model upload
Browse files- adapter_config.json +30 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +2331 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "smallcloudai/Refact-1_6B-fim",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"c_proj",
|
| 24 |
+
"kv",
|
| 25 |
+
"q"
|
| 26 |
+
],
|
| 27 |
+
"task_type": "CAUSAL_LM",
|
| 28 |
+
"use_dora": false,
|
| 29 |
+
"use_rslora": false
|
| 30 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8dc58a6fdb0389a89a691cf75cbe89e406a072aae75e70cfdf92e12ae55cfa8e
|
| 3 |
+
size 73957352
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0a31a840b8847a34b0de7b60bad4cb3b7432fe3e78f07affae81c8ac2ee73eb
|
| 3 |
+
size 37333140
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b521e669ef0b1becee8e145b3b5bdf7d00ccc00d93b2b0dbada2d0a5de7b7926
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8fe56f4b0663f44ad5274e201067af6a5dd3e0c6e7f749fd09f6956c926c3592
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2331 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.95475113122172,
|
| 5 |
+
"eval_steps": 25,
|
| 6 |
+
"global_step": 3850,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06464124111182935,
|
| 13 |
+
"grad_norm": 0.6707131266593933,
|
| 14 |
+
"learning_rate": 0.0001987561544441565,
|
| 15 |
+
"loss": 1.2216,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06464124111182935,
|
| 20 |
+
"eval_loss": 0.6498388051986694,
|
| 21 |
+
"eval_runtime": 13.8809,
|
| 22 |
+
"eval_samples_per_second": 13.976,
|
| 23 |
+
"eval_steps_per_second": 1.801,
|
| 24 |
+
"step": 25
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.1292824822236587,
|
| 28 |
+
"grad_norm": 1.3595010042190552,
|
| 29 |
+
"learning_rate": 0.0001974604819901529,
|
| 30 |
+
"loss": 0.547,
|
| 31 |
+
"step": 50
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.1292824822236587,
|
| 35 |
+
"eval_loss": 0.6438911557197571,
|
| 36 |
+
"eval_runtime": 13.8752,
|
| 37 |
+
"eval_samples_per_second": 13.982,
|
| 38 |
+
"eval_steps_per_second": 1.802,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.19392372333548805,
|
| 43 |
+
"grad_norm": 0.6108447909355164,
|
| 44 |
+
"learning_rate": 0.00019616480953614927,
|
| 45 |
+
"loss": 0.6683,
|
| 46 |
+
"step": 75
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.19392372333548805,
|
| 50 |
+
"eval_loss": 0.5715335011482239,
|
| 51 |
+
"eval_runtime": 13.8894,
|
| 52 |
+
"eval_samples_per_second": 13.967,
|
| 53 |
+
"eval_steps_per_second": 1.8,
|
| 54 |
+
"step": 75
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.2585649644473174,
|
| 58 |
+
"grad_norm": 0.5456333160400391,
|
| 59 |
+
"learning_rate": 0.00019486913708214565,
|
| 60 |
+
"loss": 0.4938,
|
| 61 |
+
"step": 100
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.2585649644473174,
|
| 65 |
+
"eval_loss": 0.5783222913742065,
|
| 66 |
+
"eval_runtime": 13.8829,
|
| 67 |
+
"eval_samples_per_second": 13.974,
|
| 68 |
+
"eval_steps_per_second": 1.801,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.32320620555914675,
|
| 73 |
+
"grad_norm": 0.49040475487709045,
|
| 74 |
+
"learning_rate": 0.000193573464628142,
|
| 75 |
+
"loss": 0.6211,
|
| 76 |
+
"step": 125
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.32320620555914675,
|
| 80 |
+
"eval_loss": 0.5169771909713745,
|
| 81 |
+
"eval_runtime": 13.8894,
|
| 82 |
+
"eval_samples_per_second": 13.967,
|
| 83 |
+
"eval_steps_per_second": 1.8,
|
| 84 |
+
"step": 125
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.3878474466709761,
|
| 88 |
+
"grad_norm": 0.5957172513008118,
|
| 89 |
+
"learning_rate": 0.00019227779217413838,
|
| 90 |
+
"loss": 0.4272,
|
| 91 |
+
"step": 150
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.3878474466709761,
|
| 95 |
+
"eval_loss": 0.5196932554244995,
|
| 96 |
+
"eval_runtime": 13.8809,
|
| 97 |
+
"eval_samples_per_second": 13.976,
|
| 98 |
+
"eval_steps_per_second": 1.801,
|
| 99 |
+
"step": 150
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.45248868778280543,
|
| 103 |
+
"grad_norm": 0.5516940951347351,
|
| 104 |
+
"learning_rate": 0.00019098211972013476,
|
| 105 |
+
"loss": 0.5702,
|
| 106 |
+
"step": 175
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.45248868778280543,
|
| 110 |
+
"eval_loss": 0.47964370250701904,
|
| 111 |
+
"eval_runtime": 13.8882,
|
| 112 |
+
"eval_samples_per_second": 13.969,
|
| 113 |
+
"eval_steps_per_second": 1.8,
|
| 114 |
+
"step": 175
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.5171299288946348,
|
| 118 |
+
"grad_norm": 0.6955189108848572,
|
| 119 |
+
"learning_rate": 0.00018968644726613114,
|
| 120 |
+
"loss": 0.3935,
|
| 121 |
+
"step": 200
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5171299288946348,
|
| 125 |
+
"eval_loss": 0.4756932258605957,
|
| 126 |
+
"eval_runtime": 13.8869,
|
| 127 |
+
"eval_samples_per_second": 13.97,
|
| 128 |
+
"eval_steps_per_second": 1.8,
|
| 129 |
+
"step": 200
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.5817711700064642,
|
| 133 |
+
"grad_norm": 0.6203818321228027,
|
| 134 |
+
"learning_rate": 0.0001883907748121275,
|
| 135 |
+
"loss": 0.5132,
|
| 136 |
+
"step": 225
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.5817711700064642,
|
| 140 |
+
"eval_loss": 0.45499277114868164,
|
| 141 |
+
"eval_runtime": 13.8818,
|
| 142 |
+
"eval_samples_per_second": 13.975,
|
| 143 |
+
"eval_steps_per_second": 1.801,
|
| 144 |
+
"step": 225
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.6464124111182935,
|
| 148 |
+
"grad_norm": 0.5430071353912354,
|
| 149 |
+
"learning_rate": 0.00018709510235812387,
|
| 150 |
+
"loss": 0.3806,
|
| 151 |
+
"step": 250
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.6464124111182935,
|
| 155 |
+
"eval_loss": 0.4564308226108551,
|
| 156 |
+
"eval_runtime": 13.8864,
|
| 157 |
+
"eval_samples_per_second": 13.97,
|
| 158 |
+
"eval_steps_per_second": 1.8,
|
| 159 |
+
"step": 250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.7110536522301228,
|
| 163 |
+
"grad_norm": 0.47872328758239746,
|
| 164 |
+
"learning_rate": 0.00018579942990412025,
|
| 165 |
+
"loss": 0.5195,
|
| 166 |
+
"step": 275
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.7110536522301228,
|
| 170 |
+
"eval_loss": 0.42872217297554016,
|
| 171 |
+
"eval_runtime": 13.8797,
|
| 172 |
+
"eval_samples_per_second": 13.977,
|
| 173 |
+
"eval_steps_per_second": 1.801,
|
| 174 |
+
"step": 275
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.7756948933419522,
|
| 178 |
+
"grad_norm": 0.43633943796157837,
|
| 179 |
+
"learning_rate": 0.0001845037574501166,
|
| 180 |
+
"loss": 0.337,
|
| 181 |
+
"step": 300
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.7756948933419522,
|
| 185 |
+
"eval_loss": 0.44021356105804443,
|
| 186 |
+
"eval_runtime": 13.8816,
|
| 187 |
+
"eval_samples_per_second": 13.975,
|
| 188 |
+
"eval_steps_per_second": 1.801,
|
| 189 |
+
"step": 300
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.8403361344537815,
|
| 193 |
+
"grad_norm": 0.4739358127117157,
|
| 194 |
+
"learning_rate": 0.00018320808499611298,
|
| 195 |
+
"loss": 0.4566,
|
| 196 |
+
"step": 325
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.8403361344537815,
|
| 200 |
+
"eval_loss": 0.41129282116889954,
|
| 201 |
+
"eval_runtime": 13.8846,
|
| 202 |
+
"eval_samples_per_second": 13.972,
|
| 203 |
+
"eval_steps_per_second": 1.801,
|
| 204 |
+
"step": 325
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.9049773755656109,
|
| 208 |
+
"grad_norm": 0.5350446105003357,
|
| 209 |
+
"learning_rate": 0.00018191241254210936,
|
| 210 |
+
"loss": 0.3097,
|
| 211 |
+
"step": 350
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.9049773755656109,
|
| 215 |
+
"eval_loss": 0.4308871626853943,
|
| 216 |
+
"eval_runtime": 13.884,
|
| 217 |
+
"eval_samples_per_second": 13.973,
|
| 218 |
+
"eval_steps_per_second": 1.801,
|
| 219 |
+
"step": 350
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.9696186166774402,
|
| 223 |
+
"grad_norm": 0.5064755082130432,
|
| 224 |
+
"learning_rate": 0.00018061674008810574,
|
| 225 |
+
"loss": 0.4391,
|
| 226 |
+
"step": 375
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.9696186166774402,
|
| 230 |
+
"eval_loss": 0.3927255868911743,
|
| 231 |
+
"eval_runtime": 13.8854,
|
| 232 |
+
"eval_samples_per_second": 13.972,
|
| 233 |
+
"eval_steps_per_second": 1.8,
|
| 234 |
+
"step": 375
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.0342598577892697,
|
| 238 |
+
"grad_norm": 0.594939649105072,
|
| 239 |
+
"learning_rate": 0.0001793210676341021,
|
| 240 |
+
"loss": 0.413,
|
| 241 |
+
"step": 400
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.0342598577892697,
|
| 245 |
+
"eval_loss": 0.38139256834983826,
|
| 246 |
+
"eval_runtime": 13.8858,
|
| 247 |
+
"eval_samples_per_second": 13.971,
|
| 248 |
+
"eval_steps_per_second": 1.8,
|
| 249 |
+
"step": 400
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.098901098901099,
|
| 253 |
+
"grad_norm": 0.5481505393981934,
|
| 254 |
+
"learning_rate": 0.00017802539518009847,
|
| 255 |
+
"loss": 0.2737,
|
| 256 |
+
"step": 425
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.098901098901099,
|
| 260 |
+
"eval_loss": 0.395649790763855,
|
| 261 |
+
"eval_runtime": 13.8927,
|
| 262 |
+
"eval_samples_per_second": 13.964,
|
| 263 |
+
"eval_steps_per_second": 1.8,
|
| 264 |
+
"step": 425
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.1635423400129283,
|
| 268 |
+
"grad_norm": 0.5053268074989319,
|
| 269 |
+
"learning_rate": 0.00017672972272609485,
|
| 270 |
+
"loss": 0.3219,
|
| 271 |
+
"step": 450
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.1635423400129283,
|
| 275 |
+
"eval_loss": 0.37703385949134827,
|
| 276 |
+
"eval_runtime": 13.8769,
|
| 277 |
+
"eval_samples_per_second": 13.98,
|
| 278 |
+
"eval_steps_per_second": 1.802,
|
| 279 |
+
"step": 450
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.2281835811247577,
|
| 283 |
+
"grad_norm": 0.5772731304168701,
|
| 284 |
+
"learning_rate": 0.00017543405027209123,
|
| 285 |
+
"loss": 0.2942,
|
| 286 |
+
"step": 475
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.2281835811247577,
|
| 290 |
+
"eval_loss": 0.37387123703956604,
|
| 291 |
+
"eval_runtime": 13.8976,
|
| 292 |
+
"eval_samples_per_second": 13.959,
|
| 293 |
+
"eval_steps_per_second": 1.799,
|
| 294 |
+
"step": 475
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.292824822236587,
|
| 298 |
+
"grad_norm": 0.5018692016601562,
|
| 299 |
+
"learning_rate": 0.00017413837781808759,
|
| 300 |
+
"loss": 0.3059,
|
| 301 |
+
"step": 500
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 1.292824822236587,
|
| 305 |
+
"eval_loss": 0.3657205402851105,
|
| 306 |
+
"eval_runtime": 13.8767,
|
| 307 |
+
"eval_samples_per_second": 13.98,
|
| 308 |
+
"eval_steps_per_second": 1.802,
|
| 309 |
+
"step": 500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.3574660633484164,
|
| 313 |
+
"grad_norm": 0.5072377324104309,
|
| 314 |
+
"learning_rate": 0.000172842705364084,
|
| 315 |
+
"loss": 0.3096,
|
| 316 |
+
"step": 525
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.3574660633484164,
|
| 320 |
+
"eval_loss": 0.3578204810619354,
|
| 321 |
+
"eval_runtime": 13.8863,
|
| 322 |
+
"eval_samples_per_second": 13.971,
|
| 323 |
+
"eval_steps_per_second": 1.8,
|
| 324 |
+
"step": 525
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.4221073044602457,
|
| 328 |
+
"grad_norm": 0.849237322807312,
|
| 329 |
+
"learning_rate": 0.00017154703291008034,
|
| 330 |
+
"loss": 0.3177,
|
| 331 |
+
"step": 550
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.4221073044602457,
|
| 335 |
+
"eval_loss": 0.3545144498348236,
|
| 336 |
+
"eval_runtime": 13.8893,
|
| 337 |
+
"eval_samples_per_second": 13.968,
|
| 338 |
+
"eval_steps_per_second": 1.8,
|
| 339 |
+
"step": 550
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.486748545572075,
|
| 343 |
+
"grad_norm": 0.5274140238761902,
|
| 344 |
+
"learning_rate": 0.0001702513604560767,
|
| 345 |
+
"loss": 0.2612,
|
| 346 |
+
"step": 575
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.486748545572075,
|
| 350 |
+
"eval_loss": 0.35140955448150635,
|
| 351 |
+
"eval_runtime": 13.8855,
|
| 352 |
+
"eval_samples_per_second": 13.971,
|
| 353 |
+
"eval_steps_per_second": 1.8,
|
| 354 |
+
"step": 575
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.5513897866839044,
|
| 358 |
+
"grad_norm": 0.5522105097770691,
|
| 359 |
+
"learning_rate": 0.00016895568800207308,
|
| 360 |
+
"loss": 0.3167,
|
| 361 |
+
"step": 600
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.5513897866839044,
|
| 365 |
+
"eval_loss": 0.3356325924396515,
|
| 366 |
+
"eval_runtime": 13.8908,
|
| 367 |
+
"eval_samples_per_second": 13.966,
|
| 368 |
+
"eval_steps_per_second": 1.8,
|
| 369 |
+
"step": 600
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.6160310277957337,
|
| 373 |
+
"grad_norm": 0.553512454032898,
|
| 374 |
+
"learning_rate": 0.00016766001554806945,
|
| 375 |
+
"loss": 0.2564,
|
| 376 |
+
"step": 625
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.6160310277957337,
|
| 380 |
+
"eval_loss": 0.34089842438697815,
|
| 381 |
+
"eval_runtime": 13.8734,
|
| 382 |
+
"eval_samples_per_second": 13.984,
|
| 383 |
+
"eval_steps_per_second": 1.802,
|
| 384 |
+
"step": 625
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.680672268907563,
|
| 388 |
+
"grad_norm": 0.624850869178772,
|
| 389 |
+
"learning_rate": 0.00016636434309406583,
|
| 390 |
+
"loss": 0.2806,
|
| 391 |
+
"step": 650
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.680672268907563,
|
| 395 |
+
"eval_loss": 0.33262547850608826,
|
| 396 |
+
"eval_runtime": 13.8806,
|
| 397 |
+
"eval_samples_per_second": 13.976,
|
| 398 |
+
"eval_steps_per_second": 1.801,
|
| 399 |
+
"step": 650
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.7453135100193924,
|
| 403 |
+
"grad_norm": 0.5675662159919739,
|
| 404 |
+
"learning_rate": 0.0001650686706400622,
|
| 405 |
+
"loss": 0.2681,
|
| 406 |
+
"step": 675
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.7453135100193924,
|
| 410 |
+
"eval_loss": 0.33418890833854675,
|
| 411 |
+
"eval_runtime": 13.8914,
|
| 412 |
+
"eval_samples_per_second": 13.965,
|
| 413 |
+
"eval_steps_per_second": 1.8,
|
| 414 |
+
"step": 675
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.8099547511312217,
|
| 418 |
+
"grad_norm": 0.4701014757156372,
|
| 419 |
+
"learning_rate": 0.00016377299818605857,
|
| 420 |
+
"loss": 0.2764,
|
| 421 |
+
"step": 700
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 1.8099547511312217,
|
| 425 |
+
"eval_loss": 0.3225066661834717,
|
| 426 |
+
"eval_runtime": 13.891,
|
| 427 |
+
"eval_samples_per_second": 13.966,
|
| 428 |
+
"eval_steps_per_second": 1.8,
|
| 429 |
+
"step": 700
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.874595992243051,
|
| 433 |
+
"grad_norm": 0.5774489641189575,
|
| 434 |
+
"learning_rate": 0.00016247732573205495,
|
| 435 |
+
"loss": 0.2597,
|
| 436 |
+
"step": 725
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.874595992243051,
|
| 440 |
+
"eval_loss": 0.31712260842323303,
|
| 441 |
+
"eval_runtime": 13.8906,
|
| 442 |
+
"eval_samples_per_second": 13.966,
|
| 443 |
+
"eval_steps_per_second": 1.8,
|
| 444 |
+
"step": 725
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.9392372333548804,
|
| 448 |
+
"grad_norm": 0.5142238736152649,
|
| 449 |
+
"learning_rate": 0.00016118165327805132,
|
| 450 |
+
"loss": 0.2555,
|
| 451 |
+
"step": 750
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.9392372333548804,
|
| 455 |
+
"eval_loss": 0.3142366409301758,
|
| 456 |
+
"eval_runtime": 13.8911,
|
| 457 |
+
"eval_samples_per_second": 13.966,
|
| 458 |
+
"eval_steps_per_second": 1.8,
|
| 459 |
+
"step": 750
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.0038784744667097,
|
| 463 |
+
"grad_norm": 0.49566784501075745,
|
| 464 |
+
"learning_rate": 0.00015988598082404768,
|
| 465 |
+
"loss": 0.235,
|
| 466 |
+
"step": 775
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 2.0038784744667097,
|
| 470 |
+
"eval_loss": 0.3169262409210205,
|
| 471 |
+
"eval_runtime": 13.8798,
|
| 472 |
+
"eval_samples_per_second": 13.977,
|
| 473 |
+
"eval_steps_per_second": 1.801,
|
| 474 |
+
"step": 775
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.0685197155785393,
|
| 478 |
+
"grad_norm": 0.5878920555114746,
|
| 479 |
+
"learning_rate": 0.00015859030837004406,
|
| 480 |
+
"loss": 0.1971,
|
| 481 |
+
"step": 800
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 2.0685197155785393,
|
| 485 |
+
"eval_loss": 0.32635125517845154,
|
| 486 |
+
"eval_runtime": 13.8909,
|
| 487 |
+
"eval_samples_per_second": 13.966,
|
| 488 |
+
"eval_steps_per_second": 1.8,
|
| 489 |
+
"step": 800
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.1331609566903684,
|
| 493 |
+
"grad_norm": 0.624754786491394,
|
| 494 |
+
"learning_rate": 0.00015729463591604044,
|
| 495 |
+
"loss": 0.1677,
|
| 496 |
+
"step": 825
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 2.1331609566903684,
|
| 500 |
+
"eval_loss": 0.3346332609653473,
|
| 501 |
+
"eval_runtime": 13.8969,
|
| 502 |
+
"eval_samples_per_second": 13.96,
|
| 503 |
+
"eval_steps_per_second": 1.799,
|
| 504 |
+
"step": 825
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.197802197802198,
|
| 508 |
+
"grad_norm": 0.6018180847167969,
|
| 509 |
+
"learning_rate": 0.0001559989634620368,
|
| 510 |
+
"loss": 0.2027,
|
| 511 |
+
"step": 850
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 2.197802197802198,
|
| 515 |
+
"eval_loss": 0.32181909680366516,
|
| 516 |
+
"eval_runtime": 13.8871,
|
| 517 |
+
"eval_samples_per_second": 13.97,
|
| 518 |
+
"eval_steps_per_second": 1.8,
|
| 519 |
+
"step": 850
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.262443438914027,
|
| 523 |
+
"grad_norm": 0.9019644856452942,
|
| 524 |
+
"learning_rate": 0.00015470329100803317,
|
| 525 |
+
"loss": 0.1793,
|
| 526 |
+
"step": 875
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 2.262443438914027,
|
| 530 |
+
"eval_loss": 0.32273176312446594,
|
| 531 |
+
"eval_runtime": 13.8886,
|
| 532 |
+
"eval_samples_per_second": 13.968,
|
| 533 |
+
"eval_steps_per_second": 1.8,
|
| 534 |
+
"step": 875
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.3270846800258567,
|
| 538 |
+
"grad_norm": 0.7112553715705872,
|
| 539 |
+
"learning_rate": 0.00015340761855402955,
|
| 540 |
+
"loss": 0.1971,
|
| 541 |
+
"step": 900
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 2.3270846800258567,
|
| 545 |
+
"eval_loss": 0.328635036945343,
|
| 546 |
+
"eval_runtime": 13.8925,
|
| 547 |
+
"eval_samples_per_second": 13.964,
|
| 548 |
+
"eval_steps_per_second": 1.8,
|
| 549 |
+
"step": 900
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.391725921137686,
|
| 553 |
+
"grad_norm": 0.9075572490692139,
|
| 554 |
+
"learning_rate": 0.00015211194610002593,
|
| 555 |
+
"loss": 0.199,
|
| 556 |
+
"step": 925
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 2.391725921137686,
|
| 560 |
+
"eval_loss": 0.31903964281082153,
|
| 561 |
+
"eval_runtime": 13.8926,
|
| 562 |
+
"eval_samples_per_second": 13.964,
|
| 563 |
+
"eval_steps_per_second": 1.8,
|
| 564 |
+
"step": 925
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.4563671622495153,
|
| 568 |
+
"grad_norm": 0.3509347140789032,
|
| 569 |
+
"learning_rate": 0.00015081627364602228,
|
| 570 |
+
"loss": 0.2201,
|
| 571 |
+
"step": 950
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.4563671622495153,
|
| 575 |
+
"eval_loss": 0.31318098306655884,
|
| 576 |
+
"eval_runtime": 13.8863,
|
| 577 |
+
"eval_samples_per_second": 13.971,
|
| 578 |
+
"eval_steps_per_second": 1.8,
|
| 579 |
+
"step": 950
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 2.5210084033613445,
|
| 583 |
+
"grad_norm": 0.6588907837867737,
|
| 584 |
+
"learning_rate": 0.00014952060119201869,
|
| 585 |
+
"loss": 0.1717,
|
| 586 |
+
"step": 975
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 2.5210084033613445,
|
| 590 |
+
"eval_loss": 0.3208658695220947,
|
| 591 |
+
"eval_runtime": 13.8946,
|
| 592 |
+
"eval_samples_per_second": 13.962,
|
| 593 |
+
"eval_steps_per_second": 1.799,
|
| 594 |
+
"step": 975
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 2.585649644473174,
|
| 598 |
+
"grad_norm": 0.30743467807769775,
|
| 599 |
+
"learning_rate": 0.00014822492873801504,
|
| 600 |
+
"loss": 0.2173,
|
| 601 |
+
"step": 1000
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 2.585649644473174,
|
| 605 |
+
"eval_loss": 0.3078968822956085,
|
| 606 |
+
"eval_runtime": 13.881,
|
| 607 |
+
"eval_samples_per_second": 13.976,
|
| 608 |
+
"eval_steps_per_second": 1.801,
|
| 609 |
+
"step": 1000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 2.650290885585003,
|
| 613 |
+
"grad_norm": 0.9775978922843933,
|
| 614 |
+
"learning_rate": 0.00014692925628401142,
|
| 615 |
+
"loss": 0.1641,
|
| 616 |
+
"step": 1025
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 2.650290885585003,
|
| 620 |
+
"eval_loss": 0.3325625956058502,
|
| 621 |
+
"eval_runtime": 13.8923,
|
| 622 |
+
"eval_samples_per_second": 13.965,
|
| 623 |
+
"eval_steps_per_second": 1.8,
|
| 624 |
+
"step": 1025
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 2.7149321266968327,
|
| 628 |
+
"grad_norm": 0.410194456577301,
|
| 629 |
+
"learning_rate": 0.00014563358383000777,
|
| 630 |
+
"loss": 0.2048,
|
| 631 |
+
"step": 1050
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 2.7149321266968327,
|
| 635 |
+
"eval_loss": 0.3071564733982086,
|
| 636 |
+
"eval_runtime": 13.8821,
|
| 637 |
+
"eval_samples_per_second": 13.975,
|
| 638 |
+
"eval_steps_per_second": 1.801,
|
| 639 |
+
"step": 1050
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.779573367808662,
|
| 643 |
+
"grad_norm": 0.7554541826248169,
|
| 644 |
+
"learning_rate": 0.00014433791137600415,
|
| 645 |
+
"loss": 0.1721,
|
| 646 |
+
"step": 1075
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 2.779573367808662,
|
| 650 |
+
"eval_loss": 0.31251639127731323,
|
| 651 |
+
"eval_runtime": 13.8879,
|
| 652 |
+
"eval_samples_per_second": 13.969,
|
| 653 |
+
"eval_steps_per_second": 1.8,
|
| 654 |
+
"step": 1075
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.8442146089204914,
|
| 658 |
+
"grad_norm": 0.6487146019935608,
|
| 659 |
+
"learning_rate": 0.00014304223892200053,
|
| 660 |
+
"loss": 0.2094,
|
| 661 |
+
"step": 1100
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 2.8442146089204914,
|
| 665 |
+
"eval_loss": 0.30554458498954773,
|
| 666 |
+
"eval_runtime": 13.9003,
|
| 667 |
+
"eval_samples_per_second": 13.957,
|
| 668 |
+
"eval_steps_per_second": 1.799,
|
| 669 |
+
"step": 1100
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.9088558500323205,
|
| 673 |
+
"grad_norm": 1.1581164598464966,
|
| 674 |
+
"learning_rate": 0.00014174656646799688,
|
| 675 |
+
"loss": 0.1646,
|
| 676 |
+
"step": 1125
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.9088558500323205,
|
| 680 |
+
"eval_loss": 0.3173879086971283,
|
| 681 |
+
"eval_runtime": 13.8916,
|
| 682 |
+
"eval_samples_per_second": 13.965,
|
| 683 |
+
"eval_steps_per_second": 1.8,
|
| 684 |
+
"step": 1125
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 2.97349709114415,
|
| 688 |
+
"grad_norm": 0.627264142036438,
|
| 689 |
+
"learning_rate": 0.00014045089401399326,
|
| 690 |
+
"loss": 0.1842,
|
| 691 |
+
"step": 1150
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 2.97349709114415,
|
| 695 |
+
"eval_loss": 0.304733008146286,
|
| 696 |
+
"eval_runtime": 13.8953,
|
| 697 |
+
"eval_samples_per_second": 13.962,
|
| 698 |
+
"eval_steps_per_second": 1.799,
|
| 699 |
+
"step": 1150
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 3.038138332255979,
|
| 703 |
+
"grad_norm": 0.5179964900016785,
|
| 704 |
+
"learning_rate": 0.00013915522155998964,
|
| 705 |
+
"loss": 0.1582,
|
| 706 |
+
"step": 1175
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 3.038138332255979,
|
| 710 |
+
"eval_loss": 0.3209947943687439,
|
| 711 |
+
"eval_runtime": 13.8893,
|
| 712 |
+
"eval_samples_per_second": 13.968,
|
| 713 |
+
"eval_steps_per_second": 1.8,
|
| 714 |
+
"step": 1175
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 3.1027795733678087,
|
| 718 |
+
"grad_norm": 0.4774376153945923,
|
| 719 |
+
"learning_rate": 0.00013785954910598602,
|
| 720 |
+
"loss": 0.1306,
|
| 721 |
+
"step": 1200
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 3.1027795733678087,
|
| 725 |
+
"eval_loss": 0.3194412589073181,
|
| 726 |
+
"eval_runtime": 13.8863,
|
| 727 |
+
"eval_samples_per_second": 13.971,
|
| 728 |
+
"eval_steps_per_second": 1.8,
|
| 729 |
+
"step": 1200
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 3.167420814479638,
|
| 733 |
+
"grad_norm": 0.5093793869018555,
|
| 734 |
+
"learning_rate": 0.00013656387665198237,
|
| 735 |
+
"loss": 0.1294,
|
| 736 |
+
"step": 1225
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 3.167420814479638,
|
| 740 |
+
"eval_loss": 0.3293355107307434,
|
| 741 |
+
"eval_runtime": 13.8881,
|
| 742 |
+
"eval_samples_per_second": 13.969,
|
| 743 |
+
"eval_steps_per_second": 1.8,
|
| 744 |
+
"step": 1225
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 3.2320620555914674,
|
| 748 |
+
"grad_norm": 0.2597694993019104,
|
| 749 |
+
"learning_rate": 0.00013526820419797878,
|
| 750 |
+
"loss": 0.1283,
|
| 751 |
+
"step": 1250
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 3.2320620555914674,
|
| 755 |
+
"eval_loss": 0.3166593313217163,
|
| 756 |
+
"eval_runtime": 13.8971,
|
| 757 |
+
"eval_samples_per_second": 13.96,
|
| 758 |
+
"eval_steps_per_second": 1.799,
|
| 759 |
+
"step": 1250
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 3.2967032967032965,
|
| 763 |
+
"grad_norm": 0.23225939273834229,
|
| 764 |
+
"learning_rate": 0.00013397253174397513,
|
| 765 |
+
"loss": 0.1464,
|
| 766 |
+
"step": 1275
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 3.2967032967032965,
|
| 770 |
+
"eval_loss": 0.3203945457935333,
|
| 771 |
+
"eval_runtime": 13.89,
|
| 772 |
+
"eval_samples_per_second": 13.967,
|
| 773 |
+
"eval_steps_per_second": 1.8,
|
| 774 |
+
"step": 1275
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 3.361344537815126,
|
| 778 |
+
"grad_norm": 0.332242488861084,
|
| 779 |
+
"learning_rate": 0.0001326768592899715,
|
| 780 |
+
"loss": 0.1398,
|
| 781 |
+
"step": 1300
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 3.361344537815126,
|
| 785 |
+
"eval_loss": 0.31326356530189514,
|
| 786 |
+
"eval_runtime": 13.8775,
|
| 787 |
+
"eval_samples_per_second": 13.979,
|
| 788 |
+
"eval_steps_per_second": 1.801,
|
| 789 |
+
"step": 1300
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 3.425985778926955,
|
| 793 |
+
"grad_norm": 0.5355468988418579,
|
| 794 |
+
"learning_rate": 0.00013138118683596786,
|
| 795 |
+
"loss": 0.142,
|
| 796 |
+
"step": 1325
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 3.425985778926955,
|
| 800 |
+
"eval_loss": 0.3070937395095825,
|
| 801 |
+
"eval_runtime": 13.8888,
|
| 802 |
+
"eval_samples_per_second": 13.968,
|
| 803 |
+
"eval_steps_per_second": 1.8,
|
| 804 |
+
"step": 1325
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 3.490627020038785,
|
| 808 |
+
"grad_norm": 0.6375517249107361,
|
| 809 |
+
"learning_rate": 0.00013008551438196424,
|
| 810 |
+
"loss": 0.1396,
|
| 811 |
+
"step": 1350
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 3.490627020038785,
|
| 815 |
+
"eval_loss": 0.3138720393180847,
|
| 816 |
+
"eval_runtime": 13.8924,
|
| 817 |
+
"eval_samples_per_second": 13.964,
|
| 818 |
+
"eval_steps_per_second": 1.8,
|
| 819 |
+
"step": 1350
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 3.555268261150614,
|
| 823 |
+
"grad_norm": 0.3490104377269745,
|
| 824 |
+
"learning_rate": 0.00012878984192796062,
|
| 825 |
+
"loss": 0.1476,
|
| 826 |
+
"step": 1375
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 3.555268261150614,
|
| 830 |
+
"eval_loss": 0.30152711272239685,
|
| 831 |
+
"eval_runtime": 13.894,
|
| 832 |
+
"eval_samples_per_second": 13.963,
|
| 833 |
+
"eval_steps_per_second": 1.799,
|
| 834 |
+
"step": 1375
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 3.6199095022624435,
|
| 838 |
+
"grad_norm": 0.3556181490421295,
|
| 839 |
+
"learning_rate": 0.00012749416947395697,
|
| 840 |
+
"loss": 0.1396,
|
| 841 |
+
"step": 1400
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 3.6199095022624435,
|
| 845 |
+
"eval_loss": 0.31680139899253845,
|
| 846 |
+
"eval_runtime": 13.8887,
|
| 847 |
+
"eval_samples_per_second": 13.968,
|
| 848 |
+
"eval_steps_per_second": 1.8,
|
| 849 |
+
"step": 1400
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 3.684550743374273,
|
| 853 |
+
"grad_norm": 0.2230699509382248,
|
| 854 |
+
"learning_rate": 0.00012619849701995338,
|
| 855 |
+
"loss": 0.1363,
|
| 856 |
+
"step": 1425
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 3.684550743374273,
|
| 860 |
+
"eval_loss": 0.3081817328929901,
|
| 861 |
+
"eval_runtime": 13.8817,
|
| 862 |
+
"eval_samples_per_second": 13.975,
|
| 863 |
+
"eval_steps_per_second": 1.801,
|
| 864 |
+
"step": 1425
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 3.749191984486102,
|
| 868 |
+
"grad_norm": 0.3208047151565552,
|
| 869 |
+
"learning_rate": 0.00012490282456594973,
|
| 870 |
+
"loss": 0.144,
|
| 871 |
+
"step": 1450
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 3.749191984486102,
|
| 875 |
+
"eval_loss": 0.31721794605255127,
|
| 876 |
+
"eval_runtime": 13.8879,
|
| 877 |
+
"eval_samples_per_second": 13.969,
|
| 878 |
+
"eval_steps_per_second": 1.8,
|
| 879 |
+
"step": 1450
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 3.8138332255979313,
|
| 883 |
+
"grad_norm": 0.32816827297210693,
|
| 884 |
+
"learning_rate": 0.0001236071521119461,
|
| 885 |
+
"loss": 0.1645,
|
| 886 |
+
"step": 1475
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 3.8138332255979313,
|
| 890 |
+
"eval_loss": 0.29447051882743835,
|
| 891 |
+
"eval_runtime": 13.8874,
|
| 892 |
+
"eval_samples_per_second": 13.97,
|
| 893 |
+
"eval_steps_per_second": 1.8,
|
| 894 |
+
"step": 1475
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 3.878474466709761,
|
| 898 |
+
"grad_norm": 0.4234698712825775,
|
| 899 |
+
"learning_rate": 0.00012231147965794246,
|
| 900 |
+
"loss": 0.1345,
|
| 901 |
+
"step": 1500
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 3.878474466709761,
|
| 905 |
+
"eval_loss": 0.32389405369758606,
|
| 906 |
+
"eval_runtime": 13.8841,
|
| 907 |
+
"eval_samples_per_second": 13.973,
|
| 908 |
+
"eval_steps_per_second": 1.801,
|
| 909 |
+
"step": 1500
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 3.9431157078215904,
|
| 913 |
+
"grad_norm": 0.5032609105110168,
|
| 914 |
+
"learning_rate": 0.00012101580720393886,
|
| 915 |
+
"loss": 0.1436,
|
| 916 |
+
"step": 1525
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 3.9431157078215904,
|
| 920 |
+
"eval_loss": 0.3067689538002014,
|
| 921 |
+
"eval_runtime": 13.8918,
|
| 922 |
+
"eval_samples_per_second": 13.965,
|
| 923 |
+
"eval_steps_per_second": 1.8,
|
| 924 |
+
"step": 1525
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 4.0077569489334195,
|
| 928 |
+
"grad_norm": 0.4656796455383301,
|
| 929 |
+
"learning_rate": 0.00011972013474993522,
|
| 930 |
+
"loss": 0.1322,
|
| 931 |
+
"step": 1550
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 4.0077569489334195,
|
| 935 |
+
"eval_loss": 0.3148553967475891,
|
| 936 |
+
"eval_runtime": 13.8941,
|
| 937 |
+
"eval_samples_per_second": 13.963,
|
| 938 |
+
"eval_steps_per_second": 1.799,
|
| 939 |
+
"step": 1550
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 4.072398190045249,
|
| 943 |
+
"grad_norm": 0.312979519367218,
|
| 944 |
+
"learning_rate": 0.0001184244622959316,
|
| 945 |
+
"loss": 0.1147,
|
| 946 |
+
"step": 1575
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 4.072398190045249,
|
| 950 |
+
"eval_loss": 0.3317333161830902,
|
| 951 |
+
"eval_runtime": 13.8904,
|
| 952 |
+
"eval_samples_per_second": 13.966,
|
| 953 |
+
"eval_steps_per_second": 1.8,
|
| 954 |
+
"step": 1575
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 4.137039431157079,
|
| 958 |
+
"grad_norm": 0.7652421593666077,
|
| 959 |
+
"learning_rate": 0.00011712878984192797,
|
| 960 |
+
"loss": 0.1092,
|
| 961 |
+
"step": 1600
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 4.137039431157079,
|
| 965 |
+
"eval_loss": 0.32812875509262085,
|
| 966 |
+
"eval_runtime": 13.8839,
|
| 967 |
+
"eval_samples_per_second": 13.973,
|
| 968 |
+
"eval_steps_per_second": 1.801,
|
| 969 |
+
"step": 1600
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 4.201680672268908,
|
| 973 |
+
"grad_norm": 0.4065840244293213,
|
| 974 |
+
"learning_rate": 0.00011583311738792433,
|
| 975 |
+
"loss": 0.1088,
|
| 976 |
+
"step": 1625
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 4.201680672268908,
|
| 980 |
+
"eval_loss": 0.32381245493888855,
|
| 981 |
+
"eval_runtime": 13.8912,
|
| 982 |
+
"eval_samples_per_second": 13.966,
|
| 983 |
+
"eval_steps_per_second": 1.8,
|
| 984 |
+
"step": 1625
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 4.266321913380737,
|
| 988 |
+
"grad_norm": 0.7044116854667664,
|
| 989 |
+
"learning_rate": 0.00011453744493392071,
|
| 990 |
+
"loss": 0.1145,
|
| 991 |
+
"step": 1650
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 4.266321913380737,
|
| 995 |
+
"eval_loss": 0.33820751309394836,
|
| 996 |
+
"eval_runtime": 13.8893,
|
| 997 |
+
"eval_samples_per_second": 13.968,
|
| 998 |
+
"eval_steps_per_second": 1.8,
|
| 999 |
+
"step": 1650
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 4.330963154492566,
|
| 1003 |
+
"grad_norm": 0.4830712676048279,
|
| 1004 |
+
"learning_rate": 0.00011324177247991708,
|
| 1005 |
+
"loss": 0.1134,
|
| 1006 |
+
"step": 1675
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 4.330963154492566,
|
| 1010 |
+
"eval_loss": 0.32449984550476074,
|
| 1011 |
+
"eval_runtime": 13.8869,
|
| 1012 |
+
"eval_samples_per_second": 13.97,
|
| 1013 |
+
"eval_steps_per_second": 1.8,
|
| 1014 |
+
"step": 1675
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 4.395604395604396,
|
| 1018 |
+
"grad_norm": 0.5964047908782959,
|
| 1019 |
+
"learning_rate": 0.00011194610002591346,
|
| 1020 |
+
"loss": 0.1202,
|
| 1021 |
+
"step": 1700
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 4.395604395604396,
|
| 1025 |
+
"eval_loss": 0.34136590361595154,
|
| 1026 |
+
"eval_runtime": 13.8979,
|
| 1027 |
+
"eval_samples_per_second": 13.959,
|
| 1028 |
+
"eval_steps_per_second": 1.799,
|
| 1029 |
+
"step": 1700
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 4.460245636716225,
|
| 1033 |
+
"grad_norm": 0.3279203176498413,
|
| 1034 |
+
"learning_rate": 0.00011065042757190982,
|
| 1035 |
+
"loss": 0.1149,
|
| 1036 |
+
"step": 1725
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 4.460245636716225,
|
| 1040 |
+
"eval_loss": 0.3160356283187866,
|
| 1041 |
+
"eval_runtime": 13.8933,
|
| 1042 |
+
"eval_samples_per_second": 13.964,
|
| 1043 |
+
"eval_steps_per_second": 1.799,
|
| 1044 |
+
"step": 1725
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 4.524886877828054,
|
| 1048 |
+
"grad_norm": 0.7072445154190063,
|
| 1049 |
+
"learning_rate": 0.0001093547551179062,
|
| 1050 |
+
"loss": 0.1185,
|
| 1051 |
+
"step": 1750
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 4.524886877828054,
|
| 1055 |
+
"eval_loss": 0.339296817779541,
|
| 1056 |
+
"eval_runtime": 13.8937,
|
| 1057 |
+
"eval_samples_per_second": 13.963,
|
| 1058 |
+
"eval_steps_per_second": 1.799,
|
| 1059 |
+
"step": 1750
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 4.589528118939883,
|
| 1063 |
+
"grad_norm": 0.2717013359069824,
|
| 1064 |
+
"learning_rate": 0.00010805908266390257,
|
| 1065 |
+
"loss": 0.1192,
|
| 1066 |
+
"step": 1775
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 4.589528118939883,
|
| 1070 |
+
"eval_loss": 0.325735867023468,
|
| 1071 |
+
"eval_runtime": 13.8932,
|
| 1072 |
+
"eval_samples_per_second": 13.964,
|
| 1073 |
+
"eval_steps_per_second": 1.799,
|
| 1074 |
+
"step": 1775
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 4.654169360051713,
|
| 1078 |
+
"grad_norm": 0.6134977340698242,
|
| 1079 |
+
"learning_rate": 0.00010676341020989895,
|
| 1080 |
+
"loss": 0.1157,
|
| 1081 |
+
"step": 1800
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 4.654169360051713,
|
| 1085 |
+
"eval_loss": 0.33217981457710266,
|
| 1086 |
+
"eval_runtime": 13.888,
|
| 1087 |
+
"eval_samples_per_second": 13.969,
|
| 1088 |
+
"eval_steps_per_second": 1.8,
|
| 1089 |
+
"step": 1800
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 4.7188106011635425,
|
| 1093 |
+
"grad_norm": 0.37782660126686096,
|
| 1094 |
+
"learning_rate": 0.00010546773775589531,
|
| 1095 |
+
"loss": 0.1111,
|
| 1096 |
+
"step": 1825
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 4.7188106011635425,
|
| 1100 |
+
"eval_loss": 0.324066698551178,
|
| 1101 |
+
"eval_runtime": 13.9001,
|
| 1102 |
+
"eval_samples_per_second": 13.957,
|
| 1103 |
+
"eval_steps_per_second": 1.799,
|
| 1104 |
+
"step": 1825
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 4.783451842275372,
|
| 1108 |
+
"grad_norm": 0.5282606482505798,
|
| 1109 |
+
"learning_rate": 0.00010417206530189169,
|
| 1110 |
+
"loss": 0.1184,
|
| 1111 |
+
"step": 1850
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 4.783451842275372,
|
| 1115 |
+
"eval_loss": 0.3346935510635376,
|
| 1116 |
+
"eval_runtime": 13.8986,
|
| 1117 |
+
"eval_samples_per_second": 13.958,
|
| 1118 |
+
"eval_steps_per_second": 1.799,
|
| 1119 |
+
"step": 1850
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 4.848093083387201,
|
| 1123 |
+
"grad_norm": 0.29640528559684753,
|
| 1124 |
+
"learning_rate": 0.00010287639284788806,
|
| 1125 |
+
"loss": 0.1097,
|
| 1126 |
+
"step": 1875
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 4.848093083387201,
|
| 1130 |
+
"eval_loss": 0.33659717440605164,
|
| 1131 |
+
"eval_runtime": 13.8932,
|
| 1132 |
+
"eval_samples_per_second": 13.964,
|
| 1133 |
+
"eval_steps_per_second": 1.799,
|
| 1134 |
+
"step": 1875
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 4.912734324499031,
|
| 1138 |
+
"grad_norm": 0.6442544460296631,
|
| 1139 |
+
"learning_rate": 0.00010158072039388442,
|
| 1140 |
+
"loss": 0.123,
|
| 1141 |
+
"step": 1900
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 4.912734324499031,
|
| 1145 |
+
"eval_loss": 0.3181850016117096,
|
| 1146 |
+
"eval_runtime": 13.89,
|
| 1147 |
+
"eval_samples_per_second": 13.967,
|
| 1148 |
+
"eval_steps_per_second": 1.8,
|
| 1149 |
+
"step": 1900
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 4.97737556561086,
|
| 1153 |
+
"grad_norm": 0.3405434489250183,
|
| 1154 |
+
"learning_rate": 0.0001002850479398808,
|
| 1155 |
+
"loss": 0.1198,
|
| 1156 |
+
"step": 1925
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 4.97737556561086,
|
| 1160 |
+
"eval_loss": 0.3185713291168213,
|
| 1161 |
+
"eval_runtime": 13.9051,
|
| 1162 |
+
"eval_samples_per_second": 13.952,
|
| 1163 |
+
"eval_steps_per_second": 1.798,
|
| 1164 |
+
"step": 1925
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 5.042016806722689,
|
| 1168 |
+
"grad_norm": 0.2473362535238266,
|
| 1169 |
+
"learning_rate": 0.00009898937548587718,
|
| 1170 |
+
"loss": 0.1015,
|
| 1171 |
+
"step": 1950
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 5.042016806722689,
|
| 1175 |
+
"eval_loss": 0.33879318833351135,
|
| 1176 |
+
"eval_runtime": 13.882,
|
| 1177 |
+
"eval_samples_per_second": 13.975,
|
| 1178 |
+
"eval_steps_per_second": 1.801,
|
| 1179 |
+
"step": 1950
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 5.106658047834518,
|
| 1183 |
+
"grad_norm": 0.6215495467185974,
|
| 1184 |
+
"learning_rate": 0.00009769370303187355,
|
| 1185 |
+
"loss": 0.0995,
|
| 1186 |
+
"step": 1975
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 5.106658047834518,
|
| 1190 |
+
"eval_loss": 0.35385414958000183,
|
| 1191 |
+
"eval_runtime": 13.895,
|
| 1192 |
+
"eval_samples_per_second": 13.962,
|
| 1193 |
+
"eval_steps_per_second": 1.799,
|
| 1194 |
+
"step": 1975
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 5.171299288946348,
|
| 1198 |
+
"grad_norm": 0.2980802357196808,
|
| 1199 |
+
"learning_rate": 0.00009639803057786993,
|
| 1200 |
+
"loss": 0.1036,
|
| 1201 |
+
"step": 2000
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 5.171299288946348,
|
| 1205 |
+
"eval_loss": 0.35115987062454224,
|
| 1206 |
+
"eval_runtime": 13.8914,
|
| 1207 |
+
"eval_samples_per_second": 13.965,
|
| 1208 |
+
"eval_steps_per_second": 1.8,
|
| 1209 |
+
"step": 2000
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 5.235940530058177,
|
| 1213 |
+
"grad_norm": 0.32530656456947327,
|
| 1214 |
+
"learning_rate": 0.00009510235812386628,
|
| 1215 |
+
"loss": 0.1091,
|
| 1216 |
+
"step": 2025
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 5.235940530058177,
|
| 1220 |
+
"eval_loss": 0.33915072679519653,
|
| 1221 |
+
"eval_runtime": 13.8895,
|
| 1222 |
+
"eval_samples_per_second": 13.967,
|
| 1223 |
+
"eval_steps_per_second": 1.8,
|
| 1224 |
+
"step": 2025
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 5.300581771170006,
|
| 1228 |
+
"grad_norm": 0.28688952326774597,
|
| 1229 |
+
"learning_rate": 0.00009380668566986266,
|
| 1230 |
+
"loss": 0.1025,
|
| 1231 |
+
"step": 2050
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 5.300581771170006,
|
| 1235 |
+
"eval_loss": 0.33742988109588623,
|
| 1236 |
+
"eval_runtime": 13.8962,
|
| 1237 |
+
"eval_samples_per_second": 13.961,
|
| 1238 |
+
"eval_steps_per_second": 1.799,
|
| 1239 |
+
"step": 2050
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 5.365223012281835,
|
| 1243 |
+
"grad_norm": 0.7334425449371338,
|
| 1244 |
+
"learning_rate": 0.00009251101321585903,
|
| 1245 |
+
"loss": 0.1012,
|
| 1246 |
+
"step": 2075
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 5.365223012281835,
|
| 1250 |
+
"eval_loss": 0.3349464535713196,
|
| 1251 |
+
"eval_runtime": 13.897,
|
| 1252 |
+
"eval_samples_per_second": 13.96,
|
| 1253 |
+
"eval_steps_per_second": 1.799,
|
| 1254 |
+
"step": 2075
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 5.429864253393665,
|
| 1258 |
+
"grad_norm": 0.4262210726737976,
|
| 1259 |
+
"learning_rate": 0.0000912153407618554,
|
| 1260 |
+
"loss": 0.1001,
|
| 1261 |
+
"step": 2100
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 5.429864253393665,
|
| 1265 |
+
"eval_loss": 0.3597383499145508,
|
| 1266 |
+
"eval_runtime": 13.8902,
|
| 1267 |
+
"eval_samples_per_second": 13.967,
|
| 1268 |
+
"eval_steps_per_second": 1.8,
|
| 1269 |
+
"step": 2100
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 5.4945054945054945,
|
| 1273 |
+
"grad_norm": 0.32452741265296936,
|
| 1274 |
+
"learning_rate": 0.00008991966830785178,
|
| 1275 |
+
"loss": 0.1034,
|
| 1276 |
+
"step": 2125
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 5.4945054945054945,
|
| 1280 |
+
"eval_loss": 0.3415992259979248,
|
| 1281 |
+
"eval_runtime": 13.9049,
|
| 1282 |
+
"eval_samples_per_second": 13.952,
|
| 1283 |
+
"eval_steps_per_second": 1.798,
|
| 1284 |
+
"step": 2125
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 5.559146735617324,
|
| 1288 |
+
"grad_norm": 0.3775513768196106,
|
| 1289 |
+
"learning_rate": 0.00008862399585384815,
|
| 1290 |
+
"loss": 0.1016,
|
| 1291 |
+
"step": 2150
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 5.559146735617324,
|
| 1295 |
+
"eval_loss": 0.33714666962623596,
|
| 1296 |
+
"eval_runtime": 13.894,
|
| 1297 |
+
"eval_samples_per_second": 13.963,
|
| 1298 |
+
"eval_steps_per_second": 1.799,
|
| 1299 |
+
"step": 2150
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 5.623787976729153,
|
| 1303 |
+
"grad_norm": 0.2996246814727783,
|
| 1304 |
+
"learning_rate": 0.00008732832339984453,
|
| 1305 |
+
"loss": 0.1073,
|
| 1306 |
+
"step": 2175
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 5.623787976729153,
|
| 1310 |
+
"eval_loss": 0.33110281825065613,
|
| 1311 |
+
"eval_runtime": 13.9004,
|
| 1312 |
+
"eval_samples_per_second": 13.956,
|
| 1313 |
+
"eval_steps_per_second": 1.799,
|
| 1314 |
+
"step": 2175
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 5.688429217840983,
|
| 1318 |
+
"grad_norm": 0.2353794425725937,
|
| 1319 |
+
"learning_rate": 0.0000860326509458409,
|
| 1320 |
+
"loss": 0.1007,
|
| 1321 |
+
"step": 2200
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 5.688429217840983,
|
| 1325 |
+
"eval_loss": 0.33147233724594116,
|
| 1326 |
+
"eval_runtime": 13.8983,
|
| 1327 |
+
"eval_samples_per_second": 13.958,
|
| 1328 |
+
"eval_steps_per_second": 1.799,
|
| 1329 |
+
"step": 2200
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 5.753070458952812,
|
| 1333 |
+
"grad_norm": 0.284140408039093,
|
| 1334 |
+
"learning_rate": 0.00008473697849183728,
|
| 1335 |
+
"loss": 0.1054,
|
| 1336 |
+
"step": 2225
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 5.753070458952812,
|
| 1340 |
+
"eval_loss": 0.3283693194389343,
|
| 1341 |
+
"eval_runtime": 13.8987,
|
| 1342 |
+
"eval_samples_per_second": 13.958,
|
| 1343 |
+
"eval_steps_per_second": 1.799,
|
| 1344 |
+
"step": 2225
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 5.817711700064641,
|
| 1348 |
+
"grad_norm": 0.322956383228302,
|
| 1349 |
+
"learning_rate": 0.00008344130603783364,
|
| 1350 |
+
"loss": 0.1023,
|
| 1351 |
+
"step": 2250
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 5.817711700064641,
|
| 1355 |
+
"eval_loss": 0.3444914221763611,
|
| 1356 |
+
"eval_runtime": 13.9073,
|
| 1357 |
+
"eval_samples_per_second": 13.95,
|
| 1358 |
+
"eval_steps_per_second": 1.798,
|
| 1359 |
+
"step": 2250
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 5.882352941176471,
|
| 1363 |
+
"grad_norm": 0.34075090289115906,
|
| 1364 |
+
"learning_rate": 0.00008214563358383001,
|
| 1365 |
+
"loss": 0.1049,
|
| 1366 |
+
"step": 2275
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 5.882352941176471,
|
| 1370 |
+
"eval_loss": 0.34979012608528137,
|
| 1371 |
+
"eval_runtime": 13.8952,
|
| 1372 |
+
"eval_samples_per_second": 13.962,
|
| 1373 |
+
"eval_steps_per_second": 1.799,
|
| 1374 |
+
"step": 2275
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 5.9469941822883,
|
| 1378 |
+
"grad_norm": 0.27347272634506226,
|
| 1379 |
+
"learning_rate": 0.00008084996112982637,
|
| 1380 |
+
"loss": 0.0988,
|
| 1381 |
+
"step": 2300
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 5.9469941822883,
|
| 1385 |
+
"eval_loss": 0.3358798325061798,
|
| 1386 |
+
"eval_runtime": 13.892,
|
| 1387 |
+
"eval_samples_per_second": 13.965,
|
| 1388 |
+
"eval_steps_per_second": 1.8,
|
| 1389 |
+
"step": 2300
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 6.011635423400129,
|
| 1393 |
+
"grad_norm": 0.2915317714214325,
|
| 1394 |
+
"learning_rate": 0.00007955428867582275,
|
| 1395 |
+
"loss": 0.0991,
|
| 1396 |
+
"step": 2325
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 6.011635423400129,
|
| 1400 |
+
"eval_loss": 0.34607139229774475,
|
| 1401 |
+
"eval_runtime": 13.903,
|
| 1402 |
+
"eval_samples_per_second": 13.954,
|
| 1403 |
+
"eval_steps_per_second": 1.798,
|
| 1404 |
+
"step": 2325
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 6.076276664511958,
|
| 1408 |
+
"grad_norm": 0.2220218926668167,
|
| 1409 |
+
"learning_rate": 0.00007825861622181913,
|
| 1410 |
+
"loss": 0.0898,
|
| 1411 |
+
"step": 2350
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 6.076276664511958,
|
| 1415 |
+
"eval_loss": 0.3418421149253845,
|
| 1416 |
+
"eval_runtime": 13.9007,
|
| 1417 |
+
"eval_samples_per_second": 13.956,
|
| 1418 |
+
"eval_steps_per_second": 1.798,
|
| 1419 |
+
"step": 2350
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 6.140917905623788,
|
| 1423 |
+
"grad_norm": 0.27043217420578003,
|
| 1424 |
+
"learning_rate": 0.0000769629437678155,
|
| 1425 |
+
"loss": 0.0919,
|
| 1426 |
+
"step": 2375
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 6.140917905623788,
|
| 1430 |
+
"eval_loss": 0.35563594102859497,
|
| 1431 |
+
"eval_runtime": 13.8899,
|
| 1432 |
+
"eval_samples_per_second": 13.967,
|
| 1433 |
+
"eval_steps_per_second": 1.8,
|
| 1434 |
+
"step": 2375
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 6.2055591467356175,
|
| 1438 |
+
"grad_norm": 0.3899531960487366,
|
| 1439 |
+
"learning_rate": 0.00007566727131381188,
|
| 1440 |
+
"loss": 0.0872,
|
| 1441 |
+
"step": 2400
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 6.2055591467356175,
|
| 1445 |
+
"eval_loss": 0.35867059230804443,
|
| 1446 |
+
"eval_runtime": 13.8991,
|
| 1447 |
+
"eval_samples_per_second": 13.958,
|
| 1448 |
+
"eval_steps_per_second": 1.799,
|
| 1449 |
+
"step": 2400
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 6.270200387847447,
|
| 1453 |
+
"grad_norm": 0.48080724477767944,
|
| 1454 |
+
"learning_rate": 0.00007437159885980824,
|
| 1455 |
+
"loss": 0.0973,
|
| 1456 |
+
"step": 2425
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 6.270200387847447,
|
| 1460 |
+
"eval_loss": 0.35043036937713623,
|
| 1461 |
+
"eval_runtime": 13.8939,
|
| 1462 |
+
"eval_samples_per_second": 13.963,
|
| 1463 |
+
"eval_steps_per_second": 1.799,
|
| 1464 |
+
"step": 2425
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 6.334841628959276,
|
| 1468 |
+
"grad_norm": 0.42479485273361206,
|
| 1469 |
+
"learning_rate": 0.00007307592640580462,
|
| 1470 |
+
"loss": 0.0917,
|
| 1471 |
+
"step": 2450
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 6.334841628959276,
|
| 1475 |
+
"eval_loss": 0.35338568687438965,
|
| 1476 |
+
"eval_runtime": 13.8934,
|
| 1477 |
+
"eval_samples_per_second": 13.964,
|
| 1478 |
+
"eval_steps_per_second": 1.799,
|
| 1479 |
+
"step": 2450
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 6.399482870071106,
|
| 1483 |
+
"grad_norm": 0.4198790490627289,
|
| 1484 |
+
"learning_rate": 0.00007178025395180099,
|
| 1485 |
+
"loss": 0.0974,
|
| 1486 |
+
"step": 2475
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 6.399482870071106,
|
| 1490 |
+
"eval_loss": 0.3527772128582001,
|
| 1491 |
+
"eval_runtime": 13.8929,
|
| 1492 |
+
"eval_samples_per_second": 13.964,
|
| 1493 |
+
"eval_steps_per_second": 1.799,
|
| 1494 |
+
"step": 2475
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 6.464124111182935,
|
| 1498 |
+
"grad_norm": 0.3013072907924652,
|
| 1499 |
+
"learning_rate": 0.00007048458149779737,
|
| 1500 |
+
"loss": 0.0924,
|
| 1501 |
+
"step": 2500
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 6.464124111182935,
|
| 1505 |
+
"eval_loss": 0.3606307804584503,
|
| 1506 |
+
"eval_runtime": 13.8994,
|
| 1507 |
+
"eval_samples_per_second": 13.957,
|
| 1508 |
+
"eval_steps_per_second": 1.799,
|
| 1509 |
+
"step": 2500
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 6.528765352294764,
|
| 1513 |
+
"grad_norm": 1.44315505027771,
|
| 1514 |
+
"learning_rate": 0.00006918890904379373,
|
| 1515 |
+
"loss": 0.0958,
|
| 1516 |
+
"step": 2525
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 6.528765352294764,
|
| 1520 |
+
"eval_loss": 0.3492783308029175,
|
| 1521 |
+
"eval_runtime": 13.8992,
|
| 1522 |
+
"eval_samples_per_second": 13.958,
|
| 1523 |
+
"eval_steps_per_second": 1.799,
|
| 1524 |
+
"step": 2525
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 6.593406593406593,
|
| 1528 |
+
"grad_norm": 0.2337220013141632,
|
| 1529 |
+
"learning_rate": 0.0000678932365897901,
|
| 1530 |
+
"loss": 0.0935,
|
| 1531 |
+
"step": 2550
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 6.593406593406593,
|
| 1535 |
+
"eval_loss": 0.3465332090854645,
|
| 1536 |
+
"eval_runtime": 13.8855,
|
| 1537 |
+
"eval_samples_per_second": 13.971,
|
| 1538 |
+
"eval_steps_per_second": 1.8,
|
| 1539 |
+
"step": 2550
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 6.658047834518423,
|
| 1543 |
+
"grad_norm": 0.560575544834137,
|
| 1544 |
+
"learning_rate": 0.00006659756413578648,
|
| 1545 |
+
"loss": 0.0989,
|
| 1546 |
+
"step": 2575
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 6.658047834518423,
|
| 1550 |
+
"eval_loss": 0.3463946580886841,
|
| 1551 |
+
"eval_runtime": 13.9011,
|
| 1552 |
+
"eval_samples_per_second": 13.956,
|
| 1553 |
+
"eval_steps_per_second": 1.798,
|
| 1554 |
+
"step": 2575
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 6.722689075630252,
|
| 1558 |
+
"grad_norm": 0.23282793164253235,
|
| 1559 |
+
"learning_rate": 0.00006530189168178284,
|
| 1560 |
+
"loss": 0.0883,
|
| 1561 |
+
"step": 2600
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 6.722689075630252,
|
| 1565 |
+
"eval_loss": 0.3596608340740204,
|
| 1566 |
+
"eval_runtime": 13.8986,
|
| 1567 |
+
"eval_samples_per_second": 13.958,
|
| 1568 |
+
"eval_steps_per_second": 1.799,
|
| 1569 |
+
"step": 2600
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 6.787330316742081,
|
| 1573 |
+
"grad_norm": 0.29077738523483276,
|
| 1574 |
+
"learning_rate": 0.00006400621922777922,
|
| 1575 |
+
"loss": 0.0997,
|
| 1576 |
+
"step": 2625
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 6.787330316742081,
|
| 1580 |
+
"eval_loss": 0.3466287851333618,
|
| 1581 |
+
"eval_runtime": 13.8997,
|
| 1582 |
+
"eval_samples_per_second": 13.957,
|
| 1583 |
+
"eval_steps_per_second": 1.799,
|
| 1584 |
+
"step": 2625
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 6.85197155785391,
|
| 1588 |
+
"grad_norm": 0.28866180777549744,
|
| 1589 |
+
"learning_rate": 0.00006271054677377559,
|
| 1590 |
+
"loss": 0.0907,
|
| 1591 |
+
"step": 2650
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 6.85197155785391,
|
| 1595 |
+
"eval_loss": 0.3554084897041321,
|
| 1596 |
+
"eval_runtime": 13.8946,
|
| 1597 |
+
"eval_samples_per_second": 13.962,
|
| 1598 |
+
"eval_steps_per_second": 1.799,
|
| 1599 |
+
"step": 2650
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 6.91661279896574,
|
| 1603 |
+
"grad_norm": 0.2319469451904297,
|
| 1604 |
+
"learning_rate": 0.00006141487431977197,
|
| 1605 |
+
"loss": 0.099,
|
| 1606 |
+
"step": 2675
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 6.91661279896574,
|
| 1610 |
+
"eval_loss": 0.3529384732246399,
|
| 1611 |
+
"eval_runtime": 13.8906,
|
| 1612 |
+
"eval_samples_per_second": 13.966,
|
| 1613 |
+
"eval_steps_per_second": 1.8,
|
| 1614 |
+
"step": 2675
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 6.98125404007757,
|
| 1618 |
+
"grad_norm": 0.25588566064834595,
|
| 1619 |
+
"learning_rate": 0.000060119201865768335,
|
| 1620 |
+
"loss": 0.0957,
|
| 1621 |
+
"step": 2700
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 6.98125404007757,
|
| 1625 |
+
"eval_loss": 0.34903913736343384,
|
| 1626 |
+
"eval_runtime": 13.9001,
|
| 1627 |
+
"eval_samples_per_second": 13.957,
|
| 1628 |
+
"eval_steps_per_second": 1.799,
|
| 1629 |
+
"step": 2700
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 7.045895281189399,
|
| 1633 |
+
"grad_norm": 0.2661280930042267,
|
| 1634 |
+
"learning_rate": 0.00005882352941176471,
|
| 1635 |
+
"loss": 0.0857,
|
| 1636 |
+
"step": 2725
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 7.045895281189399,
|
| 1640 |
+
"eval_loss": 0.3659530580043793,
|
| 1641 |
+
"eval_runtime": 13.8975,
|
| 1642 |
+
"eval_samples_per_second": 13.959,
|
| 1643 |
+
"eval_steps_per_second": 1.799,
|
| 1644 |
+
"step": 2725
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 7.110536522301228,
|
| 1648 |
+
"grad_norm": 0.26808837056159973,
|
| 1649 |
+
"learning_rate": 0.00005752785695776109,
|
| 1650 |
+
"loss": 0.0914,
|
| 1651 |
+
"step": 2750
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 7.110536522301228,
|
| 1655 |
+
"eval_loss": 0.37946397066116333,
|
| 1656 |
+
"eval_runtime": 13.8953,
|
| 1657 |
+
"eval_samples_per_second": 13.962,
|
| 1658 |
+
"eval_steps_per_second": 1.799,
|
| 1659 |
+
"step": 2750
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 7.175177763413058,
|
| 1663 |
+
"grad_norm": 0.2569040358066559,
|
| 1664 |
+
"learning_rate": 0.00005623218450375746,
|
| 1665 |
+
"loss": 0.0822,
|
| 1666 |
+
"step": 2775
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 7.175177763413058,
|
| 1670 |
+
"eval_loss": 0.3785270154476166,
|
| 1671 |
+
"eval_runtime": 13.8941,
|
| 1672 |
+
"eval_samples_per_second": 13.963,
|
| 1673 |
+
"eval_steps_per_second": 1.799,
|
| 1674 |
+
"step": 2775
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 7.239819004524887,
|
| 1678 |
+
"grad_norm": 0.2069663107395172,
|
| 1679 |
+
"learning_rate": 0.00005493651204975383,
|
| 1680 |
+
"loss": 0.0933,
|
| 1681 |
+
"step": 2800
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 7.239819004524887,
|
| 1685 |
+
"eval_loss": 0.36601343750953674,
|
| 1686 |
+
"eval_runtime": 13.9025,
|
| 1687 |
+
"eval_samples_per_second": 13.954,
|
| 1688 |
+
"eval_steps_per_second": 1.798,
|
| 1689 |
+
"step": 2800
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 7.304460245636716,
|
| 1693 |
+
"grad_norm": 0.3386838138103485,
|
| 1694 |
+
"learning_rate": 0.00005364083959575019,
|
| 1695 |
+
"loss": 0.0848,
|
| 1696 |
+
"step": 2825
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 7.304460245636716,
|
| 1700 |
+
"eval_loss": 0.3629213273525238,
|
| 1701 |
+
"eval_runtime": 13.9024,
|
| 1702 |
+
"eval_samples_per_second": 13.954,
|
| 1703 |
+
"eval_steps_per_second": 1.798,
|
| 1704 |
+
"step": 2825
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 7.369101486748546,
|
| 1708 |
+
"grad_norm": 0.24702002108097076,
|
| 1709 |
+
"learning_rate": 0.000052345167141746564,
|
| 1710 |
+
"loss": 0.0941,
|
| 1711 |
+
"step": 2850
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 7.369101486748546,
|
| 1715 |
+
"eval_loss": 0.36621519923210144,
|
| 1716 |
+
"eval_runtime": 13.9011,
|
| 1717 |
+
"eval_samples_per_second": 13.956,
|
| 1718 |
+
"eval_steps_per_second": 1.798,
|
| 1719 |
+
"step": 2850
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 7.433742727860375,
|
| 1723 |
+
"grad_norm": 0.1761961281299591,
|
| 1724 |
+
"learning_rate": 0.000051049494687742936,
|
| 1725 |
+
"loss": 0.0847,
|
| 1726 |
+
"step": 2875
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 7.433742727860375,
|
| 1730 |
+
"eval_loss": 0.3717571496963501,
|
| 1731 |
+
"eval_runtime": 13.9013,
|
| 1732 |
+
"eval_samples_per_second": 13.955,
|
| 1733 |
+
"eval_steps_per_second": 1.798,
|
| 1734 |
+
"step": 2875
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 7.498383968972204,
|
| 1738 |
+
"grad_norm": 0.22073306143283844,
|
| 1739 |
+
"learning_rate": 0.00004975382223373931,
|
| 1740 |
+
"loss": 0.0899,
|
| 1741 |
+
"step": 2900
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"epoch": 7.498383968972204,
|
| 1745 |
+
"eval_loss": 0.3767780363559723,
|
| 1746 |
+
"eval_runtime": 13.8867,
|
| 1747 |
+
"eval_samples_per_second": 13.97,
|
| 1748 |
+
"eval_steps_per_second": 1.8,
|
| 1749 |
+
"step": 2900
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 7.563025210084033,
|
| 1753 |
+
"grad_norm": 0.23177385330200195,
|
| 1754 |
+
"learning_rate": 0.00004845814977973568,
|
| 1755 |
+
"loss": 0.0857,
|
| 1756 |
+
"step": 2925
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 7.563025210084033,
|
| 1760 |
+
"eval_loss": 0.3604573607444763,
|
| 1761 |
+
"eval_runtime": 13.9028,
|
| 1762 |
+
"eval_samples_per_second": 13.954,
|
| 1763 |
+
"eval_steps_per_second": 1.798,
|
| 1764 |
+
"step": 2925
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 7.6276664511958625,
|
| 1768 |
+
"grad_norm": 0.2143615335226059,
|
| 1769 |
+
"learning_rate": 0.000047162477325732054,
|
| 1770 |
+
"loss": 0.0931,
|
| 1771 |
+
"step": 2950
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 7.6276664511958625,
|
| 1775 |
+
"eval_loss": 0.36467450857162476,
|
| 1776 |
+
"eval_runtime": 13.8939,
|
| 1777 |
+
"eval_samples_per_second": 13.963,
|
| 1778 |
+
"eval_steps_per_second": 1.799,
|
| 1779 |
+
"step": 2950
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 7.6923076923076925,
|
| 1783 |
+
"grad_norm": 0.23051580786705017,
|
| 1784 |
+
"learning_rate": 0.000045866804871728434,
|
| 1785 |
+
"loss": 0.0843,
|
| 1786 |
+
"step": 2975
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 7.6923076923076925,
|
| 1790 |
+
"eval_loss": 0.37799063324928284,
|
| 1791 |
+
"eval_runtime": 13.8887,
|
| 1792 |
+
"eval_samples_per_second": 13.968,
|
| 1793 |
+
"eval_steps_per_second": 1.8,
|
| 1794 |
+
"step": 2975
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 7.756948933419522,
|
| 1798 |
+
"grad_norm": 0.2964944541454315,
|
| 1799 |
+
"learning_rate": 0.000044571132417724806,
|
| 1800 |
+
"loss": 0.0953,
|
| 1801 |
+
"step": 3000
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 7.756948933419522,
|
| 1805 |
+
"eval_loss": 0.37458544969558716,
|
| 1806 |
+
"eval_runtime": 13.8975,
|
| 1807 |
+
"eval_samples_per_second": 13.959,
|
| 1808 |
+
"eval_steps_per_second": 1.799,
|
| 1809 |
+
"step": 3000
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 7.821590174531351,
|
| 1813 |
+
"grad_norm": 0.1789853572845459,
|
| 1814 |
+
"learning_rate": 0.00004327545996372117,
|
| 1815 |
+
"loss": 0.0846,
|
| 1816 |
+
"step": 3025
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 7.821590174531351,
|
| 1820 |
+
"eval_loss": 0.36440709233283997,
|
| 1821 |
+
"eval_runtime": 13.8936,
|
| 1822 |
+
"eval_samples_per_second": 13.963,
|
| 1823 |
+
"eval_steps_per_second": 1.799,
|
| 1824 |
+
"step": 3025
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 7.886231415643181,
|
| 1828 |
+
"grad_norm": 0.2910414934158325,
|
| 1829 |
+
"learning_rate": 0.000041979787509717545,
|
| 1830 |
+
"loss": 0.0945,
|
| 1831 |
+
"step": 3050
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 7.886231415643181,
|
| 1835 |
+
"eval_loss": 0.363972932100296,
|
| 1836 |
+
"eval_runtime": 13.899,
|
| 1837 |
+
"eval_samples_per_second": 13.958,
|
| 1838 |
+
"eval_steps_per_second": 1.799,
|
| 1839 |
+
"step": 3050
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 7.95087265675501,
|
| 1843 |
+
"grad_norm": 0.16566026210784912,
|
| 1844 |
+
"learning_rate": 0.00004068411505571392,
|
| 1845 |
+
"loss": 0.0856,
|
| 1846 |
+
"step": 3075
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 7.95087265675501,
|
| 1850 |
+
"eval_loss": 0.369998961687088,
|
| 1851 |
+
"eval_runtime": 13.8899,
|
| 1852 |
+
"eval_samples_per_second": 13.967,
|
| 1853 |
+
"eval_steps_per_second": 1.8,
|
| 1854 |
+
"step": 3075
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 8.015513897866839,
|
| 1858 |
+
"grad_norm": 0.20665214955806732,
|
| 1859 |
+
"learning_rate": 0.00003938844260171029,
|
| 1860 |
+
"loss": 0.0858,
|
| 1861 |
+
"step": 3100
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 8.015513897866839,
|
| 1865 |
+
"eval_loss": 0.3743078410625458,
|
| 1866 |
+
"eval_runtime": 13.9039,
|
| 1867 |
+
"eval_samples_per_second": 13.953,
|
| 1868 |
+
"eval_steps_per_second": 1.798,
|
| 1869 |
+
"step": 3100
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 8.080155138978668,
|
| 1873 |
+
"grad_norm": 0.22216439247131348,
|
| 1874 |
+
"learning_rate": 0.00003809277014770666,
|
| 1875 |
+
"loss": 0.0804,
|
| 1876 |
+
"step": 3125
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 8.080155138978668,
|
| 1880 |
+
"eval_loss": 0.38528111577033997,
|
| 1881 |
+
"eval_runtime": 13.9066,
|
| 1882 |
+
"eval_samples_per_second": 13.95,
|
| 1883 |
+
"eval_steps_per_second": 1.798,
|
| 1884 |
+
"step": 3125
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 8.144796380090497,
|
| 1888 |
+
"grad_norm": 0.2925605773925781,
|
| 1889 |
+
"learning_rate": 0.00003679709769370303,
|
| 1890 |
+
"loss": 0.0855,
|
| 1891 |
+
"step": 3150
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 8.144796380090497,
|
| 1895 |
+
"eval_loss": 0.3879942297935486,
|
| 1896 |
+
"eval_runtime": 13.8926,
|
| 1897 |
+
"eval_samples_per_second": 13.964,
|
| 1898 |
+
"eval_steps_per_second": 1.8,
|
| 1899 |
+
"step": 3150
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 8.209437621202326,
|
| 1903 |
+
"grad_norm": 0.1863240748643875,
|
| 1904 |
+
"learning_rate": 0.0000355014252396994,
|
| 1905 |
+
"loss": 0.0797,
|
| 1906 |
+
"step": 3175
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 8.209437621202326,
|
| 1910 |
+
"eval_loss": 0.38318556547164917,
|
| 1911 |
+
"eval_runtime": 13.8966,
|
| 1912 |
+
"eval_samples_per_second": 13.96,
|
| 1913 |
+
"eval_steps_per_second": 1.799,
|
| 1914 |
+
"step": 3175
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 8.274078862314157,
|
| 1918 |
+
"grad_norm": 0.227659672498703,
|
| 1919 |
+
"learning_rate": 0.00003420575278569578,
|
| 1920 |
+
"loss": 0.0873,
|
| 1921 |
+
"step": 3200
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 8.274078862314157,
|
| 1925 |
+
"eval_loss": 0.3866645097732544,
|
| 1926 |
+
"eval_runtime": 13.8958,
|
| 1927 |
+
"eval_samples_per_second": 13.961,
|
| 1928 |
+
"eval_steps_per_second": 1.799,
|
| 1929 |
+
"step": 3200
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 8.338720103425986,
|
| 1933 |
+
"grad_norm": 0.24623195827007294,
|
| 1934 |
+
"learning_rate": 0.00003291008033169215,
|
| 1935 |
+
"loss": 0.0805,
|
| 1936 |
+
"step": 3225
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 8.338720103425986,
|
| 1940 |
+
"eval_loss": 0.388787180185318,
|
| 1941 |
+
"eval_runtime": 13.9,
|
| 1942 |
+
"eval_samples_per_second": 13.957,
|
| 1943 |
+
"eval_steps_per_second": 1.799,
|
| 1944 |
+
"step": 3225
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 8.403361344537815,
|
| 1948 |
+
"grad_norm": 0.17468619346618652,
|
| 1949 |
+
"learning_rate": 0.000031614407877688526,
|
| 1950 |
+
"loss": 0.0845,
|
| 1951 |
+
"step": 3250
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 8.403361344537815,
|
| 1955 |
+
"eval_loss": 0.39511677622795105,
|
| 1956 |
+
"eval_runtime": 13.8992,
|
| 1957 |
+
"eval_samples_per_second": 13.958,
|
| 1958 |
+
"eval_steps_per_second": 1.799,
|
| 1959 |
+
"step": 3250
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 8.468002585649645,
|
| 1963 |
+
"grad_norm": 0.2383006066083908,
|
| 1964 |
+
"learning_rate": 0.000030318735423684895,
|
| 1965 |
+
"loss": 0.0807,
|
| 1966 |
+
"step": 3275
|
| 1967 |
+
},
|
| 1968 |
+
{
|
| 1969 |
+
"epoch": 8.468002585649645,
|
| 1970 |
+
"eval_loss": 0.39297351241111755,
|
| 1971 |
+
"eval_runtime": 13.9101,
|
| 1972 |
+
"eval_samples_per_second": 13.947,
|
| 1973 |
+
"eval_steps_per_second": 1.797,
|
| 1974 |
+
"step": 3275
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 8.532643826761474,
|
| 1978 |
+
"grad_norm": 0.7691563367843628,
|
| 1979 |
+
"learning_rate": 0.000029023062969681264,
|
| 1980 |
+
"loss": 0.0868,
|
| 1981 |
+
"step": 3300
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 8.532643826761474,
|
| 1985 |
+
"eval_loss": 0.3870464265346527,
|
| 1986 |
+
"eval_runtime": 13.9059,
|
| 1987 |
+
"eval_samples_per_second": 13.951,
|
| 1988 |
+
"eval_steps_per_second": 1.798,
|
| 1989 |
+
"step": 3300
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 8.597285067873303,
|
| 1993 |
+
"grad_norm": 0.19113022089004517,
|
| 1994 |
+
"learning_rate": 0.000027727390515677637,
|
| 1995 |
+
"loss": 0.0816,
|
| 1996 |
+
"step": 3325
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 8.597285067873303,
|
| 2000 |
+
"eval_loss": 0.3797835409641266,
|
| 2001 |
+
"eval_runtime": 13.9074,
|
| 2002 |
+
"eval_samples_per_second": 13.949,
|
| 2003 |
+
"eval_steps_per_second": 1.798,
|
| 2004 |
+
"step": 3325
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 8.661926308985132,
|
| 2008 |
+
"grad_norm": 0.20881256461143494,
|
| 2009 |
+
"learning_rate": 0.00002643171806167401,
|
| 2010 |
+
"loss": 0.0868,
|
| 2011 |
+
"step": 3350
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 8.661926308985132,
|
| 2015 |
+
"eval_loss": 0.3818240165710449,
|
| 2016 |
+
"eval_runtime": 13.901,
|
| 2017 |
+
"eval_samples_per_second": 13.956,
|
| 2018 |
+
"eval_steps_per_second": 1.798,
|
| 2019 |
+
"step": 3350
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 8.726567550096961,
|
| 2023 |
+
"grad_norm": 0.19840125739574432,
|
| 2024 |
+
"learning_rate": 0.000025136045607670382,
|
| 2025 |
+
"loss": 0.0808,
|
| 2026 |
+
"step": 3375
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 8.726567550096961,
|
| 2030 |
+
"eval_loss": 0.38280540704727173,
|
| 2031 |
+
"eval_runtime": 13.8951,
|
| 2032 |
+
"eval_samples_per_second": 13.962,
|
| 2033 |
+
"eval_steps_per_second": 1.799,
|
| 2034 |
+
"step": 3375
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 8.791208791208792,
|
| 2038 |
+
"grad_norm": 0.2708618640899658,
|
| 2039 |
+
"learning_rate": 0.000023840373153666755,
|
| 2040 |
+
"loss": 0.0915,
|
| 2041 |
+
"step": 3400
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 8.791208791208792,
|
| 2045 |
+
"eval_loss": 0.3764805495738983,
|
| 2046 |
+
"eval_runtime": 13.8956,
|
| 2047 |
+
"eval_samples_per_second": 13.961,
|
| 2048 |
+
"eval_steps_per_second": 1.799,
|
| 2049 |
+
"step": 3400
|
| 2050 |
+
},
|
| 2051 |
+
{
|
| 2052 |
+
"epoch": 8.855850032320621,
|
| 2053 |
+
"grad_norm": 0.23502439260482788,
|
| 2054 |
+
"learning_rate": 0.000022544700699663127,
|
| 2055 |
+
"loss": 0.0827,
|
| 2056 |
+
"step": 3425
|
| 2057 |
+
},
|
| 2058 |
+
{
|
| 2059 |
+
"epoch": 8.855850032320621,
|
| 2060 |
+
"eval_loss": 0.378770649433136,
|
| 2061 |
+
"eval_runtime": 13.9002,
|
| 2062 |
+
"eval_samples_per_second": 13.957,
|
| 2063 |
+
"eval_steps_per_second": 1.799,
|
| 2064 |
+
"step": 3425
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 8.92049127343245,
|
| 2068 |
+
"grad_norm": 0.25332191586494446,
|
| 2069 |
+
"learning_rate": 0.0000212490282456595,
|
| 2070 |
+
"loss": 0.0874,
|
| 2071 |
+
"step": 3450
|
| 2072 |
+
},
|
| 2073 |
+
{
|
| 2074 |
+
"epoch": 8.92049127343245,
|
| 2075 |
+
"eval_loss": 0.3801264762878418,
|
| 2076 |
+
"eval_runtime": 13.907,
|
| 2077 |
+
"eval_samples_per_second": 13.95,
|
| 2078 |
+
"eval_steps_per_second": 1.798,
|
| 2079 |
+
"step": 3450
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 8.98513251454428,
|
| 2083 |
+
"grad_norm": 0.25316667556762695,
|
| 2084 |
+
"learning_rate": 0.00001995335579165587,
|
| 2085 |
+
"loss": 0.0891,
|
| 2086 |
+
"step": 3475
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 8.98513251454428,
|
| 2090 |
+
"eval_loss": 0.3802332878112793,
|
| 2091 |
+
"eval_runtime": 13.9011,
|
| 2092 |
+
"eval_samples_per_second": 13.956,
|
| 2093 |
+
"eval_steps_per_second": 1.798,
|
| 2094 |
+
"step": 3475
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 9.049773755656108,
|
| 2098 |
+
"grad_norm": 0.21907874941825867,
|
| 2099 |
+
"learning_rate": 0.000018657683337652242,
|
| 2100 |
+
"loss": 0.075,
|
| 2101 |
+
"step": 3500
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 9.049773755656108,
|
| 2105 |
+
"eval_loss": 0.3840136229991913,
|
| 2106 |
+
"eval_runtime": 13.8958,
|
| 2107 |
+
"eval_samples_per_second": 13.961,
|
| 2108 |
+
"eval_steps_per_second": 1.799,
|
| 2109 |
+
"step": 3500
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 9.114414996767938,
|
| 2113 |
+
"grad_norm": 0.24233920872211456,
|
| 2114 |
+
"learning_rate": 0.000017362010883648614,
|
| 2115 |
+
"loss": 0.0847,
|
| 2116 |
+
"step": 3525
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 9.114414996767938,
|
| 2120 |
+
"eval_loss": 0.39279288053512573,
|
| 2121 |
+
"eval_runtime": 13.8994,
|
| 2122 |
+
"eval_samples_per_second": 13.957,
|
| 2123 |
+
"eval_steps_per_second": 1.799,
|
| 2124 |
+
"step": 3525
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 9.179056237879767,
|
| 2128 |
+
"grad_norm": 0.2361481636762619,
|
| 2129 |
+
"learning_rate": 0.000016066338429644987,
|
| 2130 |
+
"loss": 0.0756,
|
| 2131 |
+
"step": 3550
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 9.179056237879767,
|
| 2135 |
+
"eval_loss": 0.3995870351791382,
|
| 2136 |
+
"eval_runtime": 13.8927,
|
| 2137 |
+
"eval_samples_per_second": 13.964,
|
| 2138 |
+
"eval_steps_per_second": 1.8,
|
| 2139 |
+
"step": 3550
|
| 2140 |
+
},
|
| 2141 |
+
{
|
| 2142 |
+
"epoch": 9.243697478991596,
|
| 2143 |
+
"grad_norm": 0.19486679136753082,
|
| 2144 |
+
"learning_rate": 0.00001477066597564136,
|
| 2145 |
+
"loss": 0.0852,
|
| 2146 |
+
"step": 3575
|
| 2147 |
+
},
|
| 2148 |
+
{
|
| 2149 |
+
"epoch": 9.243697478991596,
|
| 2150 |
+
"eval_loss": 0.40310657024383545,
|
| 2151 |
+
"eval_runtime": 13.8953,
|
| 2152 |
+
"eval_samples_per_second": 13.962,
|
| 2153 |
+
"eval_steps_per_second": 1.799,
|
| 2154 |
+
"step": 3575
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 9.308338720103427,
|
| 2158 |
+
"grad_norm": 0.23106832802295685,
|
| 2159 |
+
"learning_rate": 0.00001347499352163773,
|
| 2160 |
+
"loss": 0.0746,
|
| 2161 |
+
"step": 3600
|
| 2162 |
+
},
|
| 2163 |
+
{
|
| 2164 |
+
"epoch": 9.308338720103427,
|
| 2165 |
+
"eval_loss": 0.4031190872192383,
|
| 2166 |
+
"eval_runtime": 13.8976,
|
| 2167 |
+
"eval_samples_per_second": 13.959,
|
| 2168 |
+
"eval_steps_per_second": 1.799,
|
| 2169 |
+
"step": 3600
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 9.372979961215256,
|
| 2173 |
+
"grad_norm": 0.21963872015476227,
|
| 2174 |
+
"learning_rate": 0.000012179321067634103,
|
| 2175 |
+
"loss": 0.0844,
|
| 2176 |
+
"step": 3625
|
| 2177 |
+
},
|
| 2178 |
+
{
|
| 2179 |
+
"epoch": 9.372979961215256,
|
| 2180 |
+
"eval_loss": 0.4036274552345276,
|
| 2181 |
+
"eval_runtime": 13.9016,
|
| 2182 |
+
"eval_samples_per_second": 13.955,
|
| 2183 |
+
"eval_steps_per_second": 1.798,
|
| 2184 |
+
"step": 3625
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 9.437621202327085,
|
| 2188 |
+
"grad_norm": 0.19979609549045563,
|
| 2189 |
+
"learning_rate": 0.000010883648613630474,
|
| 2190 |
+
"loss": 0.0763,
|
| 2191 |
+
"step": 3650
|
| 2192 |
+
},
|
| 2193 |
+
{
|
| 2194 |
+
"epoch": 9.437621202327085,
|
| 2195 |
+
"eval_loss": 0.4039681851863861,
|
| 2196 |
+
"eval_runtime": 13.8986,
|
| 2197 |
+
"eval_samples_per_second": 13.958,
|
| 2198 |
+
"eval_steps_per_second": 1.799,
|
| 2199 |
+
"step": 3650
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 9.502262443438914,
|
| 2203 |
+
"grad_norm": 0.29937314987182617,
|
| 2204 |
+
"learning_rate": 0.000009587976159626847,
|
| 2205 |
+
"loss": 0.0856,
|
| 2206 |
+
"step": 3675
|
| 2207 |
+
},
|
| 2208 |
+
{
|
| 2209 |
+
"epoch": 9.502262443438914,
|
| 2210 |
+
"eval_loss": 0.40228113532066345,
|
| 2211 |
+
"eval_runtime": 13.9023,
|
| 2212 |
+
"eval_samples_per_second": 13.955,
|
| 2213 |
+
"eval_steps_per_second": 1.798,
|
| 2214 |
+
"step": 3675
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 9.566903684550743,
|
| 2218 |
+
"grad_norm": 0.19431306421756744,
|
| 2219 |
+
"learning_rate": 0.00000829230370562322,
|
| 2220 |
+
"loss": 0.0759,
|
| 2221 |
+
"step": 3700
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 9.566903684550743,
|
| 2225 |
+
"eval_loss": 0.39987537264823914,
|
| 2226 |
+
"eval_runtime": 13.9031,
|
| 2227 |
+
"eval_samples_per_second": 13.954,
|
| 2228 |
+
"eval_steps_per_second": 1.798,
|
| 2229 |
+
"step": 3700
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 9.631544925662572,
|
| 2233 |
+
"grad_norm": 0.23780672252178192,
|
| 2234 |
+
"learning_rate": 0.000006996631251619591,
|
| 2235 |
+
"loss": 0.0855,
|
| 2236 |
+
"step": 3725
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 9.631544925662572,
|
| 2240 |
+
"eval_loss": 0.39910781383514404,
|
| 2241 |
+
"eval_runtime": 13.8918,
|
| 2242 |
+
"eval_samples_per_second": 13.965,
|
| 2243 |
+
"eval_steps_per_second": 1.8,
|
| 2244 |
+
"step": 3725
|
| 2245 |
+
},
|
| 2246 |
+
{
|
| 2247 |
+
"epoch": 9.696186166774401,
|
| 2248 |
+
"grad_norm": 0.28458669781684875,
|
| 2249 |
+
"learning_rate": 0.000005700958797615963,
|
| 2250 |
+
"loss": 0.0749,
|
| 2251 |
+
"step": 3750
|
| 2252 |
+
},
|
| 2253 |
+
{
|
| 2254 |
+
"epoch": 9.696186166774401,
|
| 2255 |
+
"eval_loss": 0.3985865116119385,
|
| 2256 |
+
"eval_runtime": 13.9024,
|
| 2257 |
+
"eval_samples_per_second": 13.954,
|
| 2258 |
+
"eval_steps_per_second": 1.798,
|
| 2259 |
+
"step": 3750
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 9.760827407886232,
|
| 2263 |
+
"grad_norm": 0.2190496027469635,
|
| 2264 |
+
"learning_rate": 0.0000044052863436123355,
|
| 2265 |
+
"loss": 0.0887,
|
| 2266 |
+
"step": 3775
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 9.760827407886232,
|
| 2270 |
+
"eval_loss": 0.39947444200515747,
|
| 2271 |
+
"eval_runtime": 13.8956,
|
| 2272 |
+
"eval_samples_per_second": 13.961,
|
| 2273 |
+
"eval_steps_per_second": 1.799,
|
| 2274 |
+
"step": 3775
|
| 2275 |
+
},
|
| 2276 |
+
{
|
| 2277 |
+
"epoch": 9.825468648998061,
|
| 2278 |
+
"grad_norm": 0.2251676619052887,
|
| 2279 |
+
"learning_rate": 0.000003109613889608707,
|
| 2280 |
+
"loss": 0.0738,
|
| 2281 |
+
"step": 3800
|
| 2282 |
+
},
|
| 2283 |
+
{
|
| 2284 |
+
"epoch": 9.825468648998061,
|
| 2285 |
+
"eval_loss": 0.4002096951007843,
|
| 2286 |
+
"eval_runtime": 13.9037,
|
| 2287 |
+
"eval_samples_per_second": 13.953,
|
| 2288 |
+
"eval_steps_per_second": 1.798,
|
| 2289 |
+
"step": 3800
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 9.89010989010989,
|
| 2293 |
+
"grad_norm": 0.29096800088882446,
|
| 2294 |
+
"learning_rate": 0.000001813941435605079,
|
| 2295 |
+
"loss": 0.0867,
|
| 2296 |
+
"step": 3825
|
| 2297 |
+
},
|
| 2298 |
+
{
|
| 2299 |
+
"epoch": 9.89010989010989,
|
| 2300 |
+
"eval_loss": 0.40017297863960266,
|
| 2301 |
+
"eval_runtime": 13.9019,
|
| 2302 |
+
"eval_samples_per_second": 13.955,
|
| 2303 |
+
"eval_steps_per_second": 1.798,
|
| 2304 |
+
"step": 3825
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 9.95475113122172,
|
| 2308 |
+
"grad_norm": 0.2308928519487381,
|
| 2309 |
+
"learning_rate": 5.182689816014512e-7,
|
| 2310 |
+
"loss": 0.0796,
|
| 2311 |
+
"step": 3850
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"epoch": 9.95475113122172,
|
| 2315 |
+
"eval_loss": 0.4002385139465332,
|
| 2316 |
+
"eval_runtime": 13.8963,
|
| 2317 |
+
"eval_samples_per_second": 13.961,
|
| 2318 |
+
"eval_steps_per_second": 1.799,
|
| 2319 |
+
"step": 3850
|
| 2320 |
+
}
|
| 2321 |
+
],
|
| 2322 |
+
"logging_steps": 25,
|
| 2323 |
+
"max_steps": 3860,
|
| 2324 |
+
"num_input_tokens_seen": 0,
|
| 2325 |
+
"num_train_epochs": 10,
|
| 2326 |
+
"save_steps": 25,
|
| 2327 |
+
"total_flos": 13719373990686720,
|
| 2328 |
+
"train_batch_size": 1,
|
| 2329 |
+
"trial_name": null,
|
| 2330 |
+
"trial_params": null
|
| 2331 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d01b13bd8cd7d6717cf43c84ee5014902a4f51b8938a2277b920bb89e65ecf6
|
| 3 |
+
size 4920
|