Instructions to use TREA-ORCA/finetuned_checkpoints with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TREA-ORCA/finetuned_checkpoints with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="TREA-ORCA/finetuned_checkpoints")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("TREA-ORCA/finetuned_checkpoints", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add Gemma 4 IT open-text order checkpoint
Browse files- finetuned_checkpoints/gemma4_it/open_text/order/adapter_config.json +50 -0
- finetuned_checkpoints/gemma4_it/open_text/order/adapter_model.safetensors +3 -0
- finetuned_checkpoints/gemma4_it/open_text/order/trainer_state.json +1324 -0
- finetuned_checkpoints/gemma4_it/open_text/order/training_args.bin +3 -0
finetuned_checkpoints/gemma4_it/open_text/order/adapter_config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "google/gemma-4-E4B-it",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 32,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"monteclora_config": null,
|
| 27 |
+
"peft_type": "LORA",
|
| 28 |
+
"peft_version": "0.20.0",
|
| 29 |
+
"qalora_group_size": 16,
|
| 30 |
+
"r": 16,
|
| 31 |
+
"rank_pattern": {},
|
| 32 |
+
"revision": null,
|
| 33 |
+
"target_modules": [
|
| 34 |
+
"q_proj.linear",
|
| 35 |
+
"up_proj.linear",
|
| 36 |
+
"o_proj.linear",
|
| 37 |
+
"down_proj.linear",
|
| 38 |
+
"k_proj.linear",
|
| 39 |
+
"v_proj.linear",
|
| 40 |
+
"gate_proj.linear"
|
| 41 |
+
],
|
| 42 |
+
"target_parameters": null,
|
| 43 |
+
"task_type": "CAUSAL_LM",
|
| 44 |
+
"trainable_token_indices": null,
|
| 45 |
+
"use_bdlora": null,
|
| 46 |
+
"use_dora": false,
|
| 47 |
+
"use_qalora": false,
|
| 48 |
+
"use_rslora": false,
|
| 49 |
+
"velora_config": null
|
| 50 |
+
}
|
finetuned_checkpoints/gemma4_it/open_text/order/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c1e97b6417803350d8069c5d7b0fa22350aac1251123444a71c94c76a1bd68d
|
| 3 |
+
size 22853136
|
finetuned_checkpoints/gemma4_it/open_text/order/trainer_state.json
ADDED
|
@@ -0,0 +1,1324 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 7.353374233128834,
|
| 6 |
+
"eval_steps": 50,
|
| 7 |
+
"global_step": 1500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.049079754601226995,
|
| 14 |
+
"grad_norm": 12.109990119934082,
|
| 15 |
+
"learning_rate": 4.97e-05,
|
| 16 |
+
"loss": 15.695257568359375,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.09815950920245399,
|
| 21 |
+
"grad_norm": 492.1185607910156,
|
| 22 |
+
"learning_rate": 4.936666666666667e-05,
|
| 23 |
+
"loss": 13.814830017089843,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.147239263803681,
|
| 28 |
+
"grad_norm": 54.357147216796875,
|
| 29 |
+
"learning_rate": 4.903333333333334e-05,
|
| 30 |
+
"loss": 14.251554870605469,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.19631901840490798,
|
| 35 |
+
"grad_norm": 23.947784423828125,
|
| 36 |
+
"learning_rate": 4.87e-05,
|
| 37 |
+
"loss": 14.981080627441406,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.24539877300613497,
|
| 42 |
+
"grad_norm": 35.929019927978516,
|
| 43 |
+
"learning_rate": 4.836666666666667e-05,
|
| 44 |
+
"loss": 14.776333618164063,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.24539877300613497,
|
| 49 |
+
"eval_loss": 15.932053565979004,
|
| 50 |
+
"eval_runtime": 44.4904,
|
| 51 |
+
"eval_samples_per_second": 4.091,
|
| 52 |
+
"eval_steps_per_second": 2.045,
|
| 53 |
+
"step": 50
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.294478527607362,
|
| 57 |
+
"grad_norm": 34.69807052612305,
|
| 58 |
+
"learning_rate": 4.803333333333333e-05,
|
| 59 |
+
"loss": 14.10513916015625,
|
| 60 |
+
"step": 60
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.34355828220858897,
|
| 64 |
+
"grad_norm": 12.818696022033691,
|
| 65 |
+
"learning_rate": 4.77e-05,
|
| 66 |
+
"loss": 13.515347290039063,
|
| 67 |
+
"step": 70
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.39263803680981596,
|
| 71 |
+
"grad_norm": 34.38349151611328,
|
| 72 |
+
"learning_rate": 4.736666666666667e-05,
|
| 73 |
+
"loss": 15.10628662109375,
|
| 74 |
+
"step": 80
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.44171779141104295,
|
| 78 |
+
"grad_norm": 22.764989852905273,
|
| 79 |
+
"learning_rate": 4.7033333333333336e-05,
|
| 80 |
+
"loss": 16.055389404296875,
|
| 81 |
+
"step": 90
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.49079754601226994,
|
| 85 |
+
"grad_norm": 35.86006164550781,
|
| 86 |
+
"learning_rate": 4.6700000000000003e-05,
|
| 87 |
+
"loss": 15.298782348632812,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.49079754601226994,
|
| 92 |
+
"eval_loss": 15.920439720153809,
|
| 93 |
+
"eval_runtime": 40.5881,
|
| 94 |
+
"eval_samples_per_second": 4.484,
|
| 95 |
+
"eval_steps_per_second": 2.242,
|
| 96 |
+
"step": 100
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.5398773006134969,
|
| 100 |
+
"grad_norm": 28.937267303466797,
|
| 101 |
+
"learning_rate": 4.636666666666667e-05,
|
| 102 |
+
"loss": 14.813005065917968,
|
| 103 |
+
"step": 110
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.588957055214724,
|
| 107 |
+
"grad_norm": 25.542634963989258,
|
| 108 |
+
"learning_rate": 4.603333333333333e-05,
|
| 109 |
+
"loss": 14.388447570800782,
|
| 110 |
+
"step": 120
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.6380368098159509,
|
| 114 |
+
"grad_norm": 16.275651931762695,
|
| 115 |
+
"learning_rate": 4.5700000000000006e-05,
|
| 116 |
+
"loss": 14.990806579589844,
|
| 117 |
+
"step": 130
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.6871165644171779,
|
| 121 |
+
"grad_norm": 15.388489723205566,
|
| 122 |
+
"learning_rate": 4.536666666666667e-05,
|
| 123 |
+
"loss": 15.5802001953125,
|
| 124 |
+
"step": 140
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.7361963190184049,
|
| 128 |
+
"grad_norm": 37.09296417236328,
|
| 129 |
+
"learning_rate": 4.5033333333333335e-05,
|
| 130 |
+
"loss": 14.799055480957032,
|
| 131 |
+
"step": 150
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.7361963190184049,
|
| 135 |
+
"eval_loss": 15.872281074523926,
|
| 136 |
+
"eval_runtime": 40.5095,
|
| 137 |
+
"eval_samples_per_second": 4.493,
|
| 138 |
+
"eval_steps_per_second": 2.246,
|
| 139 |
+
"step": 150
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 0.7852760736196319,
|
| 143 |
+
"grad_norm": 10.539022445678711,
|
| 144 |
+
"learning_rate": 4.47e-05,
|
| 145 |
+
"loss": 14.79764404296875,
|
| 146 |
+
"step": 160
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.8343558282208589,
|
| 150 |
+
"grad_norm": 12.91861629486084,
|
| 151 |
+
"learning_rate": 4.436666666666667e-05,
|
| 152 |
+
"loss": 15.114735412597657,
|
| 153 |
+
"step": 170
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.8834355828220859,
|
| 157 |
+
"grad_norm": 25.957990646362305,
|
| 158 |
+
"learning_rate": 4.403333333333334e-05,
|
| 159 |
+
"loss": 14.254658508300782,
|
| 160 |
+
"step": 180
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.9325153374233128,
|
| 164 |
+
"grad_norm": 79.86518096923828,
|
| 165 |
+
"learning_rate": 4.3700000000000005e-05,
|
| 166 |
+
"loss": 15.017611694335937,
|
| 167 |
+
"step": 190
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.9815950920245399,
|
| 171 |
+
"grad_norm": 98.87255859375,
|
| 172 |
+
"learning_rate": 4.3366666666666666e-05,
|
| 173 |
+
"loss": 14.6688720703125,
|
| 174 |
+
"step": 200
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.9815950920245399,
|
| 178 |
+
"eval_loss": 15.850311279296875,
|
| 179 |
+
"eval_runtime": 42.2481,
|
| 180 |
+
"eval_samples_per_second": 4.308,
|
| 181 |
+
"eval_steps_per_second": 2.154,
|
| 182 |
+
"step": 200
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.0294478527607362,
|
| 186 |
+
"grad_norm": 14.027493476867676,
|
| 187 |
+
"learning_rate": 4.3033333333333334e-05,
|
| 188 |
+
"loss": 14.518348693847656,
|
| 189 |
+
"step": 210
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.0785276073619632,
|
| 193 |
+
"grad_norm": 45.684993743896484,
|
| 194 |
+
"learning_rate": 4.27e-05,
|
| 195 |
+
"loss": 14.455206298828125,
|
| 196 |
+
"step": 220
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.1276073619631901,
|
| 200 |
+
"grad_norm": 17.536062240600586,
|
| 201 |
+
"learning_rate": 4.236666666666667e-05,
|
| 202 |
+
"loss": 14.860671997070312,
|
| 203 |
+
"step": 230
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.1766871165644173,
|
| 207 |
+
"grad_norm": 19.39891815185547,
|
| 208 |
+
"learning_rate": 4.2033333333333336e-05,
|
| 209 |
+
"loss": 14.830889892578124,
|
| 210 |
+
"step": 240
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.2257668711656442,
|
| 214 |
+
"grad_norm": 63.81292724609375,
|
| 215 |
+
"learning_rate": 4.17e-05,
|
| 216 |
+
"loss": 15.031045532226562,
|
| 217 |
+
"step": 250
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.2257668711656442,
|
| 221 |
+
"eval_loss": 15.82028579711914,
|
| 222 |
+
"eval_runtime": 41.9426,
|
| 223 |
+
"eval_samples_per_second": 4.339,
|
| 224 |
+
"eval_steps_per_second": 2.17,
|
| 225 |
+
"step": 250
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.2748466257668711,
|
| 229 |
+
"grad_norm": 48.59152603149414,
|
| 230 |
+
"learning_rate": 4.136666666666667e-05,
|
| 231 |
+
"loss": 15.470269775390625,
|
| 232 |
+
"step": 260
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.323926380368098,
|
| 236 |
+
"grad_norm": 25.5656795501709,
|
| 237 |
+
"learning_rate": 4.103333333333333e-05,
|
| 238 |
+
"loss": 14.8417724609375,
|
| 239 |
+
"step": 270
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.3730061349693252,
|
| 243 |
+
"grad_norm": 20.321744918823242,
|
| 244 |
+
"learning_rate": 4.07e-05,
|
| 245 |
+
"loss": 14.925482177734375,
|
| 246 |
+
"step": 280
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.4220858895705522,
|
| 250 |
+
"grad_norm": 19.240966796875,
|
| 251 |
+
"learning_rate": 4.036666666666667e-05,
|
| 252 |
+
"loss": 14.716397094726563,
|
| 253 |
+
"step": 290
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.471165644171779,
|
| 257 |
+
"grad_norm": 21.202096939086914,
|
| 258 |
+
"learning_rate": 4.0033333333333335e-05,
|
| 259 |
+
"loss": 13.729632568359374,
|
| 260 |
+
"step": 300
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.471165644171779,
|
| 264 |
+
"eval_loss": 15.803985595703125,
|
| 265 |
+
"eval_runtime": 40.3037,
|
| 266 |
+
"eval_samples_per_second": 4.516,
|
| 267 |
+
"eval_steps_per_second": 2.258,
|
| 268 |
+
"step": 300
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.5202453987730062,
|
| 272 |
+
"grad_norm": 23.94186019897461,
|
| 273 |
+
"learning_rate": 3.97e-05,
|
| 274 |
+
"loss": 14.003562927246094,
|
| 275 |
+
"step": 310
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.5693251533742332,
|
| 279 |
+
"grad_norm": 28.392412185668945,
|
| 280 |
+
"learning_rate": 3.936666666666667e-05,
|
| 281 |
+
"loss": 14.089813232421875,
|
| 282 |
+
"step": 320
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.61840490797546,
|
| 286 |
+
"grad_norm": 110.40748596191406,
|
| 287 |
+
"learning_rate": 3.903333333333333e-05,
|
| 288 |
+
"loss": 15.008158874511718,
|
| 289 |
+
"step": 330
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.6674846625766873,
|
| 293 |
+
"grad_norm": 60.18275451660156,
|
| 294 |
+
"learning_rate": 3.8700000000000006e-05,
|
| 295 |
+
"loss": 14.85462646484375,
|
| 296 |
+
"step": 340
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.716564417177914,
|
| 300 |
+
"grad_norm": 26.74403190612793,
|
| 301 |
+
"learning_rate": 3.8366666666666666e-05,
|
| 302 |
+
"loss": 14.246632385253907,
|
| 303 |
+
"step": 350
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.716564417177914,
|
| 307 |
+
"eval_loss": 15.770018577575684,
|
| 308 |
+
"eval_runtime": 39.2002,
|
| 309 |
+
"eval_samples_per_second": 4.643,
|
| 310 |
+
"eval_steps_per_second": 2.321,
|
| 311 |
+
"step": 350
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.7656441717791411,
|
| 315 |
+
"grad_norm": 24.725635528564453,
|
| 316 |
+
"learning_rate": 3.803333333333334e-05,
|
| 317 |
+
"loss": 14.098103332519532,
|
| 318 |
+
"step": 360
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.814723926380368,
|
| 322 |
+
"grad_norm": 28.752729415893555,
|
| 323 |
+
"learning_rate": 3.77e-05,
|
| 324 |
+
"loss": 14.970773315429687,
|
| 325 |
+
"step": 370
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.863803680981595,
|
| 329 |
+
"grad_norm": 17.397926330566406,
|
| 330 |
+
"learning_rate": 3.736666666666667e-05,
|
| 331 |
+
"loss": 13.70640869140625,
|
| 332 |
+
"step": 380
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.9128834355828221,
|
| 336 |
+
"grad_norm": 728.4320678710938,
|
| 337 |
+
"learning_rate": 3.703333333333334e-05,
|
| 338 |
+
"loss": 13.640745544433594,
|
| 339 |
+
"step": 390
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.961963190184049,
|
| 343 |
+
"grad_norm": 18.25234603881836,
|
| 344 |
+
"learning_rate": 3.6700000000000004e-05,
|
| 345 |
+
"loss": 15.168673706054687,
|
| 346 |
+
"step": 400
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.961963190184049,
|
| 350 |
+
"eval_loss": 15.671043395996094,
|
| 351 |
+
"eval_runtime": 39.7541,
|
| 352 |
+
"eval_samples_per_second": 4.578,
|
| 353 |
+
"eval_steps_per_second": 2.289,
|
| 354 |
+
"step": 400
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 2.0098159509202453,
|
| 358 |
+
"grad_norm": 171.92474365234375,
|
| 359 |
+
"learning_rate": 3.636666666666667e-05,
|
| 360 |
+
"loss": 13.975669860839844,
|
| 361 |
+
"step": 410
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 2.0588957055214725,
|
| 365 |
+
"grad_norm": 24.03426170349121,
|
| 366 |
+
"learning_rate": 3.603333333333333e-05,
|
| 367 |
+
"loss": 14.861257934570313,
|
| 368 |
+
"step": 420
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.107975460122699,
|
| 372 |
+
"grad_norm": 54.75859832763672,
|
| 373 |
+
"learning_rate": 3.57e-05,
|
| 374 |
+
"loss": 14.357989501953124,
|
| 375 |
+
"step": 430
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.1570552147239264,
|
| 379 |
+
"grad_norm": 26.02811050415039,
|
| 380 |
+
"learning_rate": 3.536666666666667e-05,
|
| 381 |
+
"loss": 14.351121520996093,
|
| 382 |
+
"step": 440
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 2.2061349693251535,
|
| 386 |
+
"grad_norm": 30.41547966003418,
|
| 387 |
+
"learning_rate": 3.5033333333333336e-05,
|
| 388 |
+
"loss": 14.889694213867188,
|
| 389 |
+
"step": 450
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 2.2061349693251535,
|
| 393 |
+
"eval_loss": 15.565719604492188,
|
| 394 |
+
"eval_runtime": 39.0464,
|
| 395 |
+
"eval_samples_per_second": 4.661,
|
| 396 |
+
"eval_steps_per_second": 2.331,
|
| 397 |
+
"step": 450
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 2.2552147239263802,
|
| 401 |
+
"grad_norm": 46.164703369140625,
|
| 402 |
+
"learning_rate": 3.4699999999999996e-05,
|
| 403 |
+
"loss": 14.418521118164062,
|
| 404 |
+
"step": 460
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.3042944785276074,
|
| 408 |
+
"grad_norm": 21.727312088012695,
|
| 409 |
+
"learning_rate": 3.436666666666667e-05,
|
| 410 |
+
"loss": 13.570603942871093,
|
| 411 |
+
"step": 470
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.3533742331288345,
|
| 415 |
+
"grad_norm": 16.459651947021484,
|
| 416 |
+
"learning_rate": 3.403333333333333e-05,
|
| 417 |
+
"loss": 13.92818603515625,
|
| 418 |
+
"step": 480
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 2.4024539877300612,
|
| 422 |
+
"grad_norm": 34.048397064208984,
|
| 423 |
+
"learning_rate": 3.3700000000000006e-05,
|
| 424 |
+
"loss": 14.147259521484376,
|
| 425 |
+
"step": 490
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 2.4515337423312884,
|
| 429 |
+
"grad_norm": 34.67011260986328,
|
| 430 |
+
"learning_rate": 3.336666666666667e-05,
|
| 431 |
+
"loss": 15.106980895996093,
|
| 432 |
+
"step": 500
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 2.4515337423312884,
|
| 436 |
+
"eval_loss": 15.51108169555664,
|
| 437 |
+
"eval_runtime": 41.1135,
|
| 438 |
+
"eval_samples_per_second": 4.427,
|
| 439 |
+
"eval_steps_per_second": 2.213,
|
| 440 |
+
"step": 500
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 2.500613496932515,
|
| 444 |
+
"grad_norm": 34.939857482910156,
|
| 445 |
+
"learning_rate": 3.3033333333333334e-05,
|
| 446 |
+
"loss": 14.182997131347657,
|
| 447 |
+
"step": 510
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 2.5496932515337423,
|
| 451 |
+
"grad_norm": 31.07122802734375,
|
| 452 |
+
"learning_rate": 3.27e-05,
|
| 453 |
+
"loss": 13.836663818359375,
|
| 454 |
+
"step": 520
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 2.5987730061349694,
|
| 458 |
+
"grad_norm": 25.74968910217285,
|
| 459 |
+
"learning_rate": 3.236666666666667e-05,
|
| 460 |
+
"loss": 14.66486053466797,
|
| 461 |
+
"step": 530
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 2.647852760736196,
|
| 465 |
+
"grad_norm": 30.36574363708496,
|
| 466 |
+
"learning_rate": 3.203333333333334e-05,
|
| 467 |
+
"loss": 14.257682800292969,
|
| 468 |
+
"step": 540
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 2.6969325153374233,
|
| 472 |
+
"grad_norm": 35.92825698852539,
|
| 473 |
+
"learning_rate": 3.1700000000000005e-05,
|
| 474 |
+
"loss": 14.175831604003907,
|
| 475 |
+
"step": 550
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 2.6969325153374233,
|
| 479 |
+
"eval_loss": 15.366315841674805,
|
| 480 |
+
"eval_runtime": 40.6433,
|
| 481 |
+
"eval_samples_per_second": 4.478,
|
| 482 |
+
"eval_steps_per_second": 2.239,
|
| 483 |
+
"step": 550
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.7460122699386504,
|
| 487 |
+
"grad_norm": 37.34353256225586,
|
| 488 |
+
"learning_rate": 3.1366666666666666e-05,
|
| 489 |
+
"loss": 14.266238403320312,
|
| 490 |
+
"step": 560
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 2.795092024539877,
|
| 494 |
+
"grad_norm": 31.735153198242188,
|
| 495 |
+
"learning_rate": 3.103333333333333e-05,
|
| 496 |
+
"loss": 13.365855407714843,
|
| 497 |
+
"step": 570
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 2.8441717791411043,
|
| 501 |
+
"grad_norm": 98.26312255859375,
|
| 502 |
+
"learning_rate": 3.07e-05,
|
| 503 |
+
"loss": 14.62713165283203,
|
| 504 |
+
"step": 580
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.8932515337423315,
|
| 508 |
+
"grad_norm": 17.439157485961914,
|
| 509 |
+
"learning_rate": 3.0366666666666665e-05,
|
| 510 |
+
"loss": 13.467413330078125,
|
| 511 |
+
"step": 590
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 2.942331288343558,
|
| 515 |
+
"grad_norm": 27.204893112182617,
|
| 516 |
+
"learning_rate": 3.0033333333333336e-05,
|
| 517 |
+
"loss": 14.057601928710938,
|
| 518 |
+
"step": 600
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 2.942331288343558,
|
| 522 |
+
"eval_loss": 15.246512413024902,
|
| 523 |
+
"eval_runtime": 43.2389,
|
| 524 |
+
"eval_samples_per_second": 4.209,
|
| 525 |
+
"eval_steps_per_second": 2.105,
|
| 526 |
+
"step": 600
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 2.9914110429447853,
|
| 530 |
+
"grad_norm": 12.329130172729492,
|
| 531 |
+
"learning_rate": 2.97e-05,
|
| 532 |
+
"loss": 14.812062072753907,
|
| 533 |
+
"step": 610
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 3.039263803680982,
|
| 537 |
+
"grad_norm": 24.031600952148438,
|
| 538 |
+
"learning_rate": 2.936666666666667e-05,
|
| 539 |
+
"loss": 13.966084289550782,
|
| 540 |
+
"step": 620
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 3.0883435582822085,
|
| 544 |
+
"grad_norm": 40.748779296875,
|
| 545 |
+
"learning_rate": 2.9033333333333335e-05,
|
| 546 |
+
"loss": 14.358778381347657,
|
| 547 |
+
"step": 630
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 3.1374233128834357,
|
| 551 |
+
"grad_norm": 14.254459381103516,
|
| 552 |
+
"learning_rate": 2.87e-05,
|
| 553 |
+
"loss": 13.152987670898437,
|
| 554 |
+
"step": 640
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 3.1865030674846624,
|
| 558 |
+
"grad_norm": 15.7260160446167,
|
| 559 |
+
"learning_rate": 2.836666666666667e-05,
|
| 560 |
+
"loss": 13.556698608398438,
|
| 561 |
+
"step": 650
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 3.1865030674846624,
|
| 565 |
+
"eval_loss": 15.114974021911621,
|
| 566 |
+
"eval_runtime": 42.1366,
|
| 567 |
+
"eval_samples_per_second": 4.319,
|
| 568 |
+
"eval_steps_per_second": 2.16,
|
| 569 |
+
"step": 650
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 3.2355828220858895,
|
| 573 |
+
"grad_norm": 38.213680267333984,
|
| 574 |
+
"learning_rate": 2.8033333333333335e-05,
|
| 575 |
+
"loss": 13.558474731445312,
|
| 576 |
+
"step": 660
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 3.2846625766871167,
|
| 580 |
+
"grad_norm": 104.97026062011719,
|
| 581 |
+
"learning_rate": 2.7700000000000002e-05,
|
| 582 |
+
"loss": 13.00757293701172,
|
| 583 |
+
"step": 670
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 3.3337423312883434,
|
| 587 |
+
"grad_norm": 13.806890487670898,
|
| 588 |
+
"learning_rate": 2.7366666666666667e-05,
|
| 589 |
+
"loss": 13.897848510742188,
|
| 590 |
+
"step": 680
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 3.3828220858895706,
|
| 594 |
+
"grad_norm": 29.56549072265625,
|
| 595 |
+
"learning_rate": 2.7033333333333334e-05,
|
| 596 |
+
"loss": 13.427003479003906,
|
| 597 |
+
"step": 690
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 3.4319018404907977,
|
| 601 |
+
"grad_norm": 81.19813537597656,
|
| 602 |
+
"learning_rate": 2.6700000000000002e-05,
|
| 603 |
+
"loss": 14.479643249511719,
|
| 604 |
+
"step": 700
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 3.4319018404907977,
|
| 608 |
+
"eval_loss": 14.978218078613281,
|
| 609 |
+
"eval_runtime": 43.6526,
|
| 610 |
+
"eval_samples_per_second": 4.169,
|
| 611 |
+
"eval_steps_per_second": 2.085,
|
| 612 |
+
"step": 700
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 3.4809815950920244,
|
| 616 |
+
"grad_norm": 16.091901779174805,
|
| 617 |
+
"learning_rate": 2.6366666666666666e-05,
|
| 618 |
+
"loss": 13.979498291015625,
|
| 619 |
+
"step": 710
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 3.5300613496932516,
|
| 623 |
+
"grad_norm": 22.681127548217773,
|
| 624 |
+
"learning_rate": 2.6033333333333337e-05,
|
| 625 |
+
"loss": 13.41939697265625,
|
| 626 |
+
"step": 720
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 3.5791411042944787,
|
| 630 |
+
"grad_norm": 17.96540641784668,
|
| 631 |
+
"learning_rate": 2.57e-05,
|
| 632 |
+
"loss": 12.661479187011718,
|
| 633 |
+
"step": 730
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 3.6282208588957054,
|
| 637 |
+
"grad_norm": 15.208456993103027,
|
| 638 |
+
"learning_rate": 2.5366666666666665e-05,
|
| 639 |
+
"loss": 14.115220642089843,
|
| 640 |
+
"step": 740
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 3.6773006134969326,
|
| 644 |
+
"grad_norm": 31.329551696777344,
|
| 645 |
+
"learning_rate": 2.5033333333333336e-05,
|
| 646 |
+
"loss": 13.163510131835938,
|
| 647 |
+
"step": 750
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 3.6773006134969326,
|
| 651 |
+
"eval_loss": 14.82515811920166,
|
| 652 |
+
"eval_runtime": 37.4149,
|
| 653 |
+
"eval_samples_per_second": 4.864,
|
| 654 |
+
"eval_steps_per_second": 2.432,
|
| 655 |
+
"step": 750
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 3.7263803680981598,
|
| 659 |
+
"grad_norm": 1332.45947265625,
|
| 660 |
+
"learning_rate": 2.47e-05,
|
| 661 |
+
"loss": 13.876724243164062,
|
| 662 |
+
"step": 760
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 3.7754601226993865,
|
| 666 |
+
"grad_norm": 34.76375198364258,
|
| 667 |
+
"learning_rate": 2.4366666666666668e-05,
|
| 668 |
+
"loss": 14.658612060546876,
|
| 669 |
+
"step": 770
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 3.8245398773006136,
|
| 673 |
+
"grad_norm": 48.79170227050781,
|
| 674 |
+
"learning_rate": 2.4033333333333336e-05,
|
| 675 |
+
"loss": 13.000140380859374,
|
| 676 |
+
"step": 780
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 3.8736196319018403,
|
| 680 |
+
"grad_norm": 42.13340759277344,
|
| 681 |
+
"learning_rate": 2.37e-05,
|
| 682 |
+
"loss": 14.50831298828125,
|
| 683 |
+
"step": 790
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 3.9226993865030675,
|
| 687 |
+
"grad_norm": 86.20625305175781,
|
| 688 |
+
"learning_rate": 2.3366666666666668e-05,
|
| 689 |
+
"loss": 14.822312927246093,
|
| 690 |
+
"step": 800
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 3.9226993865030675,
|
| 694 |
+
"eval_loss": 14.68934440612793,
|
| 695 |
+
"eval_runtime": 39.5638,
|
| 696 |
+
"eval_samples_per_second": 4.6,
|
| 697 |
+
"eval_steps_per_second": 2.3,
|
| 698 |
+
"step": 800
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 3.9717791411042946,
|
| 702 |
+
"grad_norm": 20.926660537719727,
|
| 703 |
+
"learning_rate": 2.3033333333333335e-05,
|
| 704 |
+
"loss": 13.783210754394531,
|
| 705 |
+
"step": 810
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 4.019631901840491,
|
| 709 |
+
"grad_norm": 23.816688537597656,
|
| 710 |
+
"learning_rate": 2.2700000000000003e-05,
|
| 711 |
+
"loss": 12.764644622802734,
|
| 712 |
+
"step": 820
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 4.068711656441717,
|
| 716 |
+
"grad_norm": 15.770354270935059,
|
| 717 |
+
"learning_rate": 2.236666666666667e-05,
|
| 718 |
+
"loss": 13.330882263183593,
|
| 719 |
+
"step": 830
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 4.117791411042945,
|
| 723 |
+
"grad_norm": 21.714099884033203,
|
| 724 |
+
"learning_rate": 2.2033333333333335e-05,
|
| 725 |
+
"loss": 13.474424743652344,
|
| 726 |
+
"step": 840
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 4.166871165644172,
|
| 730 |
+
"grad_norm": 91.50057983398438,
|
| 731 |
+
"learning_rate": 2.1700000000000002e-05,
|
| 732 |
+
"loss": 13.231269836425781,
|
| 733 |
+
"step": 850
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 4.166871165644172,
|
| 737 |
+
"eval_loss": 14.556946754455566,
|
| 738 |
+
"eval_runtime": 38.2205,
|
| 739 |
+
"eval_samples_per_second": 4.762,
|
| 740 |
+
"eval_steps_per_second": 2.381,
|
| 741 |
+
"step": 850
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 4.215950920245398,
|
| 745 |
+
"grad_norm": 17.647167205810547,
|
| 746 |
+
"learning_rate": 2.1366666666666667e-05,
|
| 747 |
+
"loss": 12.184500122070313,
|
| 748 |
+
"step": 860
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 4.265030674846626,
|
| 752 |
+
"grad_norm": 38.162235260009766,
|
| 753 |
+
"learning_rate": 2.1033333333333334e-05,
|
| 754 |
+
"loss": 13.84857635498047,
|
| 755 |
+
"step": 870
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 4.314110429447853,
|
| 759 |
+
"grad_norm": 50.7490119934082,
|
| 760 |
+
"learning_rate": 2.07e-05,
|
| 761 |
+
"loss": 13.955613708496093,
|
| 762 |
+
"step": 880
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 4.363190184049079,
|
| 766 |
+
"grad_norm": 49.21486282348633,
|
| 767 |
+
"learning_rate": 2.0366666666666666e-05,
|
| 768 |
+
"loss": 13.641081237792969,
|
| 769 |
+
"step": 890
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 4.412269938650307,
|
| 773 |
+
"grad_norm": 28.068675994873047,
|
| 774 |
+
"learning_rate": 2.0033333333333334e-05,
|
| 775 |
+
"loss": 12.916078186035156,
|
| 776 |
+
"step": 900
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 4.412269938650307,
|
| 780 |
+
"eval_loss": 14.424991607666016,
|
| 781 |
+
"eval_runtime": 38.9307,
|
| 782 |
+
"eval_samples_per_second": 4.675,
|
| 783 |
+
"eval_steps_per_second": 2.337,
|
| 784 |
+
"step": 900
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 4.461349693251534,
|
| 788 |
+
"grad_norm": 34.82908248901367,
|
| 789 |
+
"learning_rate": 1.97e-05,
|
| 790 |
+
"loss": 13.292868041992188,
|
| 791 |
+
"step": 910
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 4.5104294478527605,
|
| 795 |
+
"grad_norm": 63.21987533569336,
|
| 796 |
+
"learning_rate": 1.9366666666666665e-05,
|
| 797 |
+
"loss": 14.213397216796874,
|
| 798 |
+
"step": 920
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 4.559509202453988,
|
| 802 |
+
"grad_norm": 88.16678619384766,
|
| 803 |
+
"learning_rate": 1.9033333333333333e-05,
|
| 804 |
+
"loss": 14.995484924316406,
|
| 805 |
+
"step": 930
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 4.608588957055215,
|
| 809 |
+
"grad_norm": 28.077667236328125,
|
| 810 |
+
"learning_rate": 1.87e-05,
|
| 811 |
+
"loss": 12.535974884033203,
|
| 812 |
+
"step": 940
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 4.6576687116564415,
|
| 816 |
+
"grad_norm": 20.904939651489258,
|
| 817 |
+
"learning_rate": 1.8366666666666668e-05,
|
| 818 |
+
"loss": 13.060704040527344,
|
| 819 |
+
"step": 950
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 4.6576687116564415,
|
| 823 |
+
"eval_loss": 14.326519012451172,
|
| 824 |
+
"eval_runtime": 38.917,
|
| 825 |
+
"eval_samples_per_second": 4.677,
|
| 826 |
+
"eval_steps_per_second": 2.338,
|
| 827 |
+
"step": 950
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 4.706748466257669,
|
| 831 |
+
"grad_norm": 31.5518798828125,
|
| 832 |
+
"learning_rate": 1.8033333333333336e-05,
|
| 833 |
+
"loss": 13.33092041015625,
|
| 834 |
+
"step": 960
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 4.755828220858896,
|
| 838 |
+
"grad_norm": 653.3424072265625,
|
| 839 |
+
"learning_rate": 1.77e-05,
|
| 840 |
+
"loss": 12.219943237304687,
|
| 841 |
+
"step": 970
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 4.8049079754601225,
|
| 845 |
+
"grad_norm": 37.25469970703125,
|
| 846 |
+
"learning_rate": 1.7366666666666668e-05,
|
| 847 |
+
"loss": 12.116426086425781,
|
| 848 |
+
"step": 980
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 4.85398773006135,
|
| 852 |
+
"grad_norm": 92.45735168457031,
|
| 853 |
+
"learning_rate": 1.7033333333333335e-05,
|
| 854 |
+
"loss": 12.870594787597657,
|
| 855 |
+
"step": 990
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 4.903067484662577,
|
| 859 |
+
"grad_norm": 107.67335510253906,
|
| 860 |
+
"learning_rate": 1.6700000000000003e-05,
|
| 861 |
+
"loss": 13.02753143310547,
|
| 862 |
+
"step": 1000
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 4.903067484662577,
|
| 866 |
+
"eval_loss": 14.26012134552002,
|
| 867 |
+
"eval_runtime": 38.544,
|
| 868 |
+
"eval_samples_per_second": 4.722,
|
| 869 |
+
"eval_steps_per_second": 2.361,
|
| 870 |
+
"step": 1000
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 4.9521472392638035,
|
| 874 |
+
"grad_norm": 49.16620635986328,
|
| 875 |
+
"learning_rate": 1.6366666666666667e-05,
|
| 876 |
+
"loss": 13.61646728515625,
|
| 877 |
+
"step": 1010
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 5.0,
|
| 881 |
+
"grad_norm": 19.558124542236328,
|
| 882 |
+
"learning_rate": 1.6033333333333335e-05,
|
| 883 |
+
"loss": 12.80182342529297,
|
| 884 |
+
"step": 1020
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 5.049079754601227,
|
| 888 |
+
"grad_norm": 27.837764739990234,
|
| 889 |
+
"learning_rate": 1.5700000000000002e-05,
|
| 890 |
+
"loss": 12.663983154296876,
|
| 891 |
+
"step": 1030
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 5.098159509202454,
|
| 895 |
+
"grad_norm": 23.480735778808594,
|
| 896 |
+
"learning_rate": 1.536666666666667e-05,
|
| 897 |
+
"loss": 13.12053985595703,
|
| 898 |
+
"step": 1040
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 5.147239263803681,
|
| 902 |
+
"grad_norm": 31.407812118530273,
|
| 903 |
+
"learning_rate": 1.5033333333333336e-05,
|
| 904 |
+
"loss": 12.675830078125,
|
| 905 |
+
"step": 1050
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 5.147239263803681,
|
| 909 |
+
"eval_loss": 14.139296531677246,
|
| 910 |
+
"eval_runtime": 37.0199,
|
| 911 |
+
"eval_samples_per_second": 4.916,
|
| 912 |
+
"eval_steps_per_second": 2.458,
|
| 913 |
+
"step": 1050
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 5.196319018404908,
|
| 917 |
+
"grad_norm": 37.02568054199219,
|
| 918 |
+
"learning_rate": 1.47e-05,
|
| 919 |
+
"loss": 12.703949737548829,
|
| 920 |
+
"step": 1060
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 5.245398773006135,
|
| 924 |
+
"grad_norm": 39.249202728271484,
|
| 925 |
+
"learning_rate": 1.4366666666666667e-05,
|
| 926 |
+
"loss": 12.721959686279297,
|
| 927 |
+
"step": 1070
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 5.294478527607362,
|
| 931 |
+
"grad_norm": 22.826065063476562,
|
| 932 |
+
"learning_rate": 1.4033333333333335e-05,
|
| 933 |
+
"loss": 12.570162200927735,
|
| 934 |
+
"step": 1080
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 5.343558282208589,
|
| 938 |
+
"grad_norm": 23.219398498535156,
|
| 939 |
+
"learning_rate": 1.3700000000000001e-05,
|
| 940 |
+
"loss": 12.531348419189452,
|
| 941 |
+
"step": 1090
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 5.392638036809816,
|
| 945 |
+
"grad_norm": 62.71016311645508,
|
| 946 |
+
"learning_rate": 1.3366666666666667e-05,
|
| 947 |
+
"loss": 13.075291442871094,
|
| 948 |
+
"step": 1100
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 5.392638036809816,
|
| 952 |
+
"eval_loss": 14.105238914489746,
|
| 953 |
+
"eval_runtime": 39.2488,
|
| 954 |
+
"eval_samples_per_second": 4.637,
|
| 955 |
+
"eval_steps_per_second": 2.319,
|
| 956 |
+
"step": 1100
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 5.441717791411043,
|
| 960 |
+
"grad_norm": 23.681791305541992,
|
| 961 |
+
"learning_rate": 1.3033333333333333e-05,
|
| 962 |
+
"loss": 13.384321594238282,
|
| 963 |
+
"step": 1110
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 5.49079754601227,
|
| 967 |
+
"grad_norm": 27.000633239746094,
|
| 968 |
+
"learning_rate": 1.27e-05,
|
| 969 |
+
"loss": 13.452699279785156,
|
| 970 |
+
"step": 1120
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 5.539877300613497,
|
| 974 |
+
"grad_norm": 27.256839752197266,
|
| 975 |
+
"learning_rate": 1.2366666666666666e-05,
|
| 976 |
+
"loss": 11.978835296630859,
|
| 977 |
+
"step": 1130
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 5.588957055214724,
|
| 981 |
+
"grad_norm": 23.55782699584961,
|
| 982 |
+
"learning_rate": 1.2033333333333334e-05,
|
| 983 |
+
"loss": 12.881614685058594,
|
| 984 |
+
"step": 1140
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 5.638036809815951,
|
| 988 |
+
"grad_norm": 48.37996292114258,
|
| 989 |
+
"learning_rate": 1.1700000000000001e-05,
|
| 990 |
+
"loss": 13.591836547851562,
|
| 991 |
+
"step": 1150
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 5.638036809815951,
|
| 995 |
+
"eval_loss": 14.041095733642578,
|
| 996 |
+
"eval_runtime": 41.7982,
|
| 997 |
+
"eval_samples_per_second": 4.354,
|
| 998 |
+
"eval_steps_per_second": 2.177,
|
| 999 |
+
"step": 1150
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 5.6871165644171775,
|
| 1003 |
+
"grad_norm": 51.212158203125,
|
| 1004 |
+
"learning_rate": 1.1366666666666667e-05,
|
| 1005 |
+
"loss": 12.98650665283203,
|
| 1006 |
+
"step": 1160
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 5.736196319018405,
|
| 1010 |
+
"grad_norm": 51.17803955078125,
|
| 1011 |
+
"learning_rate": 1.1033333333333335e-05,
|
| 1012 |
+
"loss": 13.302549743652344,
|
| 1013 |
+
"step": 1170
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 5.785276073619632,
|
| 1017 |
+
"grad_norm": 48.82744216918945,
|
| 1018 |
+
"learning_rate": 1.0700000000000001e-05,
|
| 1019 |
+
"loss": 13.5542236328125,
|
| 1020 |
+
"step": 1180
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 5.8343558282208585,
|
| 1024 |
+
"grad_norm": 24.384714126586914,
|
| 1025 |
+
"learning_rate": 1.0366666666666667e-05,
|
| 1026 |
+
"loss": 12.123136138916015,
|
| 1027 |
+
"step": 1190
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 5.883435582822086,
|
| 1031 |
+
"grad_norm": 31.2034854888916,
|
| 1032 |
+
"learning_rate": 1.0033333333333333e-05,
|
| 1033 |
+
"loss": 12.414421844482423,
|
| 1034 |
+
"step": 1200
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 5.883435582822086,
|
| 1038 |
+
"eval_loss": 13.998857498168945,
|
| 1039 |
+
"eval_runtime": 38.6434,
|
| 1040 |
+
"eval_samples_per_second": 4.71,
|
| 1041 |
+
"eval_steps_per_second": 2.355,
|
| 1042 |
+
"step": 1200
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 5.932515337423313,
|
| 1046 |
+
"grad_norm": 37.432987213134766,
|
| 1047 |
+
"learning_rate": 9.7e-06,
|
| 1048 |
+
"loss": 13.408476257324219,
|
| 1049 |
+
"step": 1210
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 5.9815950920245395,
|
| 1053 |
+
"grad_norm": 26.05211067199707,
|
| 1054 |
+
"learning_rate": 9.366666666666666e-06,
|
| 1055 |
+
"loss": 12.927764892578125,
|
| 1056 |
+
"step": 1220
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 6.029447852760736,
|
| 1060 |
+
"grad_norm": 289.5566101074219,
|
| 1061 |
+
"learning_rate": 9.033333333333334e-06,
|
| 1062 |
+
"loss": 12.914114379882813,
|
| 1063 |
+
"step": 1230
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 6.078527607361964,
|
| 1067 |
+
"grad_norm": 26.149118423461914,
|
| 1068 |
+
"learning_rate": 8.7e-06,
|
| 1069 |
+
"loss": 12.25345687866211,
|
| 1070 |
+
"step": 1240
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 6.12760736196319,
|
| 1074 |
+
"grad_norm": 114.61143493652344,
|
| 1075 |
+
"learning_rate": 8.366666666666667e-06,
|
| 1076 |
+
"loss": 12.632183837890626,
|
| 1077 |
+
"step": 1250
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 6.12760736196319,
|
| 1081 |
+
"eval_loss": 13.935482025146484,
|
| 1082 |
+
"eval_runtime": 40.5064,
|
| 1083 |
+
"eval_samples_per_second": 4.493,
|
| 1084 |
+
"eval_steps_per_second": 2.247,
|
| 1085 |
+
"step": 1250
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 6.176687116564417,
|
| 1089 |
+
"grad_norm": 42.82421875,
|
| 1090 |
+
"learning_rate": 8.033333333333335e-06,
|
| 1091 |
+
"loss": 13.101655578613281,
|
| 1092 |
+
"step": 1260
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 6.225766871165644,
|
| 1096 |
+
"grad_norm": 33.23186492919922,
|
| 1097 |
+
"learning_rate": 7.7e-06,
|
| 1098 |
+
"loss": 13.450106811523437,
|
| 1099 |
+
"step": 1270
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 6.274846625766871,
|
| 1103 |
+
"grad_norm": 26.12009620666504,
|
| 1104 |
+
"learning_rate": 7.3666666666666676e-06,
|
| 1105 |
+
"loss": 12.488797760009765,
|
| 1106 |
+
"step": 1280
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 6.323926380368098,
|
| 1110 |
+
"grad_norm": 32.78421401977539,
|
| 1111 |
+
"learning_rate": 7.0333333333333335e-06,
|
| 1112 |
+
"loss": 12.555646514892578,
|
| 1113 |
+
"step": 1290
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 6.373006134969325,
|
| 1117 |
+
"grad_norm": 29.015918731689453,
|
| 1118 |
+
"learning_rate": 6.700000000000001e-06,
|
| 1119 |
+
"loss": 12.983633422851563,
|
| 1120 |
+
"step": 1300
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 6.373006134969325,
|
| 1124 |
+
"eval_loss": 13.928925514221191,
|
| 1125 |
+
"eval_runtime": 39.9512,
|
| 1126 |
+
"eval_samples_per_second": 4.556,
|
| 1127 |
+
"eval_steps_per_second": 2.278,
|
| 1128 |
+
"step": 1300
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 6.422085889570552,
|
| 1132 |
+
"grad_norm": 41.78955078125,
|
| 1133 |
+
"learning_rate": 6.366666666666667e-06,
|
| 1134 |
+
"loss": 12.635806274414062,
|
| 1135 |
+
"step": 1310
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 6.471165644171779,
|
| 1139 |
+
"grad_norm": 24.4581298828125,
|
| 1140 |
+
"learning_rate": 6.033333333333334e-06,
|
| 1141 |
+
"loss": 13.062667846679688,
|
| 1142 |
+
"step": 1320
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 6.520245398773006,
|
| 1146 |
+
"grad_norm": 50.299800872802734,
|
| 1147 |
+
"learning_rate": 5.7000000000000005e-06,
|
| 1148 |
+
"loss": 12.462434387207031,
|
| 1149 |
+
"step": 1330
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 6.569325153374233,
|
| 1153 |
+
"grad_norm": 33.94356155395508,
|
| 1154 |
+
"learning_rate": 5.366666666666667e-06,
|
| 1155 |
+
"loss": 12.54861831665039,
|
| 1156 |
+
"step": 1340
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 6.61840490797546,
|
| 1160 |
+
"grad_norm": 36.55792999267578,
|
| 1161 |
+
"learning_rate": 5.033333333333334e-06,
|
| 1162 |
+
"loss": 13.983724975585938,
|
| 1163 |
+
"step": 1350
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 6.61840490797546,
|
| 1167 |
+
"eval_loss": 13.907698631286621,
|
| 1168 |
+
"eval_runtime": 41.4124,
|
| 1169 |
+
"eval_samples_per_second": 4.395,
|
| 1170 |
+
"eval_steps_per_second": 2.197,
|
| 1171 |
+
"step": 1350
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 6.667484662576687,
|
| 1175 |
+
"grad_norm": 25.11964988708496,
|
| 1176 |
+
"learning_rate": 4.7e-06,
|
| 1177 |
+
"loss": 13.335467529296874,
|
| 1178 |
+
"step": 1360
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 6.716564417177914,
|
| 1182 |
+
"grad_norm": 17.177019119262695,
|
| 1183 |
+
"learning_rate": 4.366666666666667e-06,
|
| 1184 |
+
"loss": 11.984165954589844,
|
| 1185 |
+
"step": 1370
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 6.765644171779141,
|
| 1189 |
+
"grad_norm": 35.68173599243164,
|
| 1190 |
+
"learning_rate": 4.033333333333333e-06,
|
| 1191 |
+
"loss": 12.69136962890625,
|
| 1192 |
+
"step": 1380
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 6.814723926380368,
|
| 1196 |
+
"grad_norm": 37.65143585205078,
|
| 1197 |
+
"learning_rate": 3.7e-06,
|
| 1198 |
+
"loss": 13.1892333984375,
|
| 1199 |
+
"step": 1390
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 6.863803680981595,
|
| 1203 |
+
"grad_norm": 23.39664077758789,
|
| 1204 |
+
"learning_rate": 3.3666666666666665e-06,
|
| 1205 |
+
"loss": 13.339341735839843,
|
| 1206 |
+
"step": 1400
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 6.863803680981595,
|
| 1210 |
+
"eval_loss": 13.878008842468262,
|
| 1211 |
+
"eval_runtime": 39.4923,
|
| 1212 |
+
"eval_samples_per_second": 4.608,
|
| 1213 |
+
"eval_steps_per_second": 2.304,
|
| 1214 |
+
"step": 1400
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 6.912883435582822,
|
| 1218 |
+
"grad_norm": 23.29909324645996,
|
| 1219 |
+
"learning_rate": 3.0333333333333337e-06,
|
| 1220 |
+
"loss": 12.268131256103516,
|
| 1221 |
+
"step": 1410
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 6.961963190184049,
|
| 1225 |
+
"grad_norm": 36.48480987548828,
|
| 1226 |
+
"learning_rate": 2.7e-06,
|
| 1227 |
+
"loss": 11.793212890625,
|
| 1228 |
+
"step": 1420
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 7.009815950920245,
|
| 1232 |
+
"grad_norm": 22.55660629272461,
|
| 1233 |
+
"learning_rate": 2.3666666666666667e-06,
|
| 1234 |
+
"loss": 12.747257232666016,
|
| 1235 |
+
"step": 1430
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 7.058895705521472,
|
| 1239 |
+
"grad_norm": 19.58152961730957,
|
| 1240 |
+
"learning_rate": 2.033333333333333e-06,
|
| 1241 |
+
"loss": 12.71964111328125,
|
| 1242 |
+
"step": 1440
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 7.1079754601227,
|
| 1246 |
+
"grad_norm": 53.886444091796875,
|
| 1247 |
+
"learning_rate": 1.7000000000000002e-06,
|
| 1248 |
+
"loss": 11.690947723388671,
|
| 1249 |
+
"step": 1450
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 7.1079754601227,
|
| 1253 |
+
"eval_loss": 13.852093696594238,
|
| 1254 |
+
"eval_runtime": 36.145,
|
| 1255 |
+
"eval_samples_per_second": 5.035,
|
| 1256 |
+
"eval_steps_per_second": 2.518,
|
| 1257 |
+
"step": 1450
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 7.157055214723926,
|
| 1261 |
+
"grad_norm": 22.625911712646484,
|
| 1262 |
+
"learning_rate": 1.3666666666666668e-06,
|
| 1263 |
+
"loss": 11.432347869873047,
|
| 1264 |
+
"step": 1460
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 7.206134969325153,
|
| 1268 |
+
"grad_norm": 32.625022888183594,
|
| 1269 |
+
"learning_rate": 1.0333333333333333e-06,
|
| 1270 |
+
"loss": 12.800825500488282,
|
| 1271 |
+
"step": 1470
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 7.255214723926381,
|
| 1275 |
+
"grad_norm": 154.76283264160156,
|
| 1276 |
+
"learning_rate": 7.000000000000001e-07,
|
| 1277 |
+
"loss": 13.552883911132813,
|
| 1278 |
+
"step": 1480
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 7.304294478527607,
|
| 1282 |
+
"grad_norm": 28.690673828125,
|
| 1283 |
+
"learning_rate": 3.6666666666666667e-07,
|
| 1284 |
+
"loss": 13.66332550048828,
|
| 1285 |
+
"step": 1490
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 7.353374233128834,
|
| 1289 |
+
"grad_norm": 130.90518188476562,
|
| 1290 |
+
"learning_rate": 3.3333333333333334e-08,
|
| 1291 |
+
"loss": 12.21392364501953,
|
| 1292 |
+
"step": 1500
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 7.353374233128834,
|
| 1296 |
+
"eval_loss": 13.874632835388184,
|
| 1297 |
+
"eval_runtime": 37.9723,
|
| 1298 |
+
"eval_samples_per_second": 4.793,
|
| 1299 |
+
"eval_steps_per_second": 2.396,
|
| 1300 |
+
"step": 1500
|
| 1301 |
+
}
|
| 1302 |
+
],
|
| 1303 |
+
"logging_steps": 10,
|
| 1304 |
+
"max_steps": 1500,
|
| 1305 |
+
"num_input_tokens_seen": 0,
|
| 1306 |
+
"num_train_epochs": 8,
|
| 1307 |
+
"save_steps": 50,
|
| 1308 |
+
"stateful_callbacks": {
|
| 1309 |
+
"TrainerControl": {
|
| 1310 |
+
"args": {
|
| 1311 |
+
"should_epoch_stop": false,
|
| 1312 |
+
"should_evaluate": false,
|
| 1313 |
+
"should_log": false,
|
| 1314 |
+
"should_save": true,
|
| 1315 |
+
"should_training_stop": true
|
| 1316 |
+
},
|
| 1317 |
+
"attributes": {}
|
| 1318 |
+
}
|
| 1319 |
+
},
|
| 1320 |
+
"total_flos": 2.504250677142766e+17,
|
| 1321 |
+
"train_batch_size": 2,
|
| 1322 |
+
"trial_name": null,
|
| 1323 |
+
"trial_params": null
|
| 1324 |
+
}
|
finetuned_checkpoints/gemma4_it/open_text/order/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:305c8cee4aff594fe4d0f94a97b7b5d11c87d544a7f577e693f47b45391798eb
|
| 3 |
+
size 5201
|