|
| 1625 |
+
"loss": 0.030836066603660582,
|
| 1626 |
+
"step": 1120
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.767394270122783,
|
| 1630 |
+
"grad_norm": 0.02030811458826065,
|
| 1631 |
+
"learning_rate": 6.946918446196215e-05,
|
| 1632 |
+
"loss": 0.0715795874595642,
|
| 1633 |
+
"step": 1125
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.7708049113233287,
|
| 1637 |
+
"grad_norm": 0.20006906986236572,
|
| 1638 |
+
"learning_rate": 6.94154798614975e-05,
|
| 1639 |
+
"loss": 0.09267728328704834,
|
| 1640 |
+
"step": 1130
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.7742155525238745,
|
| 1644 |
+
"grad_norm": 1.3217955827713013,
|
| 1645 |
+
"learning_rate": 6.936153674937074e-05,
|
| 1646 |
+
"loss": 0.057087546586990355,
|
| 1647 |
+
"step": 1135
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.7776261937244202,
|
| 1651 |
+
"grad_norm": 0.97421795129776,
|
| 1652 |
+
"learning_rate": 6.930735552871105e-05,
|
| 1653 |
+
"loss": 0.02381356656551361,
|
| 1654 |
+
"step": 1140
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.7810368349249659,
|
| 1658 |
+
"grad_norm": 1.1994248628616333,
|
| 1659 |
+
"learning_rate": 6.925293660442705e-05,
|
| 1660 |
+
"loss": 0.03957775831222534,
|
| 1661 |
+
"step": 1145
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.7844474761255116,
|
| 1665 |
+
"grad_norm": 1.0654077529907227,
|
| 1666 |
+
"learning_rate": 6.919828038320378e-05,
|
| 1667 |
+
"loss": 0.04088171124458313,
|
| 1668 |
+
"step": 1150
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.7878581173260573,
|
| 1672 |
+
"grad_norm": 0.6241940855979919,
|
| 1673 |
+
"learning_rate": 6.914338727349963e-05,
|
| 1674 |
+
"loss": 0.0698228895664215,
|
| 1675 |
+
"step": 1155
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.791268758526603,
|
| 1679 |
+
"grad_norm": 1.4655344486236572,
|
| 1680 |
+
"learning_rate": 6.908825768554337e-05,
|
| 1681 |
+
"loss": 0.0430897206068039,
|
| 1682 |
+
"step": 1160
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.7946793997271487,
|
| 1686 |
+
"grad_norm": 0.3493589162826538,
|
| 1687 |
+
"learning_rate": 6.903289203133096e-05,
|
| 1688 |
+
"loss": 0.05850836634635925,
|
| 1689 |
+
"step": 1165
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.7980900409276944,
|
| 1693 |
+
"grad_norm": 1.1164323091506958,
|
| 1694 |
+
"learning_rate": 6.897729072462257e-05,
|
| 1695 |
+
"loss": 0.02702825963497162,
|
| 1696 |
+
"step": 1170
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.8015006821282401,
|
| 1700 |
+
"grad_norm": 0.056947700679302216,
|
| 1701 |
+
"learning_rate": 6.892145418093947e-05,
|
| 1702 |
+
"loss": 0.11043190956115723,
|
| 1703 |
+
"step": 1175
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.8049113233287858,
|
| 1707 |
+
"grad_norm": 1.2450393438339233,
|
| 1708 |
+
"learning_rate": 6.886538281756085e-05,
|
| 1709 |
+
"loss": 0.06005706787109375,
|
| 1710 |
+
"step": 1180
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.8083219645293315,
|
| 1714 |
+
"grad_norm": 0.10885969549417496,
|
| 1715 |
+
"learning_rate": 6.880907705352083e-05,
|
| 1716 |
+
"loss": 0.022018623352050782,
|
| 1717 |
+
"step": 1185
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.8117326057298773,
|
| 1721 |
+
"grad_norm": 0.17044247686862946,
|
| 1722 |
+
"learning_rate": 6.875253730960522e-05,
|
| 1723 |
+
"loss": 0.024727573990821837,
|
| 1724 |
+
"step": 1190
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.815143246930423,
|
| 1728 |
+
"grad_norm": 0.22665634751319885,
|
| 1729 |
+
"learning_rate": 6.869576400834843e-05,
|
| 1730 |
+
"loss": 0.014500510692596436,
|
| 1731 |
+
"step": 1195
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.8185538881309686,
|
| 1735 |
+
"grad_norm": 0.6808337569236755,
|
| 1736 |
+
"learning_rate": 6.863875757403028e-05,
|
| 1737 |
+
"loss": 0.040313297510147096,
|
| 1738 |
+
"step": 1200
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.8219645293315143,
|
| 1742 |
+
"grad_norm": 0.37714090943336487,
|
| 1743 |
+
"learning_rate": 6.858151843267289e-05,
|
| 1744 |
+
"loss": 0.02225676029920578,
|
| 1745 |
+
"step": 1205
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.82537517053206,
|
| 1749 |
+
"grad_norm": 0.28732752799987793,
|
| 1750 |
+
"learning_rate": 6.852404701203738e-05,
|
| 1751 |
+
"loss": 0.017132116854190825,
|
| 1752 |
+
"step": 1210
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.8287858117326057,
|
| 1756 |
+
"grad_norm": 0.011728805489838123,
|
| 1757 |
+
"learning_rate": 6.846634374162082e-05,
|
| 1758 |
+
"loss": 0.043106210231781,
|
| 1759 |
+
"step": 1215
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.8321964529331515,
|
| 1763 |
+
"grad_norm": 0.06264204531908035,
|
| 1764 |
+
"learning_rate": 6.84084090526529e-05,
|
| 1765 |
+
"loss": 0.09258266687393188,
|
| 1766 |
+
"step": 1220
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.8356070941336972,
|
| 1770 |
+
"grad_norm": 0.024779995903372765,
|
| 1771 |
+
"learning_rate": 6.835024337809278e-05,
|
| 1772 |
+
"loss": 0.08440889716148377,
|
| 1773 |
+
"step": 1225
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.8390177353342428,
|
| 1777 |
+
"grad_norm": 0.3760814964771271,
|
| 1778 |
+
"learning_rate": 6.829184715262579e-05,
|
| 1779 |
+
"loss": 0.046157938241958615,
|
| 1780 |
+
"step": 1230
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.8424283765347885,
|
| 1784 |
+
"grad_norm": 0.41763243079185486,
|
| 1785 |
+
"learning_rate": 6.823322081266027e-05,
|
| 1786 |
+
"loss": 0.007576120644807815,
|
| 1787 |
+
"step": 1235
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.8458390177353342,
|
| 1791 |
+
"grad_norm": 0.20451563596725464,
|
| 1792 |
+
"learning_rate": 6.817436479632423e-05,
|
| 1793 |
+
"loss": 0.00685272142291069,
|
| 1794 |
+
"step": 1240
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.8492496589358799,
|
| 1798 |
+
"grad_norm": 0.19664883613586426,
|
| 1799 |
+
"learning_rate": 6.811527954346208e-05,
|
| 1800 |
+
"loss": 0.029371869564056397,
|
| 1801 |
+
"step": 1245
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.8526603001364257,
|
| 1805 |
+
"grad_norm": 0.18445859849452972,
|
| 1806 |
+
"learning_rate": 6.805596549563143e-05,
|
| 1807 |
+
"loss": 0.013169947266578674,
|
| 1808 |
+
"step": 1250
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.8560709413369714,
|
| 1812 |
+
"grad_norm": 0.25306227803230286,
|
| 1813 |
+
"learning_rate": 6.799642309609968e-05,
|
| 1814 |
+
"loss": 0.04840644598007202,
|
| 1815 |
+
"step": 1255
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.859481582537517,
|
| 1819 |
+
"grad_norm": 0.013680736534297466,
|
| 1820 |
+
"learning_rate": 6.793665278984076e-05,
|
| 1821 |
+
"loss": 0.005744677782058716,
|
| 1822 |
+
"step": 1260
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.8628922237380627,
|
| 1826 |
+
"grad_norm": 0.896000862121582,
|
| 1827 |
+
"learning_rate": 6.78766550235318e-05,
|
| 1828 |
+
"loss": 0.06524677276611328,
|
| 1829 |
+
"step": 1265
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.8663028649386084,
|
| 1833 |
+
"grad_norm": 0.028516558930277824,
|
| 1834 |
+
"learning_rate": 6.781643024554982e-05,
|
| 1835 |
+
"loss": 0.011343669146299362,
|
| 1836 |
+
"step": 1270
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.8697135061391542,
|
| 1840 |
+
"grad_norm": 0.8379983305931091,
|
| 1841 |
+
"learning_rate": 6.775597890596829e-05,
|
| 1842 |
+
"loss": 0.022122929990291595,
|
| 1843 |
+
"step": 1275
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.8731241473396999,
|
| 1847 |
+
"grad_norm": 1.4136202335357666,
|
| 1848 |
+
"learning_rate": 6.769530145655389e-05,
|
| 1849 |
+
"loss": 0.0679425597190857,
|
| 1850 |
+
"step": 1280
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.8765347885402456,
|
| 1854 |
+
"grad_norm": 1.3402701616287231,
|
| 1855 |
+
"learning_rate": 6.763439835076303e-05,
|
| 1856 |
+
"loss": 0.04459039568901062,
|
| 1857 |
+
"step": 1285
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.8799454297407913,
|
| 1861 |
+
"grad_norm": 1.0337740182876587,
|
| 1862 |
+
"learning_rate": 6.757327004373852e-05,
|
| 1863 |
+
"loss": 0.03138587772846222,
|
| 1864 |
+
"step": 1290
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.883356070941337,
|
| 1868 |
+
"grad_norm": 0.0886356458067894,
|
| 1869 |
+
"learning_rate": 6.751191699230613e-05,
|
| 1870 |
+
"loss": 0.008893608301877975,
|
| 1871 |
+
"step": 1295
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.8867667121418826,
|
| 1875 |
+
"grad_norm": 0.2752978801727295,
|
| 1876 |
+
"learning_rate": 6.745033965497122e-05,
|
| 1877 |
+
"loss": 0.036550650000572206,
|
| 1878 |
+
"step": 1300
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 0.8901773533424284,
|
| 1882 |
+
"grad_norm": 0.17057837545871735,
|
| 1883 |
+
"learning_rate": 6.73885384919153e-05,
|
| 1884 |
+
"loss": 0.34759960174560545,
|
| 1885 |
+
"step": 1305
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.8935879945429741,
|
| 1889 |
+
"grad_norm": 0.9223344326019287,
|
| 1890 |
+
"learning_rate": 6.732651396499253e-05,
|
| 1891 |
+
"loss": 0.017408999800682067,
|
| 1892 |
+
"step": 1310
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.8969986357435198,
|
| 1896 |
+
"grad_norm": 0.3093169033527374,
|
| 1897 |
+
"learning_rate": 6.726426653772635e-05,
|
| 1898 |
+
"loss": 0.05584460496902466,
|
| 1899 |
+
"step": 1315
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.9004092769440655,
|
| 1903 |
+
"grad_norm": 1.0157201290130615,
|
| 1904 |
+
"learning_rate": 6.7201796675306e-05,
|
| 1905 |
+
"loss": 0.023202185332775117,
|
| 1906 |
+
"step": 1320
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.9038199181446112,
|
| 1910 |
+
"grad_norm": 0.9780434370040894,
|
| 1911 |
+
"learning_rate": 6.713910484458302e-05,
|
| 1912 |
+
"loss": 0.029402348399162292,
|
| 1913 |
+
"step": 1325
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.9072305593451568,
|
| 1917 |
+
"grad_norm": 0.07956309616565704,
|
| 1918 |
+
"learning_rate": 6.707619151406774e-05,
|
| 1919 |
+
"loss": 0.02493150979280472,
|
| 1920 |
+
"step": 1330
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.9106412005457026,
|
| 1924 |
+
"grad_norm": 0.18366064131259918,
|
| 1925 |
+
"learning_rate": 6.701305715392586e-05,
|
| 1926 |
+
"loss": 0.06721556782722474,
|
| 1927 |
+
"step": 1335
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.9140518417462483,
|
| 1931 |
+
"grad_norm": 0.8265342116355896,
|
| 1932 |
+
"learning_rate": 6.694970223597483e-05,
|
| 1933 |
+
"loss": 0.03872359693050385,
|
| 1934 |
+
"step": 1340
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.917462482946794,
|
| 1938 |
+
"grad_norm": 1.9715158939361572,
|
| 1939 |
+
"learning_rate": 6.688612723368042e-05,
|
| 1940 |
+
"loss": 0.05604517459869385,
|
| 1941 |
+
"step": 1345
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.9208731241473397,
|
| 1945 |
+
"grad_norm": 0.06577733904123306,
|
| 1946 |
+
"learning_rate": 6.682233262215312e-05,
|
| 1947 |
+
"loss": 0.04941270649433136,
|
| 1948 |
+
"step": 1350
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 0.9242837653478854,
|
| 1952 |
+
"grad_norm": 0.2798021733760834,
|
| 1953 |
+
"learning_rate": 6.67583188781446e-05,
|
| 1954 |
+
"loss": 0.011715996265411376,
|
| 1955 |
+
"step": 1355
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.927694406548431,
|
| 1959 |
+
"grad_norm": 0.7599299550056458,
|
| 1960 |
+
"learning_rate": 6.669408648004423e-05,
|
| 1961 |
+
"loss": 0.030529171228408813,
|
| 1962 |
+
"step": 1360
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.9311050477489768,
|
| 1966 |
+
"grad_norm": 0.3893057405948639,
|
| 1967 |
+
"learning_rate": 6.662963590787532e-05,
|
| 1968 |
+
"loss": 0.06623916625976563,
|
| 1969 |
+
"step": 1365
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.9345156889495225,
|
| 1973 |
+
"grad_norm": 0.3796108365058899,
|
| 1974 |
+
"learning_rate": 6.656496764329171e-05,
|
| 1975 |
+
"loss": 0.02021588236093521,
|
| 1976 |
+
"step": 1370
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.9379263301500682,
|
| 1980 |
+
"grad_norm": 0.9708864688873291,
|
| 1981 |
+
"learning_rate": 6.65000821695741e-05,
|
| 1982 |
+
"loss": 0.05283964872360229,
|
| 1983 |
+
"step": 1375
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.9413369713506139,
|
| 1987 |
+
"grad_norm": 1.2553836107254028,
|
| 1988 |
+
"learning_rate": 6.643497997162645e-05,
|
| 1989 |
+
"loss": 0.11128103733062744,
|
| 1990 |
+
"step": 1380
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.9447476125511596,
|
| 1994 |
+
"grad_norm": 1.7390260696411133,
|
| 1995 |
+
"learning_rate": 6.636966153597231e-05,
|
| 1996 |
+
"loss": 0.051687347888946536,
|
| 1997 |
+
"step": 1385
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.9481582537517054,
|
| 2001 |
+
"grad_norm": 0.575423538684845,
|
| 2002 |
+
"learning_rate": 6.630412735075128e-05,
|
| 2003 |
+
"loss": 0.03732641041278839,
|
| 2004 |
+
"step": 1390
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.951568894952251,
|
| 2008 |
+
"grad_norm": 0.8504135608673096,
|
| 2009 |
+
"learning_rate": 6.623837790571525e-05,
|
| 2010 |
+
"loss": 0.038179832696914676,
|
| 2011 |
+
"step": 1395
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.9549795361527967,
|
| 2015 |
+
"grad_norm": 0.3777940273284912,
|
| 2016 |
+
"learning_rate": 6.617241369222483e-05,
|
| 2017 |
+
"loss": 0.01817839443683624,
|
| 2018 |
+
"step": 1400
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.9583901773533424,
|
| 2022 |
+
"grad_norm": 1.1219260692596436,
|
| 2023 |
+
"learning_rate": 6.610623520324567e-05,
|
| 2024 |
+
"loss": 0.0864151120185852,
|
| 2025 |
+
"step": 1405
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.9618008185538881,
|
| 2029 |
+
"grad_norm": 0.2320811152458191,
|
| 2030 |
+
"learning_rate": 6.603984293334466e-05,
|
| 2031 |
+
"loss": 0.0041168566793203356,
|
| 2032 |
+
"step": 1410
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.9652114597544338,
|
| 2036 |
+
"grad_norm": 0.5541130304336548,
|
| 2037 |
+
"learning_rate": 6.597323737868642e-05,
|
| 2038 |
+
"loss": 0.06572380065917968,
|
| 2039 |
+
"step": 1415
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.9686221009549796,
|
| 2043 |
+
"grad_norm": 0.1585462987422943,
|
| 2044 |
+
"learning_rate": 6.590641903702944e-05,
|
| 2045 |
+
"loss": 0.03849715292453766,
|
| 2046 |
+
"step": 1420
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.9720327421555253,
|
| 2050 |
+
"grad_norm": 1.7849252223968506,
|
| 2051 |
+
"learning_rate": 6.583938840772245e-05,
|
| 2052 |
+
"loss": 0.10304104089736939,
|
| 2053 |
+
"step": 1425
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.975443383356071,
|
| 2057 |
+
"grad_norm": 2.1307897567749023,
|
| 2058 |
+
"learning_rate": 6.57721459917006e-05,
|
| 2059 |
+
"loss": 0.036449754238128663,
|
| 2060 |
+
"step": 1430
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.9788540245566166,
|
| 2064 |
+
"grad_norm": 1.857226848602295,
|
| 2065 |
+
"learning_rate": 6.570469229148184e-05,
|
| 2066 |
+
"loss": 0.04441194534301758,
|
| 2067 |
+
"step": 1435
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.9822646657571623,
|
| 2071 |
+
"grad_norm": 0.27433109283447266,
|
| 2072 |
+
"learning_rate": 6.563702781116302e-05,
|
| 2073 |
+
"loss": 0.028930380940437317,
|
| 2074 |
+
"step": 1440
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.985675306957708,
|
| 2078 |
+
"grad_norm": 0.314373642206192,
|
| 2079 |
+
"learning_rate": 6.556915305641629e-05,
|
| 2080 |
+
"loss": 0.04347030222415924,
|
| 2081 |
+
"step": 1445
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.9890859481582538,
|
| 2085 |
+
"grad_norm": 0.3977321982383728,
|
| 2086 |
+
"learning_rate": 6.550106853448513e-05,
|
| 2087 |
+
"loss": 0.0386979341506958,
|
| 2088 |
+
"step": 1450
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.9924965893587995,
|
| 2092 |
+
"grad_norm": 1.6032801866531372,
|
| 2093 |
+
"learning_rate": 6.543277475418074e-05,
|
| 2094 |
+
"loss": 0.03199186325073242,
|
| 2095 |
+
"step": 1455
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.9959072305593452,
|
| 2099 |
+
"grad_norm": 1.1229087114334106,
|
| 2100 |
+
"learning_rate": 6.53642722258781e-05,
|
| 2101 |
+
"loss": 0.046002286672592166,
|
| 2102 |
+
"step": 1460
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.9986357435197817,
|
| 2106 |
+
"eval_loss": 0.05529617890715599,
|
| 2107 |
+
"eval_runtime": 0.9152,
|
| 2108 |
+
"eval_samples_per_second": 81.948,
|
| 2109 |
+
"eval_steps_per_second": 2.185,
|
| 2110 |
+
"step": 1464
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"eval_cer_subset": 0.024662760594086387,
|
| 2114 |
+
"eval_cer_subset_edit_distance": 181,
|
| 2115 |
+
"eval_cer_subset_groups": 75,
|
| 2116 |
+
"eval_cer_subset_items": 75,
|
| 2117 |
+
"eval_cer_subset_ref_chars": 7339,
|
| 2118 |
+
"step": 1464
|
| 2119 |
+
},
|
| 2120 |
+
{
|
| 2121 |
+
"epoch": 0.9993178717598908,
|
| 2122 |
+
"grad_norm": 0.8476057648658752,
|
| 2123 |
+
"learning_rate": 6.529556146151224e-05,
|
| 2124 |
+
"loss": 0.01695575416088104,
|
| 2125 |
+
"step": 1465
|
| 2126 |
+
},
|
| 2127 |
+
{
|
| 2128 |
+
"epoch": 1.0027285129604366,
|
| 2129 |
+
"grad_norm": 0.0731077790260315,
|
| 2130 |
+
"learning_rate": 6.522664297457437e-05,
|
| 2131 |
+
"loss": 0.0027170730754733086,
|
| 2132 |
+
"step": 1470
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"epoch": 1.0061391541609823,
|
| 2136 |
+
"grad_norm": 0.05015791580080986,
|
| 2137 |
+
"learning_rate": 6.515751728010807e-05,
|
| 2138 |
+
"loss": 0.015530210733413697,
|
| 2139 |
+
"step": 1475
|
| 2140 |
+
},
|
| 2141 |
+
{
|
| 2142 |
+
"epoch": 1.009549795361528,
|
| 2143 |
+
"grad_norm": 1.0450271368026733,
|
| 2144 |
+
"learning_rate": 6.508818489470543e-05,
|
| 2145 |
+
"loss": 0.028301748633384704,
|
| 2146 |
+
"step": 1480
|
| 2147 |
+
},
|
| 2148 |
+
{
|
| 2149 |
+
"epoch": 1.0129604365620737,
|
| 2150 |
+
"grad_norm": 0.007203489542007446,
|
| 2151 |
+
"learning_rate": 6.501864633650318e-05,
|
| 2152 |
+
"loss": 0.013968841731548309,
|
| 2153 |
+
"step": 1485
|
| 2154 |
+
},
|
| 2155 |
+
{
|
| 2156 |
+
"epoch": 1.0163710777626194,
|
| 2157 |
+
"grad_norm": 0.02691703289747238,
|
| 2158 |
+
"learning_rate": 6.494890212517883e-05,
|
| 2159 |
+
"loss": 0.005682830139994622,
|
| 2160 |
+
"step": 1490
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"epoch": 1.019781718963165,
|
| 2164 |
+
"grad_norm": 0.6411488652229309,
|
| 2165 |
+
"learning_rate": 6.487895278194678e-05,
|
| 2166 |
+
"loss": 0.005073993653059006,
|
| 2167 |
+
"step": 1495
|
| 2168 |
+
},
|
| 2169 |
+
{
|
| 2170 |
+
"epoch": 1.0231923601637107,
|
| 2171 |
+
"grad_norm": 0.13043923676013947,
|
| 2172 |
+
"learning_rate": 6.480879882955443e-05,
|
| 2173 |
+
"loss": 0.034558257460594176,
|
| 2174 |
+
"step": 1500
|
| 2175 |
+
},
|
| 2176 |
+
{
|
| 2177 |
+
"epoch": 1.0266030013642564,
|
| 2178 |
+
"grad_norm": 0.42835143208503723,
|
| 2179 |
+
"learning_rate": 6.473844079227828e-05,
|
| 2180 |
+
"loss": 0.008179995417594909,
|
| 2181 |
+
"step": 1505
|
| 2182 |
+
},
|
| 2183 |
+
{
|
| 2184 |
+
"epoch": 1.030013642564802,
|
| 2185 |
+
"grad_norm": 0.08968371897935867,
|
| 2186 |
+
"learning_rate": 6.466787919591997e-05,
|
| 2187 |
+
"loss": 0.06659101843833923,
|
| 2188 |
+
"step": 1510
|
| 2189 |
+
},
|
| 2190 |
+
{
|
| 2191 |
+
"epoch": 1.0334242837653478,
|
| 2192 |
+
"grad_norm": 0.028647486120462418,
|
| 2193 |
+
"learning_rate": 6.459711456780243e-05,
|
| 2194 |
+
"loss": 0.002646555379033089,
|
| 2195 |
+
"step": 1515
|
| 2196 |
+
},
|
| 2197 |
+
{
|
| 2198 |
+
"epoch": 1.0368349249658937,
|
| 2199 |
+
"grad_norm": 0.49801063537597656,
|
| 2200 |
+
"learning_rate": 6.452614743676588e-05,
|
| 2201 |
+
"loss": 0.014094460010528564,
|
| 2202 |
+
"step": 1520
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 1.0402455661664394,
|
| 2206 |
+
"grad_norm": 1.1292961835861206,
|
| 2207 |
+
"learning_rate": 6.445497833316385e-05,
|
| 2208 |
+
"loss": 0.03136319518089294,
|
| 2209 |
+
"step": 1525
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 1.043656207366985,
|
| 2213 |
+
"grad_norm": 0.07291857898235321,
|
| 2214 |
+
"learning_rate": 6.438360778885929e-05,
|
| 2215 |
+
"loss": 0.013663257658481597,
|
| 2216 |
+
"step": 1530
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 1.0470668485675307,
|
| 2220 |
+
"grad_norm": 0.4733221232891083,
|
| 2221 |
+
"learning_rate": 6.43120363372206e-05,
|
| 2222 |
+
"loss": 0.011823048442602157,
|
| 2223 |
+
"step": 1535
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 1.0504774897680764,
|
| 2227 |
+
"grad_norm": 0.03299790620803833,
|
| 2228 |
+
"learning_rate": 6.424026451311753e-05,
|
| 2229 |
+
"loss": 0.017025044560432433,
|
| 2230 |
+
"step": 1540
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 1.053888130968622,
|
| 2234 |
+
"grad_norm": 2.0730843544006348,
|
| 2235 |
+
"learning_rate": 6.416829285291728e-05,
|
| 2236 |
+
"loss": 0.022110742330551148,
|
| 2237 |
+
"step": 1545
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 1.0572987721691678,
|
| 2241 |
+
"grad_norm": 0.004568230360746384,
|
| 2242 |
+
"learning_rate": 6.409612189448053e-05,
|
| 2243 |
+
"loss": 0.03601303398609161,
|
| 2244 |
+
"step": 1550
|
| 2245 |
+
},
|
| 2246 |
+
{
|
| 2247 |
+
"epoch": 1.0607094133697135,
|
| 2248 |
+
"grad_norm": 1.453091025352478,
|
| 2249 |
+
"learning_rate": 6.402375217715729e-05,
|
| 2250 |
+
"loss": 0.014915446937084197,
|
| 2251 |
+
"step": 1555
|
| 2252 |
+
},
|
| 2253 |
+
{
|
| 2254 |
+
"epoch": 1.0641200545702592,
|
| 2255 |
+
"grad_norm": 0.5859401226043701,
|
| 2256 |
+
"learning_rate": 6.395118424178299e-05,
|
| 2257 |
+
"loss": 0.03671925961971283,
|
| 2258 |
+
"step": 1560
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 1.0675306957708048,
|
| 2262 |
+
"grad_norm": 0.007798578590154648,
|
| 2263 |
+
"learning_rate": 6.387841863067433e-05,
|
| 2264 |
+
"loss": 0.024042302370071413,
|
| 2265 |
+
"step": 1565
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 1.0709413369713505,
|
| 2269 |
+
"grad_norm": 0.05673844739794731,
|
| 2270 |
+
"learning_rate": 6.380545588762534e-05,
|
| 2271 |
+
"loss": 0.014150387048721314,
|
| 2272 |
+
"step": 1570
|
| 2273 |
+
},
|
| 2274 |
+
{
|
| 2275 |
+
"epoch": 1.0743519781718964,
|
| 2276 |
+
"grad_norm": 0.6972388029098511,
|
| 2277 |
+
"learning_rate": 6.373229655790325e-05,
|
| 2278 |
+
"loss": 0.03881770372390747,
|
| 2279 |
+
"step": 1575
|
| 2280 |
+
},
|
| 2281 |
+
{
|
| 2282 |
+
"epoch": 1.077762619372442,
|
| 2283 |
+
"grad_norm": 0.8956314325332642,
|
| 2284 |
+
"learning_rate": 6.365894118824444e-05,
|
| 2285 |
+
"loss": 0.021957725286483765,
|
| 2286 |
+
"step": 1580
|
| 2287 |
+
},
|
| 2288 |
+
{
|
| 2289 |
+
"epoch": 1.0811732605729878,
|
| 2290 |
+
"grad_norm": 1.0231817960739136,
|
| 2291 |
+
"learning_rate": 6.358539032685029e-05,
|
| 2292 |
+
"loss": 0.03818466663360596,
|
| 2293 |
+
"step": 1585
|
| 2294 |
+
},
|
| 2295 |
+
{
|
| 2296 |
+
"epoch": 1.0845839017735335,
|
| 2297 |
+
"grad_norm": 0.32065045833587646,
|
| 2298 |
+
"learning_rate": 6.351164452338316e-05,
|
| 2299 |
+
"loss": 0.017974501848220824,
|
| 2300 |
+
"step": 1590
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 1.0879945429740792,
|
| 2304 |
+
"grad_norm": 0.052197907119989395,
|
| 2305 |
+
"learning_rate": 6.34377043289623e-05,
|
| 2306 |
+
"loss": 0.34247732162475586,
|
| 2307 |
+
"step": 1595
|
| 2308 |
+
},
|
| 2309 |
+
{
|
| 2310 |
+
"epoch": 1.0914051841746248,
|
| 2311 |
+
"grad_norm": 0.1314801126718521,
|
| 2312 |
+
"learning_rate": 6.336357029615964e-05,
|
| 2313 |
+
"loss": 0.007924404740333558,
|
| 2314 |
+
"step": 1600
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 1.0948158253751705,
|
| 2318 |
+
"grad_norm": 0.013010814785957336,
|
| 2319 |
+
"learning_rate": 6.32892429789957e-05,
|
| 2320 |
+
"loss": 0.013722099363803864,
|
| 2321 |
+
"step": 1605
|
| 2322 |
+
},
|
| 2323 |
+
{
|
| 2324 |
+
"epoch": 1.0982264665757162,
|
| 2325 |
+
"grad_norm": 0.07680380344390869,
|
| 2326 |
+
"learning_rate": 6.321472293293549e-05,
|
| 2327 |
+
"loss": 0.020718716084957123,
|
| 2328 |
+
"step": 1610
|
| 2329 |
+
},
|
| 2330 |
+
{
|
| 2331 |
+
"epoch": 1.101637107776262,
|
| 2332 |
+
"grad_norm": 0.3573530912399292,
|
| 2333 |
+
"learning_rate": 6.314001071488434e-05,
|
| 2334 |
+
"loss": 0.017910942435264587,
|
| 2335 |
+
"step": 1615
|
| 2336 |
+
},
|
| 2337 |
+
{
|
| 2338 |
+
"epoch": 1.1050477489768076,
|
| 2339 |
+
"grad_norm": 0.0073904613964259624,
|
| 2340 |
+
"learning_rate": 6.306510688318365e-05,
|
| 2341 |
+
"loss": 0.009220895171165467,
|
| 2342 |
+
"step": 1620
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 1.1084583901773533,
|
| 2346 |
+
"grad_norm": 0.0597323514521122,
|
| 2347 |
+
"learning_rate": 6.299001199760687e-05,
|
| 2348 |
+
"loss": 0.010637883096933365,
|
| 2349 |
+
"step": 1625
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 1.111869031377899,
|
| 2353 |
+
"grad_norm": 0.07265184819698334,
|
| 2354 |
+
"learning_rate": 6.291472661935522e-05,
|
| 2355 |
+
"loss": 0.00596662349998951,
|
| 2356 |
+
"step": 1630
|
| 2357 |
+
},
|
| 2358 |
+
{
|
| 2359 |
+
"epoch": 1.1152796725784448,
|
| 2360 |
+
"grad_norm": 5.774064064025879,
|
| 2361 |
+
"learning_rate": 6.283925131105348e-05,
|
| 2362 |
+
"loss": 0.032669514417648315,
|
| 2363 |
+
"step": 1635
|
| 2364 |
+
},
|
| 2365 |
+
{
|
| 2366 |
+
"epoch": 1.1186903137789905,
|
| 2367 |
+
"grad_norm": 0.42285504937171936,
|
| 2368 |
+
"learning_rate": 6.276358663674589e-05,
|
| 2369 |
+
"loss": 0.028756555914878846,
|
| 2370 |
+
"step": 1640
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"epoch": 1.1221009549795362,
|
| 2374 |
+
"grad_norm": 0.014294124208390713,
|
| 2375 |
+
"learning_rate": 6.268773316189178e-05,
|
| 2376 |
+
"loss": 0.0047109007835388185,
|
| 2377 |
+
"step": 1645
|
| 2378 |
+
},
|
| 2379 |
+
{
|
| 2380 |
+
"epoch": 1.125511596180082,
|
| 2381 |
+
"grad_norm": 0.34502843022346497,
|
| 2382 |
+
"learning_rate": 6.261169145336151e-05,
|
| 2383 |
+
"loss": 0.015978309512138366,
|
| 2384 |
+
"step": 1650
|
| 2385 |
+
},
|
| 2386 |
+
{
|
| 2387 |
+
"epoch": 1.1289222373806276,
|
| 2388 |
+
"grad_norm": 0.02683340758085251,
|
| 2389 |
+
"learning_rate": 6.253546207943209e-05,
|
| 2390 |
+
"loss": 0.014604611694812775,
|
| 2391 |
+
"step": 1655
|
| 2392 |
+
},
|
| 2393 |
+
{
|
| 2394 |
+
"epoch": 1.1323328785811733,
|
| 2395 |
+
"grad_norm": 0.02333923988044262,
|
| 2396 |
+
"learning_rate": 6.245904560978302e-05,
|
| 2397 |
+
"loss": 0.021287524700164796,
|
| 2398 |
+
"step": 1660
|
| 2399 |
+
},
|
| 2400 |
+
{
|
| 2401 |
+
"epoch": 1.135743519781719,
|
| 2402 |
+
"grad_norm": 0.2537156939506531,
|
| 2403 |
+
"learning_rate": 6.238244261549203e-05,
|
| 2404 |
+
"loss": 0.01746509373188019,
|
| 2405 |
+
"step": 1665
|
| 2406 |
+
},
|
| 2407 |
+
{
|
| 2408 |
+
"epoch": 1.1391541609822646,
|
| 2409 |
+
"grad_norm": 0.2644752860069275,
|
| 2410 |
+
"learning_rate": 6.230565366903075e-05,
|
| 2411 |
+
"loss": 0.021785764396190642,
|
| 2412 |
+
"step": 1670
|
| 2413 |
+
},
|
| 2414 |
+
{
|
| 2415 |
+
"epoch": 1.1425648021828103,
|
| 2416 |
+
"grad_norm": 0.3956565260887146,
|
| 2417 |
+
"learning_rate": 6.222867934426052e-05,
|
| 2418 |
+
"loss": 0.003387744724750519,
|
| 2419 |
+
"step": 1675
|
| 2420 |
+
},
|
| 2421 |
+
{
|
| 2422 |
+
"epoch": 1.145975443383356,
|
| 2423 |
+
"grad_norm": 0.5124446153640747,
|
| 2424 |
+
"learning_rate": 6.215152021642801e-05,
|
| 2425 |
+
"loss": 0.013412350416183471,
|
| 2426 |
+
"step": 1680
|
| 2427 |
+
},
|
| 2428 |
+
{
|
| 2429 |
+
"epoch": 1.1493860845839017,
|
| 2430 |
+
"grad_norm": 0.0077205742709338665,
|
| 2431 |
+
"learning_rate": 6.2074176862161e-05,
|
| 2432 |
+
"loss": 0.06386477947235107,
|
| 2433 |
+
"step": 1685
|
| 2434 |
+
},
|
| 2435 |
+
{
|
| 2436 |
+
"epoch": 1.1527967257844476,
|
| 2437 |
+
"grad_norm": 0.044003162533044815,
|
| 2438 |
+
"learning_rate": 6.1996649859464e-05,
|
| 2439 |
+
"loss": 0.002909707650542259,
|
| 2440 |
+
"step": 1690
|
| 2441 |
+
},
|
| 2442 |
+
{
|
| 2443 |
+
"epoch": 1.1562073669849933,
|
| 2444 |
+
"grad_norm": 0.358694463968277,
|
| 2445 |
+
"learning_rate": 6.191893978771402e-05,
|
| 2446 |
+
"loss": 0.021670857071876527,
|
| 2447 |
+
"step": 1695
|
| 2448 |
+
},
|
| 2449 |
+
{
|
| 2450 |
+
"epoch": 1.159618008185539,
|
| 2451 |
+
"grad_norm": 0.09412632882595062,
|
| 2452 |
+
"learning_rate": 6.184104722765613e-05,
|
| 2453 |
+
"loss": 0.019501471519470216,
|
| 2454 |
+
"step": 1700
|
| 2455 |
+
},
|
| 2456 |
+
{
|
| 2457 |
+
"epoch": 1.1630286493860846,
|
| 2458 |
+
"grad_norm": 0.8273324370384216,
|
| 2459 |
+
"learning_rate": 6.17629727613992e-05,
|
| 2460 |
+
"loss": 0.034558022022247316,
|
| 2461 |
+
"step": 1705
|
| 2462 |
+
},
|
| 2463 |
+
{
|
| 2464 |
+
"epoch": 1.1664392905866303,
|
| 2465 |
+
"grad_norm": 0.3224208950996399,
|
| 2466 |
+
"learning_rate": 6.168471697241155e-05,
|
| 2467 |
+
"loss": 0.022453221678733825,
|
| 2468 |
+
"step": 1710
|
| 2469 |
+
},
|
| 2470 |
+
{
|
| 2471 |
+
"epoch": 1.169849931787176,
|
| 2472 |
+
"grad_norm": 0.27806228399276733,
|
| 2473 |
+
"learning_rate": 6.160628044551652e-05,
|
| 2474 |
+
"loss": 0.028394827246665956,
|
| 2475 |
+
"step": 1715
|
| 2476 |
+
},
|
| 2477 |
+
{
|
| 2478 |
+
"epoch": 1.1732605729877217,
|
| 2479 |
+
"grad_norm": 0.05991955101490021,
|
| 2480 |
+
"learning_rate": 6.152766376688818e-05,
|
| 2481 |
+
"loss": 0.02458793669939041,
|
| 2482 |
+
"step": 1720
|
| 2483 |
+
},
|
| 2484 |
+
{
|
| 2485 |
+
"epoch": 1.1766712141882674,
|
| 2486 |
+
"grad_norm": 0.5648256540298462,
|
| 2487 |
+
"learning_rate": 6.14488675240469e-05,
|
| 2488 |
+
"loss": 0.019231566786766054,
|
| 2489 |
+
"step": 1725
|
| 2490 |
+
},
|
| 2491 |
+
{
|
| 2492 |
+
"epoch": 1.180081855388813,
|
| 2493 |
+
"grad_norm": 0.5112252831459045,
|
| 2494 |
+
"learning_rate": 6.1369892305855e-05,
|
| 2495 |
+
"loss": 0.00729234516620636,
|
| 2496 |
+
"step": 1730
|
| 2497 |
+
},
|
| 2498 |
+
{
|
| 2499 |
+
"epoch": 1.1834924965893587,
|
| 2500 |
+
"grad_norm": 0.10093241930007935,
|
| 2501 |
+
"learning_rate": 6.129073870251228e-05,
|
| 2502 |
+
"loss": 0.026474124193191527,
|
| 2503 |
+
"step": 1735
|
| 2504 |
+
},
|
| 2505 |
+
{
|
| 2506 |
+
"epoch": 1.1869031377899044,
|
| 2507 |
+
"grad_norm": 0.007164946291595697,
|
| 2508 |
+
"learning_rate": 6.12114073055517e-05,
|
| 2509 |
+
"loss": 0.011781595647335052,
|
| 2510 |
+
"step": 1740
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 1.19031377899045,
|
| 2514 |
+
"grad_norm": 0.0596928596496582,
|
| 2515 |
+
"learning_rate": 6.113189870783484e-05,
|
| 2516 |
+
"loss": 0.022979708015918733,
|
| 2517 |
+
"step": 1745
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 1.1937244201909958,
|
| 2521 |
+
"grad_norm": 0.07026170939207077,
|
| 2522 |
+
"learning_rate": 6.105221350354764e-05,
|
| 2523 |
+
"loss": 0.021880485117435455,
|
| 2524 |
+
"step": 1750
|
| 2525 |
+
},
|
| 2526 |
+
{
|
| 2527 |
+
"epoch": 1.1971350613915417,
|
| 2528 |
+
"grad_norm": 0.4536992311477661,
|
| 2529 |
+
"learning_rate": 6.097235228819578e-05,
|
| 2530 |
+
"loss": 0.0312265545129776,
|
| 2531 |
+
"step": 1755
|
| 2532 |
+
},
|
| 2533 |
+
{
|
| 2534 |
+
"epoch": 1.2005457025920874,
|
| 2535 |
+
"grad_norm": 0.013953015208244324,
|
| 2536 |
+
"learning_rate": 6.089231565860035e-05,
|
| 2537 |
+
"loss": 0.006989015638828278,
|
| 2538 |
+
"step": 1760
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"epoch": 1.203956343792633,
|
| 2542 |
+
"grad_norm": 0.12421152740716934,
|
| 2543 |
+
"learning_rate": 6.0812104212893353e-05,
|
| 2544 |
+
"loss": 0.010978200286626816,
|
| 2545 |
+
"step": 1765
|
| 2546 |
+
},
|
| 2547 |
+
{
|
| 2548 |
+
"epoch": 1.2073669849931787,
|
| 2549 |
+
"grad_norm": 0.0044771963730454445,
|
| 2550 |
+
"learning_rate": 6.073171855051322e-05,
|
| 2551 |
+
"loss": 0.029409635066986083,
|
| 2552 |
+
"step": 1770
|
| 2553 |
+
},
|
| 2554 |
+
{
|
| 2555 |
+
"epoch": 1.2107776261937244,
|
| 2556 |
+
"grad_norm": 0.07688756287097931,
|
| 2557 |
+
"learning_rate": 6.065115927220032e-05,
|
| 2558 |
+
"loss": 0.013059450685977936,
|
| 2559 |
+
"step": 1775
|
| 2560 |
+
},
|
| 2561 |
+
{
|
| 2562 |
+
"epoch": 1.21418826739427,
|
| 2563 |
+
"grad_norm": 0.3248527944087982,
|
| 2564 |
+
"learning_rate": 6.0570426979992546e-05,
|
| 2565 |
+
"loss": 0.005089572072029114,
|
| 2566 |
+
"step": 1780
|
| 2567 |
+
},
|
| 2568 |
+
{
|
| 2569 |
+
"epoch": 1.2175989085948158,
|
| 2570 |
+
"grad_norm": 0.13590829074382782,
|
| 2571 |
+
"learning_rate": 6.048952227722073e-05,
|
| 2572 |
+
"loss": 0.013443182408809661,
|
| 2573 |
+
"step": 1785
|
| 2574 |
+
},
|
| 2575 |
+
{
|
| 2576 |
+
"epoch": 1.2210095497953615,
|
| 2577 |
+
"grad_norm": 0.8500165343284607,
|
| 2578 |
+
"learning_rate": 6.040844576850416e-05,
|
| 2579 |
+
"loss": 0.05245064496994019,
|
| 2580 |
+
"step": 1790
|
| 2581 |
+
},
|
| 2582 |
+
{
|
| 2583 |
+
"epoch": 1.2244201909959072,
|
| 2584 |
+
"grad_norm": 0.009083034470677376,
|
| 2585 |
+
"learning_rate": 6.0327198059746115e-05,
|
| 2586 |
+
"loss": 0.02519877254962921,
|
| 2587 |
+
"step": 1795
|
| 2588 |
+
},
|
| 2589 |
+
{
|
| 2590 |
+
"epoch": 1.2278308321964528,
|
| 2591 |
+
"grad_norm": 0.010473054833710194,
|
| 2592 |
+
"learning_rate": 6.024577975812922e-05,
|
| 2593 |
+
"loss": 0.0116177037358284,
|
| 2594 |
+
"step": 1800
|
| 2595 |
+
},
|
| 2596 |
+
{
|
| 2597 |
+
"epoch": 1.2312414733969987,
|
| 2598 |
+
"grad_norm": 0.01996340975165367,
|
| 2599 |
+
"learning_rate": 6.016419147211102e-05,
|
| 2600 |
+
"loss": 0.002756960690021515,
|
| 2601 |
+
"step": 1805
|
| 2602 |
+
},
|
| 2603 |
+
{
|
| 2604 |
+
"epoch": 1.2346521145975444,
|
| 2605 |
+
"grad_norm": 0.046663638204336166,
|
| 2606 |
+
"learning_rate": 6.008243381141942e-05,
|
| 2607 |
+
"loss": 0.006187716126441955,
|
| 2608 |
+
"step": 1810
|
| 2609 |
+
},
|
| 2610 |
+
{
|
| 2611 |
+
"epoch": 1.23806275579809,
|
| 2612 |
+
"grad_norm": 0.5459519624710083,
|
| 2613 |
+
"learning_rate": 6.000050738704805e-05,
|
| 2614 |
+
"loss": 0.032647940516471866,
|
| 2615 |
+
"step": 1815
|
| 2616 |
+
},
|
| 2617 |
+
{
|
| 2618 |
+
"epoch": 1.2414733969986358,
|
| 2619 |
+
"grad_norm": 0.24907033145427704,
|
| 2620 |
+
"learning_rate": 5.991841281125177e-05,
|
| 2621 |
+
"loss": 0.007942546159029007,
|
| 2622 |
+
"step": 1820
|
| 2623 |
+
},
|
| 2624 |
+
{
|
| 2625 |
+
"epoch": 1.2448840381991815,
|
| 2626 |
+
"grad_norm": 0.05362895876169205,
|
| 2627 |
+
"learning_rate": 5.9836150697542086e-05,
|
| 2628 |
+
"loss": 0.009079506993293763,
|
| 2629 |
+
"step": 1825
|
| 2630 |
+
},
|
| 2631 |
+
{
|
| 2632 |
+
"epoch": 1.2482946793997272,
|
| 2633 |
+
"grad_norm": 0.34499797224998474,
|
| 2634 |
+
"learning_rate": 5.9753721660682515e-05,
|
| 2635 |
+
"loss": 0.0033931449055671693,
|
| 2636 |
+
"step": 1830
|
| 2637 |
+
},
|
| 2638 |
+
{
|
| 2639 |
+
"epoch": 1.2482946793997272,
|
| 2640 |
+
"eval_loss": 0.05778764560818672,
|
| 2641 |
+
"eval_runtime": 0.8976,
|
| 2642 |
+
"eval_samples_per_second": 83.554,
|
| 2643 |
+
"eval_steps_per_second": 2.228,
|
| 2644 |
+
"step": 1830
|
| 2645 |
+
},
|
| 2646 |
+
{
|
| 2647 |
+
"eval_cer_subset": 0.019484943452786483,
|
| 2648 |
+
"eval_cer_subset_edit_distance": 143,
|
| 2649 |
+
"eval_cer_subset_groups": 75,
|
| 2650 |
+
"eval_cer_subset_items": 75,
|
| 2651 |
+
"eval_cer_subset_ref_chars": 7339,
|
| 2652 |
+
"step": 1830
|
| 2653 |
+
},
|
| 2654 |
+
{
|
| 2655 |
+
"epoch": 1.2517053206002728,
|
| 2656 |
+
"grad_norm": 4.153449058532715,
|
| 2657 |
+
"learning_rate": 5.967112631668409e-05,
|
| 2658 |
+
"loss": 0.012082754075527192,
|
| 2659 |
+
"step": 1835
|
| 2660 |
+
},
|
| 2661 |
+
{
|
| 2662 |
+
"epoch": 1.2551159618008185,
|
| 2663 |
+
"grad_norm": 3.670395612716675,
|
| 2664 |
+
"learning_rate": 5.958836528280062e-05,
|
| 2665 |
+
"loss": 0.009738349914550781,
|
| 2666 |
+
"step": 1840
|
| 2667 |
+
},
|
| 2668 |
+
{
|
| 2669 |
+
"epoch": 1.2585266030013642,
|
| 2670 |
+
"grad_norm": 0.10426812618970871,
|
| 2671 |
+
"learning_rate": 5.950543917752422e-05,
|
| 2672 |
+
"loss": 0.0026493463665246964,
|
| 2673 |
+
"step": 1845
|
| 2674 |
+
},
|
| 2675 |
+
{
|
| 2676 |
+
"epoch": 1.26193724420191,
|
| 2677 |
+
"grad_norm": 0.022981934249401093,
|
| 2678 |
+
"learning_rate": 5.942234862058059e-05,
|
| 2679 |
+
"loss": 0.005860285460948944,
|
| 2680 |
+
"step": 1850
|
| 2681 |
+
},
|
| 2682 |
+
{
|
| 2683 |
+
"epoch": 1.2653478854024556,
|
| 2684 |
+
"grad_norm": 0.0007500631618313491,
|
| 2685 |
+
"learning_rate": 5.933909423292441e-05,
|
| 2686 |
+
"loss": 0.05660415887832641,
|
| 2687 |
+
"step": 1855
|
| 2688 |
+
},
|
| 2689 |
+
{
|
| 2690 |
+
"epoch": 1.2687585266030013,
|
| 2691 |
+
"grad_norm": 0.37151023745536804,
|
| 2692 |
+
"learning_rate": 5.925567663673472e-05,
|
| 2693 |
+
"loss": 0.0029373887926340105,
|
| 2694 |
+
"step": 1860
|
| 2695 |
+
},
|
| 2696 |
+
{
|
| 2697 |
+
"epoch": 1.272169167803547,
|
| 2698 |
+
"grad_norm": 0.036931321024894714,
|
| 2699 |
+
"learning_rate": 5.9172096455410244e-05,
|
| 2700 |
+
"loss": 0.007140242308378219,
|
| 2701 |
+
"step": 1865
|
| 2702 |
+
},
|
| 2703 |
+
{
|
| 2704 |
+
"epoch": 1.2755798090040928,
|
| 2705 |
+
"grad_norm": 0.008696082048118114,
|
| 2706 |
+
"learning_rate": 5.908835431356475e-05,
|
| 2707 |
+
"loss": 0.03127997815608978,
|
| 2708 |
+
"step": 1870
|
| 2709 |
+
},
|
| 2710 |
+
{
|
| 2711 |
+
"epoch": 1.2789904502046385,
|
| 2712 |
+
"grad_norm": 1.442112684249878,
|
| 2713 |
+
"learning_rate": 5.900445083702235e-05,
|
| 2714 |
+
"loss": 0.05517878532409668,
|
| 2715 |
+
"step": 1875
|
| 2716 |
+
},
|
| 2717 |
+
{
|
| 2718 |
+
"epoch": 1.2824010914051842,
|
| 2719 |
+
"grad_norm": 0.5617618560791016,
|
| 2720 |
+
"learning_rate": 5.8920386652812894e-05,
|
| 2721 |
+
"loss": 0.018300823867321014,
|
| 2722 |
+
"step": 1880
|
| 2723 |
+
},
|
| 2724 |
+
{
|
| 2725 |
+
"epoch": 1.28581173260573,
|
| 2726 |
+
"grad_norm": 0.7440968751907349,
|
| 2727 |
+
"learning_rate": 5.883616238916718e-05,
|
| 2728 |
+
"loss": 0.025746351480484007,
|
| 2729 |
+
"step": 1885
|
| 2730 |
+
},
|
| 2731 |
+
{
|
| 2732 |
+
"epoch": 1.2892223738062756,
|
| 2733 |
+
"grad_norm": 0.23570798337459564,
|
| 2734 |
+
"learning_rate": 5.875177867551236e-05,
|
| 2735 |
+
"loss": 0.009138952195644378,
|
| 2736 |
+
"step": 1890
|
| 2737 |
+
},
|
| 2738 |
+
{
|
| 2739 |
+
"epoch": 1.2926330150068213,
|
| 2740 |
+
"grad_norm": 0.8084076046943665,
|
| 2741 |
+
"learning_rate": 5.866723614246718e-05,
|
| 2742 |
+
"loss": 0.029955285787582397,
|
| 2743 |
+
"step": 1895
|
| 2744 |
+
},
|
| 2745 |
+
{
|
| 2746 |
+
"epoch": 1.296043656207367,
|
| 2747 |
+
"grad_norm": 0.40341874957084656,
|
| 2748 |
+
"learning_rate": 5.858253542183727e-05,
|
| 2749 |
+
"loss": 0.03340296447277069,
|
| 2750 |
+
"step": 1900
|
| 2751 |
+
},
|
| 2752 |
+
{
|
| 2753 |
+
"epoch": 1.2994542974079126,
|
| 2754 |
+
"grad_norm": 1.6409776210784912,
|
| 2755 |
+
"learning_rate": 5.8497677146610444e-05,
|
| 2756 |
+
"loss": 0.037276041507720944,
|
| 2757 |
+
"step": 1905
|
| 2758 |
+
},
|
| 2759 |
+
{
|
| 2760 |
+
"epoch": 1.3028649386084583,
|
| 2761 |
+
"grad_norm": 0.1204327791929245,
|
| 2762 |
+
"learning_rate": 5.841266195095195e-05,
|
| 2763 |
+
"loss": 0.008522054553031922,
|
| 2764 |
+
"step": 1910
|
| 2765 |
+
},
|
| 2766 |
+
{
|
| 2767 |
+
"epoch": 1.3062755798090042,
|
| 2768 |
+
"grad_norm": 0.07556264847517014,
|
| 2769 |
+
"learning_rate": 5.832749047019973e-05,
|
| 2770 |
+
"loss": 0.0024863181635737417,
|
| 2771 |
+
"step": 1915
|
| 2772 |
+
},
|
| 2773 |
+
{
|
| 2774 |
+
"epoch": 1.30968622100955,
|
| 2775 |
+
"grad_norm": 0.03532743453979492,
|
| 2776 |
+
"learning_rate": 5.824216334085971e-05,
|
| 2777 |
+
"loss": 0.004078276455402374,
|
| 2778 |
+
"step": 1920
|
| 2779 |
+
},
|
| 2780 |
+
{
|
| 2781 |
+
"epoch": 1.3130968622100956,
|
| 2782 |
+
"grad_norm": 0.8705688118934631,
|
| 2783 |
+
"learning_rate": 5.815668120060098e-05,
|
| 2784 |
+
"loss": 0.02017311155796051,
|
| 2785 |
+
"step": 1925
|
| 2786 |
+
},
|
| 2787 |
+
{
|
| 2788 |
+
"epoch": 1.3165075034106413,
|
| 2789 |
+
"grad_norm": 0.0009952038526535034,
|
| 2790 |
+
"learning_rate": 5.8071044688251086e-05,
|
| 2791 |
+
"loss": 0.008325689285993577,
|
| 2792 |
+
"step": 1930
|
| 2793 |
+
},
|
| 2794 |
+
{
|
| 2795 |
+
"epoch": 1.319918144611187,
|
| 2796 |
+
"grad_norm": 2.50828218460083,
|
| 2797 |
+
"learning_rate": 5.7985254443791206e-05,
|
| 2798 |
+
"loss": 0.006225927546620369,
|
| 2799 |
+
"step": 1935
|
| 2800 |
+
},
|
| 2801 |
+
{
|
| 2802 |
+
"epoch": 1.3233287858117326,
|
| 2803 |
+
"grad_norm": 0.6447598934173584,
|
| 2804 |
+
"learning_rate": 5.789931110835142e-05,
|
| 2805 |
+
"loss": 0.005092256143689156,
|
| 2806 |
+
"step": 1940
|
| 2807 |
+
},
|
| 2808 |
+
{
|
| 2809 |
+
"epoch": 1.3267394270122783,
|
| 2810 |
+
"grad_norm": 0.00778482249006629,
|
| 2811 |
+
"learning_rate": 5.781321532420588e-05,
|
| 2812 |
+
"loss": 0.003357316926121712,
|
| 2813 |
+
"step": 1945
|
| 2814 |
+
},
|
| 2815 |
+
{
|
| 2816 |
+
"epoch": 1.330150068212824,
|
| 2817 |
+
"grad_norm": 0.5357232689857483,
|
| 2818 |
+
"learning_rate": 5.772696773476801e-05,
|
| 2819 |
+
"loss": 0.01329006552696228,
|
| 2820 |
+
"step": 1950
|
| 2821 |
+
},
|
| 2822 |
+
{
|
| 2823 |
+
"epoch": 1.3335607094133697,
|
| 2824 |
+
"grad_norm": 0.8402428030967712,
|
| 2825 |
+
"learning_rate": 5.7640568984585756e-05,
|
| 2826 |
+
"loss": 0.05447224378585815,
|
| 2827 |
+
"step": 1955
|
| 2828 |
+
},
|
| 2829 |
+
{
|
| 2830 |
+
"epoch": 1.3369713506139154,
|
| 2831 |
+
"grad_norm": 1.4458378553390503,
|
| 2832 |
+
"learning_rate": 5.755401971933664e-05,
|
| 2833 |
+
"loss": 0.017956557869911193,
|
| 2834 |
+
"step": 1960
|
| 2835 |
+
},
|
| 2836 |
+
{
|
| 2837 |
+
"epoch": 1.340381991814461,
|
| 2838 |
+
"grad_norm": 0.3120212256908417,
|
| 2839 |
+
"learning_rate": 5.746732058582311e-05,
|
| 2840 |
+
"loss": 0.025589832663536073,
|
| 2841 |
+
"step": 1965
|
| 2842 |
+
},
|
| 2843 |
+
{
|
| 2844 |
+
"epoch": 1.3437926330150067,
|
| 2845 |
+
"grad_norm": 0.5558730363845825,
|
| 2846 |
+
"learning_rate": 5.738047223196755e-05,
|
| 2847 |
+
"loss": 0.012551702558994293,
|
| 2848 |
+
"step": 1970
|
| 2849 |
+
},
|
| 2850 |
+
{
|
| 2851 |
+
"epoch": 1.3472032742155524,
|
| 2852 |
+
"grad_norm": 1.4269353151321411,
|
| 2853 |
+
"learning_rate": 5.729347530680753e-05,
|
| 2854 |
+
"loss": 0.056649971008300784,
|
| 2855 |
+
"step": 1975
|
| 2856 |
+
},
|
| 2857 |
+
{
|
| 2858 |
+
"epoch": 1.350613915416098,
|
| 2859 |
+
"grad_norm": 0.2933025062084198,
|
| 2860 |
+
"learning_rate": 5.720633046049091e-05,
|
| 2861 |
+
"loss": 0.008710381388664246,
|
| 2862 |
+
"step": 1980
|
| 2863 |
+
},
|
| 2864 |
+
{
|
| 2865 |
+
"epoch": 1.354024556616644,
|
| 2866 |
+
"grad_norm": 0.9624903798103333,
|
| 2867 |
+
"learning_rate": 5.7119038344271e-05,
|
| 2868 |
+
"loss": 0.014256273210048676,
|
| 2869 |
+
"step": 1985
|
| 2870 |
+
},
|
| 2871 |
+
{
|
| 2872 |
+
"epoch": 1.3574351978171897,
|
| 2873 |
+
"grad_norm": 1.7939856052398682,
|
| 2874 |
+
"learning_rate": 5.703159961050172e-05,
|
| 2875 |
+
"loss": 0.02518789768218994,
|
| 2876 |
+
"step": 1990
|
| 2877 |
+
},
|
| 2878 |
+
{
|
| 2879 |
+
"epoch": 1.3608458390177354,
|
| 2880 |
+
"grad_norm": 0.49102070927619934,
|
| 2881 |
+
"learning_rate": 5.694401491263267e-05,
|
| 2882 |
+
"loss": 0.019194112718105318,
|
| 2883 |
+
"step": 1995
|
| 2884 |
+
},
|
| 2885 |
+
{
|
| 2886 |
+
"epoch": 1.364256480218281,
|
| 2887 |
+
"grad_norm": 0.04536288231611252,
|
| 2888 |
+
"learning_rate": 5.6856284905204266e-05,
|
| 2889 |
+
"loss": 0.0032343052327632902,
|
| 2890 |
+
"step": 2000
|
| 2891 |
+
},
|
| 2892 |
+
{
|
| 2893 |
+
"epoch": 1.3676671214188267,
|
| 2894 |
+
"grad_norm": 1.0203709602355957,
|
| 2895 |
+
"learning_rate": 5.676841024384287e-05,
|
| 2896 |
+
"loss": 0.03292953073978424,
|
| 2897 |
+
"step": 2005
|
| 2898 |
+
},
|
| 2899 |
+
{
|
| 2900 |
+
"epoch": 1.3710777626193724,
|
| 2901 |
+
"grad_norm": 0.9504344463348389,
|
| 2902 |
+
"learning_rate": 5.6680391585255886e-05,
|
| 2903 |
+
"loss": 0.005538972094655037,
|
| 2904 |
+
"step": 2010
|
| 2905 |
+
},
|
| 2906 |
+
{
|
| 2907 |
+
"epoch": 1.374488403819918,
|
| 2908 |
+
"grad_norm": 0.0067398096434772015,
|
| 2909 |
+
"learning_rate": 5.6592229587226823e-05,
|
| 2910 |
+
"loss": 0.0005991209298372268,
|
| 2911 |
+
"step": 2015
|
| 2912 |
+
},
|
| 2913 |
+
{
|
| 2914 |
+
"epoch": 1.3778990450204638,
|
| 2915 |
+
"grad_norm": 1.5757488012313843,
|
| 2916 |
+
"learning_rate": 5.6503924908610405e-05,
|
| 2917 |
+
"loss": 0.012159132212400437,
|
| 2918 |
+
"step": 2020
|
| 2919 |
+
},
|
| 2920 |
+
{
|
| 2921 |
+
"epoch": 1.3813096862210095,
|
| 2922 |
+
"grad_norm": 0.5669568181037903,
|
| 2923 |
+
"learning_rate": 5.641547820932765e-05,
|
| 2924 |
+
"loss": 0.010695122182369232,
|
| 2925 |
+
"step": 2025
|
| 2926 |
+
},
|
| 2927 |
+
{
|
| 2928 |
+
"epoch": 1.3847203274215554,
|
| 2929 |
+
"grad_norm": 0.23352237045764923,
|
| 2930 |
+
"learning_rate": 5.63268901503609e-05,
|
| 2931 |
+
"loss": 0.012255635857582093,
|
| 2932 |
+
"step": 2030
|
| 2933 |
+
},
|
| 2934 |
+
{
|
| 2935 |
+
"epoch": 1.388130968622101,
|
| 2936 |
+
"grad_norm": 1.5650484561920166,
|
| 2937 |
+
"learning_rate": 5.623816139374895e-05,
|
| 2938 |
+
"loss": 0.05114143490791321,
|
| 2939 |
+
"step": 2035
|
| 2940 |
+
},
|
| 2941 |
+
{
|
| 2942 |
+
"epoch": 1.3915416098226467,
|
| 2943 |
+
"grad_norm": 0.05920939892530441,
|
| 2944 |
+
"learning_rate": 5.614929260258202e-05,
|
| 2945 |
+
"loss": 0.002235228754580021,
|
| 2946 |
+
"step": 2040
|
| 2947 |
+
},
|
| 2948 |
+
{
|
| 2949 |
+
"epoch": 1.3949522510231924,
|
| 2950 |
+
"grad_norm": 0.015943612903356552,
|
| 2951 |
+
"learning_rate": 5.606028444099689e-05,
|
| 2952 |
+
"loss": 0.00463336743414402,
|
| 2953 |
+
"step": 2045
|
| 2954 |
+
},
|
| 2955 |
+
{
|
| 2956 |
+
"epoch": 1.398362892223738,
|
| 2957 |
+
"grad_norm": 1.171777606010437,
|
| 2958 |
+
"learning_rate": 5.597113757417183e-05,
|
| 2959 |
+
"loss": 0.010701537132263184,
|
| 2960 |
+
"step": 2050
|
| 2961 |
+
},
|
| 2962 |
+
{
|
| 2963 |
+
"epoch": 1.4017735334242838,
|
| 2964 |
+
"grad_norm": 1.0710582733154297,
|
| 2965 |
+
"learning_rate": 5.588185266832173e-05,
|
| 2966 |
+
"loss": 0.0072472900152206424,
|
| 2967 |
+
"step": 2055
|
| 2968 |
+
},
|
| 2969 |
+
{
|
| 2970 |
+
"epoch": 1.4051841746248295,
|
| 2971 |
+
"grad_norm": 0.0567881241440773,
|
| 2972 |
+
"learning_rate": 5.5792430390693046e-05,
|
| 2973 |
+
"loss": 0.0031896911561489103,
|
| 2974 |
+
"step": 2060
|
| 2975 |
+
},
|
| 2976 |
+
{
|
| 2977 |
+
"epoch": 1.4085948158253752,
|
| 2978 |
+
"grad_norm": 0.5927397608757019,
|
| 2979 |
+
"learning_rate": 5.570287140955886e-05,
|
| 2980 |
+
"loss": 0.004600095748901367,
|
| 2981 |
+
"step": 2065
|
| 2982 |
+
},
|
| 2983 |
+
{
|
| 2984 |
+
"epoch": 1.4120054570259208,
|
| 2985 |
+
"grad_norm": 1.6821774244308472,
|
| 2986 |
+
"learning_rate": 5.5613176394213896e-05,
|
| 2987 |
+
"loss": 0.010283125936985016,
|
| 2988 |
+
"step": 2070
|
| 2989 |
+
},
|
| 2990 |
+
{
|
| 2991 |
+
"epoch": 1.4154160982264665,
|
| 2992 |
+
"grad_norm": 0.3331978917121887,
|
| 2993 |
+
"learning_rate": 5.552334601496944e-05,
|
| 2994 |
+
"loss": 0.00821176841855049,
|
| 2995 |
+
"step": 2075
|
| 2996 |
+
},
|
| 2997 |
+
{
|
| 2998 |
+
"epoch": 1.4188267394270122,
|
| 2999 |
+
"grad_norm": 0.0056209871545434,
|
| 3000 |
+
"learning_rate": 5.5433380943148414e-05,
|
| 3001 |
+
"loss": 0.00954909473657608,
|
| 3002 |
+
"step": 2080
|
| 3003 |
+
},
|
| 3004 |
+
{
|
| 3005 |
+
"epoch": 1.422237380627558,
|
| 3006 |
+
"grad_norm": 0.059546198695898056,
|
| 3007 |
+
"learning_rate": 5.534328185108033e-05,
|
| 3008 |
+
"loss": 0.004072617739439011,
|
| 3009 |
+
"step": 2085
|
| 3010 |
+
},
|
| 3011 |
+
{
|
| 3012 |
+
"epoch": 1.4256480218281036,
|
| 3013 |
+
"grad_norm": 2.5227770805358887,
|
| 3014 |
+
"learning_rate": 5.525304941209626e-05,
|
| 3015 |
+
"loss": 0.006328310817480087,
|
| 3016 |
+
"step": 2090
|
| 3017 |
+
},
|
| 3018 |
+
{
|
| 3019 |
+
"epoch": 1.4290586630286493,
|
| 3020 |
+
"grad_norm": 0.012882530689239502,
|
| 3021 |
+
"learning_rate": 5.5162684300523796e-05,
|
| 3022 |
+
"loss": 0.0069836869835853575,
|
| 3023 |
+
"step": 2095
|
| 3024 |
+
},
|
| 3025 |
+
{
|
| 3026 |
+
"epoch": 1.4324693042291952,
|
| 3027 |
+
"grad_norm": 0.44880563020706177,
|
| 3028 |
+
"learning_rate": 5.507218719168204e-05,
|
| 3029 |
+
"loss": 0.006641192734241486,
|
| 3030 |
+
"step": 2100
|
| 3031 |
+
},
|
| 3032 |
+
{
|
| 3033 |
+
"epoch": 1.4358799454297408,
|
| 3034 |
+
"grad_norm": 0.03564910218119621,
|
| 3035 |
+
"learning_rate": 5.498155876187654e-05,
|
| 3036 |
+
"loss": 0.03126881420612335,
|
| 3037 |
+
"step": 2105
|
| 3038 |
+
},
|
| 3039 |
+
{
|
| 3040 |
+
"epoch": 1.4392905866302865,
|
| 3041 |
+
"grad_norm": 0.12222933769226074,
|
| 3042 |
+
"learning_rate": 5.48907996883942e-05,
|
| 3043 |
+
"loss": 0.0010469739325344562,
|
| 3044 |
+
"step": 2110
|
| 3045 |
+
},
|
| 3046 |
+
{
|
| 3047 |
+
"epoch": 1.4427012278308322,
|
| 3048 |
+
"grad_norm": 0.2652647793292999,
|
| 3049 |
+
"learning_rate": 5.4799910649498316e-05,
|
| 3050 |
+
"loss": 0.004861130565404892,
|
| 3051 |
+
"step": 2115
|
| 3052 |
+
},
|
| 3053 |
+
{
|
| 3054 |
+
"epoch": 1.446111869031378,
|
| 3055 |
+
"grad_norm": 0.45194199681282043,
|
| 3056 |
+
"learning_rate": 5.4708892324423375e-05,
|
| 3057 |
+
"loss": 0.03450656533241272,
|
| 3058 |
+
"step": 2120
|
| 3059 |
+
},
|
| 3060 |
+
{
|
| 3061 |
+
"epoch": 1.4495225102319236,
|
| 3062 |
+
"grad_norm": 7.245598316192627,
|
| 3063 |
+
"learning_rate": 5.4617745393370124e-05,
|
| 3064 |
+
"loss": 0.020797762274742126,
|
| 3065 |
+
"step": 2125
|
| 3066 |
+
},
|
| 3067 |
+
{
|
| 3068 |
+
"epoch": 1.4529331514324693,
|
| 3069 |
+
"grad_norm": 0.003704208880662918,
|
| 3070 |
+
"learning_rate": 5.452647053750035e-05,
|
| 3071 |
+
"loss": 0.0023305635899305344,
|
| 3072 |
+
"step": 2130
|
| 3073 |
+
},
|
| 3074 |
+
{
|
| 3075 |
+
"epoch": 1.456343792633015,
|
| 3076 |
+
"grad_norm": 0.1513793021440506,
|
| 3077 |
+
"learning_rate": 5.4435068438931866e-05,
|
| 3078 |
+
"loss": 0.004804682731628418,
|
| 3079 |
+
"step": 2135
|
| 3080 |
+
},
|
| 3081 |
+
{
|
| 3082 |
+
"epoch": 1.4597544338335606,
|
| 3083 |
+
"grad_norm": 0.8121495246887207,
|
| 3084 |
+
"learning_rate": 5.434353978073342e-05,
|
| 3085 |
+
"loss": 0.012413371354341507,
|
| 3086 |
+
"step": 2140
|
| 3087 |
+
},
|
| 3088 |
+
{
|
| 3089 |
+
"epoch": 1.4631650750341065,
|
| 3090 |
+
"grad_norm": 0.01748906634747982,
|
| 3091 |
+
"learning_rate": 5.425188524691956e-05,
|
| 3092 |
+
"loss": 0.004680215567350388,
|
| 3093 |
+
"step": 2145
|
| 3094 |
+
},
|
| 3095 |
+
{
|
| 3096 |
+
"epoch": 1.4665757162346522,
|
| 3097 |
+
"grad_norm": 0.8548330068588257,
|
| 3098 |
+
"learning_rate": 5.4160105522445514e-05,
|
| 3099 |
+
"loss": 0.023970893025398253,
|
| 3100 |
+
"step": 2150
|
| 3101 |
+
},
|
| 3102 |
+
{
|
| 3103 |
+
"epoch": 1.469986357435198,
|
| 3104 |
+
"grad_norm": 0.005144836381077766,
|
| 3105 |
+
"learning_rate": 5.406820129320212e-05,
|
| 3106 |
+
"loss": 0.031422802805900575,
|
| 3107 |
+
"step": 2155
|
| 3108 |
+
},
|
| 3109 |
+
{
|
| 3110 |
+
"epoch": 1.4733969986357436,
|
| 3111 |
+
"grad_norm": 0.5495908856391907,
|
| 3112 |
+
"learning_rate": 5.397617324601062e-05,
|
| 3113 |
+
"loss": 0.019562892615795135,
|
| 3114 |
+
"step": 2160
|
| 3115 |
+
},
|
| 3116 |
+
{
|
| 3117 |
+
"epoch": 1.4768076398362893,
|
| 3118 |
+
"grad_norm": 0.0021735087502747774,
|
| 3119 |
+
"learning_rate": 5.388402206861764e-05,
|
| 3120 |
+
"loss": 0.01983659714460373,
|
| 3121 |
+
"step": 2165
|
| 3122 |
+
},
|
| 3123 |
+
{
|
| 3124 |
+
"epoch": 1.480218281036835,
|
| 3125 |
+
"grad_norm": 0.06112198159098625,
|
| 3126 |
+
"learning_rate": 5.3791748449689934e-05,
|
| 3127 |
+
"loss": 0.0020502086728811262,
|
| 3128 |
+
"step": 2170
|
| 3129 |
+
},
|
| 3130 |
+
{
|
| 3131 |
+
"epoch": 1.4836289222373806,
|
| 3132 |
+
"grad_norm": 0.7758064866065979,
|
| 3133 |
+
"learning_rate": 5.36993530788093e-05,
|
| 3134 |
+
"loss": 0.05557147264480591,
|
| 3135 |
+
"step": 2175
|
| 3136 |
+
},
|
| 3137 |
+
{
|
| 3138 |
+
"epoch": 1.4870395634379263,
|
| 3139 |
+
"grad_norm": 0.03924431651830673,
|
| 3140 |
+
"learning_rate": 5.360683664646744e-05,
|
| 3141 |
+
"loss": 0.0065080620348453525,
|
| 3142 |
+
"step": 2180
|
| 3143 |
+
},
|
| 3144 |
+
{
|
| 3145 |
+
"epoch": 1.490450204638472,
|
| 3146 |
+
"grad_norm": 0.03558855503797531,
|
| 3147 |
+
"learning_rate": 5.351419984406074e-05,
|
| 3148 |
+
"loss": 0.013747562468051911,
|
| 3149 |
+
"step": 2185
|
| 3150 |
+
},
|
| 3151 |
+
{
|
| 3152 |
+
"epoch": 1.4938608458390177,
|
| 3153 |
+
"grad_norm": 0.018586739897727966,
|
| 3154 |
+
"learning_rate": 5.3421443363885186e-05,
|
| 3155 |
+
"loss": 0.006936004757881165,
|
| 3156 |
+
"step": 2190
|
| 3157 |
+
},
|
| 3158 |
+
{
|
| 3159 |
+
"epoch": 1.4972714870395634,
|
| 3160 |
+
"grad_norm": 0.02448296919465065,
|
| 3161 |
+
"learning_rate": 5.332856789913109e-05,
|
| 3162 |
+
"loss": 0.0032054468989372253,
|
| 3163 |
+
"step": 2195
|
| 3164 |
+
},
|
| 3165 |
+
{
|
| 3166 |
+
"epoch": 1.4979536152796726,
|
| 3167 |
+
"eval_loss": 0.05913596600294113,
|
| 3168 |
+
"eval_runtime": 0.906,
|
| 3169 |
+
"eval_samples_per_second": 82.784,
|
| 3170 |
+
"eval_steps_per_second": 2.208,
|
| 3171 |
+
"step": 2196
|
| 3172 |
+
},
|
| 3173 |
+
{
|
| 3174 |
+
"eval_cer_subset": 0.018803651723668074,
|
| 3175 |
+
"eval_cer_subset_edit_distance": 138,
|
| 3176 |
+
"eval_cer_subset_groups": 75,
|
| 3177 |
+
"eval_cer_subset_items": 75,
|
| 3178 |
+
"eval_cer_subset_ref_chars": 7339,
|
| 3179 |
+
"step": 2196
|
| 3180 |
+
}
|
| 3181 |
+
],
|
| 3182 |
+
"logging_steps": 5,
|
| 3183 |
+
"max_steps": 5864,
|
| 3184 |
+
"num_input_tokens_seen": 0,
|
| 3185 |
+
"num_train_epochs": 4,
|
| 3186 |
+
"save_steps": 366,
|
| 3187 |
+
"stateful_callbacks": {
|
| 3188 |
+
"TrainerControl": {
|
| 3189 |
+
"args": {
|
| 3190 |
+
"should_epoch_stop": false,
|
| 3191 |
+
"should_evaluate": false,
|
| 3192 |
+
"should_log": false,
|
| 3193 |
+
"should_save": true,
|
| 3194 |
+
"should_training_stop": false
|
| 3195 |
+
},
|
| 3196 |
+
"attributes": {}
|
| 3197 |
+
}
|
| 3198 |
+
},
|
| 3199 |
+
"total_flos": 2.297930050038989e+16,
|
| 3200 |
+
"train_batch_size": 2,
|
| 3201 |
+
"trial_name": null,
|
| 3202 |
+
"trial_params": null
|
| 3203 |
+
}
|
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2196/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc6915d8d9dd9b5c9c17756c87ba7ec8221fd06789232d79225f9518167f0aa1
|
| 3 |
+
size 5841
|
meta-llama__meta-llama-3.1-8b/sft/run_manifest.json
CHANGED
|
@@ -9,7 +9,7 @@
|
|
| 9 |
"best_metric_value": 0.05529617890715599,
|
| 10 |
"best_step": 1464,
|
| 11 |
"best_checkpoint_step": 1464,
|
| 12 |
-
"latest_checkpoint_step":
|
| 13 |
"checkpoints": [
|
| 14 |
{
|
| 15 |
"step": 366,
|
|
@@ -40,6 +40,12 @@
|
|
| 40 |
"epoch": 1.2482946793997272,
|
| 41 |
"repo_path": "meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-1830",
|
| 42 |
"timestamp": "2026-04-09T22:17:26.694730+00:00"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
}
|
| 44 |
],
|
| 45 |
"epoch_artifacts": [
|
|
@@ -52,5 +58,5 @@
|
|
| 52 |
],
|
| 53 |
"resume_history": [],
|
| 54 |
"created_at": "2026-04-09T22:12:40.588264+00:00",
|
| 55 |
-
"updated_at": "2026-04-09T22:
|
| 56 |
}
|
|
|
|
| 9 |
"best_metric_value": 0.05529617890715599,
|
| 10 |
"best_step": 1464,
|
| 11 |
"best_checkpoint_step": 1464,
|
| 12 |
+
"latest_checkpoint_step": 2196,
|
| 13 |
"checkpoints": [
|
| 14 |
{
|
| 15 |
"step": 366,
|
|
|
|
| 40 |
"epoch": 1.2482946793997272,
|
| 41 |
"repo_path": "meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-1830",
|
| 42 |
"timestamp": "2026-04-09T22:17:26.694730+00:00"
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"step": 2196,
|
| 46 |
+
"epoch": 1.4979536152796726,
|
| 47 |
+
"repo_path": "meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2196",
|
| 48 |
+
"timestamp": "2026-04-09T22:18:17.356046+00:00"
|
| 49 |
}
|
| 50 |
],
|
| 51 |
"epoch_artifacts": [
|
|
|
|
| 58 |
],
|
| 59 |
"resume_history": [],
|
| 60 |
"created_at": "2026-04-09T22:12:40.588264+00:00",
|
| 61 |
+
"updated_at": "2026-04-09T22:18:17.356062+00:00"
|
| 62 |
}
|