Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
trl
unsloth
sft
text-generation-inference
Instructions to use Ba2han/TR_CPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ba2han/TR_CPT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ba2han/TR_CPT")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Ba2han/TR_CPT") model = AutoModelForCausalLM.from_pretrained("Ba2han/TR_CPT", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Ba2han/TR_CPT with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ba2han/TR_CPT" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ba2han/TR_CPT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Ba2han/TR_CPT
- SGLang
How to use Ba2han/TR_CPT with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Ba2han/TR_CPT" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ba2han/TR_CPT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Ba2han/TR_CPT" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ba2han/TR_CPT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Unsloth Desktop
- Docker Model Runner
How to use Ba2han/TR_CPT with Docker Model Runner:
docker model run hf.co/Ba2han/TR_CPT
Training in progress, step 2000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2519929824
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cf9736311ec86a9135d4488de58dafbff76358732dd7f268c244071d6c610a4
|
| 3 |
size 2519929824
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1264230316
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91ba86b9e96bc6e8f0acb1104f5a6206d286fdacde92fe13c1e78022e1a7e374
|
| 3 |
size 1264230316
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c800b778fa7e115e4c34de8529902de8b61c9a1b4bab3eb8295d06dafff030e
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 10233
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9213965ca8492fec0b6a152109755436e0afea81460fccf56ea3e4d7a97695d8
|
| 3 |
size 10233
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 2000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -3508,6 +3508,3514 @@
|
|
| 3508 |
"learning_rate": 0.002,
|
| 3509 |
"loss": 2.0810580253601074,
|
| 3510 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3511 |
}
|
| 3512 |
],
|
| 3513 |
"logging_steps": 2,
|
|
@@ -3527,7 +7035,7 @@
|
|
| 3527 |
"attributes": {}
|
| 3528 |
}
|
| 3529 |
},
|
| 3530 |
-
"total_flos":
|
| 3531 |
"train_batch_size": 8,
|
| 3532 |
"trial_name": null,
|
| 3533 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.2,
|
| 6 |
"eval_steps": 2000,
|
| 7 |
+
"global_step": 2000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3508 |
"learning_rate": 0.002,
|
| 3509 |
"loss": 2.0810580253601074,
|
| 3510 |
"step": 1000
|
| 3511 |
+
},
|
| 3512 |
+
{
|
| 3513 |
+
"epoch": 0.1002,
|
| 3514 |
+
"grad_norm": 0.08144240826368332,
|
| 3515 |
+
"learning_rate": 0.002,
|
| 3516 |
+
"loss": 2.040194511413574,
|
| 3517 |
+
"step": 1002
|
| 3518 |
+
},
|
| 3519 |
+
{
|
| 3520 |
+
"epoch": 0.1004,
|
| 3521 |
+
"grad_norm": 0.08272895216941833,
|
| 3522 |
+
"learning_rate": 0.002,
|
| 3523 |
+
"loss": 2.0771665573120117,
|
| 3524 |
+
"step": 1004
|
| 3525 |
+
},
|
| 3526 |
+
{
|
| 3527 |
+
"epoch": 0.1006,
|
| 3528 |
+
"grad_norm": 0.08309302479028702,
|
| 3529 |
+
"learning_rate": 0.002,
|
| 3530 |
+
"loss": 2.1700282096862793,
|
| 3531 |
+
"step": 1006
|
| 3532 |
+
},
|
| 3533 |
+
{
|
| 3534 |
+
"epoch": 0.1008,
|
| 3535 |
+
"grad_norm": 0.0821627601981163,
|
| 3536 |
+
"learning_rate": 0.002,
|
| 3537 |
+
"loss": 1.9310054779052734,
|
| 3538 |
+
"step": 1008
|
| 3539 |
+
},
|
| 3540 |
+
{
|
| 3541 |
+
"epoch": 0.101,
|
| 3542 |
+
"grad_norm": 0.08486980199813843,
|
| 3543 |
+
"learning_rate": 0.002,
|
| 3544 |
+
"loss": 1.9665870666503906,
|
| 3545 |
+
"step": 1010
|
| 3546 |
+
},
|
| 3547 |
+
{
|
| 3548 |
+
"epoch": 0.1012,
|
| 3549 |
+
"grad_norm": 0.07736771553754807,
|
| 3550 |
+
"learning_rate": 0.002,
|
| 3551 |
+
"loss": 2.1191978454589844,
|
| 3552 |
+
"step": 1012
|
| 3553 |
+
},
|
| 3554 |
+
{
|
| 3555 |
+
"epoch": 0.1014,
|
| 3556 |
+
"grad_norm": 0.08738190680742264,
|
| 3557 |
+
"learning_rate": 0.002,
|
| 3558 |
+
"loss": 2.1413991451263428,
|
| 3559 |
+
"step": 1014
|
| 3560 |
+
},
|
| 3561 |
+
{
|
| 3562 |
+
"epoch": 0.1016,
|
| 3563 |
+
"grad_norm": 0.08060958236455917,
|
| 3564 |
+
"learning_rate": 0.002,
|
| 3565 |
+
"loss": 2.053593158721924,
|
| 3566 |
+
"step": 1016
|
| 3567 |
+
},
|
| 3568 |
+
{
|
| 3569 |
+
"epoch": 0.1018,
|
| 3570 |
+
"grad_norm": 0.08549308031797409,
|
| 3571 |
+
"learning_rate": 0.002,
|
| 3572 |
+
"loss": 2.2351629734039307,
|
| 3573 |
+
"step": 1018
|
| 3574 |
+
},
|
| 3575 |
+
{
|
| 3576 |
+
"epoch": 0.102,
|
| 3577 |
+
"grad_norm": 0.0951957181096077,
|
| 3578 |
+
"learning_rate": 0.002,
|
| 3579 |
+
"loss": 2.0900161266326904,
|
| 3580 |
+
"step": 1020
|
| 3581 |
+
},
|
| 3582 |
+
{
|
| 3583 |
+
"epoch": 0.1022,
|
| 3584 |
+
"grad_norm": 0.09305122494697571,
|
| 3585 |
+
"learning_rate": 0.002,
|
| 3586 |
+
"loss": 2.0782663822174072,
|
| 3587 |
+
"step": 1022
|
| 3588 |
+
},
|
| 3589 |
+
{
|
| 3590 |
+
"epoch": 0.1024,
|
| 3591 |
+
"grad_norm": 0.08745758980512619,
|
| 3592 |
+
"learning_rate": 0.002,
|
| 3593 |
+
"loss": 2.112008810043335,
|
| 3594 |
+
"step": 1024
|
| 3595 |
+
},
|
| 3596 |
+
{
|
| 3597 |
+
"epoch": 0.1026,
|
| 3598 |
+
"grad_norm": 0.09555797278881073,
|
| 3599 |
+
"learning_rate": 0.002,
|
| 3600 |
+
"loss": 2.0057218074798584,
|
| 3601 |
+
"step": 1026
|
| 3602 |
+
},
|
| 3603 |
+
{
|
| 3604 |
+
"epoch": 0.1028,
|
| 3605 |
+
"grad_norm": 0.08803076297044754,
|
| 3606 |
+
"learning_rate": 0.002,
|
| 3607 |
+
"loss": 1.9368822574615479,
|
| 3608 |
+
"step": 1028
|
| 3609 |
+
},
|
| 3610 |
+
{
|
| 3611 |
+
"epoch": 0.103,
|
| 3612 |
+
"grad_norm": 0.08392704278230667,
|
| 3613 |
+
"learning_rate": 0.002,
|
| 3614 |
+
"loss": 2.203640937805176,
|
| 3615 |
+
"step": 1030
|
| 3616 |
+
},
|
| 3617 |
+
{
|
| 3618 |
+
"epoch": 0.1032,
|
| 3619 |
+
"grad_norm": 0.09330909699201584,
|
| 3620 |
+
"learning_rate": 0.002,
|
| 3621 |
+
"loss": 1.9989039897918701,
|
| 3622 |
+
"step": 1032
|
| 3623 |
+
},
|
| 3624 |
+
{
|
| 3625 |
+
"epoch": 0.1034,
|
| 3626 |
+
"grad_norm": 0.08549216389656067,
|
| 3627 |
+
"learning_rate": 0.002,
|
| 3628 |
+
"loss": 2.0902061462402344,
|
| 3629 |
+
"step": 1034
|
| 3630 |
+
},
|
| 3631 |
+
{
|
| 3632 |
+
"epoch": 0.1036,
|
| 3633 |
+
"grad_norm": 0.08370019495487213,
|
| 3634 |
+
"learning_rate": 0.002,
|
| 3635 |
+
"loss": 2.1310465335845947,
|
| 3636 |
+
"step": 1036
|
| 3637 |
+
},
|
| 3638 |
+
{
|
| 3639 |
+
"epoch": 0.1038,
|
| 3640 |
+
"grad_norm": 0.09530872106552124,
|
| 3641 |
+
"learning_rate": 0.002,
|
| 3642 |
+
"loss": 2.1101088523864746,
|
| 3643 |
+
"step": 1038
|
| 3644 |
+
},
|
| 3645 |
+
{
|
| 3646 |
+
"epoch": 0.104,
|
| 3647 |
+
"grad_norm": 0.08453866839408875,
|
| 3648 |
+
"learning_rate": 0.002,
|
| 3649 |
+
"loss": 2.044961929321289,
|
| 3650 |
+
"step": 1040
|
| 3651 |
+
},
|
| 3652 |
+
{
|
| 3653 |
+
"epoch": 0.1042,
|
| 3654 |
+
"grad_norm": 0.08468504995107651,
|
| 3655 |
+
"learning_rate": 0.002,
|
| 3656 |
+
"loss": 2.267702102661133,
|
| 3657 |
+
"step": 1042
|
| 3658 |
+
},
|
| 3659 |
+
{
|
| 3660 |
+
"epoch": 0.1044,
|
| 3661 |
+
"grad_norm": 0.08485621213912964,
|
| 3662 |
+
"learning_rate": 0.002,
|
| 3663 |
+
"loss": 2.112591028213501,
|
| 3664 |
+
"step": 1044
|
| 3665 |
+
},
|
| 3666 |
+
{
|
| 3667 |
+
"epoch": 0.1046,
|
| 3668 |
+
"grad_norm": 0.08785756677389145,
|
| 3669 |
+
"learning_rate": 0.002,
|
| 3670 |
+
"loss": 1.9623355865478516,
|
| 3671 |
+
"step": 1046
|
| 3672 |
+
},
|
| 3673 |
+
{
|
| 3674 |
+
"epoch": 0.1048,
|
| 3675 |
+
"grad_norm": 0.09318473190069199,
|
| 3676 |
+
"learning_rate": 0.002,
|
| 3677 |
+
"loss": 2.1089303493499756,
|
| 3678 |
+
"step": 1048
|
| 3679 |
+
},
|
| 3680 |
+
{
|
| 3681 |
+
"epoch": 0.105,
|
| 3682 |
+
"grad_norm": 0.08206820487976074,
|
| 3683 |
+
"learning_rate": 0.002,
|
| 3684 |
+
"loss": 2.2320778369903564,
|
| 3685 |
+
"step": 1050
|
| 3686 |
+
},
|
| 3687 |
+
{
|
| 3688 |
+
"epoch": 0.1052,
|
| 3689 |
+
"grad_norm": 0.08517453819513321,
|
| 3690 |
+
"learning_rate": 0.002,
|
| 3691 |
+
"loss": 2.005950927734375,
|
| 3692 |
+
"step": 1052
|
| 3693 |
+
},
|
| 3694 |
+
{
|
| 3695 |
+
"epoch": 0.1054,
|
| 3696 |
+
"grad_norm": 0.0872499942779541,
|
| 3697 |
+
"learning_rate": 0.002,
|
| 3698 |
+
"loss": 2.032996654510498,
|
| 3699 |
+
"step": 1054
|
| 3700 |
+
},
|
| 3701 |
+
{
|
| 3702 |
+
"epoch": 0.1056,
|
| 3703 |
+
"grad_norm": 0.08218297362327576,
|
| 3704 |
+
"learning_rate": 0.002,
|
| 3705 |
+
"loss": 1.9941152334213257,
|
| 3706 |
+
"step": 1056
|
| 3707 |
+
},
|
| 3708 |
+
{
|
| 3709 |
+
"epoch": 0.1058,
|
| 3710 |
+
"grad_norm": 0.08805368840694427,
|
| 3711 |
+
"learning_rate": 0.002,
|
| 3712 |
+
"loss": 2.1603922843933105,
|
| 3713 |
+
"step": 1058
|
| 3714 |
+
},
|
| 3715 |
+
{
|
| 3716 |
+
"epoch": 0.106,
|
| 3717 |
+
"grad_norm": 0.0835268646478653,
|
| 3718 |
+
"learning_rate": 0.002,
|
| 3719 |
+
"loss": 1.8843207359313965,
|
| 3720 |
+
"step": 1060
|
| 3721 |
+
},
|
| 3722 |
+
{
|
| 3723 |
+
"epoch": 0.1062,
|
| 3724 |
+
"grad_norm": 0.08661171793937683,
|
| 3725 |
+
"learning_rate": 0.002,
|
| 3726 |
+
"loss": 2.143033504486084,
|
| 3727 |
+
"step": 1062
|
| 3728 |
+
},
|
| 3729 |
+
{
|
| 3730 |
+
"epoch": 0.1064,
|
| 3731 |
+
"grad_norm": 0.08741480112075806,
|
| 3732 |
+
"learning_rate": 0.002,
|
| 3733 |
+
"loss": 1.9643219709396362,
|
| 3734 |
+
"step": 1064
|
| 3735 |
+
},
|
| 3736 |
+
{
|
| 3737 |
+
"epoch": 0.1066,
|
| 3738 |
+
"grad_norm": 0.08474089205265045,
|
| 3739 |
+
"learning_rate": 0.002,
|
| 3740 |
+
"loss": 1.9824506044387817,
|
| 3741 |
+
"step": 1066
|
| 3742 |
+
},
|
| 3743 |
+
{
|
| 3744 |
+
"epoch": 0.1068,
|
| 3745 |
+
"grad_norm": 0.08600416034460068,
|
| 3746 |
+
"learning_rate": 0.002,
|
| 3747 |
+
"loss": 2.0218515396118164,
|
| 3748 |
+
"step": 1068
|
| 3749 |
+
},
|
| 3750 |
+
{
|
| 3751 |
+
"epoch": 0.107,
|
| 3752 |
+
"grad_norm": 0.09156841784715652,
|
| 3753 |
+
"learning_rate": 0.002,
|
| 3754 |
+
"loss": 1.9574592113494873,
|
| 3755 |
+
"step": 1070
|
| 3756 |
+
},
|
| 3757 |
+
{
|
| 3758 |
+
"epoch": 0.1072,
|
| 3759 |
+
"grad_norm": 0.07863934338092804,
|
| 3760 |
+
"learning_rate": 0.002,
|
| 3761 |
+
"loss": 1.9684548377990723,
|
| 3762 |
+
"step": 1072
|
| 3763 |
+
},
|
| 3764 |
+
{
|
| 3765 |
+
"epoch": 0.1074,
|
| 3766 |
+
"grad_norm": 0.08361982554197311,
|
| 3767 |
+
"learning_rate": 0.002,
|
| 3768 |
+
"loss": 2.0725059509277344,
|
| 3769 |
+
"step": 1074
|
| 3770 |
+
},
|
| 3771 |
+
{
|
| 3772 |
+
"epoch": 0.1076,
|
| 3773 |
+
"grad_norm": 0.08357243984937668,
|
| 3774 |
+
"learning_rate": 0.002,
|
| 3775 |
+
"loss": 2.0255863666534424,
|
| 3776 |
+
"step": 1076
|
| 3777 |
+
},
|
| 3778 |
+
{
|
| 3779 |
+
"epoch": 0.1078,
|
| 3780 |
+
"grad_norm": 0.08284170925617218,
|
| 3781 |
+
"learning_rate": 0.002,
|
| 3782 |
+
"loss": 2.123167037963867,
|
| 3783 |
+
"step": 1078
|
| 3784 |
+
},
|
| 3785 |
+
{
|
| 3786 |
+
"epoch": 0.108,
|
| 3787 |
+
"grad_norm": 0.08012061566114426,
|
| 3788 |
+
"learning_rate": 0.002,
|
| 3789 |
+
"loss": 1.9576153755187988,
|
| 3790 |
+
"step": 1080
|
| 3791 |
+
},
|
| 3792 |
+
{
|
| 3793 |
+
"epoch": 0.1082,
|
| 3794 |
+
"grad_norm": 0.08395293354988098,
|
| 3795 |
+
"learning_rate": 0.002,
|
| 3796 |
+
"loss": 2.124877691268921,
|
| 3797 |
+
"step": 1082
|
| 3798 |
+
},
|
| 3799 |
+
{
|
| 3800 |
+
"epoch": 0.1084,
|
| 3801 |
+
"grad_norm": 0.08838649839162827,
|
| 3802 |
+
"learning_rate": 0.002,
|
| 3803 |
+
"loss": 2.0684261322021484,
|
| 3804 |
+
"step": 1084
|
| 3805 |
+
},
|
| 3806 |
+
{
|
| 3807 |
+
"epoch": 0.1086,
|
| 3808 |
+
"grad_norm": 0.08425189554691315,
|
| 3809 |
+
"learning_rate": 0.002,
|
| 3810 |
+
"loss": 1.8929017782211304,
|
| 3811 |
+
"step": 1086
|
| 3812 |
+
},
|
| 3813 |
+
{
|
| 3814 |
+
"epoch": 0.1088,
|
| 3815 |
+
"grad_norm": 0.08429091423749924,
|
| 3816 |
+
"learning_rate": 0.002,
|
| 3817 |
+
"loss": 2.0337469577789307,
|
| 3818 |
+
"step": 1088
|
| 3819 |
+
},
|
| 3820 |
+
{
|
| 3821 |
+
"epoch": 0.109,
|
| 3822 |
+
"grad_norm": 0.08154532313346863,
|
| 3823 |
+
"learning_rate": 0.002,
|
| 3824 |
+
"loss": 2.051666498184204,
|
| 3825 |
+
"step": 1090
|
| 3826 |
+
},
|
| 3827 |
+
{
|
| 3828 |
+
"epoch": 0.1092,
|
| 3829 |
+
"grad_norm": 0.09230396896600723,
|
| 3830 |
+
"learning_rate": 0.002,
|
| 3831 |
+
"loss": 2.0522727966308594,
|
| 3832 |
+
"step": 1092
|
| 3833 |
+
},
|
| 3834 |
+
{
|
| 3835 |
+
"epoch": 0.1094,
|
| 3836 |
+
"grad_norm": 0.08772566169500351,
|
| 3837 |
+
"learning_rate": 0.002,
|
| 3838 |
+
"loss": 2.1167776584625244,
|
| 3839 |
+
"step": 1094
|
| 3840 |
+
},
|
| 3841 |
+
{
|
| 3842 |
+
"epoch": 0.1096,
|
| 3843 |
+
"grad_norm": 0.08110581338405609,
|
| 3844 |
+
"learning_rate": 0.002,
|
| 3845 |
+
"loss": 2.104281425476074,
|
| 3846 |
+
"step": 1096
|
| 3847 |
+
},
|
| 3848 |
+
{
|
| 3849 |
+
"epoch": 0.1098,
|
| 3850 |
+
"grad_norm": 0.08904805779457092,
|
| 3851 |
+
"learning_rate": 0.002,
|
| 3852 |
+
"loss": 2.062429189682007,
|
| 3853 |
+
"step": 1098
|
| 3854 |
+
},
|
| 3855 |
+
{
|
| 3856 |
+
"epoch": 0.11,
|
| 3857 |
+
"grad_norm": 0.08452310413122177,
|
| 3858 |
+
"learning_rate": 0.002,
|
| 3859 |
+
"loss": 2.104130744934082,
|
| 3860 |
+
"step": 1100
|
| 3861 |
+
},
|
| 3862 |
+
{
|
| 3863 |
+
"epoch": 0.1102,
|
| 3864 |
+
"grad_norm": 0.0857018306851387,
|
| 3865 |
+
"learning_rate": 0.002,
|
| 3866 |
+
"loss": 2.093200206756592,
|
| 3867 |
+
"step": 1102
|
| 3868 |
+
},
|
| 3869 |
+
{
|
| 3870 |
+
"epoch": 0.1104,
|
| 3871 |
+
"grad_norm": 0.08385004103183746,
|
| 3872 |
+
"learning_rate": 0.002,
|
| 3873 |
+
"loss": 2.0353457927703857,
|
| 3874 |
+
"step": 1104
|
| 3875 |
+
},
|
| 3876 |
+
{
|
| 3877 |
+
"epoch": 0.1106,
|
| 3878 |
+
"grad_norm": 0.08778984844684601,
|
| 3879 |
+
"learning_rate": 0.002,
|
| 3880 |
+
"loss": 2.123830556869507,
|
| 3881 |
+
"step": 1106
|
| 3882 |
+
},
|
| 3883 |
+
{
|
| 3884 |
+
"epoch": 0.1108,
|
| 3885 |
+
"grad_norm": 0.08281433582305908,
|
| 3886 |
+
"learning_rate": 0.002,
|
| 3887 |
+
"loss": 2.0778861045837402,
|
| 3888 |
+
"step": 1108
|
| 3889 |
+
},
|
| 3890 |
+
{
|
| 3891 |
+
"epoch": 0.111,
|
| 3892 |
+
"grad_norm": 0.07921630889177322,
|
| 3893 |
+
"learning_rate": 0.002,
|
| 3894 |
+
"loss": 2.048490285873413,
|
| 3895 |
+
"step": 1110
|
| 3896 |
+
},
|
| 3897 |
+
{
|
| 3898 |
+
"epoch": 0.1112,
|
| 3899 |
+
"grad_norm": 0.08667758107185364,
|
| 3900 |
+
"learning_rate": 0.002,
|
| 3901 |
+
"loss": 2.0113866329193115,
|
| 3902 |
+
"step": 1112
|
| 3903 |
+
},
|
| 3904 |
+
{
|
| 3905 |
+
"epoch": 0.1114,
|
| 3906 |
+
"grad_norm": 0.08297854661941528,
|
| 3907 |
+
"learning_rate": 0.002,
|
| 3908 |
+
"loss": 1.9370574951171875,
|
| 3909 |
+
"step": 1114
|
| 3910 |
+
},
|
| 3911 |
+
{
|
| 3912 |
+
"epoch": 0.1116,
|
| 3913 |
+
"grad_norm": 0.08787955343723297,
|
| 3914 |
+
"learning_rate": 0.002,
|
| 3915 |
+
"loss": 2.1908116340637207,
|
| 3916 |
+
"step": 1116
|
| 3917 |
+
},
|
| 3918 |
+
{
|
| 3919 |
+
"epoch": 0.1118,
|
| 3920 |
+
"grad_norm": 0.09227648377418518,
|
| 3921 |
+
"learning_rate": 0.002,
|
| 3922 |
+
"loss": 2.018409490585327,
|
| 3923 |
+
"step": 1118
|
| 3924 |
+
},
|
| 3925 |
+
{
|
| 3926 |
+
"epoch": 0.112,
|
| 3927 |
+
"grad_norm": 0.08470617979764938,
|
| 3928 |
+
"learning_rate": 0.002,
|
| 3929 |
+
"loss": 2.2633841037750244,
|
| 3930 |
+
"step": 1120
|
| 3931 |
+
},
|
| 3932 |
+
{
|
| 3933 |
+
"epoch": 0.1122,
|
| 3934 |
+
"grad_norm": 0.08956170082092285,
|
| 3935 |
+
"learning_rate": 0.002,
|
| 3936 |
+
"loss": 1.9378591775894165,
|
| 3937 |
+
"step": 1122
|
| 3938 |
+
},
|
| 3939 |
+
{
|
| 3940 |
+
"epoch": 0.1124,
|
| 3941 |
+
"grad_norm": 0.08724003285169601,
|
| 3942 |
+
"learning_rate": 0.002,
|
| 3943 |
+
"loss": 2.1270406246185303,
|
| 3944 |
+
"step": 1124
|
| 3945 |
+
},
|
| 3946 |
+
{
|
| 3947 |
+
"epoch": 0.1126,
|
| 3948 |
+
"grad_norm": 0.08309338986873627,
|
| 3949 |
+
"learning_rate": 0.002,
|
| 3950 |
+
"loss": 2.024172067642212,
|
| 3951 |
+
"step": 1126
|
| 3952 |
+
},
|
| 3953 |
+
{
|
| 3954 |
+
"epoch": 0.1128,
|
| 3955 |
+
"grad_norm": 0.08448407799005508,
|
| 3956 |
+
"learning_rate": 0.002,
|
| 3957 |
+
"loss": 2.034794807434082,
|
| 3958 |
+
"step": 1128
|
| 3959 |
+
},
|
| 3960 |
+
{
|
| 3961 |
+
"epoch": 0.113,
|
| 3962 |
+
"grad_norm": 0.07977596670389175,
|
| 3963 |
+
"learning_rate": 0.002,
|
| 3964 |
+
"loss": 2.0115578174591064,
|
| 3965 |
+
"step": 1130
|
| 3966 |
+
},
|
| 3967 |
+
{
|
| 3968 |
+
"epoch": 0.1132,
|
| 3969 |
+
"grad_norm": 0.08561068028211594,
|
| 3970 |
+
"learning_rate": 0.002,
|
| 3971 |
+
"loss": 2.022027015686035,
|
| 3972 |
+
"step": 1132
|
| 3973 |
+
},
|
| 3974 |
+
{
|
| 3975 |
+
"epoch": 0.1134,
|
| 3976 |
+
"grad_norm": 0.08134664595127106,
|
| 3977 |
+
"learning_rate": 0.002,
|
| 3978 |
+
"loss": 2.1603844165802,
|
| 3979 |
+
"step": 1134
|
| 3980 |
+
},
|
| 3981 |
+
{
|
| 3982 |
+
"epoch": 0.1136,
|
| 3983 |
+
"grad_norm": 0.0817975252866745,
|
| 3984 |
+
"learning_rate": 0.002,
|
| 3985 |
+
"loss": 2.0459768772125244,
|
| 3986 |
+
"step": 1136
|
| 3987 |
+
},
|
| 3988 |
+
{
|
| 3989 |
+
"epoch": 0.1138,
|
| 3990 |
+
"grad_norm": 0.08369145542383194,
|
| 3991 |
+
"learning_rate": 0.002,
|
| 3992 |
+
"loss": 2.014500856399536,
|
| 3993 |
+
"step": 1138
|
| 3994 |
+
},
|
| 3995 |
+
{
|
| 3996 |
+
"epoch": 0.114,
|
| 3997 |
+
"grad_norm": 0.08317965269088745,
|
| 3998 |
+
"learning_rate": 0.002,
|
| 3999 |
+
"loss": 2.0618274211883545,
|
| 4000 |
+
"step": 1140
|
| 4001 |
+
},
|
| 4002 |
+
{
|
| 4003 |
+
"epoch": 0.1142,
|
| 4004 |
+
"grad_norm": 0.08403006196022034,
|
| 4005 |
+
"learning_rate": 0.002,
|
| 4006 |
+
"loss": 2.056919813156128,
|
| 4007 |
+
"step": 1142
|
| 4008 |
+
},
|
| 4009 |
+
{
|
| 4010 |
+
"epoch": 0.1144,
|
| 4011 |
+
"grad_norm": 0.08624644577503204,
|
| 4012 |
+
"learning_rate": 0.002,
|
| 4013 |
+
"loss": 2.1261184215545654,
|
| 4014 |
+
"step": 1144
|
| 4015 |
+
},
|
| 4016 |
+
{
|
| 4017 |
+
"epoch": 0.1146,
|
| 4018 |
+
"grad_norm": 0.09393399953842163,
|
| 4019 |
+
"learning_rate": 0.002,
|
| 4020 |
+
"loss": 1.9532134532928467,
|
| 4021 |
+
"step": 1146
|
| 4022 |
+
},
|
| 4023 |
+
{
|
| 4024 |
+
"epoch": 0.1148,
|
| 4025 |
+
"grad_norm": 0.08186756819486618,
|
| 4026 |
+
"learning_rate": 0.002,
|
| 4027 |
+
"loss": 1.9701474905014038,
|
| 4028 |
+
"step": 1148
|
| 4029 |
+
},
|
| 4030 |
+
{
|
| 4031 |
+
"epoch": 0.115,
|
| 4032 |
+
"grad_norm": 0.08925191313028336,
|
| 4033 |
+
"learning_rate": 0.002,
|
| 4034 |
+
"loss": 2.02519154548645,
|
| 4035 |
+
"step": 1150
|
| 4036 |
+
},
|
| 4037 |
+
{
|
| 4038 |
+
"epoch": 0.1152,
|
| 4039 |
+
"grad_norm": 0.08585000783205032,
|
| 4040 |
+
"learning_rate": 0.002,
|
| 4041 |
+
"loss": 1.9593058824539185,
|
| 4042 |
+
"step": 1152
|
| 4043 |
+
},
|
| 4044 |
+
{
|
| 4045 |
+
"epoch": 0.1154,
|
| 4046 |
+
"grad_norm": 0.08077649772167206,
|
| 4047 |
+
"learning_rate": 0.002,
|
| 4048 |
+
"loss": 1.9867432117462158,
|
| 4049 |
+
"step": 1154
|
| 4050 |
+
},
|
| 4051 |
+
{
|
| 4052 |
+
"epoch": 0.1156,
|
| 4053 |
+
"grad_norm": 0.0841299295425415,
|
| 4054 |
+
"learning_rate": 0.002,
|
| 4055 |
+
"loss": 2.0073344707489014,
|
| 4056 |
+
"step": 1156
|
| 4057 |
+
},
|
| 4058 |
+
{
|
| 4059 |
+
"epoch": 0.1158,
|
| 4060 |
+
"grad_norm": 0.08617623150348663,
|
| 4061 |
+
"learning_rate": 0.002,
|
| 4062 |
+
"loss": 2.055337905883789,
|
| 4063 |
+
"step": 1158
|
| 4064 |
+
},
|
| 4065 |
+
{
|
| 4066 |
+
"epoch": 0.116,
|
| 4067 |
+
"grad_norm": 0.08616787195205688,
|
| 4068 |
+
"learning_rate": 0.002,
|
| 4069 |
+
"loss": 2.165081739425659,
|
| 4070 |
+
"step": 1160
|
| 4071 |
+
},
|
| 4072 |
+
{
|
| 4073 |
+
"epoch": 0.1162,
|
| 4074 |
+
"grad_norm": 0.08450275659561157,
|
| 4075 |
+
"learning_rate": 0.002,
|
| 4076 |
+
"loss": 1.9545855522155762,
|
| 4077 |
+
"step": 1162
|
| 4078 |
+
},
|
| 4079 |
+
{
|
| 4080 |
+
"epoch": 0.1164,
|
| 4081 |
+
"grad_norm": 0.09259680658578873,
|
| 4082 |
+
"learning_rate": 0.002,
|
| 4083 |
+
"loss": 2.0461883544921875,
|
| 4084 |
+
"step": 1164
|
| 4085 |
+
},
|
| 4086 |
+
{
|
| 4087 |
+
"epoch": 0.1166,
|
| 4088 |
+
"grad_norm": 0.08266383409500122,
|
| 4089 |
+
"learning_rate": 0.002,
|
| 4090 |
+
"loss": 1.9070090055465698,
|
| 4091 |
+
"step": 1166
|
| 4092 |
+
},
|
| 4093 |
+
{
|
| 4094 |
+
"epoch": 0.1168,
|
| 4095 |
+
"grad_norm": 0.08327124267816544,
|
| 4096 |
+
"learning_rate": 0.002,
|
| 4097 |
+
"loss": 1.9365736246109009,
|
| 4098 |
+
"step": 1168
|
| 4099 |
+
},
|
| 4100 |
+
{
|
| 4101 |
+
"epoch": 0.117,
|
| 4102 |
+
"grad_norm": 0.0869339257478714,
|
| 4103 |
+
"learning_rate": 0.002,
|
| 4104 |
+
"loss": 2.068601131439209,
|
| 4105 |
+
"step": 1170
|
| 4106 |
+
},
|
| 4107 |
+
{
|
| 4108 |
+
"epoch": 0.1172,
|
| 4109 |
+
"grad_norm": 0.08477666229009628,
|
| 4110 |
+
"learning_rate": 0.002,
|
| 4111 |
+
"loss": 2.068366527557373,
|
| 4112 |
+
"step": 1172
|
| 4113 |
+
},
|
| 4114 |
+
{
|
| 4115 |
+
"epoch": 0.1174,
|
| 4116 |
+
"grad_norm": 0.08698020130395889,
|
| 4117 |
+
"learning_rate": 0.002,
|
| 4118 |
+
"loss": 2.003343105316162,
|
| 4119 |
+
"step": 1174
|
| 4120 |
+
},
|
| 4121 |
+
{
|
| 4122 |
+
"epoch": 0.1176,
|
| 4123 |
+
"grad_norm": 0.08435402065515518,
|
| 4124 |
+
"learning_rate": 0.002,
|
| 4125 |
+
"loss": 1.9344985485076904,
|
| 4126 |
+
"step": 1176
|
| 4127 |
+
},
|
| 4128 |
+
{
|
| 4129 |
+
"epoch": 0.1178,
|
| 4130 |
+
"grad_norm": 0.08306105434894562,
|
| 4131 |
+
"learning_rate": 0.002,
|
| 4132 |
+
"loss": 2.047485828399658,
|
| 4133 |
+
"step": 1178
|
| 4134 |
+
},
|
| 4135 |
+
{
|
| 4136 |
+
"epoch": 0.118,
|
| 4137 |
+
"grad_norm": 0.08435844630002975,
|
| 4138 |
+
"learning_rate": 0.002,
|
| 4139 |
+
"loss": 1.8901934623718262,
|
| 4140 |
+
"step": 1180
|
| 4141 |
+
},
|
| 4142 |
+
{
|
| 4143 |
+
"epoch": 0.1182,
|
| 4144 |
+
"grad_norm": 0.09012391418218613,
|
| 4145 |
+
"learning_rate": 0.002,
|
| 4146 |
+
"loss": 2.106781005859375,
|
| 4147 |
+
"step": 1182
|
| 4148 |
+
},
|
| 4149 |
+
{
|
| 4150 |
+
"epoch": 0.1184,
|
| 4151 |
+
"grad_norm": 0.08325701206922531,
|
| 4152 |
+
"learning_rate": 0.002,
|
| 4153 |
+
"loss": 2.0709898471832275,
|
| 4154 |
+
"step": 1184
|
| 4155 |
+
},
|
| 4156 |
+
{
|
| 4157 |
+
"epoch": 0.1186,
|
| 4158 |
+
"grad_norm": 0.08456530421972275,
|
| 4159 |
+
"learning_rate": 0.002,
|
| 4160 |
+
"loss": 2.1262314319610596,
|
| 4161 |
+
"step": 1186
|
| 4162 |
+
},
|
| 4163 |
+
{
|
| 4164 |
+
"epoch": 0.1188,
|
| 4165 |
+
"grad_norm": 0.08413276821374893,
|
| 4166 |
+
"learning_rate": 0.002,
|
| 4167 |
+
"loss": 1.9871206283569336,
|
| 4168 |
+
"step": 1188
|
| 4169 |
+
},
|
| 4170 |
+
{
|
| 4171 |
+
"epoch": 0.119,
|
| 4172 |
+
"grad_norm": 0.08718832582235336,
|
| 4173 |
+
"learning_rate": 0.002,
|
| 4174 |
+
"loss": 2.084408760070801,
|
| 4175 |
+
"step": 1190
|
| 4176 |
+
},
|
| 4177 |
+
{
|
| 4178 |
+
"epoch": 0.1192,
|
| 4179 |
+
"grad_norm": 0.08340590447187424,
|
| 4180 |
+
"learning_rate": 0.002,
|
| 4181 |
+
"loss": 1.8883227109909058,
|
| 4182 |
+
"step": 1192
|
| 4183 |
+
},
|
| 4184 |
+
{
|
| 4185 |
+
"epoch": 0.1194,
|
| 4186 |
+
"grad_norm": 0.07996539771556854,
|
| 4187 |
+
"learning_rate": 0.002,
|
| 4188 |
+
"loss": 2.039456367492676,
|
| 4189 |
+
"step": 1194
|
| 4190 |
+
},
|
| 4191 |
+
{
|
| 4192 |
+
"epoch": 0.1196,
|
| 4193 |
+
"grad_norm": 0.08217329531908035,
|
| 4194 |
+
"learning_rate": 0.002,
|
| 4195 |
+
"loss": 2.024759531021118,
|
| 4196 |
+
"step": 1196
|
| 4197 |
+
},
|
| 4198 |
+
{
|
| 4199 |
+
"epoch": 0.1198,
|
| 4200 |
+
"grad_norm": 0.08313747495412827,
|
| 4201 |
+
"learning_rate": 0.002,
|
| 4202 |
+
"loss": 2.103900194168091,
|
| 4203 |
+
"step": 1198
|
| 4204 |
+
},
|
| 4205 |
+
{
|
| 4206 |
+
"epoch": 0.12,
|
| 4207 |
+
"grad_norm": 0.0881541520357132,
|
| 4208 |
+
"learning_rate": 0.002,
|
| 4209 |
+
"loss": 2.222304344177246,
|
| 4210 |
+
"step": 1200
|
| 4211 |
+
},
|
| 4212 |
+
{
|
| 4213 |
+
"epoch": 0.1202,
|
| 4214 |
+
"grad_norm": 0.08509214967489243,
|
| 4215 |
+
"learning_rate": 0.002,
|
| 4216 |
+
"loss": 2.061307907104492,
|
| 4217 |
+
"step": 1202
|
| 4218 |
+
},
|
| 4219 |
+
{
|
| 4220 |
+
"epoch": 0.1204,
|
| 4221 |
+
"grad_norm": 0.08412045985460281,
|
| 4222 |
+
"learning_rate": 0.002,
|
| 4223 |
+
"loss": 2.0424652099609375,
|
| 4224 |
+
"step": 1204
|
| 4225 |
+
},
|
| 4226 |
+
{
|
| 4227 |
+
"epoch": 0.1206,
|
| 4228 |
+
"grad_norm": 0.08259782195091248,
|
| 4229 |
+
"learning_rate": 0.002,
|
| 4230 |
+
"loss": 1.8773162364959717,
|
| 4231 |
+
"step": 1206
|
| 4232 |
+
},
|
| 4233 |
+
{
|
| 4234 |
+
"epoch": 0.1208,
|
| 4235 |
+
"grad_norm": 0.08027885109186172,
|
| 4236 |
+
"learning_rate": 0.002,
|
| 4237 |
+
"loss": 2.0441079139709473,
|
| 4238 |
+
"step": 1208
|
| 4239 |
+
},
|
| 4240 |
+
{
|
| 4241 |
+
"epoch": 0.121,
|
| 4242 |
+
"grad_norm": 0.08164530247449875,
|
| 4243 |
+
"learning_rate": 0.002,
|
| 4244 |
+
"loss": 1.7741857767105103,
|
| 4245 |
+
"step": 1210
|
| 4246 |
+
},
|
| 4247 |
+
{
|
| 4248 |
+
"epoch": 0.1212,
|
| 4249 |
+
"grad_norm": 0.07959095388650894,
|
| 4250 |
+
"learning_rate": 0.002,
|
| 4251 |
+
"loss": 1.986232876777649,
|
| 4252 |
+
"step": 1212
|
| 4253 |
+
},
|
| 4254 |
+
{
|
| 4255 |
+
"epoch": 0.1214,
|
| 4256 |
+
"grad_norm": 0.0858709067106247,
|
| 4257 |
+
"learning_rate": 0.002,
|
| 4258 |
+
"loss": 2.1754837036132812,
|
| 4259 |
+
"step": 1214
|
| 4260 |
+
},
|
| 4261 |
+
{
|
| 4262 |
+
"epoch": 0.1216,
|
| 4263 |
+
"grad_norm": 0.08982837945222855,
|
| 4264 |
+
"learning_rate": 0.002,
|
| 4265 |
+
"loss": 2.0495615005493164,
|
| 4266 |
+
"step": 1216
|
| 4267 |
+
},
|
| 4268 |
+
{
|
| 4269 |
+
"epoch": 0.1218,
|
| 4270 |
+
"grad_norm": 0.08699710667133331,
|
| 4271 |
+
"learning_rate": 0.002,
|
| 4272 |
+
"loss": 2.140305995941162,
|
| 4273 |
+
"step": 1218
|
| 4274 |
+
},
|
| 4275 |
+
{
|
| 4276 |
+
"epoch": 0.122,
|
| 4277 |
+
"grad_norm": 0.08187000453472137,
|
| 4278 |
+
"learning_rate": 0.002,
|
| 4279 |
+
"loss": 2.2325439453125,
|
| 4280 |
+
"step": 1220
|
| 4281 |
+
},
|
| 4282 |
+
{
|
| 4283 |
+
"epoch": 0.1222,
|
| 4284 |
+
"grad_norm": 0.08354407548904419,
|
| 4285 |
+
"learning_rate": 0.002,
|
| 4286 |
+
"loss": 1.9623830318450928,
|
| 4287 |
+
"step": 1222
|
| 4288 |
+
},
|
| 4289 |
+
{
|
| 4290 |
+
"epoch": 0.1224,
|
| 4291 |
+
"grad_norm": 0.0819743424654007,
|
| 4292 |
+
"learning_rate": 0.002,
|
| 4293 |
+
"loss": 1.944139003753662,
|
| 4294 |
+
"step": 1224
|
| 4295 |
+
},
|
| 4296 |
+
{
|
| 4297 |
+
"epoch": 0.1226,
|
| 4298 |
+
"grad_norm": 0.0813278779387474,
|
| 4299 |
+
"learning_rate": 0.002,
|
| 4300 |
+
"loss": 2.115978479385376,
|
| 4301 |
+
"step": 1226
|
| 4302 |
+
},
|
| 4303 |
+
{
|
| 4304 |
+
"epoch": 0.1228,
|
| 4305 |
+
"grad_norm": 0.07694555073976517,
|
| 4306 |
+
"learning_rate": 0.002,
|
| 4307 |
+
"loss": 2.039741277694702,
|
| 4308 |
+
"step": 1228
|
| 4309 |
+
},
|
| 4310 |
+
{
|
| 4311 |
+
"epoch": 0.123,
|
| 4312 |
+
"grad_norm": 0.085311658680439,
|
| 4313 |
+
"learning_rate": 0.002,
|
| 4314 |
+
"loss": 2.0899102687835693,
|
| 4315 |
+
"step": 1230
|
| 4316 |
+
},
|
| 4317 |
+
{
|
| 4318 |
+
"epoch": 0.1232,
|
| 4319 |
+
"grad_norm": 0.09176570177078247,
|
| 4320 |
+
"learning_rate": 0.002,
|
| 4321 |
+
"loss": 2.0086252689361572,
|
| 4322 |
+
"step": 1232
|
| 4323 |
+
},
|
| 4324 |
+
{
|
| 4325 |
+
"epoch": 0.1234,
|
| 4326 |
+
"grad_norm": 0.09619509428739548,
|
| 4327 |
+
"learning_rate": 0.002,
|
| 4328 |
+
"loss": 2.032975196838379,
|
| 4329 |
+
"step": 1234
|
| 4330 |
+
},
|
| 4331 |
+
{
|
| 4332 |
+
"epoch": 0.1236,
|
| 4333 |
+
"grad_norm": 0.08549220860004425,
|
| 4334 |
+
"learning_rate": 0.002,
|
| 4335 |
+
"loss": 2.0882456302642822,
|
| 4336 |
+
"step": 1236
|
| 4337 |
+
},
|
| 4338 |
+
{
|
| 4339 |
+
"epoch": 0.1238,
|
| 4340 |
+
"grad_norm": 0.08163252472877502,
|
| 4341 |
+
"learning_rate": 0.002,
|
| 4342 |
+
"loss": 2.1956636905670166,
|
| 4343 |
+
"step": 1238
|
| 4344 |
+
},
|
| 4345 |
+
{
|
| 4346 |
+
"epoch": 0.124,
|
| 4347 |
+
"grad_norm": 0.090960793197155,
|
| 4348 |
+
"learning_rate": 0.002,
|
| 4349 |
+
"loss": 1.989876627922058,
|
| 4350 |
+
"step": 1240
|
| 4351 |
+
},
|
| 4352 |
+
{
|
| 4353 |
+
"epoch": 0.1242,
|
| 4354 |
+
"grad_norm": 0.08690346032381058,
|
| 4355 |
+
"learning_rate": 0.002,
|
| 4356 |
+
"loss": 1.9766404628753662,
|
| 4357 |
+
"step": 1242
|
| 4358 |
+
},
|
| 4359 |
+
{
|
| 4360 |
+
"epoch": 0.1244,
|
| 4361 |
+
"grad_norm": 0.08295867592096329,
|
| 4362 |
+
"learning_rate": 0.002,
|
| 4363 |
+
"loss": 1.9767091274261475,
|
| 4364 |
+
"step": 1244
|
| 4365 |
+
},
|
| 4366 |
+
{
|
| 4367 |
+
"epoch": 0.1246,
|
| 4368 |
+
"grad_norm": 0.09051886945962906,
|
| 4369 |
+
"learning_rate": 0.002,
|
| 4370 |
+
"loss": 1.9998339414596558,
|
| 4371 |
+
"step": 1246
|
| 4372 |
+
},
|
| 4373 |
+
{
|
| 4374 |
+
"epoch": 0.1248,
|
| 4375 |
+
"grad_norm": 0.08345075696706772,
|
| 4376 |
+
"learning_rate": 0.002,
|
| 4377 |
+
"loss": 2.077249050140381,
|
| 4378 |
+
"step": 1248
|
| 4379 |
+
},
|
| 4380 |
+
{
|
| 4381 |
+
"epoch": 0.125,
|
| 4382 |
+
"grad_norm": 0.08784466981887817,
|
| 4383 |
+
"learning_rate": 0.002,
|
| 4384 |
+
"loss": 1.9706625938415527,
|
| 4385 |
+
"step": 1250
|
| 4386 |
+
},
|
| 4387 |
+
{
|
| 4388 |
+
"epoch": 0.1252,
|
| 4389 |
+
"grad_norm": 0.08191345632076263,
|
| 4390 |
+
"learning_rate": 0.002,
|
| 4391 |
+
"loss": 1.9752776622772217,
|
| 4392 |
+
"step": 1252
|
| 4393 |
+
},
|
| 4394 |
+
{
|
| 4395 |
+
"epoch": 0.1254,
|
| 4396 |
+
"grad_norm": 0.08956123888492584,
|
| 4397 |
+
"learning_rate": 0.002,
|
| 4398 |
+
"loss": 2.182732105255127,
|
| 4399 |
+
"step": 1254
|
| 4400 |
+
},
|
| 4401 |
+
{
|
| 4402 |
+
"epoch": 0.1256,
|
| 4403 |
+
"grad_norm": 0.08047401160001755,
|
| 4404 |
+
"learning_rate": 0.002,
|
| 4405 |
+
"loss": 1.9972858428955078,
|
| 4406 |
+
"step": 1256
|
| 4407 |
+
},
|
| 4408 |
+
{
|
| 4409 |
+
"epoch": 0.1258,
|
| 4410 |
+
"grad_norm": 0.08208698779344559,
|
| 4411 |
+
"learning_rate": 0.002,
|
| 4412 |
+
"loss": 2.0774693489074707,
|
| 4413 |
+
"step": 1258
|
| 4414 |
+
},
|
| 4415 |
+
{
|
| 4416 |
+
"epoch": 0.126,
|
| 4417 |
+
"grad_norm": 0.08476417511701584,
|
| 4418 |
+
"learning_rate": 0.002,
|
| 4419 |
+
"loss": 1.952588677406311,
|
| 4420 |
+
"step": 1260
|
| 4421 |
+
},
|
| 4422 |
+
{
|
| 4423 |
+
"epoch": 0.1262,
|
| 4424 |
+
"grad_norm": 0.0856880471110344,
|
| 4425 |
+
"learning_rate": 0.002,
|
| 4426 |
+
"loss": 1.926142692565918,
|
| 4427 |
+
"step": 1262
|
| 4428 |
+
},
|
| 4429 |
+
{
|
| 4430 |
+
"epoch": 0.1264,
|
| 4431 |
+
"grad_norm": 0.07638447731733322,
|
| 4432 |
+
"learning_rate": 0.002,
|
| 4433 |
+
"loss": 2.017592430114746,
|
| 4434 |
+
"step": 1264
|
| 4435 |
+
},
|
| 4436 |
+
{
|
| 4437 |
+
"epoch": 0.1266,
|
| 4438 |
+
"grad_norm": 0.09431228041648865,
|
| 4439 |
+
"learning_rate": 0.002,
|
| 4440 |
+
"loss": 2.0062355995178223,
|
| 4441 |
+
"step": 1266
|
| 4442 |
+
},
|
| 4443 |
+
{
|
| 4444 |
+
"epoch": 0.1268,
|
| 4445 |
+
"grad_norm": 0.08278736472129822,
|
| 4446 |
+
"learning_rate": 0.002,
|
| 4447 |
+
"loss": 2.0274674892425537,
|
| 4448 |
+
"step": 1268
|
| 4449 |
+
},
|
| 4450 |
+
{
|
| 4451 |
+
"epoch": 0.127,
|
| 4452 |
+
"grad_norm": 0.07975926250219345,
|
| 4453 |
+
"learning_rate": 0.002,
|
| 4454 |
+
"loss": 2.0235726833343506,
|
| 4455 |
+
"step": 1270
|
| 4456 |
+
},
|
| 4457 |
+
{
|
| 4458 |
+
"epoch": 0.1272,
|
| 4459 |
+
"grad_norm": 0.08381231129169464,
|
| 4460 |
+
"learning_rate": 0.002,
|
| 4461 |
+
"loss": 1.9192882776260376,
|
| 4462 |
+
"step": 1272
|
| 4463 |
+
},
|
| 4464 |
+
{
|
| 4465 |
+
"epoch": 0.1274,
|
| 4466 |
+
"grad_norm": 0.08344686776399612,
|
| 4467 |
+
"learning_rate": 0.002,
|
| 4468 |
+
"loss": 2.1065878868103027,
|
| 4469 |
+
"step": 1274
|
| 4470 |
+
},
|
| 4471 |
+
{
|
| 4472 |
+
"epoch": 0.1276,
|
| 4473 |
+
"grad_norm": 0.0879516452550888,
|
| 4474 |
+
"learning_rate": 0.002,
|
| 4475 |
+
"loss": 2.0292720794677734,
|
| 4476 |
+
"step": 1276
|
| 4477 |
+
},
|
| 4478 |
+
{
|
| 4479 |
+
"epoch": 0.1278,
|
| 4480 |
+
"grad_norm": 0.07877160608768463,
|
| 4481 |
+
"learning_rate": 0.002,
|
| 4482 |
+
"loss": 1.9498127698898315,
|
| 4483 |
+
"step": 1278
|
| 4484 |
+
},
|
| 4485 |
+
{
|
| 4486 |
+
"epoch": 0.128,
|
| 4487 |
+
"grad_norm": 0.08284289389848709,
|
| 4488 |
+
"learning_rate": 0.002,
|
| 4489 |
+
"loss": 1.961515188217163,
|
| 4490 |
+
"step": 1280
|
| 4491 |
+
},
|
| 4492 |
+
{
|
| 4493 |
+
"epoch": 0.1282,
|
| 4494 |
+
"grad_norm": 0.09120652824640274,
|
| 4495 |
+
"learning_rate": 0.002,
|
| 4496 |
+
"loss": 1.9631229639053345,
|
| 4497 |
+
"step": 1282
|
| 4498 |
+
},
|
| 4499 |
+
{
|
| 4500 |
+
"epoch": 0.1284,
|
| 4501 |
+
"grad_norm": 0.07842068374156952,
|
| 4502 |
+
"learning_rate": 0.002,
|
| 4503 |
+
"loss": 1.9782634973526,
|
| 4504 |
+
"step": 1284
|
| 4505 |
+
},
|
| 4506 |
+
{
|
| 4507 |
+
"epoch": 0.1286,
|
| 4508 |
+
"grad_norm": 0.0847662091255188,
|
| 4509 |
+
"learning_rate": 0.002,
|
| 4510 |
+
"loss": 2.046393394470215,
|
| 4511 |
+
"step": 1286
|
| 4512 |
+
},
|
| 4513 |
+
{
|
| 4514 |
+
"epoch": 0.1288,
|
| 4515 |
+
"grad_norm": 0.08472472429275513,
|
| 4516 |
+
"learning_rate": 0.002,
|
| 4517 |
+
"loss": 2.0080883502960205,
|
| 4518 |
+
"step": 1288
|
| 4519 |
+
},
|
| 4520 |
+
{
|
| 4521 |
+
"epoch": 0.129,
|
| 4522 |
+
"grad_norm": 0.08054573088884354,
|
| 4523 |
+
"learning_rate": 0.002,
|
| 4524 |
+
"loss": 1.985576868057251,
|
| 4525 |
+
"step": 1290
|
| 4526 |
+
},
|
| 4527 |
+
{
|
| 4528 |
+
"epoch": 0.1292,
|
| 4529 |
+
"grad_norm": 0.07891428470611572,
|
| 4530 |
+
"learning_rate": 0.002,
|
| 4531 |
+
"loss": 1.9087384939193726,
|
| 4532 |
+
"step": 1292
|
| 4533 |
+
},
|
| 4534 |
+
{
|
| 4535 |
+
"epoch": 0.1294,
|
| 4536 |
+
"grad_norm": 0.08551960438489914,
|
| 4537 |
+
"learning_rate": 0.002,
|
| 4538 |
+
"loss": 2.0102670192718506,
|
| 4539 |
+
"step": 1294
|
| 4540 |
+
},
|
| 4541 |
+
{
|
| 4542 |
+
"epoch": 0.1296,
|
| 4543 |
+
"grad_norm": 0.08134318888187408,
|
| 4544 |
+
"learning_rate": 0.002,
|
| 4545 |
+
"loss": 2.0879855155944824,
|
| 4546 |
+
"step": 1296
|
| 4547 |
+
},
|
| 4548 |
+
{
|
| 4549 |
+
"epoch": 0.1298,
|
| 4550 |
+
"grad_norm": 0.08065108954906464,
|
| 4551 |
+
"learning_rate": 0.002,
|
| 4552 |
+
"loss": 2.0096890926361084,
|
| 4553 |
+
"step": 1298
|
| 4554 |
+
},
|
| 4555 |
+
{
|
| 4556 |
+
"epoch": 0.13,
|
| 4557 |
+
"grad_norm": 0.08614367246627808,
|
| 4558 |
+
"learning_rate": 0.002,
|
| 4559 |
+
"loss": 1.9494773149490356,
|
| 4560 |
+
"step": 1300
|
| 4561 |
+
},
|
| 4562 |
+
{
|
| 4563 |
+
"epoch": 0.1302,
|
| 4564 |
+
"grad_norm": 0.08957385271787643,
|
| 4565 |
+
"learning_rate": 0.002,
|
| 4566 |
+
"loss": 1.9771714210510254,
|
| 4567 |
+
"step": 1302
|
| 4568 |
+
},
|
| 4569 |
+
{
|
| 4570 |
+
"epoch": 0.1304,
|
| 4571 |
+
"grad_norm": 0.07945297658443451,
|
| 4572 |
+
"learning_rate": 0.002,
|
| 4573 |
+
"loss": 1.8320209980010986,
|
| 4574 |
+
"step": 1304
|
| 4575 |
+
},
|
| 4576 |
+
{
|
| 4577 |
+
"epoch": 0.1306,
|
| 4578 |
+
"grad_norm": 0.08779644221067429,
|
| 4579 |
+
"learning_rate": 0.002,
|
| 4580 |
+
"loss": 1.9819495677947998,
|
| 4581 |
+
"step": 1306
|
| 4582 |
+
},
|
| 4583 |
+
{
|
| 4584 |
+
"epoch": 0.1308,
|
| 4585 |
+
"grad_norm": 0.08483578264713287,
|
| 4586 |
+
"learning_rate": 0.002,
|
| 4587 |
+
"loss": 2.0804686546325684,
|
| 4588 |
+
"step": 1308
|
| 4589 |
+
},
|
| 4590 |
+
{
|
| 4591 |
+
"epoch": 0.131,
|
| 4592 |
+
"grad_norm": 0.08246662467718124,
|
| 4593 |
+
"learning_rate": 0.002,
|
| 4594 |
+
"loss": 1.9303864240646362,
|
| 4595 |
+
"step": 1310
|
| 4596 |
+
},
|
| 4597 |
+
{
|
| 4598 |
+
"epoch": 0.1312,
|
| 4599 |
+
"grad_norm": 0.08496952056884766,
|
| 4600 |
+
"learning_rate": 0.002,
|
| 4601 |
+
"loss": 2.158707618713379,
|
| 4602 |
+
"step": 1312
|
| 4603 |
+
},
|
| 4604 |
+
{
|
| 4605 |
+
"epoch": 0.1314,
|
| 4606 |
+
"grad_norm": 0.08043855428695679,
|
| 4607 |
+
"learning_rate": 0.002,
|
| 4608 |
+
"loss": 2.0037665367126465,
|
| 4609 |
+
"step": 1314
|
| 4610 |
+
},
|
| 4611 |
+
{
|
| 4612 |
+
"epoch": 0.1316,
|
| 4613 |
+
"grad_norm": 0.08313608914613724,
|
| 4614 |
+
"learning_rate": 0.002,
|
| 4615 |
+
"loss": 2.0118744373321533,
|
| 4616 |
+
"step": 1316
|
| 4617 |
+
},
|
| 4618 |
+
{
|
| 4619 |
+
"epoch": 0.1318,
|
| 4620 |
+
"grad_norm": 0.08287588506937027,
|
| 4621 |
+
"learning_rate": 0.002,
|
| 4622 |
+
"loss": 2.1368191242218018,
|
| 4623 |
+
"step": 1318
|
| 4624 |
+
},
|
| 4625 |
+
{
|
| 4626 |
+
"epoch": 0.132,
|
| 4627 |
+
"grad_norm": 0.08581621944904327,
|
| 4628 |
+
"learning_rate": 0.002,
|
| 4629 |
+
"loss": 2.2238590717315674,
|
| 4630 |
+
"step": 1320
|
| 4631 |
+
},
|
| 4632 |
+
{
|
| 4633 |
+
"epoch": 0.1322,
|
| 4634 |
+
"grad_norm": 0.08289754390716553,
|
| 4635 |
+
"learning_rate": 0.002,
|
| 4636 |
+
"loss": 1.9536819458007812,
|
| 4637 |
+
"step": 1322
|
| 4638 |
+
},
|
| 4639 |
+
{
|
| 4640 |
+
"epoch": 0.1324,
|
| 4641 |
+
"grad_norm": 0.08500684797763824,
|
| 4642 |
+
"learning_rate": 0.002,
|
| 4643 |
+
"loss": 1.9097071886062622,
|
| 4644 |
+
"step": 1324
|
| 4645 |
+
},
|
| 4646 |
+
{
|
| 4647 |
+
"epoch": 0.1326,
|
| 4648 |
+
"grad_norm": 0.08194470405578613,
|
| 4649 |
+
"learning_rate": 0.002,
|
| 4650 |
+
"loss": 2.009051561355591,
|
| 4651 |
+
"step": 1326
|
| 4652 |
+
},
|
| 4653 |
+
{
|
| 4654 |
+
"epoch": 0.1328,
|
| 4655 |
+
"grad_norm": 0.08581238985061646,
|
| 4656 |
+
"learning_rate": 0.002,
|
| 4657 |
+
"loss": 2.0748465061187744,
|
| 4658 |
+
"step": 1328
|
| 4659 |
+
},
|
| 4660 |
+
{
|
| 4661 |
+
"epoch": 0.133,
|
| 4662 |
+
"grad_norm": 0.08034423738718033,
|
| 4663 |
+
"learning_rate": 0.002,
|
| 4664 |
+
"loss": 2.1352503299713135,
|
| 4665 |
+
"step": 1330
|
| 4666 |
+
},
|
| 4667 |
+
{
|
| 4668 |
+
"epoch": 0.1332,
|
| 4669 |
+
"grad_norm": 0.08761461079120636,
|
| 4670 |
+
"learning_rate": 0.002,
|
| 4671 |
+
"loss": 1.940513253211975,
|
| 4672 |
+
"step": 1332
|
| 4673 |
+
},
|
| 4674 |
+
{
|
| 4675 |
+
"epoch": 0.1334,
|
| 4676 |
+
"grad_norm": 0.09479259699583054,
|
| 4677 |
+
"learning_rate": 0.002,
|
| 4678 |
+
"loss": 2.0859739780426025,
|
| 4679 |
+
"step": 1334
|
| 4680 |
+
},
|
| 4681 |
+
{
|
| 4682 |
+
"epoch": 0.1336,
|
| 4683 |
+
"grad_norm": 0.08276405930519104,
|
| 4684 |
+
"learning_rate": 0.002,
|
| 4685 |
+
"loss": 1.9383325576782227,
|
| 4686 |
+
"step": 1336
|
| 4687 |
+
},
|
| 4688 |
+
{
|
| 4689 |
+
"epoch": 0.1338,
|
| 4690 |
+
"grad_norm": 0.08897998183965683,
|
| 4691 |
+
"learning_rate": 0.002,
|
| 4692 |
+
"loss": 1.9012813568115234,
|
| 4693 |
+
"step": 1338
|
| 4694 |
+
},
|
| 4695 |
+
{
|
| 4696 |
+
"epoch": 0.134,
|
| 4697 |
+
"grad_norm": 0.08546336740255356,
|
| 4698 |
+
"learning_rate": 0.002,
|
| 4699 |
+
"loss": 2.0785326957702637,
|
| 4700 |
+
"step": 1340
|
| 4701 |
+
},
|
| 4702 |
+
{
|
| 4703 |
+
"epoch": 0.1342,
|
| 4704 |
+
"grad_norm": 0.07834289968013763,
|
| 4705 |
+
"learning_rate": 0.002,
|
| 4706 |
+
"loss": 1.9747636318206787,
|
| 4707 |
+
"step": 1342
|
| 4708 |
+
},
|
| 4709 |
+
{
|
| 4710 |
+
"epoch": 0.1344,
|
| 4711 |
+
"grad_norm": 0.08041142672300339,
|
| 4712 |
+
"learning_rate": 0.002,
|
| 4713 |
+
"loss": 1.8900039196014404,
|
| 4714 |
+
"step": 1344
|
| 4715 |
+
},
|
| 4716 |
+
{
|
| 4717 |
+
"epoch": 0.1346,
|
| 4718 |
+
"grad_norm": 0.08464096486568451,
|
| 4719 |
+
"learning_rate": 0.002,
|
| 4720 |
+
"loss": 1.9109103679656982,
|
| 4721 |
+
"step": 1346
|
| 4722 |
+
},
|
| 4723 |
+
{
|
| 4724 |
+
"epoch": 0.1348,
|
| 4725 |
+
"grad_norm": 0.08302085101604462,
|
| 4726 |
+
"learning_rate": 0.002,
|
| 4727 |
+
"loss": 2.083608865737915,
|
| 4728 |
+
"step": 1348
|
| 4729 |
+
},
|
| 4730 |
+
{
|
| 4731 |
+
"epoch": 0.135,
|
| 4732 |
+
"grad_norm": 0.08918166160583496,
|
| 4733 |
+
"learning_rate": 0.002,
|
| 4734 |
+
"loss": 2.1519148349761963,
|
| 4735 |
+
"step": 1350
|
| 4736 |
+
},
|
| 4737 |
+
{
|
| 4738 |
+
"epoch": 0.1352,
|
| 4739 |
+
"grad_norm": 0.08706078678369522,
|
| 4740 |
+
"learning_rate": 0.002,
|
| 4741 |
+
"loss": 1.8809285163879395,
|
| 4742 |
+
"step": 1352
|
| 4743 |
+
},
|
| 4744 |
+
{
|
| 4745 |
+
"epoch": 0.1354,
|
| 4746 |
+
"grad_norm": 0.08329781889915466,
|
| 4747 |
+
"learning_rate": 0.002,
|
| 4748 |
+
"loss": 1.9737176895141602,
|
| 4749 |
+
"step": 1354
|
| 4750 |
+
},
|
| 4751 |
+
{
|
| 4752 |
+
"epoch": 0.1356,
|
| 4753 |
+
"grad_norm": 0.081386499106884,
|
| 4754 |
+
"learning_rate": 0.002,
|
| 4755 |
+
"loss": 2.104400873184204,
|
| 4756 |
+
"step": 1356
|
| 4757 |
+
},
|
| 4758 |
+
{
|
| 4759 |
+
"epoch": 0.1358,
|
| 4760 |
+
"grad_norm": 0.08352888375520706,
|
| 4761 |
+
"learning_rate": 0.002,
|
| 4762 |
+
"loss": 2.0278191566467285,
|
| 4763 |
+
"step": 1358
|
| 4764 |
+
},
|
| 4765 |
+
{
|
| 4766 |
+
"epoch": 0.136,
|
| 4767 |
+
"grad_norm": 0.09237174689769745,
|
| 4768 |
+
"learning_rate": 0.002,
|
| 4769 |
+
"loss": 2.112232208251953,
|
| 4770 |
+
"step": 1360
|
| 4771 |
+
},
|
| 4772 |
+
{
|
| 4773 |
+
"epoch": 0.1362,
|
| 4774 |
+
"grad_norm": 0.08363782614469528,
|
| 4775 |
+
"learning_rate": 0.002,
|
| 4776 |
+
"loss": 1.9792081117630005,
|
| 4777 |
+
"step": 1362
|
| 4778 |
+
},
|
| 4779 |
+
{
|
| 4780 |
+
"epoch": 0.1364,
|
| 4781 |
+
"grad_norm": 0.08287493884563446,
|
| 4782 |
+
"learning_rate": 0.002,
|
| 4783 |
+
"loss": 2.1652090549468994,
|
| 4784 |
+
"step": 1364
|
| 4785 |
+
},
|
| 4786 |
+
{
|
| 4787 |
+
"epoch": 0.1366,
|
| 4788 |
+
"grad_norm": 0.08788807690143585,
|
| 4789 |
+
"learning_rate": 0.002,
|
| 4790 |
+
"loss": 2.1167266368865967,
|
| 4791 |
+
"step": 1366
|
| 4792 |
+
},
|
| 4793 |
+
{
|
| 4794 |
+
"epoch": 0.1368,
|
| 4795 |
+
"grad_norm": 0.08260025829076767,
|
| 4796 |
+
"learning_rate": 0.002,
|
| 4797 |
+
"loss": 1.980812430381775,
|
| 4798 |
+
"step": 1368
|
| 4799 |
+
},
|
| 4800 |
+
{
|
| 4801 |
+
"epoch": 0.137,
|
| 4802 |
+
"grad_norm": 0.08492080122232437,
|
| 4803 |
+
"learning_rate": 0.002,
|
| 4804 |
+
"loss": 2.1833114624023438,
|
| 4805 |
+
"step": 1370
|
| 4806 |
+
},
|
| 4807 |
+
{
|
| 4808 |
+
"epoch": 0.1372,
|
| 4809 |
+
"grad_norm": 0.09278244525194168,
|
| 4810 |
+
"learning_rate": 0.002,
|
| 4811 |
+
"loss": 2.0212106704711914,
|
| 4812 |
+
"step": 1372
|
| 4813 |
+
},
|
| 4814 |
+
{
|
| 4815 |
+
"epoch": 0.1374,
|
| 4816 |
+
"grad_norm": 0.08107468485832214,
|
| 4817 |
+
"learning_rate": 0.002,
|
| 4818 |
+
"loss": 2.0436851978302,
|
| 4819 |
+
"step": 1374
|
| 4820 |
+
},
|
| 4821 |
+
{
|
| 4822 |
+
"epoch": 0.1376,
|
| 4823 |
+
"grad_norm": 0.0862237960100174,
|
| 4824 |
+
"learning_rate": 0.002,
|
| 4825 |
+
"loss": 2.1253888607025146,
|
| 4826 |
+
"step": 1376
|
| 4827 |
+
},
|
| 4828 |
+
{
|
| 4829 |
+
"epoch": 0.1378,
|
| 4830 |
+
"grad_norm": 0.08353643864393234,
|
| 4831 |
+
"learning_rate": 0.002,
|
| 4832 |
+
"loss": 2.0461161136627197,
|
| 4833 |
+
"step": 1378
|
| 4834 |
+
},
|
| 4835 |
+
{
|
| 4836 |
+
"epoch": 0.138,
|
| 4837 |
+
"grad_norm": 0.08285964280366898,
|
| 4838 |
+
"learning_rate": 0.002,
|
| 4839 |
+
"loss": 1.9251466989517212,
|
| 4840 |
+
"step": 1380
|
| 4841 |
+
},
|
| 4842 |
+
{
|
| 4843 |
+
"epoch": 0.1382,
|
| 4844 |
+
"grad_norm": 0.0818663164973259,
|
| 4845 |
+
"learning_rate": 0.002,
|
| 4846 |
+
"loss": 2.0516092777252197,
|
| 4847 |
+
"step": 1382
|
| 4848 |
+
},
|
| 4849 |
+
{
|
| 4850 |
+
"epoch": 0.1384,
|
| 4851 |
+
"grad_norm": 0.08050210773944855,
|
| 4852 |
+
"learning_rate": 0.002,
|
| 4853 |
+
"loss": 1.8944146633148193,
|
| 4854 |
+
"step": 1384
|
| 4855 |
+
},
|
| 4856 |
+
{
|
| 4857 |
+
"epoch": 0.1386,
|
| 4858 |
+
"grad_norm": 0.08588985353708267,
|
| 4859 |
+
"learning_rate": 0.002,
|
| 4860 |
+
"loss": 2.0791821479797363,
|
| 4861 |
+
"step": 1386
|
| 4862 |
+
},
|
| 4863 |
+
{
|
| 4864 |
+
"epoch": 0.1388,
|
| 4865 |
+
"grad_norm": 0.08128977566957474,
|
| 4866 |
+
"learning_rate": 0.002,
|
| 4867 |
+
"loss": 2.0822651386260986,
|
| 4868 |
+
"step": 1388
|
| 4869 |
+
},
|
| 4870 |
+
{
|
| 4871 |
+
"epoch": 0.139,
|
| 4872 |
+
"grad_norm": 0.08936209976673126,
|
| 4873 |
+
"learning_rate": 0.002,
|
| 4874 |
+
"loss": 2.119364023208618,
|
| 4875 |
+
"step": 1390
|
| 4876 |
+
},
|
| 4877 |
+
{
|
| 4878 |
+
"epoch": 0.1392,
|
| 4879 |
+
"grad_norm": 0.082890585064888,
|
| 4880 |
+
"learning_rate": 0.002,
|
| 4881 |
+
"loss": 1.938192367553711,
|
| 4882 |
+
"step": 1392
|
| 4883 |
+
},
|
| 4884 |
+
{
|
| 4885 |
+
"epoch": 0.1394,
|
| 4886 |
+
"grad_norm": 0.07707413285970688,
|
| 4887 |
+
"learning_rate": 0.002,
|
| 4888 |
+
"loss": 2.1069889068603516,
|
| 4889 |
+
"step": 1394
|
| 4890 |
+
},
|
| 4891 |
+
{
|
| 4892 |
+
"epoch": 0.1396,
|
| 4893 |
+
"grad_norm": 0.09440362453460693,
|
| 4894 |
+
"learning_rate": 0.002,
|
| 4895 |
+
"loss": 2.0704145431518555,
|
| 4896 |
+
"step": 1396
|
| 4897 |
+
},
|
| 4898 |
+
{
|
| 4899 |
+
"epoch": 0.1398,
|
| 4900 |
+
"grad_norm": 0.08753009885549545,
|
| 4901 |
+
"learning_rate": 0.002,
|
| 4902 |
+
"loss": 1.9484301805496216,
|
| 4903 |
+
"step": 1398
|
| 4904 |
+
},
|
| 4905 |
+
{
|
| 4906 |
+
"epoch": 0.14,
|
| 4907 |
+
"grad_norm": 0.08215557783842087,
|
| 4908 |
+
"learning_rate": 0.002,
|
| 4909 |
+
"loss": 2.124666452407837,
|
| 4910 |
+
"step": 1400
|
| 4911 |
+
},
|
| 4912 |
+
{
|
| 4913 |
+
"epoch": 0.1402,
|
| 4914 |
+
"grad_norm": 0.0817045196890831,
|
| 4915 |
+
"learning_rate": 0.002,
|
| 4916 |
+
"loss": 1.984005093574524,
|
| 4917 |
+
"step": 1402
|
| 4918 |
+
},
|
| 4919 |
+
{
|
| 4920 |
+
"epoch": 0.1404,
|
| 4921 |
+
"grad_norm": 0.08075842261314392,
|
| 4922 |
+
"learning_rate": 0.002,
|
| 4923 |
+
"loss": 2.00469708442688,
|
| 4924 |
+
"step": 1404
|
| 4925 |
+
},
|
| 4926 |
+
{
|
| 4927 |
+
"epoch": 0.1406,
|
| 4928 |
+
"grad_norm": 0.08940353244543076,
|
| 4929 |
+
"learning_rate": 0.002,
|
| 4930 |
+
"loss": 2.082493543624878,
|
| 4931 |
+
"step": 1406
|
| 4932 |
+
},
|
| 4933 |
+
{
|
| 4934 |
+
"epoch": 0.1408,
|
| 4935 |
+
"grad_norm": 0.08476462215185165,
|
| 4936 |
+
"learning_rate": 0.002,
|
| 4937 |
+
"loss": 1.9702262878417969,
|
| 4938 |
+
"step": 1408
|
| 4939 |
+
},
|
| 4940 |
+
{
|
| 4941 |
+
"epoch": 0.141,
|
| 4942 |
+
"grad_norm": 0.08214747905731201,
|
| 4943 |
+
"learning_rate": 0.002,
|
| 4944 |
+
"loss": 1.8237375020980835,
|
| 4945 |
+
"step": 1410
|
| 4946 |
+
},
|
| 4947 |
+
{
|
| 4948 |
+
"epoch": 0.1412,
|
| 4949 |
+
"grad_norm": 0.08178984373807907,
|
| 4950 |
+
"learning_rate": 0.002,
|
| 4951 |
+
"loss": 2.025057077407837,
|
| 4952 |
+
"step": 1412
|
| 4953 |
+
},
|
| 4954 |
+
{
|
| 4955 |
+
"epoch": 0.1414,
|
| 4956 |
+
"grad_norm": 0.08408454805612564,
|
| 4957 |
+
"learning_rate": 0.002,
|
| 4958 |
+
"loss": 1.9185508489608765,
|
| 4959 |
+
"step": 1414
|
| 4960 |
+
},
|
| 4961 |
+
{
|
| 4962 |
+
"epoch": 0.1416,
|
| 4963 |
+
"grad_norm": 0.0835493877530098,
|
| 4964 |
+
"learning_rate": 0.002,
|
| 4965 |
+
"loss": 1.8612854480743408,
|
| 4966 |
+
"step": 1416
|
| 4967 |
+
},
|
| 4968 |
+
{
|
| 4969 |
+
"epoch": 0.1418,
|
| 4970 |
+
"grad_norm": 0.08780626207590103,
|
| 4971 |
+
"learning_rate": 0.002,
|
| 4972 |
+
"loss": 1.9259387254714966,
|
| 4973 |
+
"step": 1418
|
| 4974 |
+
},
|
| 4975 |
+
{
|
| 4976 |
+
"epoch": 0.142,
|
| 4977 |
+
"grad_norm": 0.08390364050865173,
|
| 4978 |
+
"learning_rate": 0.002,
|
| 4979 |
+
"loss": 1.9215179681777954,
|
| 4980 |
+
"step": 1420
|
| 4981 |
+
},
|
| 4982 |
+
{
|
| 4983 |
+
"epoch": 0.1422,
|
| 4984 |
+
"grad_norm": 0.07897157967090607,
|
| 4985 |
+
"learning_rate": 0.002,
|
| 4986 |
+
"loss": 1.8806076049804688,
|
| 4987 |
+
"step": 1422
|
| 4988 |
+
},
|
| 4989 |
+
{
|
| 4990 |
+
"epoch": 0.1424,
|
| 4991 |
+
"grad_norm": 0.08310697227716446,
|
| 4992 |
+
"learning_rate": 0.002,
|
| 4993 |
+
"loss": 2.0307650566101074,
|
| 4994 |
+
"step": 1424
|
| 4995 |
+
},
|
| 4996 |
+
{
|
| 4997 |
+
"epoch": 0.1426,
|
| 4998 |
+
"grad_norm": 0.08411696553230286,
|
| 4999 |
+
"learning_rate": 0.002,
|
| 5000 |
+
"loss": 1.9524784088134766,
|
| 5001 |
+
"step": 1426
|
| 5002 |
+
},
|
| 5003 |
+
{
|
| 5004 |
+
"epoch": 0.1428,
|
| 5005 |
+
"grad_norm": 0.09483884274959564,
|
| 5006 |
+
"learning_rate": 0.002,
|
| 5007 |
+
"loss": 2.1354057788848877,
|
| 5008 |
+
"step": 1428
|
| 5009 |
+
},
|
| 5010 |
+
{
|
| 5011 |
+
"epoch": 0.143,
|
| 5012 |
+
"grad_norm": 0.08339402079582214,
|
| 5013 |
+
"learning_rate": 0.002,
|
| 5014 |
+
"loss": 2.0050485134124756,
|
| 5015 |
+
"step": 1430
|
| 5016 |
+
},
|
| 5017 |
+
{
|
| 5018 |
+
"epoch": 0.1432,
|
| 5019 |
+
"grad_norm": 0.08105912059545517,
|
| 5020 |
+
"learning_rate": 0.002,
|
| 5021 |
+
"loss": 2.0065789222717285,
|
| 5022 |
+
"step": 1432
|
| 5023 |
+
},
|
| 5024 |
+
{
|
| 5025 |
+
"epoch": 0.1434,
|
| 5026 |
+
"grad_norm": 0.08590013533830643,
|
| 5027 |
+
"learning_rate": 0.002,
|
| 5028 |
+
"loss": 2.036484479904175,
|
| 5029 |
+
"step": 1434
|
| 5030 |
+
},
|
| 5031 |
+
{
|
| 5032 |
+
"epoch": 0.1436,
|
| 5033 |
+
"grad_norm": 0.08551734685897827,
|
| 5034 |
+
"learning_rate": 0.002,
|
| 5035 |
+
"loss": 2.053032875061035,
|
| 5036 |
+
"step": 1436
|
| 5037 |
+
},
|
| 5038 |
+
{
|
| 5039 |
+
"epoch": 0.1438,
|
| 5040 |
+
"grad_norm": 0.08437639474868774,
|
| 5041 |
+
"learning_rate": 0.002,
|
| 5042 |
+
"loss": 1.9124197959899902,
|
| 5043 |
+
"step": 1438
|
| 5044 |
+
},
|
| 5045 |
+
{
|
| 5046 |
+
"epoch": 0.144,
|
| 5047 |
+
"grad_norm": 0.08546862751245499,
|
| 5048 |
+
"learning_rate": 0.002,
|
| 5049 |
+
"loss": 2.0219709873199463,
|
| 5050 |
+
"step": 1440
|
| 5051 |
+
},
|
| 5052 |
+
{
|
| 5053 |
+
"epoch": 0.1442,
|
| 5054 |
+
"grad_norm": 0.09397388249635696,
|
| 5055 |
+
"learning_rate": 0.002,
|
| 5056 |
+
"loss": 2.005190849304199,
|
| 5057 |
+
"step": 1442
|
| 5058 |
+
},
|
| 5059 |
+
{
|
| 5060 |
+
"epoch": 0.1444,
|
| 5061 |
+
"grad_norm": 0.08086714148521423,
|
| 5062 |
+
"learning_rate": 0.002,
|
| 5063 |
+
"loss": 1.977594256401062,
|
| 5064 |
+
"step": 1444
|
| 5065 |
+
},
|
| 5066 |
+
{
|
| 5067 |
+
"epoch": 0.1446,
|
| 5068 |
+
"grad_norm": 0.08263556659221649,
|
| 5069 |
+
"learning_rate": 0.002,
|
| 5070 |
+
"loss": 2.159130573272705,
|
| 5071 |
+
"step": 1446
|
| 5072 |
+
},
|
| 5073 |
+
{
|
| 5074 |
+
"epoch": 0.1448,
|
| 5075 |
+
"grad_norm": 0.08463070541620255,
|
| 5076 |
+
"learning_rate": 0.002,
|
| 5077 |
+
"loss": 2.046889305114746,
|
| 5078 |
+
"step": 1448
|
| 5079 |
+
},
|
| 5080 |
+
{
|
| 5081 |
+
"epoch": 0.145,
|
| 5082 |
+
"grad_norm": 0.08332529664039612,
|
| 5083 |
+
"learning_rate": 0.002,
|
| 5084 |
+
"loss": 1.8495128154754639,
|
| 5085 |
+
"step": 1450
|
| 5086 |
+
},
|
| 5087 |
+
{
|
| 5088 |
+
"epoch": 0.1452,
|
| 5089 |
+
"grad_norm": 0.08365868777036667,
|
| 5090 |
+
"learning_rate": 0.002,
|
| 5091 |
+
"loss": 1.9837555885314941,
|
| 5092 |
+
"step": 1452
|
| 5093 |
+
},
|
| 5094 |
+
{
|
| 5095 |
+
"epoch": 0.1454,
|
| 5096 |
+
"grad_norm": 0.0867474228143692,
|
| 5097 |
+
"learning_rate": 0.002,
|
| 5098 |
+
"loss": 2.0188663005828857,
|
| 5099 |
+
"step": 1454
|
| 5100 |
+
},
|
| 5101 |
+
{
|
| 5102 |
+
"epoch": 0.1456,
|
| 5103 |
+
"grad_norm": 0.09054825454950333,
|
| 5104 |
+
"learning_rate": 0.002,
|
| 5105 |
+
"loss": 1.9647122621536255,
|
| 5106 |
+
"step": 1456
|
| 5107 |
+
},
|
| 5108 |
+
{
|
| 5109 |
+
"epoch": 0.1458,
|
| 5110 |
+
"grad_norm": 0.08483801037073135,
|
| 5111 |
+
"learning_rate": 0.002,
|
| 5112 |
+
"loss": 1.855425477027893,
|
| 5113 |
+
"step": 1458
|
| 5114 |
+
},
|
| 5115 |
+
{
|
| 5116 |
+
"epoch": 0.146,
|
| 5117 |
+
"grad_norm": 0.09346556663513184,
|
| 5118 |
+
"learning_rate": 0.002,
|
| 5119 |
+
"loss": 2.191694736480713,
|
| 5120 |
+
"step": 1460
|
| 5121 |
+
},
|
| 5122 |
+
{
|
| 5123 |
+
"epoch": 0.1462,
|
| 5124 |
+
"grad_norm": 0.08465056121349335,
|
| 5125 |
+
"learning_rate": 0.002,
|
| 5126 |
+
"loss": 2.0250799655914307,
|
| 5127 |
+
"step": 1462
|
| 5128 |
+
},
|
| 5129 |
+
{
|
| 5130 |
+
"epoch": 0.1464,
|
| 5131 |
+
"grad_norm": 0.08501332998275757,
|
| 5132 |
+
"learning_rate": 0.002,
|
| 5133 |
+
"loss": 2.0752594470977783,
|
| 5134 |
+
"step": 1464
|
| 5135 |
+
},
|
| 5136 |
+
{
|
| 5137 |
+
"epoch": 0.1466,
|
| 5138 |
+
"grad_norm": 0.08634602278470993,
|
| 5139 |
+
"learning_rate": 0.002,
|
| 5140 |
+
"loss": 2.071413993835449,
|
| 5141 |
+
"step": 1466
|
| 5142 |
+
},
|
| 5143 |
+
{
|
| 5144 |
+
"epoch": 0.1468,
|
| 5145 |
+
"grad_norm": 0.08813812583684921,
|
| 5146 |
+
"learning_rate": 0.002,
|
| 5147 |
+
"loss": 2.019972324371338,
|
| 5148 |
+
"step": 1468
|
| 5149 |
+
},
|
| 5150 |
+
{
|
| 5151 |
+
"epoch": 0.147,
|
| 5152 |
+
"grad_norm": 0.08231979608535767,
|
| 5153 |
+
"learning_rate": 0.002,
|
| 5154 |
+
"loss": 2.0380661487579346,
|
| 5155 |
+
"step": 1470
|
| 5156 |
+
},
|
| 5157 |
+
{
|
| 5158 |
+
"epoch": 0.1472,
|
| 5159 |
+
"grad_norm": 0.08754221349954605,
|
| 5160 |
+
"learning_rate": 0.002,
|
| 5161 |
+
"loss": 1.8944451808929443,
|
| 5162 |
+
"step": 1472
|
| 5163 |
+
},
|
| 5164 |
+
{
|
| 5165 |
+
"epoch": 0.1474,
|
| 5166 |
+
"grad_norm": 0.081061452627182,
|
| 5167 |
+
"learning_rate": 0.002,
|
| 5168 |
+
"loss": 2.084580898284912,
|
| 5169 |
+
"step": 1474
|
| 5170 |
+
},
|
| 5171 |
+
{
|
| 5172 |
+
"epoch": 0.1476,
|
| 5173 |
+
"grad_norm": 0.08811423182487488,
|
| 5174 |
+
"learning_rate": 0.002,
|
| 5175 |
+
"loss": 2.010695695877075,
|
| 5176 |
+
"step": 1476
|
| 5177 |
+
},
|
| 5178 |
+
{
|
| 5179 |
+
"epoch": 0.1478,
|
| 5180 |
+
"grad_norm": 0.0883941501379013,
|
| 5181 |
+
"learning_rate": 0.002,
|
| 5182 |
+
"loss": 2.0035157203674316,
|
| 5183 |
+
"step": 1478
|
| 5184 |
+
},
|
| 5185 |
+
{
|
| 5186 |
+
"epoch": 0.148,
|
| 5187 |
+
"grad_norm": 0.08566522598266602,
|
| 5188 |
+
"learning_rate": 0.002,
|
| 5189 |
+
"loss": 2.150222063064575,
|
| 5190 |
+
"step": 1480
|
| 5191 |
+
},
|
| 5192 |
+
{
|
| 5193 |
+
"epoch": 0.1482,
|
| 5194 |
+
"grad_norm": 0.0847812071442604,
|
| 5195 |
+
"learning_rate": 0.002,
|
| 5196 |
+
"loss": 2.1005401611328125,
|
| 5197 |
+
"step": 1482
|
| 5198 |
+
},
|
| 5199 |
+
{
|
| 5200 |
+
"epoch": 0.1484,
|
| 5201 |
+
"grad_norm": 0.0855879932641983,
|
| 5202 |
+
"learning_rate": 0.002,
|
| 5203 |
+
"loss": 1.962319254875183,
|
| 5204 |
+
"step": 1484
|
| 5205 |
+
},
|
| 5206 |
+
{
|
| 5207 |
+
"epoch": 0.1486,
|
| 5208 |
+
"grad_norm": 0.08677064627408981,
|
| 5209 |
+
"learning_rate": 0.002,
|
| 5210 |
+
"loss": 1.96921968460083,
|
| 5211 |
+
"step": 1486
|
| 5212 |
+
},
|
| 5213 |
+
{
|
| 5214 |
+
"epoch": 0.1488,
|
| 5215 |
+
"grad_norm": 0.08283451199531555,
|
| 5216 |
+
"learning_rate": 0.002,
|
| 5217 |
+
"loss": 1.9546277523040771,
|
| 5218 |
+
"step": 1488
|
| 5219 |
+
},
|
| 5220 |
+
{
|
| 5221 |
+
"epoch": 0.149,
|
| 5222 |
+
"grad_norm": 0.08457811921834946,
|
| 5223 |
+
"learning_rate": 0.002,
|
| 5224 |
+
"loss": 2.0715556144714355,
|
| 5225 |
+
"step": 1490
|
| 5226 |
+
},
|
| 5227 |
+
{
|
| 5228 |
+
"epoch": 0.1492,
|
| 5229 |
+
"grad_norm": 0.08524119108915329,
|
| 5230 |
+
"learning_rate": 0.002,
|
| 5231 |
+
"loss": 1.8723537921905518,
|
| 5232 |
+
"step": 1492
|
| 5233 |
+
},
|
| 5234 |
+
{
|
| 5235 |
+
"epoch": 0.1494,
|
| 5236 |
+
"grad_norm": 0.08556007593870163,
|
| 5237 |
+
"learning_rate": 0.002,
|
| 5238 |
+
"loss": 1.972347617149353,
|
| 5239 |
+
"step": 1494
|
| 5240 |
+
},
|
| 5241 |
+
{
|
| 5242 |
+
"epoch": 0.1496,
|
| 5243 |
+
"grad_norm": 0.08538345992565155,
|
| 5244 |
+
"learning_rate": 0.002,
|
| 5245 |
+
"loss": 2.0747456550598145,
|
| 5246 |
+
"step": 1496
|
| 5247 |
+
},
|
| 5248 |
+
{
|
| 5249 |
+
"epoch": 0.1498,
|
| 5250 |
+
"grad_norm": 0.08342566341161728,
|
| 5251 |
+
"learning_rate": 0.002,
|
| 5252 |
+
"loss": 1.9905140399932861,
|
| 5253 |
+
"step": 1498
|
| 5254 |
+
},
|
| 5255 |
+
{
|
| 5256 |
+
"epoch": 0.15,
|
| 5257 |
+
"grad_norm": 0.08465108275413513,
|
| 5258 |
+
"learning_rate": 0.002,
|
| 5259 |
+
"loss": 2.118013620376587,
|
| 5260 |
+
"step": 1500
|
| 5261 |
+
},
|
| 5262 |
+
{
|
| 5263 |
+
"epoch": 0.1502,
|
| 5264 |
+
"grad_norm": 0.09234253317117691,
|
| 5265 |
+
"learning_rate": 0.002,
|
| 5266 |
+
"loss": 1.91473388671875,
|
| 5267 |
+
"step": 1502
|
| 5268 |
+
},
|
| 5269 |
+
{
|
| 5270 |
+
"epoch": 0.1504,
|
| 5271 |
+
"grad_norm": 0.08265455812215805,
|
| 5272 |
+
"learning_rate": 0.002,
|
| 5273 |
+
"loss": 2.0202364921569824,
|
| 5274 |
+
"step": 1504
|
| 5275 |
+
},
|
| 5276 |
+
{
|
| 5277 |
+
"epoch": 0.1506,
|
| 5278 |
+
"grad_norm": 0.08589425683021545,
|
| 5279 |
+
"learning_rate": 0.002,
|
| 5280 |
+
"loss": 2.0076608657836914,
|
| 5281 |
+
"step": 1506
|
| 5282 |
+
},
|
| 5283 |
+
{
|
| 5284 |
+
"epoch": 0.1508,
|
| 5285 |
+
"grad_norm": 0.08468682318925858,
|
| 5286 |
+
"learning_rate": 0.002,
|
| 5287 |
+
"loss": 2.0685858726501465,
|
| 5288 |
+
"step": 1508
|
| 5289 |
+
},
|
| 5290 |
+
{
|
| 5291 |
+
"epoch": 0.151,
|
| 5292 |
+
"grad_norm": 0.08672576397657394,
|
| 5293 |
+
"learning_rate": 0.002,
|
| 5294 |
+
"loss": 2.0356192588806152,
|
| 5295 |
+
"step": 1510
|
| 5296 |
+
},
|
| 5297 |
+
{
|
| 5298 |
+
"epoch": 0.1512,
|
| 5299 |
+
"grad_norm": 0.08560921996831894,
|
| 5300 |
+
"learning_rate": 0.002,
|
| 5301 |
+
"loss": 1.9504189491271973,
|
| 5302 |
+
"step": 1512
|
| 5303 |
+
},
|
| 5304 |
+
{
|
| 5305 |
+
"epoch": 0.1514,
|
| 5306 |
+
"grad_norm": 0.08880069106817245,
|
| 5307 |
+
"learning_rate": 0.002,
|
| 5308 |
+
"loss": 1.9090538024902344,
|
| 5309 |
+
"step": 1514
|
| 5310 |
+
},
|
| 5311 |
+
{
|
| 5312 |
+
"epoch": 0.1516,
|
| 5313 |
+
"grad_norm": 0.08352338522672653,
|
| 5314 |
+
"learning_rate": 0.002,
|
| 5315 |
+
"loss": 1.9770448207855225,
|
| 5316 |
+
"step": 1516
|
| 5317 |
+
},
|
| 5318 |
+
{
|
| 5319 |
+
"epoch": 0.1518,
|
| 5320 |
+
"grad_norm": 0.0834403857588768,
|
| 5321 |
+
"learning_rate": 0.002,
|
| 5322 |
+
"loss": 2.032268762588501,
|
| 5323 |
+
"step": 1518
|
| 5324 |
+
},
|
| 5325 |
+
{
|
| 5326 |
+
"epoch": 0.152,
|
| 5327 |
+
"grad_norm": 0.08182430267333984,
|
| 5328 |
+
"learning_rate": 0.002,
|
| 5329 |
+
"loss": 1.7237893342971802,
|
| 5330 |
+
"step": 1520
|
| 5331 |
+
},
|
| 5332 |
+
{
|
| 5333 |
+
"epoch": 0.1522,
|
| 5334 |
+
"grad_norm": 0.0823986604809761,
|
| 5335 |
+
"learning_rate": 0.002,
|
| 5336 |
+
"loss": 2.0870168209075928,
|
| 5337 |
+
"step": 1522
|
| 5338 |
+
},
|
| 5339 |
+
{
|
| 5340 |
+
"epoch": 0.1524,
|
| 5341 |
+
"grad_norm": 0.08288682997226715,
|
| 5342 |
+
"learning_rate": 0.002,
|
| 5343 |
+
"loss": 2.04171085357666,
|
| 5344 |
+
"step": 1524
|
| 5345 |
+
},
|
| 5346 |
+
{
|
| 5347 |
+
"epoch": 0.1526,
|
| 5348 |
+
"grad_norm": 0.09022911638021469,
|
| 5349 |
+
"learning_rate": 0.002,
|
| 5350 |
+
"loss": 2.058595895767212,
|
| 5351 |
+
"step": 1526
|
| 5352 |
+
},
|
| 5353 |
+
{
|
| 5354 |
+
"epoch": 0.1528,
|
| 5355 |
+
"grad_norm": 0.08884043991565704,
|
| 5356 |
+
"learning_rate": 0.002,
|
| 5357 |
+
"loss": 2.112304449081421,
|
| 5358 |
+
"step": 1528
|
| 5359 |
+
},
|
| 5360 |
+
{
|
| 5361 |
+
"epoch": 0.153,
|
| 5362 |
+
"grad_norm": 0.08846046030521393,
|
| 5363 |
+
"learning_rate": 0.002,
|
| 5364 |
+
"loss": 2.1000938415527344,
|
| 5365 |
+
"step": 1530
|
| 5366 |
+
},
|
| 5367 |
+
{
|
| 5368 |
+
"epoch": 0.1532,
|
| 5369 |
+
"grad_norm": 0.08225948363542557,
|
| 5370 |
+
"learning_rate": 0.002,
|
| 5371 |
+
"loss": 1.9290692806243896,
|
| 5372 |
+
"step": 1532
|
| 5373 |
+
},
|
| 5374 |
+
{
|
| 5375 |
+
"epoch": 0.1534,
|
| 5376 |
+
"grad_norm": 0.08358252048492432,
|
| 5377 |
+
"learning_rate": 0.002,
|
| 5378 |
+
"loss": 1.880184531211853,
|
| 5379 |
+
"step": 1534
|
| 5380 |
+
},
|
| 5381 |
+
{
|
| 5382 |
+
"epoch": 0.1536,
|
| 5383 |
+
"grad_norm": 0.08781662583351135,
|
| 5384 |
+
"learning_rate": 0.002,
|
| 5385 |
+
"loss": 2.03822660446167,
|
| 5386 |
+
"step": 1536
|
| 5387 |
+
},
|
| 5388 |
+
{
|
| 5389 |
+
"epoch": 0.1538,
|
| 5390 |
+
"grad_norm": 0.0874786451458931,
|
| 5391 |
+
"learning_rate": 0.002,
|
| 5392 |
+
"loss": 2.003692626953125,
|
| 5393 |
+
"step": 1538
|
| 5394 |
+
},
|
| 5395 |
+
{
|
| 5396 |
+
"epoch": 0.154,
|
| 5397 |
+
"grad_norm": 0.08314626663923264,
|
| 5398 |
+
"learning_rate": 0.002,
|
| 5399 |
+
"loss": 2.103372812271118,
|
| 5400 |
+
"step": 1540
|
| 5401 |
+
},
|
| 5402 |
+
{
|
| 5403 |
+
"epoch": 0.1542,
|
| 5404 |
+
"grad_norm": 0.08071058243513107,
|
| 5405 |
+
"learning_rate": 0.002,
|
| 5406 |
+
"loss": 1.988526463508606,
|
| 5407 |
+
"step": 1542
|
| 5408 |
+
},
|
| 5409 |
+
{
|
| 5410 |
+
"epoch": 0.1544,
|
| 5411 |
+
"grad_norm": 0.08185788989067078,
|
| 5412 |
+
"learning_rate": 0.002,
|
| 5413 |
+
"loss": 1.8805160522460938,
|
| 5414 |
+
"step": 1544
|
| 5415 |
+
},
|
| 5416 |
+
{
|
| 5417 |
+
"epoch": 0.1546,
|
| 5418 |
+
"grad_norm": 0.08340204507112503,
|
| 5419 |
+
"learning_rate": 0.002,
|
| 5420 |
+
"loss": 2.0312440395355225,
|
| 5421 |
+
"step": 1546
|
| 5422 |
+
},
|
| 5423 |
+
{
|
| 5424 |
+
"epoch": 0.1548,
|
| 5425 |
+
"grad_norm": 0.08513487875461578,
|
| 5426 |
+
"learning_rate": 0.002,
|
| 5427 |
+
"loss": 1.9365514516830444,
|
| 5428 |
+
"step": 1548
|
| 5429 |
+
},
|
| 5430 |
+
{
|
| 5431 |
+
"epoch": 0.155,
|
| 5432 |
+
"grad_norm": 0.0839838907122612,
|
| 5433 |
+
"learning_rate": 0.002,
|
| 5434 |
+
"loss": 1.9162694215774536,
|
| 5435 |
+
"step": 1550
|
| 5436 |
+
},
|
| 5437 |
+
{
|
| 5438 |
+
"epoch": 0.1552,
|
| 5439 |
+
"grad_norm": 0.08493292331695557,
|
| 5440 |
+
"learning_rate": 0.002,
|
| 5441 |
+
"loss": 1.9749780893325806,
|
| 5442 |
+
"step": 1552
|
| 5443 |
+
},
|
| 5444 |
+
{
|
| 5445 |
+
"epoch": 0.1554,
|
| 5446 |
+
"grad_norm": 0.08738046139478683,
|
| 5447 |
+
"learning_rate": 0.002,
|
| 5448 |
+
"loss": 1.8714990615844727,
|
| 5449 |
+
"step": 1554
|
| 5450 |
+
},
|
| 5451 |
+
{
|
| 5452 |
+
"epoch": 0.1556,
|
| 5453 |
+
"grad_norm": 0.08110321313142776,
|
| 5454 |
+
"learning_rate": 0.002,
|
| 5455 |
+
"loss": 1.947487235069275,
|
| 5456 |
+
"step": 1556
|
| 5457 |
+
},
|
| 5458 |
+
{
|
| 5459 |
+
"epoch": 0.1558,
|
| 5460 |
+
"grad_norm": 0.08131778240203857,
|
| 5461 |
+
"learning_rate": 0.002,
|
| 5462 |
+
"loss": 1.9373154640197754,
|
| 5463 |
+
"step": 1558
|
| 5464 |
+
},
|
| 5465 |
+
{
|
| 5466 |
+
"epoch": 0.156,
|
| 5467 |
+
"grad_norm": 0.0785713717341423,
|
| 5468 |
+
"learning_rate": 0.002,
|
| 5469 |
+
"loss": 2.0550003051757812,
|
| 5470 |
+
"step": 1560
|
| 5471 |
+
},
|
| 5472 |
+
{
|
| 5473 |
+
"epoch": 0.1562,
|
| 5474 |
+
"grad_norm": 0.08419571071863174,
|
| 5475 |
+
"learning_rate": 0.002,
|
| 5476 |
+
"loss": 1.9248937368392944,
|
| 5477 |
+
"step": 1562
|
| 5478 |
+
},
|
| 5479 |
+
{
|
| 5480 |
+
"epoch": 0.1564,
|
| 5481 |
+
"grad_norm": 0.08059526234865189,
|
| 5482 |
+
"learning_rate": 0.002,
|
| 5483 |
+
"loss": 1.9841457605361938,
|
| 5484 |
+
"step": 1564
|
| 5485 |
+
},
|
| 5486 |
+
{
|
| 5487 |
+
"epoch": 0.1566,
|
| 5488 |
+
"grad_norm": 0.08866710215806961,
|
| 5489 |
+
"learning_rate": 0.002,
|
| 5490 |
+
"loss": 1.9777973890304565,
|
| 5491 |
+
"step": 1566
|
| 5492 |
+
},
|
| 5493 |
+
{
|
| 5494 |
+
"epoch": 0.1568,
|
| 5495 |
+
"grad_norm": 0.08271918445825577,
|
| 5496 |
+
"learning_rate": 0.002,
|
| 5497 |
+
"loss": 2.074117422103882,
|
| 5498 |
+
"step": 1568
|
| 5499 |
+
},
|
| 5500 |
+
{
|
| 5501 |
+
"epoch": 0.157,
|
| 5502 |
+
"grad_norm": 0.08722631633281708,
|
| 5503 |
+
"learning_rate": 0.002,
|
| 5504 |
+
"loss": 2.1816694736480713,
|
| 5505 |
+
"step": 1570
|
| 5506 |
+
},
|
| 5507 |
+
{
|
| 5508 |
+
"epoch": 0.1572,
|
| 5509 |
+
"grad_norm": 0.08447971940040588,
|
| 5510 |
+
"learning_rate": 0.002,
|
| 5511 |
+
"loss": 2.109995126724243,
|
| 5512 |
+
"step": 1572
|
| 5513 |
+
},
|
| 5514 |
+
{
|
| 5515 |
+
"epoch": 0.1574,
|
| 5516 |
+
"grad_norm": 0.08193506300449371,
|
| 5517 |
+
"learning_rate": 0.002,
|
| 5518 |
+
"loss": 1.8912419080734253,
|
| 5519 |
+
"step": 1574
|
| 5520 |
+
},
|
| 5521 |
+
{
|
| 5522 |
+
"epoch": 0.1576,
|
| 5523 |
+
"grad_norm": 0.0820985659956932,
|
| 5524 |
+
"learning_rate": 0.002,
|
| 5525 |
+
"loss": 1.9356868267059326,
|
| 5526 |
+
"step": 1576
|
| 5527 |
+
},
|
| 5528 |
+
{
|
| 5529 |
+
"epoch": 0.1578,
|
| 5530 |
+
"grad_norm": 0.08184309303760529,
|
| 5531 |
+
"learning_rate": 0.002,
|
| 5532 |
+
"loss": 1.9752860069274902,
|
| 5533 |
+
"step": 1578
|
| 5534 |
+
},
|
| 5535 |
+
{
|
| 5536 |
+
"epoch": 0.158,
|
| 5537 |
+
"grad_norm": 0.08817871659994125,
|
| 5538 |
+
"learning_rate": 0.002,
|
| 5539 |
+
"loss": 2.0186655521392822,
|
| 5540 |
+
"step": 1580
|
| 5541 |
+
},
|
| 5542 |
+
{
|
| 5543 |
+
"epoch": 0.1582,
|
| 5544 |
+
"grad_norm": 0.08116264641284943,
|
| 5545 |
+
"learning_rate": 0.002,
|
| 5546 |
+
"loss": 2.0638322830200195,
|
| 5547 |
+
"step": 1582
|
| 5548 |
+
},
|
| 5549 |
+
{
|
| 5550 |
+
"epoch": 0.1584,
|
| 5551 |
+
"grad_norm": 0.10066129267215729,
|
| 5552 |
+
"learning_rate": 0.002,
|
| 5553 |
+
"loss": 1.9643419981002808,
|
| 5554 |
+
"step": 1584
|
| 5555 |
+
},
|
| 5556 |
+
{
|
| 5557 |
+
"epoch": 0.1586,
|
| 5558 |
+
"grad_norm": 0.07976362854242325,
|
| 5559 |
+
"learning_rate": 0.002,
|
| 5560 |
+
"loss": 1.9309545755386353,
|
| 5561 |
+
"step": 1586
|
| 5562 |
+
},
|
| 5563 |
+
{
|
| 5564 |
+
"epoch": 0.1588,
|
| 5565 |
+
"grad_norm": 0.08252105861902237,
|
| 5566 |
+
"learning_rate": 0.002,
|
| 5567 |
+
"loss": 1.942662239074707,
|
| 5568 |
+
"step": 1588
|
| 5569 |
+
},
|
| 5570 |
+
{
|
| 5571 |
+
"epoch": 0.159,
|
| 5572 |
+
"grad_norm": 0.08732359856367111,
|
| 5573 |
+
"learning_rate": 0.002,
|
| 5574 |
+
"loss": 1.936599850654602,
|
| 5575 |
+
"step": 1590
|
| 5576 |
+
},
|
| 5577 |
+
{
|
| 5578 |
+
"epoch": 0.1592,
|
| 5579 |
+
"grad_norm": 0.08256518840789795,
|
| 5580 |
+
"learning_rate": 0.002,
|
| 5581 |
+
"loss": 2.0580368041992188,
|
| 5582 |
+
"step": 1592
|
| 5583 |
+
},
|
| 5584 |
+
{
|
| 5585 |
+
"epoch": 0.1594,
|
| 5586 |
+
"grad_norm": 0.0870324894785881,
|
| 5587 |
+
"learning_rate": 0.002,
|
| 5588 |
+
"loss": 2.0031468868255615,
|
| 5589 |
+
"step": 1594
|
| 5590 |
+
},
|
| 5591 |
+
{
|
| 5592 |
+
"epoch": 0.1596,
|
| 5593 |
+
"grad_norm": 0.08515676110982895,
|
| 5594 |
+
"learning_rate": 0.002,
|
| 5595 |
+
"loss": 2.0998167991638184,
|
| 5596 |
+
"step": 1596
|
| 5597 |
+
},
|
| 5598 |
+
{
|
| 5599 |
+
"epoch": 0.1598,
|
| 5600 |
+
"grad_norm": 0.10461036115884781,
|
| 5601 |
+
"learning_rate": 0.002,
|
| 5602 |
+
"loss": 1.9901013374328613,
|
| 5603 |
+
"step": 1598
|
| 5604 |
+
},
|
| 5605 |
+
{
|
| 5606 |
+
"epoch": 0.16,
|
| 5607 |
+
"grad_norm": 0.08584758639335632,
|
| 5608 |
+
"learning_rate": 0.002,
|
| 5609 |
+
"loss": 1.888537049293518,
|
| 5610 |
+
"step": 1600
|
| 5611 |
+
},
|
| 5612 |
+
{
|
| 5613 |
+
"epoch": 0.1602,
|
| 5614 |
+
"grad_norm": 0.08241167664527893,
|
| 5615 |
+
"learning_rate": 0.002,
|
| 5616 |
+
"loss": 2.0399234294891357,
|
| 5617 |
+
"step": 1602
|
| 5618 |
+
},
|
| 5619 |
+
{
|
| 5620 |
+
"epoch": 0.1604,
|
| 5621 |
+
"grad_norm": 0.08698111772537231,
|
| 5622 |
+
"learning_rate": 0.002,
|
| 5623 |
+
"loss": 1.869358777999878,
|
| 5624 |
+
"step": 1604
|
| 5625 |
+
},
|
| 5626 |
+
{
|
| 5627 |
+
"epoch": 0.1606,
|
| 5628 |
+
"grad_norm": 0.08399704098701477,
|
| 5629 |
+
"learning_rate": 0.002,
|
| 5630 |
+
"loss": 1.9496454000473022,
|
| 5631 |
+
"step": 1606
|
| 5632 |
+
},
|
| 5633 |
+
{
|
| 5634 |
+
"epoch": 0.1608,
|
| 5635 |
+
"grad_norm": 0.08519057184457779,
|
| 5636 |
+
"learning_rate": 0.002,
|
| 5637 |
+
"loss": 2.175718307495117,
|
| 5638 |
+
"step": 1608
|
| 5639 |
+
},
|
| 5640 |
+
{
|
| 5641 |
+
"epoch": 0.161,
|
| 5642 |
+
"grad_norm": 0.07982669025659561,
|
| 5643 |
+
"learning_rate": 0.002,
|
| 5644 |
+
"loss": 2.018760919570923,
|
| 5645 |
+
"step": 1610
|
| 5646 |
+
},
|
| 5647 |
+
{
|
| 5648 |
+
"epoch": 0.1612,
|
| 5649 |
+
"grad_norm": 0.08624474704265594,
|
| 5650 |
+
"learning_rate": 0.002,
|
| 5651 |
+
"loss": 1.9684149026870728,
|
| 5652 |
+
"step": 1612
|
| 5653 |
+
},
|
| 5654 |
+
{
|
| 5655 |
+
"epoch": 0.1614,
|
| 5656 |
+
"grad_norm": 0.08299598097801208,
|
| 5657 |
+
"learning_rate": 0.002,
|
| 5658 |
+
"loss": 1.9885144233703613,
|
| 5659 |
+
"step": 1614
|
| 5660 |
+
},
|
| 5661 |
+
{
|
| 5662 |
+
"epoch": 0.1616,
|
| 5663 |
+
"grad_norm": 0.08168502897024155,
|
| 5664 |
+
"learning_rate": 0.002,
|
| 5665 |
+
"loss": 1.9772814512252808,
|
| 5666 |
+
"step": 1616
|
| 5667 |
+
},
|
| 5668 |
+
{
|
| 5669 |
+
"epoch": 0.1618,
|
| 5670 |
+
"grad_norm": 0.09290925413370132,
|
| 5671 |
+
"learning_rate": 0.002,
|
| 5672 |
+
"loss": 2.070359468460083,
|
| 5673 |
+
"step": 1618
|
| 5674 |
+
},
|
| 5675 |
+
{
|
| 5676 |
+
"epoch": 0.162,
|
| 5677 |
+
"grad_norm": 0.0804649293422699,
|
| 5678 |
+
"learning_rate": 0.002,
|
| 5679 |
+
"loss": 1.988921046257019,
|
| 5680 |
+
"step": 1620
|
| 5681 |
+
},
|
| 5682 |
+
{
|
| 5683 |
+
"epoch": 0.1622,
|
| 5684 |
+
"grad_norm": 0.08479253202676773,
|
| 5685 |
+
"learning_rate": 0.002,
|
| 5686 |
+
"loss": 1.9732486009597778,
|
| 5687 |
+
"step": 1622
|
| 5688 |
+
},
|
| 5689 |
+
{
|
| 5690 |
+
"epoch": 0.1624,
|
| 5691 |
+
"grad_norm": 0.08966785669326782,
|
| 5692 |
+
"learning_rate": 0.002,
|
| 5693 |
+
"loss": 1.9530940055847168,
|
| 5694 |
+
"step": 1624
|
| 5695 |
+
},
|
| 5696 |
+
{
|
| 5697 |
+
"epoch": 0.1626,
|
| 5698 |
+
"grad_norm": 0.08252689987421036,
|
| 5699 |
+
"learning_rate": 0.002,
|
| 5700 |
+
"loss": 2.0290355682373047,
|
| 5701 |
+
"step": 1626
|
| 5702 |
+
},
|
| 5703 |
+
{
|
| 5704 |
+
"epoch": 0.1628,
|
| 5705 |
+
"grad_norm": 0.08560115844011307,
|
| 5706 |
+
"learning_rate": 0.002,
|
| 5707 |
+
"loss": 1.955880045890808,
|
| 5708 |
+
"step": 1628
|
| 5709 |
+
},
|
| 5710 |
+
{
|
| 5711 |
+
"epoch": 0.163,
|
| 5712 |
+
"grad_norm": 0.08271026611328125,
|
| 5713 |
+
"learning_rate": 0.002,
|
| 5714 |
+
"loss": 2.0511937141418457,
|
| 5715 |
+
"step": 1630
|
| 5716 |
+
},
|
| 5717 |
+
{
|
| 5718 |
+
"epoch": 0.1632,
|
| 5719 |
+
"grad_norm": 0.08341914415359497,
|
| 5720 |
+
"learning_rate": 0.002,
|
| 5721 |
+
"loss": 2.062037706375122,
|
| 5722 |
+
"step": 1632
|
| 5723 |
+
},
|
| 5724 |
+
{
|
| 5725 |
+
"epoch": 0.1634,
|
| 5726 |
+
"grad_norm": 0.08394568413496017,
|
| 5727 |
+
"learning_rate": 0.002,
|
| 5728 |
+
"loss": 1.9848227500915527,
|
| 5729 |
+
"step": 1634
|
| 5730 |
+
},
|
| 5731 |
+
{
|
| 5732 |
+
"epoch": 0.1636,
|
| 5733 |
+
"grad_norm": 0.08560135960578918,
|
| 5734 |
+
"learning_rate": 0.002,
|
| 5735 |
+
"loss": 2.127549409866333,
|
| 5736 |
+
"step": 1636
|
| 5737 |
+
},
|
| 5738 |
+
{
|
| 5739 |
+
"epoch": 0.1638,
|
| 5740 |
+
"grad_norm": 0.08927592635154724,
|
| 5741 |
+
"learning_rate": 0.002,
|
| 5742 |
+
"loss": 1.9887274503707886,
|
| 5743 |
+
"step": 1638
|
| 5744 |
+
},
|
| 5745 |
+
{
|
| 5746 |
+
"epoch": 0.164,
|
| 5747 |
+
"grad_norm": 0.08311126381158829,
|
| 5748 |
+
"learning_rate": 0.002,
|
| 5749 |
+
"loss": 2.021876335144043,
|
| 5750 |
+
"step": 1640
|
| 5751 |
+
},
|
| 5752 |
+
{
|
| 5753 |
+
"epoch": 0.1642,
|
| 5754 |
+
"grad_norm": 0.08075287938117981,
|
| 5755 |
+
"learning_rate": 0.002,
|
| 5756 |
+
"loss": 2.0108084678649902,
|
| 5757 |
+
"step": 1642
|
| 5758 |
+
},
|
| 5759 |
+
{
|
| 5760 |
+
"epoch": 0.1644,
|
| 5761 |
+
"grad_norm": 0.08535883575677872,
|
| 5762 |
+
"learning_rate": 0.002,
|
| 5763 |
+
"loss": 2.025994300842285,
|
| 5764 |
+
"step": 1644
|
| 5765 |
+
},
|
| 5766 |
+
{
|
| 5767 |
+
"epoch": 0.1646,
|
| 5768 |
+
"grad_norm": 0.08394721895456314,
|
| 5769 |
+
"learning_rate": 0.002,
|
| 5770 |
+
"loss": 1.9767261743545532,
|
| 5771 |
+
"step": 1646
|
| 5772 |
+
},
|
| 5773 |
+
{
|
| 5774 |
+
"epoch": 0.1648,
|
| 5775 |
+
"grad_norm": 0.08777830749750137,
|
| 5776 |
+
"learning_rate": 0.002,
|
| 5777 |
+
"loss": 1.9552806615829468,
|
| 5778 |
+
"step": 1648
|
| 5779 |
+
},
|
| 5780 |
+
{
|
| 5781 |
+
"epoch": 0.165,
|
| 5782 |
+
"grad_norm": 0.08747299760580063,
|
| 5783 |
+
"learning_rate": 0.002,
|
| 5784 |
+
"loss": 2.0201032161712646,
|
| 5785 |
+
"step": 1650
|
| 5786 |
+
},
|
| 5787 |
+
{
|
| 5788 |
+
"epoch": 0.1652,
|
| 5789 |
+
"grad_norm": 0.08579709380865097,
|
| 5790 |
+
"learning_rate": 0.002,
|
| 5791 |
+
"loss": 1.9406492710113525,
|
| 5792 |
+
"step": 1652
|
| 5793 |
+
},
|
| 5794 |
+
{
|
| 5795 |
+
"epoch": 0.1654,
|
| 5796 |
+
"grad_norm": 0.08180826902389526,
|
| 5797 |
+
"learning_rate": 0.002,
|
| 5798 |
+
"loss": 2.0655133724212646,
|
| 5799 |
+
"step": 1654
|
| 5800 |
+
},
|
| 5801 |
+
{
|
| 5802 |
+
"epoch": 0.1656,
|
| 5803 |
+
"grad_norm": 0.08200948685407639,
|
| 5804 |
+
"learning_rate": 0.002,
|
| 5805 |
+
"loss": 1.9462840557098389,
|
| 5806 |
+
"step": 1656
|
| 5807 |
+
},
|
| 5808 |
+
{
|
| 5809 |
+
"epoch": 0.1658,
|
| 5810 |
+
"grad_norm": 0.07699384540319443,
|
| 5811 |
+
"learning_rate": 0.002,
|
| 5812 |
+
"loss": 1.9783786535263062,
|
| 5813 |
+
"step": 1658
|
| 5814 |
+
},
|
| 5815 |
+
{
|
| 5816 |
+
"epoch": 0.166,
|
| 5817 |
+
"grad_norm": 0.08740390837192535,
|
| 5818 |
+
"learning_rate": 0.002,
|
| 5819 |
+
"loss": 2.0780999660491943,
|
| 5820 |
+
"step": 1660
|
| 5821 |
+
},
|
| 5822 |
+
{
|
| 5823 |
+
"epoch": 0.1662,
|
| 5824 |
+
"grad_norm": 0.08262025564908981,
|
| 5825 |
+
"learning_rate": 0.002,
|
| 5826 |
+
"loss": 1.9985356330871582,
|
| 5827 |
+
"step": 1662
|
| 5828 |
+
},
|
| 5829 |
+
{
|
| 5830 |
+
"epoch": 0.1664,
|
| 5831 |
+
"grad_norm": 0.08615583926439285,
|
| 5832 |
+
"learning_rate": 0.002,
|
| 5833 |
+
"loss": 2.0267257690429688,
|
| 5834 |
+
"step": 1664
|
| 5835 |
+
},
|
| 5836 |
+
{
|
| 5837 |
+
"epoch": 0.1666,
|
| 5838 |
+
"grad_norm": 0.08822714537382126,
|
| 5839 |
+
"learning_rate": 0.002,
|
| 5840 |
+
"loss": 2.11911678314209,
|
| 5841 |
+
"step": 1666
|
| 5842 |
+
},
|
| 5843 |
+
{
|
| 5844 |
+
"epoch": 0.1668,
|
| 5845 |
+
"grad_norm": 0.09044399857521057,
|
| 5846 |
+
"learning_rate": 0.002,
|
| 5847 |
+
"loss": 1.91670823097229,
|
| 5848 |
+
"step": 1668
|
| 5849 |
+
},
|
| 5850 |
+
{
|
| 5851 |
+
"epoch": 0.167,
|
| 5852 |
+
"grad_norm": 0.08889217674732208,
|
| 5853 |
+
"learning_rate": 0.002,
|
| 5854 |
+
"loss": 1.8854286670684814,
|
| 5855 |
+
"step": 1670
|
| 5856 |
+
},
|
| 5857 |
+
{
|
| 5858 |
+
"epoch": 0.1672,
|
| 5859 |
+
"grad_norm": 0.08416656404733658,
|
| 5860 |
+
"learning_rate": 0.002,
|
| 5861 |
+
"loss": 1.9102697372436523,
|
| 5862 |
+
"step": 1672
|
| 5863 |
+
},
|
| 5864 |
+
{
|
| 5865 |
+
"epoch": 0.1674,
|
| 5866 |
+
"grad_norm": 0.0856962502002716,
|
| 5867 |
+
"learning_rate": 0.002,
|
| 5868 |
+
"loss": 1.95755934715271,
|
| 5869 |
+
"step": 1674
|
| 5870 |
+
},
|
| 5871 |
+
{
|
| 5872 |
+
"epoch": 0.1676,
|
| 5873 |
+
"grad_norm": 0.08149226754903793,
|
| 5874 |
+
"learning_rate": 0.002,
|
| 5875 |
+
"loss": 1.8925155401229858,
|
| 5876 |
+
"step": 1676
|
| 5877 |
+
},
|
| 5878 |
+
{
|
| 5879 |
+
"epoch": 0.1678,
|
| 5880 |
+
"grad_norm": 0.08411500602960587,
|
| 5881 |
+
"learning_rate": 0.002,
|
| 5882 |
+
"loss": 2.0812156200408936,
|
| 5883 |
+
"step": 1678
|
| 5884 |
+
},
|
| 5885 |
+
{
|
| 5886 |
+
"epoch": 0.168,
|
| 5887 |
+
"grad_norm": 0.09518945217132568,
|
| 5888 |
+
"learning_rate": 0.002,
|
| 5889 |
+
"loss": 1.850506067276001,
|
| 5890 |
+
"step": 1680
|
| 5891 |
+
},
|
| 5892 |
+
{
|
| 5893 |
+
"epoch": 0.1682,
|
| 5894 |
+
"grad_norm": 0.08547048270702362,
|
| 5895 |
+
"learning_rate": 0.002,
|
| 5896 |
+
"loss": 2.069958209991455,
|
| 5897 |
+
"step": 1682
|
| 5898 |
+
},
|
| 5899 |
+
{
|
| 5900 |
+
"epoch": 0.1684,
|
| 5901 |
+
"grad_norm": 0.08539139479398727,
|
| 5902 |
+
"learning_rate": 0.002,
|
| 5903 |
+
"loss": 2.0619094371795654,
|
| 5904 |
+
"step": 1684
|
| 5905 |
+
},
|
| 5906 |
+
{
|
| 5907 |
+
"epoch": 0.1686,
|
| 5908 |
+
"grad_norm": 0.0835799127817154,
|
| 5909 |
+
"learning_rate": 0.002,
|
| 5910 |
+
"loss": 1.986047387123108,
|
| 5911 |
+
"step": 1686
|
| 5912 |
+
},
|
| 5913 |
+
{
|
| 5914 |
+
"epoch": 0.1688,
|
| 5915 |
+
"grad_norm": 0.08559209108352661,
|
| 5916 |
+
"learning_rate": 0.002,
|
| 5917 |
+
"loss": 2.079071283340454,
|
| 5918 |
+
"step": 1688
|
| 5919 |
+
},
|
| 5920 |
+
{
|
| 5921 |
+
"epoch": 0.169,
|
| 5922 |
+
"grad_norm": 0.08535871654748917,
|
| 5923 |
+
"learning_rate": 0.002,
|
| 5924 |
+
"loss": 1.9463937282562256,
|
| 5925 |
+
"step": 1690
|
| 5926 |
+
},
|
| 5927 |
+
{
|
| 5928 |
+
"epoch": 0.1692,
|
| 5929 |
+
"grad_norm": 0.08502212911844254,
|
| 5930 |
+
"learning_rate": 0.002,
|
| 5931 |
+
"loss": 1.9606218338012695,
|
| 5932 |
+
"step": 1692
|
| 5933 |
+
},
|
| 5934 |
+
{
|
| 5935 |
+
"epoch": 0.1694,
|
| 5936 |
+
"grad_norm": 0.0909137949347496,
|
| 5937 |
+
"learning_rate": 0.002,
|
| 5938 |
+
"loss": 1.8967794179916382,
|
| 5939 |
+
"step": 1694
|
| 5940 |
+
},
|
| 5941 |
+
{
|
| 5942 |
+
"epoch": 0.1696,
|
| 5943 |
+
"grad_norm": 0.08144690096378326,
|
| 5944 |
+
"learning_rate": 0.002,
|
| 5945 |
+
"loss": 1.8653541803359985,
|
| 5946 |
+
"step": 1696
|
| 5947 |
+
},
|
| 5948 |
+
{
|
| 5949 |
+
"epoch": 0.1698,
|
| 5950 |
+
"grad_norm": 0.08554151654243469,
|
| 5951 |
+
"learning_rate": 0.002,
|
| 5952 |
+
"loss": 1.82559072971344,
|
| 5953 |
+
"step": 1698
|
| 5954 |
+
},
|
| 5955 |
+
{
|
| 5956 |
+
"epoch": 0.17,
|
| 5957 |
+
"grad_norm": 0.08355498313903809,
|
| 5958 |
+
"learning_rate": 0.002,
|
| 5959 |
+
"loss": 1.9472588300704956,
|
| 5960 |
+
"step": 1700
|
| 5961 |
+
},
|
| 5962 |
+
{
|
| 5963 |
+
"epoch": 0.1702,
|
| 5964 |
+
"grad_norm": 0.08412764966487885,
|
| 5965 |
+
"learning_rate": 0.002,
|
| 5966 |
+
"loss": 2.054037094116211,
|
| 5967 |
+
"step": 1702
|
| 5968 |
+
},
|
| 5969 |
+
{
|
| 5970 |
+
"epoch": 0.1704,
|
| 5971 |
+
"grad_norm": 0.08119752258062363,
|
| 5972 |
+
"learning_rate": 0.002,
|
| 5973 |
+
"loss": 1.98397696018219,
|
| 5974 |
+
"step": 1704
|
| 5975 |
+
},
|
| 5976 |
+
{
|
| 5977 |
+
"epoch": 0.1706,
|
| 5978 |
+
"grad_norm": 0.08186545222997665,
|
| 5979 |
+
"learning_rate": 0.002,
|
| 5980 |
+
"loss": 1.811954140663147,
|
| 5981 |
+
"step": 1706
|
| 5982 |
+
},
|
| 5983 |
+
{
|
| 5984 |
+
"epoch": 0.1708,
|
| 5985 |
+
"grad_norm": 0.0800834372639656,
|
| 5986 |
+
"learning_rate": 0.002,
|
| 5987 |
+
"loss": 2.0531461238861084,
|
| 5988 |
+
"step": 1708
|
| 5989 |
+
},
|
| 5990 |
+
{
|
| 5991 |
+
"epoch": 0.171,
|
| 5992 |
+
"grad_norm": 0.0843147560954094,
|
| 5993 |
+
"learning_rate": 0.002,
|
| 5994 |
+
"loss": 2.086811065673828,
|
| 5995 |
+
"step": 1710
|
| 5996 |
+
},
|
| 5997 |
+
{
|
| 5998 |
+
"epoch": 0.1712,
|
| 5999 |
+
"grad_norm": 0.08326831459999084,
|
| 6000 |
+
"learning_rate": 0.002,
|
| 6001 |
+
"loss": 1.9017562866210938,
|
| 6002 |
+
"step": 1712
|
| 6003 |
+
},
|
| 6004 |
+
{
|
| 6005 |
+
"epoch": 0.1714,
|
| 6006 |
+
"grad_norm": 0.0864068940281868,
|
| 6007 |
+
"learning_rate": 0.002,
|
| 6008 |
+
"loss": 2.0999181270599365,
|
| 6009 |
+
"step": 1714
|
| 6010 |
+
},
|
| 6011 |
+
{
|
| 6012 |
+
"epoch": 0.1716,
|
| 6013 |
+
"grad_norm": 0.08121897280216217,
|
| 6014 |
+
"learning_rate": 0.002,
|
| 6015 |
+
"loss": 1.8443279266357422,
|
| 6016 |
+
"step": 1716
|
| 6017 |
+
},
|
| 6018 |
+
{
|
| 6019 |
+
"epoch": 0.1718,
|
| 6020 |
+
"grad_norm": 0.09560268372297287,
|
| 6021 |
+
"learning_rate": 0.002,
|
| 6022 |
+
"loss": 2.0472049713134766,
|
| 6023 |
+
"step": 1718
|
| 6024 |
+
},
|
| 6025 |
+
{
|
| 6026 |
+
"epoch": 0.172,
|
| 6027 |
+
"grad_norm": 0.08162263035774231,
|
| 6028 |
+
"learning_rate": 0.002,
|
| 6029 |
+
"loss": 1.9566751718521118,
|
| 6030 |
+
"step": 1720
|
| 6031 |
+
},
|
| 6032 |
+
{
|
| 6033 |
+
"epoch": 0.1722,
|
| 6034 |
+
"grad_norm": 0.08066337555646896,
|
| 6035 |
+
"learning_rate": 0.002,
|
| 6036 |
+
"loss": 2.077460289001465,
|
| 6037 |
+
"step": 1722
|
| 6038 |
+
},
|
| 6039 |
+
{
|
| 6040 |
+
"epoch": 0.1724,
|
| 6041 |
+
"grad_norm": 0.08657451719045639,
|
| 6042 |
+
"learning_rate": 0.002,
|
| 6043 |
+
"loss": 2.007951498031616,
|
| 6044 |
+
"step": 1724
|
| 6045 |
+
},
|
| 6046 |
+
{
|
| 6047 |
+
"epoch": 0.1726,
|
| 6048 |
+
"grad_norm": 0.08407124876976013,
|
| 6049 |
+
"learning_rate": 0.002,
|
| 6050 |
+
"loss": 1.9007164239883423,
|
| 6051 |
+
"step": 1726
|
| 6052 |
+
},
|
| 6053 |
+
{
|
| 6054 |
+
"epoch": 0.1728,
|
| 6055 |
+
"grad_norm": 0.0846768319606781,
|
| 6056 |
+
"learning_rate": 0.002,
|
| 6057 |
+
"loss": 1.9592881202697754,
|
| 6058 |
+
"step": 1728
|
| 6059 |
+
},
|
| 6060 |
+
{
|
| 6061 |
+
"epoch": 0.173,
|
| 6062 |
+
"grad_norm": 0.0836617574095726,
|
| 6063 |
+
"learning_rate": 0.002,
|
| 6064 |
+
"loss": 1.9015003442764282,
|
| 6065 |
+
"step": 1730
|
| 6066 |
+
},
|
| 6067 |
+
{
|
| 6068 |
+
"epoch": 0.1732,
|
| 6069 |
+
"grad_norm": 0.08796169608831406,
|
| 6070 |
+
"learning_rate": 0.002,
|
| 6071 |
+
"loss": 2.019059658050537,
|
| 6072 |
+
"step": 1732
|
| 6073 |
+
},
|
| 6074 |
+
{
|
| 6075 |
+
"epoch": 0.1734,
|
| 6076 |
+
"grad_norm": 0.08226469159126282,
|
| 6077 |
+
"learning_rate": 0.002,
|
| 6078 |
+
"loss": 1.9710384607315063,
|
| 6079 |
+
"step": 1734
|
| 6080 |
+
},
|
| 6081 |
+
{
|
| 6082 |
+
"epoch": 0.1736,
|
| 6083 |
+
"grad_norm": 0.08608261495828629,
|
| 6084 |
+
"learning_rate": 0.002,
|
| 6085 |
+
"loss": 2.0204579830169678,
|
| 6086 |
+
"step": 1736
|
| 6087 |
+
},
|
| 6088 |
+
{
|
| 6089 |
+
"epoch": 0.1738,
|
| 6090 |
+
"grad_norm": 0.09337099641561508,
|
| 6091 |
+
"learning_rate": 0.002,
|
| 6092 |
+
"loss": 1.914751648902893,
|
| 6093 |
+
"step": 1738
|
| 6094 |
+
},
|
| 6095 |
+
{
|
| 6096 |
+
"epoch": 0.174,
|
| 6097 |
+
"grad_norm": 0.08730588853359222,
|
| 6098 |
+
"learning_rate": 0.002,
|
| 6099 |
+
"loss": 2.0349481105804443,
|
| 6100 |
+
"step": 1740
|
| 6101 |
+
},
|
| 6102 |
+
{
|
| 6103 |
+
"epoch": 0.1742,
|
| 6104 |
+
"grad_norm": 0.08293639868497849,
|
| 6105 |
+
"learning_rate": 0.002,
|
| 6106 |
+
"loss": 1.9420349597930908,
|
| 6107 |
+
"step": 1742
|
| 6108 |
+
},
|
| 6109 |
+
{
|
| 6110 |
+
"epoch": 0.1744,
|
| 6111 |
+
"grad_norm": 0.08442080765962601,
|
| 6112 |
+
"learning_rate": 0.002,
|
| 6113 |
+
"loss": 1.8389413356781006,
|
| 6114 |
+
"step": 1744
|
| 6115 |
+
},
|
| 6116 |
+
{
|
| 6117 |
+
"epoch": 0.1746,
|
| 6118 |
+
"grad_norm": 0.0882704108953476,
|
| 6119 |
+
"learning_rate": 0.002,
|
| 6120 |
+
"loss": 2.055248498916626,
|
| 6121 |
+
"step": 1746
|
| 6122 |
+
},
|
| 6123 |
+
{
|
| 6124 |
+
"epoch": 0.1748,
|
| 6125 |
+
"grad_norm": 0.0814896747469902,
|
| 6126 |
+
"learning_rate": 0.002,
|
| 6127 |
+
"loss": 1.9105103015899658,
|
| 6128 |
+
"step": 1748
|
| 6129 |
+
},
|
| 6130 |
+
{
|
| 6131 |
+
"epoch": 0.175,
|
| 6132 |
+
"grad_norm": 0.09156211465597153,
|
| 6133 |
+
"learning_rate": 0.002,
|
| 6134 |
+
"loss": 1.9891000986099243,
|
| 6135 |
+
"step": 1750
|
| 6136 |
+
},
|
| 6137 |
+
{
|
| 6138 |
+
"epoch": 0.1752,
|
| 6139 |
+
"grad_norm": 0.09001124650239944,
|
| 6140 |
+
"learning_rate": 0.002,
|
| 6141 |
+
"loss": 1.9349809885025024,
|
| 6142 |
+
"step": 1752
|
| 6143 |
+
},
|
| 6144 |
+
{
|
| 6145 |
+
"epoch": 0.1754,
|
| 6146 |
+
"grad_norm": 0.087516650557518,
|
| 6147 |
+
"learning_rate": 0.002,
|
| 6148 |
+
"loss": 1.8842822313308716,
|
| 6149 |
+
"step": 1754
|
| 6150 |
+
},
|
| 6151 |
+
{
|
| 6152 |
+
"epoch": 0.1756,
|
| 6153 |
+
"grad_norm": 0.0836789458990097,
|
| 6154 |
+
"learning_rate": 0.002,
|
| 6155 |
+
"loss": 1.9222761392593384,
|
| 6156 |
+
"step": 1756
|
| 6157 |
+
},
|
| 6158 |
+
{
|
| 6159 |
+
"epoch": 0.1758,
|
| 6160 |
+
"grad_norm": 0.08474660664796829,
|
| 6161 |
+
"learning_rate": 0.002,
|
| 6162 |
+
"loss": 2.075972557067871,
|
| 6163 |
+
"step": 1758
|
| 6164 |
+
},
|
| 6165 |
+
{
|
| 6166 |
+
"epoch": 0.176,
|
| 6167 |
+
"grad_norm": 0.6000994443893433,
|
| 6168 |
+
"learning_rate": 0.002,
|
| 6169 |
+
"loss": 2.0548179149627686,
|
| 6170 |
+
"step": 1760
|
| 6171 |
+
},
|
| 6172 |
+
{
|
| 6173 |
+
"epoch": 0.1762,
|
| 6174 |
+
"grad_norm": 0.08651186525821686,
|
| 6175 |
+
"learning_rate": 0.002,
|
| 6176 |
+
"loss": 2.043919563293457,
|
| 6177 |
+
"step": 1762
|
| 6178 |
+
},
|
| 6179 |
+
{
|
| 6180 |
+
"epoch": 0.1764,
|
| 6181 |
+
"grad_norm": 0.08672037720680237,
|
| 6182 |
+
"learning_rate": 0.002,
|
| 6183 |
+
"loss": 1.9761316776275635,
|
| 6184 |
+
"step": 1764
|
| 6185 |
+
},
|
| 6186 |
+
{
|
| 6187 |
+
"epoch": 0.1766,
|
| 6188 |
+
"grad_norm": 0.08266716450452805,
|
| 6189 |
+
"learning_rate": 0.002,
|
| 6190 |
+
"loss": 1.9101964235305786,
|
| 6191 |
+
"step": 1766
|
| 6192 |
+
},
|
| 6193 |
+
{
|
| 6194 |
+
"epoch": 0.1768,
|
| 6195 |
+
"grad_norm": 0.08747704327106476,
|
| 6196 |
+
"learning_rate": 0.002,
|
| 6197 |
+
"loss": 1.858526349067688,
|
| 6198 |
+
"step": 1768
|
| 6199 |
+
},
|
| 6200 |
+
{
|
| 6201 |
+
"epoch": 0.177,
|
| 6202 |
+
"grad_norm": 0.08086052536964417,
|
| 6203 |
+
"learning_rate": 0.002,
|
| 6204 |
+
"loss": 2.04201602935791,
|
| 6205 |
+
"step": 1770
|
| 6206 |
+
},
|
| 6207 |
+
{
|
| 6208 |
+
"epoch": 0.1772,
|
| 6209 |
+
"grad_norm": 0.08061601221561432,
|
| 6210 |
+
"learning_rate": 0.002,
|
| 6211 |
+
"loss": 1.9362319707870483,
|
| 6212 |
+
"step": 1772
|
| 6213 |
+
},
|
| 6214 |
+
{
|
| 6215 |
+
"epoch": 0.1774,
|
| 6216 |
+
"grad_norm": 0.08680877089500427,
|
| 6217 |
+
"learning_rate": 0.002,
|
| 6218 |
+
"loss": 1.8955398797988892,
|
| 6219 |
+
"step": 1774
|
| 6220 |
+
},
|
| 6221 |
+
{
|
| 6222 |
+
"epoch": 0.1776,
|
| 6223 |
+
"grad_norm": 0.08626703172922134,
|
| 6224 |
+
"learning_rate": 0.002,
|
| 6225 |
+
"loss": 1.9597290754318237,
|
| 6226 |
+
"step": 1776
|
| 6227 |
+
},
|
| 6228 |
+
{
|
| 6229 |
+
"epoch": 0.1778,
|
| 6230 |
+
"grad_norm": 0.08292295783758163,
|
| 6231 |
+
"learning_rate": 0.002,
|
| 6232 |
+
"loss": 2.015136957168579,
|
| 6233 |
+
"step": 1778
|
| 6234 |
+
},
|
| 6235 |
+
{
|
| 6236 |
+
"epoch": 0.178,
|
| 6237 |
+
"grad_norm": 0.09201980382204056,
|
| 6238 |
+
"learning_rate": 0.002,
|
| 6239 |
+
"loss": 1.9670177698135376,
|
| 6240 |
+
"step": 1780
|
| 6241 |
+
},
|
| 6242 |
+
{
|
| 6243 |
+
"epoch": 0.1782,
|
| 6244 |
+
"grad_norm": 0.08161337673664093,
|
| 6245 |
+
"learning_rate": 0.002,
|
| 6246 |
+
"loss": 1.9454771280288696,
|
| 6247 |
+
"step": 1782
|
| 6248 |
+
},
|
| 6249 |
+
{
|
| 6250 |
+
"epoch": 0.1784,
|
| 6251 |
+
"grad_norm": 0.08982264995574951,
|
| 6252 |
+
"learning_rate": 0.002,
|
| 6253 |
+
"loss": 1.9867963790893555,
|
| 6254 |
+
"step": 1784
|
| 6255 |
+
},
|
| 6256 |
+
{
|
| 6257 |
+
"epoch": 0.1786,
|
| 6258 |
+
"grad_norm": 0.08044017106294632,
|
| 6259 |
+
"learning_rate": 0.002,
|
| 6260 |
+
"loss": 1.960343599319458,
|
| 6261 |
+
"step": 1786
|
| 6262 |
+
},
|
| 6263 |
+
{
|
| 6264 |
+
"epoch": 0.1788,
|
| 6265 |
+
"grad_norm": 0.08217635005712509,
|
| 6266 |
+
"learning_rate": 0.002,
|
| 6267 |
+
"loss": 1.8296501636505127,
|
| 6268 |
+
"step": 1788
|
| 6269 |
+
},
|
| 6270 |
+
{
|
| 6271 |
+
"epoch": 0.179,
|
| 6272 |
+
"grad_norm": 0.08359440416097641,
|
| 6273 |
+
"learning_rate": 0.002,
|
| 6274 |
+
"loss": 1.9807384014129639,
|
| 6275 |
+
"step": 1790
|
| 6276 |
+
},
|
| 6277 |
+
{
|
| 6278 |
+
"epoch": 0.1792,
|
| 6279 |
+
"grad_norm": 0.08547817915678024,
|
| 6280 |
+
"learning_rate": 0.002,
|
| 6281 |
+
"loss": 1.9460605382919312,
|
| 6282 |
+
"step": 1792
|
| 6283 |
+
},
|
| 6284 |
+
{
|
| 6285 |
+
"epoch": 0.1794,
|
| 6286 |
+
"grad_norm": 0.08134095370769501,
|
| 6287 |
+
"learning_rate": 0.002,
|
| 6288 |
+
"loss": 2.0722501277923584,
|
| 6289 |
+
"step": 1794
|
| 6290 |
+
},
|
| 6291 |
+
{
|
| 6292 |
+
"epoch": 0.1796,
|
| 6293 |
+
"grad_norm": 0.084647998213768,
|
| 6294 |
+
"learning_rate": 0.002,
|
| 6295 |
+
"loss": 1.8832693099975586,
|
| 6296 |
+
"step": 1796
|
| 6297 |
+
},
|
| 6298 |
+
{
|
| 6299 |
+
"epoch": 0.1798,
|
| 6300 |
+
"grad_norm": 0.08631309121847153,
|
| 6301 |
+
"learning_rate": 0.002,
|
| 6302 |
+
"loss": 1.9553685188293457,
|
| 6303 |
+
"step": 1798
|
| 6304 |
+
},
|
| 6305 |
+
{
|
| 6306 |
+
"epoch": 0.18,
|
| 6307 |
+
"grad_norm": 0.08567328006029129,
|
| 6308 |
+
"learning_rate": 0.002,
|
| 6309 |
+
"loss": 2.0348782539367676,
|
| 6310 |
+
"step": 1800
|
| 6311 |
+
},
|
| 6312 |
+
{
|
| 6313 |
+
"epoch": 0.1802,
|
| 6314 |
+
"grad_norm": 0.08318687230348587,
|
| 6315 |
+
"learning_rate": 0.002,
|
| 6316 |
+
"loss": 1.779697060585022,
|
| 6317 |
+
"step": 1802
|
| 6318 |
+
},
|
| 6319 |
+
{
|
| 6320 |
+
"epoch": 0.1804,
|
| 6321 |
+
"grad_norm": 0.08443592488765717,
|
| 6322 |
+
"learning_rate": 0.002,
|
| 6323 |
+
"loss": 2.09885573387146,
|
| 6324 |
+
"step": 1804
|
| 6325 |
+
},
|
| 6326 |
+
{
|
| 6327 |
+
"epoch": 0.1806,
|
| 6328 |
+
"grad_norm": 0.09795618057250977,
|
| 6329 |
+
"learning_rate": 0.002,
|
| 6330 |
+
"loss": 2.0944602489471436,
|
| 6331 |
+
"step": 1806
|
| 6332 |
+
},
|
| 6333 |
+
{
|
| 6334 |
+
"epoch": 0.1808,
|
| 6335 |
+
"grad_norm": 0.09287634491920471,
|
| 6336 |
+
"learning_rate": 0.002,
|
| 6337 |
+
"loss": 1.956834077835083,
|
| 6338 |
+
"step": 1808
|
| 6339 |
+
},
|
| 6340 |
+
{
|
| 6341 |
+
"epoch": 0.181,
|
| 6342 |
+
"grad_norm": 0.08185828477144241,
|
| 6343 |
+
"learning_rate": 0.002,
|
| 6344 |
+
"loss": 1.877648949623108,
|
| 6345 |
+
"step": 1810
|
| 6346 |
+
},
|
| 6347 |
+
{
|
| 6348 |
+
"epoch": 0.1812,
|
| 6349 |
+
"grad_norm": 0.08287682384252548,
|
| 6350 |
+
"learning_rate": 0.002,
|
| 6351 |
+
"loss": 1.947015404701233,
|
| 6352 |
+
"step": 1812
|
| 6353 |
+
},
|
| 6354 |
+
{
|
| 6355 |
+
"epoch": 0.1814,
|
| 6356 |
+
"grad_norm": 0.08119559288024902,
|
| 6357 |
+
"learning_rate": 0.002,
|
| 6358 |
+
"loss": 1.9950679540634155,
|
| 6359 |
+
"step": 1814
|
| 6360 |
+
},
|
| 6361 |
+
{
|
| 6362 |
+
"epoch": 0.1816,
|
| 6363 |
+
"grad_norm": 0.08255063742399216,
|
| 6364 |
+
"learning_rate": 0.002,
|
| 6365 |
+
"loss": 1.9064756631851196,
|
| 6366 |
+
"step": 1816
|
| 6367 |
+
},
|
| 6368 |
+
{
|
| 6369 |
+
"epoch": 0.1818,
|
| 6370 |
+
"grad_norm": 0.07887885719537735,
|
| 6371 |
+
"learning_rate": 0.002,
|
| 6372 |
+
"loss": 1.8976937532424927,
|
| 6373 |
+
"step": 1818
|
| 6374 |
+
},
|
| 6375 |
+
{
|
| 6376 |
+
"epoch": 0.182,
|
| 6377 |
+
"grad_norm": 0.08447431772947311,
|
| 6378 |
+
"learning_rate": 0.002,
|
| 6379 |
+
"loss": 1.8944346904754639,
|
| 6380 |
+
"step": 1820
|
| 6381 |
+
},
|
| 6382 |
+
{
|
| 6383 |
+
"epoch": 0.1822,
|
| 6384 |
+
"grad_norm": 0.08535470813512802,
|
| 6385 |
+
"learning_rate": 0.002,
|
| 6386 |
+
"loss": 2.0893661975860596,
|
| 6387 |
+
"step": 1822
|
| 6388 |
+
},
|
| 6389 |
+
{
|
| 6390 |
+
"epoch": 0.1824,
|
| 6391 |
+
"grad_norm": 0.08468759804964066,
|
| 6392 |
+
"learning_rate": 0.002,
|
| 6393 |
+
"loss": 2.001993417739868,
|
| 6394 |
+
"step": 1824
|
| 6395 |
+
},
|
| 6396 |
+
{
|
| 6397 |
+
"epoch": 0.1826,
|
| 6398 |
+
"grad_norm": 0.08959305286407471,
|
| 6399 |
+
"learning_rate": 0.002,
|
| 6400 |
+
"loss": 2.005653142929077,
|
| 6401 |
+
"step": 1826
|
| 6402 |
+
},
|
| 6403 |
+
{
|
| 6404 |
+
"epoch": 0.1828,
|
| 6405 |
+
"grad_norm": 0.08373583853244781,
|
| 6406 |
+
"learning_rate": 0.002,
|
| 6407 |
+
"loss": 2.0966317653656006,
|
| 6408 |
+
"step": 1828
|
| 6409 |
+
},
|
| 6410 |
+
{
|
| 6411 |
+
"epoch": 0.183,
|
| 6412 |
+
"grad_norm": 0.09113795310258865,
|
| 6413 |
+
"learning_rate": 0.002,
|
| 6414 |
+
"loss": 1.9518117904663086,
|
| 6415 |
+
"step": 1830
|
| 6416 |
+
},
|
| 6417 |
+
{
|
| 6418 |
+
"epoch": 0.1832,
|
| 6419 |
+
"grad_norm": 0.08594139665365219,
|
| 6420 |
+
"learning_rate": 0.002,
|
| 6421 |
+
"loss": 2.1065845489501953,
|
| 6422 |
+
"step": 1832
|
| 6423 |
+
},
|
| 6424 |
+
{
|
| 6425 |
+
"epoch": 0.1834,
|
| 6426 |
+
"grad_norm": 0.08325822651386261,
|
| 6427 |
+
"learning_rate": 0.002,
|
| 6428 |
+
"loss": 1.9954397678375244,
|
| 6429 |
+
"step": 1834
|
| 6430 |
+
},
|
| 6431 |
+
{
|
| 6432 |
+
"epoch": 0.1836,
|
| 6433 |
+
"grad_norm": 0.08779548108577728,
|
| 6434 |
+
"learning_rate": 0.002,
|
| 6435 |
+
"loss": 1.9716862440109253,
|
| 6436 |
+
"step": 1836
|
| 6437 |
+
},
|
| 6438 |
+
{
|
| 6439 |
+
"epoch": 0.1838,
|
| 6440 |
+
"grad_norm": 0.08372428268194199,
|
| 6441 |
+
"learning_rate": 0.002,
|
| 6442 |
+
"loss": 1.9748488664627075,
|
| 6443 |
+
"step": 1838
|
| 6444 |
+
},
|
| 6445 |
+
{
|
| 6446 |
+
"epoch": 0.184,
|
| 6447 |
+
"grad_norm": 0.08295018970966339,
|
| 6448 |
+
"learning_rate": 0.002,
|
| 6449 |
+
"loss": 2.0002617835998535,
|
| 6450 |
+
"step": 1840
|
| 6451 |
+
},
|
| 6452 |
+
{
|
| 6453 |
+
"epoch": 0.1842,
|
| 6454 |
+
"grad_norm": 0.08405480533838272,
|
| 6455 |
+
"learning_rate": 0.002,
|
| 6456 |
+
"loss": 1.9223436117172241,
|
| 6457 |
+
"step": 1842
|
| 6458 |
+
},
|
| 6459 |
+
{
|
| 6460 |
+
"epoch": 0.1844,
|
| 6461 |
+
"grad_norm": 0.08446697890758514,
|
| 6462 |
+
"learning_rate": 0.002,
|
| 6463 |
+
"loss": 1.8754009008407593,
|
| 6464 |
+
"step": 1844
|
| 6465 |
+
},
|
| 6466 |
+
{
|
| 6467 |
+
"epoch": 0.1846,
|
| 6468 |
+
"grad_norm": 0.08543042838573456,
|
| 6469 |
+
"learning_rate": 0.002,
|
| 6470 |
+
"loss": 1.8577792644500732,
|
| 6471 |
+
"step": 1846
|
| 6472 |
+
},
|
| 6473 |
+
{
|
| 6474 |
+
"epoch": 0.1848,
|
| 6475 |
+
"grad_norm": 0.08950234204530716,
|
| 6476 |
+
"learning_rate": 0.002,
|
| 6477 |
+
"loss": 2.096989870071411,
|
| 6478 |
+
"step": 1848
|
| 6479 |
+
},
|
| 6480 |
+
{
|
| 6481 |
+
"epoch": 0.185,
|
| 6482 |
+
"grad_norm": 0.0939083844423294,
|
| 6483 |
+
"learning_rate": 0.002,
|
| 6484 |
+
"loss": 1.8748059272766113,
|
| 6485 |
+
"step": 1850
|
| 6486 |
+
},
|
| 6487 |
+
{
|
| 6488 |
+
"epoch": 0.1852,
|
| 6489 |
+
"grad_norm": 0.09873612225055695,
|
| 6490 |
+
"learning_rate": 0.002,
|
| 6491 |
+
"loss": 1.9742906093597412,
|
| 6492 |
+
"step": 1852
|
| 6493 |
+
},
|
| 6494 |
+
{
|
| 6495 |
+
"epoch": 0.1854,
|
| 6496 |
+
"grad_norm": 0.08476125448942184,
|
| 6497 |
+
"learning_rate": 0.002,
|
| 6498 |
+
"loss": 2.1047325134277344,
|
| 6499 |
+
"step": 1854
|
| 6500 |
+
},
|
| 6501 |
+
{
|
| 6502 |
+
"epoch": 0.1856,
|
| 6503 |
+
"grad_norm": 0.0880674496293068,
|
| 6504 |
+
"learning_rate": 0.002,
|
| 6505 |
+
"loss": 1.8781228065490723,
|
| 6506 |
+
"step": 1856
|
| 6507 |
+
},
|
| 6508 |
+
{
|
| 6509 |
+
"epoch": 0.1858,
|
| 6510 |
+
"grad_norm": 0.0865429937839508,
|
| 6511 |
+
"learning_rate": 0.002,
|
| 6512 |
+
"loss": 1.9451115131378174,
|
| 6513 |
+
"step": 1858
|
| 6514 |
+
},
|
| 6515 |
+
{
|
| 6516 |
+
"epoch": 0.186,
|
| 6517 |
+
"grad_norm": 0.08469100296497345,
|
| 6518 |
+
"learning_rate": 0.002,
|
| 6519 |
+
"loss": 2.0146076679229736,
|
| 6520 |
+
"step": 1860
|
| 6521 |
+
},
|
| 6522 |
+
{
|
| 6523 |
+
"epoch": 0.1862,
|
| 6524 |
+
"grad_norm": 0.08361531794071198,
|
| 6525 |
+
"learning_rate": 0.002,
|
| 6526 |
+
"loss": 1.9248909950256348,
|
| 6527 |
+
"step": 1862
|
| 6528 |
+
},
|
| 6529 |
+
{
|
| 6530 |
+
"epoch": 0.1864,
|
| 6531 |
+
"grad_norm": 0.08243401348590851,
|
| 6532 |
+
"learning_rate": 0.002,
|
| 6533 |
+
"loss": 2.044677257537842,
|
| 6534 |
+
"step": 1864
|
| 6535 |
+
},
|
| 6536 |
+
{
|
| 6537 |
+
"epoch": 0.1866,
|
| 6538 |
+
"grad_norm": 0.08730989694595337,
|
| 6539 |
+
"learning_rate": 0.002,
|
| 6540 |
+
"loss": 1.9625319242477417,
|
| 6541 |
+
"step": 1866
|
| 6542 |
+
},
|
| 6543 |
+
{
|
| 6544 |
+
"epoch": 0.1868,
|
| 6545 |
+
"grad_norm": 0.0863344743847847,
|
| 6546 |
+
"learning_rate": 0.002,
|
| 6547 |
+
"loss": 1.8846096992492676,
|
| 6548 |
+
"step": 1868
|
| 6549 |
+
},
|
| 6550 |
+
{
|
| 6551 |
+
"epoch": 0.187,
|
| 6552 |
+
"grad_norm": 0.08576243370771408,
|
| 6553 |
+
"learning_rate": 0.002,
|
| 6554 |
+
"loss": 1.9552323818206787,
|
| 6555 |
+
"step": 1870
|
| 6556 |
+
},
|
| 6557 |
+
{
|
| 6558 |
+
"epoch": 0.1872,
|
| 6559 |
+
"grad_norm": 0.08861047029495239,
|
| 6560 |
+
"learning_rate": 0.002,
|
| 6561 |
+
"loss": 2.0286762714385986,
|
| 6562 |
+
"step": 1872
|
| 6563 |
+
},
|
| 6564 |
+
{
|
| 6565 |
+
"epoch": 0.1874,
|
| 6566 |
+
"grad_norm": 0.08303575962781906,
|
| 6567 |
+
"learning_rate": 0.002,
|
| 6568 |
+
"loss": 1.9901646375656128,
|
| 6569 |
+
"step": 1874
|
| 6570 |
+
},
|
| 6571 |
+
{
|
| 6572 |
+
"epoch": 0.1876,
|
| 6573 |
+
"grad_norm": 0.08088395744562149,
|
| 6574 |
+
"learning_rate": 0.002,
|
| 6575 |
+
"loss": 1.7853816747665405,
|
| 6576 |
+
"step": 1876
|
| 6577 |
+
},
|
| 6578 |
+
{
|
| 6579 |
+
"epoch": 0.1878,
|
| 6580 |
+
"grad_norm": 0.08346857875585556,
|
| 6581 |
+
"learning_rate": 0.002,
|
| 6582 |
+
"loss": 1.9030942916870117,
|
| 6583 |
+
"step": 1878
|
| 6584 |
+
},
|
| 6585 |
+
{
|
| 6586 |
+
"epoch": 0.188,
|
| 6587 |
+
"grad_norm": 0.08730462193489075,
|
| 6588 |
+
"learning_rate": 0.002,
|
| 6589 |
+
"loss": 1.9499236345291138,
|
| 6590 |
+
"step": 1880
|
| 6591 |
+
},
|
| 6592 |
+
{
|
| 6593 |
+
"epoch": 0.1882,
|
| 6594 |
+
"grad_norm": 0.08578626811504364,
|
| 6595 |
+
"learning_rate": 0.002,
|
| 6596 |
+
"loss": 1.9349133968353271,
|
| 6597 |
+
"step": 1882
|
| 6598 |
+
},
|
| 6599 |
+
{
|
| 6600 |
+
"epoch": 0.1884,
|
| 6601 |
+
"grad_norm": 0.08277959376573563,
|
| 6602 |
+
"learning_rate": 0.002,
|
| 6603 |
+
"loss": 1.8892171382904053,
|
| 6604 |
+
"step": 1884
|
| 6605 |
+
},
|
| 6606 |
+
{
|
| 6607 |
+
"epoch": 0.1886,
|
| 6608 |
+
"grad_norm": 0.08430566638708115,
|
| 6609 |
+
"learning_rate": 0.002,
|
| 6610 |
+
"loss": 1.9678326845169067,
|
| 6611 |
+
"step": 1886
|
| 6612 |
+
},
|
| 6613 |
+
{
|
| 6614 |
+
"epoch": 0.1888,
|
| 6615 |
+
"grad_norm": 0.08673564344644547,
|
| 6616 |
+
"learning_rate": 0.002,
|
| 6617 |
+
"loss": 1.9515163898468018,
|
| 6618 |
+
"step": 1888
|
| 6619 |
+
},
|
| 6620 |
+
{
|
| 6621 |
+
"epoch": 0.189,
|
| 6622 |
+
"grad_norm": 0.0811837762594223,
|
| 6623 |
+
"learning_rate": 0.002,
|
| 6624 |
+
"loss": 1.9885120391845703,
|
| 6625 |
+
"step": 1890
|
| 6626 |
+
},
|
| 6627 |
+
{
|
| 6628 |
+
"epoch": 0.1892,
|
| 6629 |
+
"grad_norm": 0.09070060402154922,
|
| 6630 |
+
"learning_rate": 0.002,
|
| 6631 |
+
"loss": 1.9701941013336182,
|
| 6632 |
+
"step": 1892
|
| 6633 |
+
},
|
| 6634 |
+
{
|
| 6635 |
+
"epoch": 0.1894,
|
| 6636 |
+
"grad_norm": 0.0852934792637825,
|
| 6637 |
+
"learning_rate": 0.002,
|
| 6638 |
+
"loss": 1.8665810823440552,
|
| 6639 |
+
"step": 1894
|
| 6640 |
+
},
|
| 6641 |
+
{
|
| 6642 |
+
"epoch": 0.1896,
|
| 6643 |
+
"grad_norm": 0.08353486657142639,
|
| 6644 |
+
"learning_rate": 0.002,
|
| 6645 |
+
"loss": 1.9298522472381592,
|
| 6646 |
+
"step": 1896
|
| 6647 |
+
},
|
| 6648 |
+
{
|
| 6649 |
+
"epoch": 0.1898,
|
| 6650 |
+
"grad_norm": 0.09107336401939392,
|
| 6651 |
+
"learning_rate": 0.002,
|
| 6652 |
+
"loss": 1.899435043334961,
|
| 6653 |
+
"step": 1898
|
| 6654 |
+
},
|
| 6655 |
+
{
|
| 6656 |
+
"epoch": 0.19,
|
| 6657 |
+
"grad_norm": 0.08662459999322891,
|
| 6658 |
+
"learning_rate": 0.002,
|
| 6659 |
+
"loss": 2.028043031692505,
|
| 6660 |
+
"step": 1900
|
| 6661 |
+
},
|
| 6662 |
+
{
|
| 6663 |
+
"epoch": 0.1902,
|
| 6664 |
+
"grad_norm": 0.08985409140586853,
|
| 6665 |
+
"learning_rate": 0.002,
|
| 6666 |
+
"loss": 2.043958902359009,
|
| 6667 |
+
"step": 1902
|
| 6668 |
+
},
|
| 6669 |
+
{
|
| 6670 |
+
"epoch": 0.1904,
|
| 6671 |
+
"grad_norm": 0.08701593428850174,
|
| 6672 |
+
"learning_rate": 0.002,
|
| 6673 |
+
"loss": 1.9687647819519043,
|
| 6674 |
+
"step": 1904
|
| 6675 |
+
},
|
| 6676 |
+
{
|
| 6677 |
+
"epoch": 0.1906,
|
| 6678 |
+
"grad_norm": 0.08502478152513504,
|
| 6679 |
+
"learning_rate": 0.002,
|
| 6680 |
+
"loss": 2.1415886878967285,
|
| 6681 |
+
"step": 1906
|
| 6682 |
+
},
|
| 6683 |
+
{
|
| 6684 |
+
"epoch": 0.1908,
|
| 6685 |
+
"grad_norm": 0.0901290699839592,
|
| 6686 |
+
"learning_rate": 0.002,
|
| 6687 |
+
"loss": 1.940739393234253,
|
| 6688 |
+
"step": 1908
|
| 6689 |
+
},
|
| 6690 |
+
{
|
| 6691 |
+
"epoch": 0.191,
|
| 6692 |
+
"grad_norm": 0.08363977819681168,
|
| 6693 |
+
"learning_rate": 0.002,
|
| 6694 |
+
"loss": 1.9836229085922241,
|
| 6695 |
+
"step": 1910
|
| 6696 |
+
},
|
| 6697 |
+
{
|
| 6698 |
+
"epoch": 0.1912,
|
| 6699 |
+
"grad_norm": 0.08620919287204742,
|
| 6700 |
+
"learning_rate": 0.002,
|
| 6701 |
+
"loss": 2.012991189956665,
|
| 6702 |
+
"step": 1912
|
| 6703 |
+
},
|
| 6704 |
+
{
|
| 6705 |
+
"epoch": 0.1914,
|
| 6706 |
+
"grad_norm": 0.08760473877191544,
|
| 6707 |
+
"learning_rate": 0.002,
|
| 6708 |
+
"loss": 2.0166289806365967,
|
| 6709 |
+
"step": 1914
|
| 6710 |
+
},
|
| 6711 |
+
{
|
| 6712 |
+
"epoch": 0.1916,
|
| 6713 |
+
"grad_norm": 0.08473231643438339,
|
| 6714 |
+
"learning_rate": 0.002,
|
| 6715 |
+
"loss": 2.0080785751342773,
|
| 6716 |
+
"step": 1916
|
| 6717 |
+
},
|
| 6718 |
+
{
|
| 6719 |
+
"epoch": 0.1918,
|
| 6720 |
+
"grad_norm": 0.08816628158092499,
|
| 6721 |
+
"learning_rate": 0.002,
|
| 6722 |
+
"loss": 2.0298595428466797,
|
| 6723 |
+
"step": 1918
|
| 6724 |
+
},
|
| 6725 |
+
{
|
| 6726 |
+
"epoch": 0.192,
|
| 6727 |
+
"grad_norm": 0.08431993424892426,
|
| 6728 |
+
"learning_rate": 0.002,
|
| 6729 |
+
"loss": 1.9413989782333374,
|
| 6730 |
+
"step": 1920
|
| 6731 |
+
},
|
| 6732 |
+
{
|
| 6733 |
+
"epoch": 0.1922,
|
| 6734 |
+
"grad_norm": 0.08576439321041107,
|
| 6735 |
+
"learning_rate": 0.002,
|
| 6736 |
+
"loss": 1.836694598197937,
|
| 6737 |
+
"step": 1922
|
| 6738 |
+
},
|
| 6739 |
+
{
|
| 6740 |
+
"epoch": 0.1924,
|
| 6741 |
+
"grad_norm": 0.08376266062259674,
|
| 6742 |
+
"learning_rate": 0.002,
|
| 6743 |
+
"loss": 1.9192601442337036,
|
| 6744 |
+
"step": 1924
|
| 6745 |
+
},
|
| 6746 |
+
{
|
| 6747 |
+
"epoch": 0.1926,
|
| 6748 |
+
"grad_norm": 0.0852290689945221,
|
| 6749 |
+
"learning_rate": 0.002,
|
| 6750 |
+
"loss": 1.9260629415512085,
|
| 6751 |
+
"step": 1926
|
| 6752 |
+
},
|
| 6753 |
+
{
|
| 6754 |
+
"epoch": 0.1928,
|
| 6755 |
+
"grad_norm": 0.0883747860789299,
|
| 6756 |
+
"learning_rate": 0.002,
|
| 6757 |
+
"loss": 1.9678843021392822,
|
| 6758 |
+
"step": 1928
|
| 6759 |
+
},
|
| 6760 |
+
{
|
| 6761 |
+
"epoch": 0.193,
|
| 6762 |
+
"grad_norm": 0.08285381644964218,
|
| 6763 |
+
"learning_rate": 0.002,
|
| 6764 |
+
"loss": 2.0911788940429688,
|
| 6765 |
+
"step": 1930
|
| 6766 |
+
},
|
| 6767 |
+
{
|
| 6768 |
+
"epoch": 0.1932,
|
| 6769 |
+
"grad_norm": 0.08180463314056396,
|
| 6770 |
+
"learning_rate": 0.002,
|
| 6771 |
+
"loss": 1.877135157585144,
|
| 6772 |
+
"step": 1932
|
| 6773 |
+
},
|
| 6774 |
+
{
|
| 6775 |
+
"epoch": 0.1934,
|
| 6776 |
+
"grad_norm": 0.08843019604682922,
|
| 6777 |
+
"learning_rate": 0.002,
|
| 6778 |
+
"loss": 1.8937883377075195,
|
| 6779 |
+
"step": 1934
|
| 6780 |
+
},
|
| 6781 |
+
{
|
| 6782 |
+
"epoch": 0.1936,
|
| 6783 |
+
"grad_norm": 0.08965593576431274,
|
| 6784 |
+
"learning_rate": 0.002,
|
| 6785 |
+
"loss": 2.018563985824585,
|
| 6786 |
+
"step": 1936
|
| 6787 |
+
},
|
| 6788 |
+
{
|
| 6789 |
+
"epoch": 0.1938,
|
| 6790 |
+
"grad_norm": 0.09083735197782516,
|
| 6791 |
+
"learning_rate": 0.002,
|
| 6792 |
+
"loss": 1.9771754741668701,
|
| 6793 |
+
"step": 1938
|
| 6794 |
+
},
|
| 6795 |
+
{
|
| 6796 |
+
"epoch": 0.194,
|
| 6797 |
+
"grad_norm": 0.08669350296258926,
|
| 6798 |
+
"learning_rate": 0.002,
|
| 6799 |
+
"loss": 1.9471850395202637,
|
| 6800 |
+
"step": 1940
|
| 6801 |
+
},
|
| 6802 |
+
{
|
| 6803 |
+
"epoch": 0.1942,
|
| 6804 |
+
"grad_norm": 0.08626765757799149,
|
| 6805 |
+
"learning_rate": 0.002,
|
| 6806 |
+
"loss": 1.8741486072540283,
|
| 6807 |
+
"step": 1942
|
| 6808 |
+
},
|
| 6809 |
+
{
|
| 6810 |
+
"epoch": 0.1944,
|
| 6811 |
+
"grad_norm": 0.08252197504043579,
|
| 6812 |
+
"learning_rate": 0.002,
|
| 6813 |
+
"loss": 1.8809633255004883,
|
| 6814 |
+
"step": 1944
|
| 6815 |
+
},
|
| 6816 |
+
{
|
| 6817 |
+
"epoch": 0.1946,
|
| 6818 |
+
"grad_norm": 0.0845436081290245,
|
| 6819 |
+
"learning_rate": 0.002,
|
| 6820 |
+
"loss": 1.8249372243881226,
|
| 6821 |
+
"step": 1946
|
| 6822 |
+
},
|
| 6823 |
+
{
|
| 6824 |
+
"epoch": 0.1948,
|
| 6825 |
+
"grad_norm": 0.0836493968963623,
|
| 6826 |
+
"learning_rate": 0.002,
|
| 6827 |
+
"loss": 1.8964265584945679,
|
| 6828 |
+
"step": 1948
|
| 6829 |
+
},
|
| 6830 |
+
{
|
| 6831 |
+
"epoch": 0.195,
|
| 6832 |
+
"grad_norm": 0.08754970878362656,
|
| 6833 |
+
"learning_rate": 0.002,
|
| 6834 |
+
"loss": 1.9884169101715088,
|
| 6835 |
+
"step": 1950
|
| 6836 |
+
},
|
| 6837 |
+
{
|
| 6838 |
+
"epoch": 0.1952,
|
| 6839 |
+
"grad_norm": 0.08162931352853775,
|
| 6840 |
+
"learning_rate": 0.002,
|
| 6841 |
+
"loss": 1.9248230457305908,
|
| 6842 |
+
"step": 1952
|
| 6843 |
+
},
|
| 6844 |
+
{
|
| 6845 |
+
"epoch": 0.1954,
|
| 6846 |
+
"grad_norm": 0.08138412982225418,
|
| 6847 |
+
"learning_rate": 0.002,
|
| 6848 |
+
"loss": 1.9708248376846313,
|
| 6849 |
+
"step": 1954
|
| 6850 |
+
},
|
| 6851 |
+
{
|
| 6852 |
+
"epoch": 0.1956,
|
| 6853 |
+
"grad_norm": 0.08538922667503357,
|
| 6854 |
+
"learning_rate": 0.002,
|
| 6855 |
+
"loss": 1.8737009763717651,
|
| 6856 |
+
"step": 1956
|
| 6857 |
+
},
|
| 6858 |
+
{
|
| 6859 |
+
"epoch": 0.1958,
|
| 6860 |
+
"grad_norm": 0.08595019578933716,
|
| 6861 |
+
"learning_rate": 0.002,
|
| 6862 |
+
"loss": 1.902658224105835,
|
| 6863 |
+
"step": 1958
|
| 6864 |
+
},
|
| 6865 |
+
{
|
| 6866 |
+
"epoch": 0.196,
|
| 6867 |
+
"grad_norm": 0.08747034519910812,
|
| 6868 |
+
"learning_rate": 0.002,
|
| 6869 |
+
"loss": 2.1205339431762695,
|
| 6870 |
+
"step": 1960
|
| 6871 |
+
},
|
| 6872 |
+
{
|
| 6873 |
+
"epoch": 0.1962,
|
| 6874 |
+
"grad_norm": 0.08311095833778381,
|
| 6875 |
+
"learning_rate": 0.002,
|
| 6876 |
+
"loss": 2.0103437900543213,
|
| 6877 |
+
"step": 1962
|
| 6878 |
+
},
|
| 6879 |
+
{
|
| 6880 |
+
"epoch": 0.1964,
|
| 6881 |
+
"grad_norm": 0.08260630071163177,
|
| 6882 |
+
"learning_rate": 0.002,
|
| 6883 |
+
"loss": 2.08880352973938,
|
| 6884 |
+
"step": 1964
|
| 6885 |
+
},
|
| 6886 |
+
{
|
| 6887 |
+
"epoch": 0.1966,
|
| 6888 |
+
"grad_norm": 0.08510100841522217,
|
| 6889 |
+
"learning_rate": 0.002,
|
| 6890 |
+
"loss": 1.9506934881210327,
|
| 6891 |
+
"step": 1966
|
| 6892 |
+
},
|
| 6893 |
+
{
|
| 6894 |
+
"epoch": 0.1968,
|
| 6895 |
+
"grad_norm": 0.08761399984359741,
|
| 6896 |
+
"learning_rate": 0.002,
|
| 6897 |
+
"loss": 1.925706386566162,
|
| 6898 |
+
"step": 1968
|
| 6899 |
+
},
|
| 6900 |
+
{
|
| 6901 |
+
"epoch": 0.197,
|
| 6902 |
+
"grad_norm": 0.08779874444007874,
|
| 6903 |
+
"learning_rate": 0.002,
|
| 6904 |
+
"loss": 1.9873325824737549,
|
| 6905 |
+
"step": 1970
|
| 6906 |
+
},
|
| 6907 |
+
{
|
| 6908 |
+
"epoch": 0.1972,
|
| 6909 |
+
"grad_norm": 0.08690716326236725,
|
| 6910 |
+
"learning_rate": 0.002,
|
| 6911 |
+
"loss": 1.9406440258026123,
|
| 6912 |
+
"step": 1972
|
| 6913 |
+
},
|
| 6914 |
+
{
|
| 6915 |
+
"epoch": 0.1974,
|
| 6916 |
+
"grad_norm": 0.09347079694271088,
|
| 6917 |
+
"learning_rate": 0.002,
|
| 6918 |
+
"loss": 1.909558653831482,
|
| 6919 |
+
"step": 1974
|
| 6920 |
+
},
|
| 6921 |
+
{
|
| 6922 |
+
"epoch": 0.1976,
|
| 6923 |
+
"grad_norm": 0.08548922091722488,
|
| 6924 |
+
"learning_rate": 0.002,
|
| 6925 |
+
"loss": 1.9357054233551025,
|
| 6926 |
+
"step": 1976
|
| 6927 |
+
},
|
| 6928 |
+
{
|
| 6929 |
+
"epoch": 0.1978,
|
| 6930 |
+
"grad_norm": 0.08342369645833969,
|
| 6931 |
+
"learning_rate": 0.002,
|
| 6932 |
+
"loss": 1.9169145822525024,
|
| 6933 |
+
"step": 1978
|
| 6934 |
+
},
|
| 6935 |
+
{
|
| 6936 |
+
"epoch": 0.198,
|
| 6937 |
+
"grad_norm": 0.09005551040172577,
|
| 6938 |
+
"learning_rate": 0.002,
|
| 6939 |
+
"loss": 2.041494846343994,
|
| 6940 |
+
"step": 1980
|
| 6941 |
+
},
|
| 6942 |
+
{
|
| 6943 |
+
"epoch": 0.1982,
|
| 6944 |
+
"grad_norm": 0.0824834331870079,
|
| 6945 |
+
"learning_rate": 0.002,
|
| 6946 |
+
"loss": 1.9692611694335938,
|
| 6947 |
+
"step": 1982
|
| 6948 |
+
},
|
| 6949 |
+
{
|
| 6950 |
+
"epoch": 0.1984,
|
| 6951 |
+
"grad_norm": 0.08805745840072632,
|
| 6952 |
+
"learning_rate": 0.002,
|
| 6953 |
+
"loss": 1.8638404607772827,
|
| 6954 |
+
"step": 1984
|
| 6955 |
+
},
|
| 6956 |
+
{
|
| 6957 |
+
"epoch": 0.1986,
|
| 6958 |
+
"grad_norm": 0.08590634167194366,
|
| 6959 |
+
"learning_rate": 0.002,
|
| 6960 |
+
"loss": 2.159425735473633,
|
| 6961 |
+
"step": 1986
|
| 6962 |
+
},
|
| 6963 |
+
{
|
| 6964 |
+
"epoch": 0.1988,
|
| 6965 |
+
"grad_norm": 0.09385378658771515,
|
| 6966 |
+
"learning_rate": 0.002,
|
| 6967 |
+
"loss": 1.94144868850708,
|
| 6968 |
+
"step": 1988
|
| 6969 |
+
},
|
| 6970 |
+
{
|
| 6971 |
+
"epoch": 0.199,
|
| 6972 |
+
"grad_norm": 0.09556061029434204,
|
| 6973 |
+
"learning_rate": 0.002,
|
| 6974 |
+
"loss": 1.9435380697250366,
|
| 6975 |
+
"step": 1990
|
| 6976 |
+
},
|
| 6977 |
+
{
|
| 6978 |
+
"epoch": 0.1992,
|
| 6979 |
+
"grad_norm": 0.08348517119884491,
|
| 6980 |
+
"learning_rate": 0.002,
|
| 6981 |
+
"loss": 2.0118563175201416,
|
| 6982 |
+
"step": 1992
|
| 6983 |
+
},
|
| 6984 |
+
{
|
| 6985 |
+
"epoch": 0.1994,
|
| 6986 |
+
"grad_norm": 0.08558572828769684,
|
| 6987 |
+
"learning_rate": 0.002,
|
| 6988 |
+
"loss": 2.076636791229248,
|
| 6989 |
+
"step": 1994
|
| 6990 |
+
},
|
| 6991 |
+
{
|
| 6992 |
+
"epoch": 0.1996,
|
| 6993 |
+
"grad_norm": 0.0863652303814888,
|
| 6994 |
+
"learning_rate": 0.002,
|
| 6995 |
+
"loss": 1.9437497854232788,
|
| 6996 |
+
"step": 1996
|
| 6997 |
+
},
|
| 6998 |
+
{
|
| 6999 |
+
"epoch": 0.1998,
|
| 7000 |
+
"grad_norm": 0.08715331554412842,
|
| 7001 |
+
"learning_rate": 0.002,
|
| 7002 |
+
"loss": 2.138975143432617,
|
| 7003 |
+
"step": 1998
|
| 7004 |
+
},
|
| 7005 |
+
{
|
| 7006 |
+
"epoch": 0.2,
|
| 7007 |
+
"grad_norm": 0.08320055156946182,
|
| 7008 |
+
"learning_rate": 0.002,
|
| 7009 |
+
"loss": 1.9396672248840332,
|
| 7010 |
+
"step": 2000
|
| 7011 |
+
},
|
| 7012 |
+
{
|
| 7013 |
+
"epoch": 0.2,
|
| 7014 |
+
"eval_loss": 2.0632307529449463,
|
| 7015 |
+
"eval_runtime": 204.5116,
|
| 7016 |
+
"eval_samples_per_second": 3.056,
|
| 7017 |
+
"eval_steps_per_second": 0.386,
|
| 7018 |
+
"step": 2000
|
| 7019 |
}
|
| 7020 |
],
|
| 7021 |
"logging_steps": 2,
|
|
|
|
| 7035 |
"attributes": {}
|
| 7036 |
}
|
| 7037 |
},
|
| 7038 |
+
"total_flos": 1.7568125032652122e+18,
|
| 7039 |
"train_batch_size": 8,
|
| 7040 |
"trial_name": null,
|
| 7041 |
"trial_params": null
|