Commit
•
fe3b357
1
Parent(s):
68a6a6b
Upload folder using huggingface_hub
Browse files- README.md +0 -19
- adapter_config.json +4 -4
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1279 -0
- training_args.bin +3 -0
README.md
CHANGED
|
@@ -216,23 +216,4 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 216 |
### Framework versions
|
| 217 |
|
| 218 |
|
| 219 |
-
- PEFT 0.7.0.dev0
|
| 220 |
-
## Training procedure
|
| 221 |
-
|
| 222 |
-
|
| 223 |
-
The following `bitsandbytes` quantization config was used during training:
|
| 224 |
-
- quant_method: bitsandbytes
|
| 225 |
-
- load_in_8bit: False
|
| 226 |
-
- load_in_4bit: True
|
| 227 |
-
- llm_int8_threshold: 6.0
|
| 228 |
-
- llm_int8_skip_modules: None
|
| 229 |
-
- llm_int8_enable_fp32_cpu_offload: False
|
| 230 |
-
- llm_int8_has_fp16_weight: False
|
| 231 |
-
- bnb_4bit_quant_type: nf4
|
| 232 |
-
- bnb_4bit_use_double_quant: True
|
| 233 |
-
- bnb_4bit_compute_dtype: bfloat16
|
| 234 |
-
|
| 235 |
-
### Framework versions
|
| 236 |
-
|
| 237 |
-
|
| 238 |
- PEFT 0.7.0.dev0
|
|
|
|
| 216 |
### Framework versions
|
| 217 |
|
| 218 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 219 |
- PEFT 0.7.0.dev0
|
adapter_config.json
CHANGED
|
@@ -16,14 +16,14 @@
|
|
| 16 |
"rank_pattern": {},
|
| 17 |
"revision": null,
|
| 18 |
"target_modules": [
|
| 19 |
-
"gate_proj",
|
| 20 |
-
"down_proj",
|
| 21 |
"k_proj",
|
| 22 |
"o_proj",
|
| 23 |
-
"lm_head",
|
| 24 |
"q_proj",
|
|
|
|
|
|
|
| 25 |
"up_proj",
|
| 26 |
-
"
|
|
|
|
| 27 |
],
|
| 28 |
"task_type": "CAUSAL_LM"
|
| 29 |
}
|
|
|
|
| 16 |
"rank_pattern": {},
|
| 17 |
"revision": null,
|
| 18 |
"target_modules": [
|
|
|
|
|
|
|
| 19 |
"k_proj",
|
| 20 |
"o_proj",
|
|
|
|
| 21 |
"q_proj",
|
| 22 |
+
"v_proj",
|
| 23 |
+
"down_proj",
|
| 24 |
"up_proj",
|
| 25 |
+
"lm_head",
|
| 26 |
+
"gate_proj"
|
| 27 |
],
|
| 28 |
"task_type": "CAUSAL_LM"
|
| 29 |
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bffdc183a59dfb36195ce253d74c9924bdae11972dfac4922b0ef86469709c5
|
| 3 |
+
size 86901726
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:773d63cabd080b38561b6648396f327441253b0af63553ac0d565e64291776ec
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d249bbc310c2a8e902a0ac4b30e99765cde378df014e6bc46677cef7d2e80d88
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1279 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.988950276243094,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 9000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"learning_rate": 2.4737423991155337e-05,
|
| 14 |
+
"loss": 1.4587,
|
| 15 |
+
"step": 100
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"eval_loss": 1.3197085857391357,
|
| 20 |
+
"eval_runtime": 65.3939,
|
| 21 |
+
"eval_samples_per_second": 13.992,
|
| 22 |
+
"eval_steps_per_second": 0.352,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.04,
|
| 27 |
+
"learning_rate": 2.4461028192371477e-05,
|
| 28 |
+
"loss": 1.2795,
|
| 29 |
+
"step": 200
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.04,
|
| 33 |
+
"eval_loss": 1.2743616104125977,
|
| 34 |
+
"eval_runtime": 65.3955,
|
| 35 |
+
"eval_samples_per_second": 13.992,
|
| 36 |
+
"eval_steps_per_second": 0.352,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.07,
|
| 41 |
+
"learning_rate": 2.418463239358762e-05,
|
| 42 |
+
"loss": 1.2566,
|
| 43 |
+
"step": 300
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.07,
|
| 47 |
+
"eval_loss": 1.256579875946045,
|
| 48 |
+
"eval_runtime": 65.3852,
|
| 49 |
+
"eval_samples_per_second": 13.994,
|
| 50 |
+
"eval_steps_per_second": 0.352,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.09,
|
| 55 |
+
"learning_rate": 2.390823659480376e-05,
|
| 56 |
+
"loss": 1.2463,
|
| 57 |
+
"step": 400
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.09,
|
| 61 |
+
"eval_loss": 1.2438602447509766,
|
| 62 |
+
"eval_runtime": 65.3739,
|
| 63 |
+
"eval_samples_per_second": 13.996,
|
| 64 |
+
"eval_steps_per_second": 0.352,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.11,
|
| 69 |
+
"learning_rate": 2.3631840796019903e-05,
|
| 70 |
+
"loss": 1.2276,
|
| 71 |
+
"step": 500
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.11,
|
| 75 |
+
"eval_loss": 1.2349315881729126,
|
| 76 |
+
"eval_runtime": 65.3806,
|
| 77 |
+
"eval_samples_per_second": 13.995,
|
| 78 |
+
"eval_steps_per_second": 0.352,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.13,
|
| 83 |
+
"learning_rate": 2.3355444997236043e-05,
|
| 84 |
+
"loss": 1.2233,
|
| 85 |
+
"step": 600
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.13,
|
| 89 |
+
"eval_loss": 1.2274835109710693,
|
| 90 |
+
"eval_runtime": 65.3699,
|
| 91 |
+
"eval_samples_per_second": 13.997,
|
| 92 |
+
"eval_steps_per_second": 0.352,
|
| 93 |
+
"step": 600
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.15,
|
| 97 |
+
"learning_rate": 2.3079049198452184e-05,
|
| 98 |
+
"loss": 1.2182,
|
| 99 |
+
"step": 700
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.15,
|
| 103 |
+
"eval_loss": 1.2212377786636353,
|
| 104 |
+
"eval_runtime": 65.3863,
|
| 105 |
+
"eval_samples_per_second": 13.994,
|
| 106 |
+
"eval_steps_per_second": 0.352,
|
| 107 |
+
"step": 700
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.18,
|
| 111 |
+
"learning_rate": 2.2802653399668325e-05,
|
| 112 |
+
"loss": 1.2184,
|
| 113 |
+
"step": 800
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.18,
|
| 117 |
+
"eval_loss": 1.2167881727218628,
|
| 118 |
+
"eval_runtime": 65.4277,
|
| 119 |
+
"eval_samples_per_second": 13.985,
|
| 120 |
+
"eval_steps_per_second": 0.352,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2,
|
| 125 |
+
"learning_rate": 2.252625760088447e-05,
|
| 126 |
+
"loss": 1.2163,
|
| 127 |
+
"step": 900
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.2,
|
| 131 |
+
"eval_loss": 1.2119972705841064,
|
| 132 |
+
"eval_runtime": 65.3982,
|
| 133 |
+
"eval_samples_per_second": 13.991,
|
| 134 |
+
"eval_steps_per_second": 0.352,
|
| 135 |
+
"step": 900
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.22,
|
| 139 |
+
"learning_rate": 2.224986180210061e-05,
|
| 140 |
+
"loss": 1.1956,
|
| 141 |
+
"step": 1000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.22,
|
| 145 |
+
"eval_loss": 1.2085155248641968,
|
| 146 |
+
"eval_runtime": 65.4054,
|
| 147 |
+
"eval_samples_per_second": 13.99,
|
| 148 |
+
"eval_steps_per_second": 0.352,
|
| 149 |
+
"step": 1000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.24,
|
| 153 |
+
"learning_rate": 2.197346600331675e-05,
|
| 154 |
+
"loss": 1.2108,
|
| 155 |
+
"step": 1100
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.24,
|
| 159 |
+
"eval_loss": 1.2050749063491821,
|
| 160 |
+
"eval_runtime": 65.3891,
|
| 161 |
+
"eval_samples_per_second": 13.993,
|
| 162 |
+
"eval_steps_per_second": 0.352,
|
| 163 |
+
"step": 1100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.27,
|
| 167 |
+
"learning_rate": 2.1697070204532894e-05,
|
| 168 |
+
"loss": 1.1973,
|
| 169 |
+
"step": 1200
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.27,
|
| 173 |
+
"eval_loss": 1.2018028497695923,
|
| 174 |
+
"eval_runtime": 65.3989,
|
| 175 |
+
"eval_samples_per_second": 13.991,
|
| 176 |
+
"eval_steps_per_second": 0.352,
|
| 177 |
+
"step": 1200
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.29,
|
| 181 |
+
"learning_rate": 2.1420674405749035e-05,
|
| 182 |
+
"loss": 1.2038,
|
| 183 |
+
"step": 1300
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.29,
|
| 187 |
+
"eval_loss": 1.198926329612732,
|
| 188 |
+
"eval_runtime": 65.3902,
|
| 189 |
+
"eval_samples_per_second": 13.993,
|
| 190 |
+
"eval_steps_per_second": 0.352,
|
| 191 |
+
"step": 1300
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.31,
|
| 195 |
+
"learning_rate": 2.1144278606965175e-05,
|
| 196 |
+
"loss": 1.1999,
|
| 197 |
+
"step": 1400
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.31,
|
| 201 |
+
"eval_loss": 1.1960697174072266,
|
| 202 |
+
"eval_runtime": 65.3767,
|
| 203 |
+
"eval_samples_per_second": 13.996,
|
| 204 |
+
"eval_steps_per_second": 0.352,
|
| 205 |
+
"step": 1400
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.33,
|
| 209 |
+
"learning_rate": 2.0867882808181316e-05,
|
| 210 |
+
"loss": 1.1862,
|
| 211 |
+
"step": 1500
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.33,
|
| 215 |
+
"eval_loss": 1.1933324337005615,
|
| 216 |
+
"eval_runtime": 65.3845,
|
| 217 |
+
"eval_samples_per_second": 13.994,
|
| 218 |
+
"eval_steps_per_second": 0.352,
|
| 219 |
+
"step": 1500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.35,
|
| 223 |
+
"learning_rate": 2.059148700939746e-05,
|
| 224 |
+
"loss": 1.1896,
|
| 225 |
+
"step": 1600
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.35,
|
| 229 |
+
"eval_loss": 1.1911386251449585,
|
| 230 |
+
"eval_runtime": 65.3997,
|
| 231 |
+
"eval_samples_per_second": 13.991,
|
| 232 |
+
"eval_steps_per_second": 0.352,
|
| 233 |
+
"step": 1600
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.38,
|
| 237 |
+
"learning_rate": 2.0315091210613597e-05,
|
| 238 |
+
"loss": 1.1895,
|
| 239 |
+
"step": 1700
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.38,
|
| 243 |
+
"eval_loss": 1.188926100730896,
|
| 244 |
+
"eval_runtime": 65.3962,
|
| 245 |
+
"eval_samples_per_second": 13.992,
|
| 246 |
+
"eval_steps_per_second": 0.352,
|
| 247 |
+
"step": 1700
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.4,
|
| 251 |
+
"learning_rate": 2.003869541182974e-05,
|
| 252 |
+
"loss": 1.1881,
|
| 253 |
+
"step": 1800
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.4,
|
| 257 |
+
"eval_loss": 1.186944842338562,
|
| 258 |
+
"eval_runtime": 65.374,
|
| 259 |
+
"eval_samples_per_second": 13.996,
|
| 260 |
+
"eval_steps_per_second": 0.352,
|
| 261 |
+
"step": 1800
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.42,
|
| 265 |
+
"learning_rate": 1.9762299613045882e-05,
|
| 266 |
+
"loss": 1.1874,
|
| 267 |
+
"step": 1900
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.42,
|
| 271 |
+
"eval_loss": 1.1846946477890015,
|
| 272 |
+
"eval_runtime": 65.3986,
|
| 273 |
+
"eval_samples_per_second": 13.991,
|
| 274 |
+
"eval_steps_per_second": 0.352,
|
| 275 |
+
"step": 1900
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.44,
|
| 279 |
+
"learning_rate": 1.9485903814262023e-05,
|
| 280 |
+
"loss": 1.1905,
|
| 281 |
+
"step": 2000
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.44,
|
| 285 |
+
"eval_loss": 1.1831568479537964,
|
| 286 |
+
"eval_runtime": 65.3641,
|
| 287 |
+
"eval_samples_per_second": 13.999,
|
| 288 |
+
"eval_steps_per_second": 0.352,
|
| 289 |
+
"step": 2000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.46,
|
| 293 |
+
"learning_rate": 1.9209508015478167e-05,
|
| 294 |
+
"loss": 1.1872,
|
| 295 |
+
"step": 2100
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.46,
|
| 299 |
+
"eval_loss": 1.1817291975021362,
|
| 300 |
+
"eval_runtime": 65.4068,
|
| 301 |
+
"eval_samples_per_second": 13.989,
|
| 302 |
+
"eval_steps_per_second": 0.352,
|
| 303 |
+
"step": 2100
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.49,
|
| 307 |
+
"learning_rate": 1.8933112216694307e-05,
|
| 308 |
+
"loss": 1.1773,
|
| 309 |
+
"step": 2200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.49,
|
| 313 |
+
"eval_loss": 1.17881178855896,
|
| 314 |
+
"eval_runtime": 65.3689,
|
| 315 |
+
"eval_samples_per_second": 13.997,
|
| 316 |
+
"eval_steps_per_second": 0.352,
|
| 317 |
+
"step": 2200
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.51,
|
| 321 |
+
"learning_rate": 1.865671641791045e-05,
|
| 322 |
+
"loss": 1.1754,
|
| 323 |
+
"step": 2300
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.51,
|
| 327 |
+
"eval_loss": 1.177442193031311,
|
| 328 |
+
"eval_runtime": 65.3786,
|
| 329 |
+
"eval_samples_per_second": 13.995,
|
| 330 |
+
"eval_steps_per_second": 0.352,
|
| 331 |
+
"step": 2300
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.53,
|
| 335 |
+
"learning_rate": 1.838032061912659e-05,
|
| 336 |
+
"loss": 1.1784,
|
| 337 |
+
"step": 2400
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.53,
|
| 341 |
+
"eval_loss": 1.1754305362701416,
|
| 342 |
+
"eval_runtime": 65.4015,
|
| 343 |
+
"eval_samples_per_second": 13.991,
|
| 344 |
+
"eval_steps_per_second": 0.352,
|
| 345 |
+
"step": 2400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.55,
|
| 349 |
+
"learning_rate": 1.8103924820342733e-05,
|
| 350 |
+
"loss": 1.1763,
|
| 351 |
+
"step": 2500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.55,
|
| 355 |
+
"eval_loss": 1.1741561889648438,
|
| 356 |
+
"eval_runtime": 65.3967,
|
| 357 |
+
"eval_samples_per_second": 13.992,
|
| 358 |
+
"eval_steps_per_second": 0.352,
|
| 359 |
+
"step": 2500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.57,
|
| 363 |
+
"learning_rate": 1.7827529021558873e-05,
|
| 364 |
+
"loss": 1.1705,
|
| 365 |
+
"step": 2600
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.57,
|
| 369 |
+
"eval_loss": 1.172415852546692,
|
| 370 |
+
"eval_runtime": 65.3819,
|
| 371 |
+
"eval_samples_per_second": 13.995,
|
| 372 |
+
"eval_steps_per_second": 0.352,
|
| 373 |
+
"step": 2600
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.6,
|
| 377 |
+
"learning_rate": 1.7551133222775014e-05,
|
| 378 |
+
"loss": 1.1726,
|
| 379 |
+
"step": 2700
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 0.6,
|
| 383 |
+
"eval_loss": 1.170956015586853,
|
| 384 |
+
"eval_runtime": 65.4953,
|
| 385 |
+
"eval_samples_per_second": 13.97,
|
| 386 |
+
"eval_steps_per_second": 0.351,
|
| 387 |
+
"step": 2700
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.62,
|
| 391 |
+
"learning_rate": 1.7274737423991155e-05,
|
| 392 |
+
"loss": 1.1542,
|
| 393 |
+
"step": 2800
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.62,
|
| 397 |
+
"eval_loss": 1.169766902923584,
|
| 398 |
+
"eval_runtime": 65.4615,
|
| 399 |
+
"eval_samples_per_second": 13.978,
|
| 400 |
+
"eval_steps_per_second": 0.351,
|
| 401 |
+
"step": 2800
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.64,
|
| 405 |
+
"learning_rate": 1.69983416252073e-05,
|
| 406 |
+
"loss": 1.1733,
|
| 407 |
+
"step": 2900
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.64,
|
| 411 |
+
"eval_loss": 1.168212652206421,
|
| 412 |
+
"eval_runtime": 65.4725,
|
| 413 |
+
"eval_samples_per_second": 13.975,
|
| 414 |
+
"eval_steps_per_second": 0.351,
|
| 415 |
+
"step": 2900
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.66,
|
| 419 |
+
"learning_rate": 1.672194582642344e-05,
|
| 420 |
+
"loss": 1.1596,
|
| 421 |
+
"step": 3000
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.66,
|
| 425 |
+
"eval_loss": 1.1670770645141602,
|
| 426 |
+
"eval_runtime": 65.4866,
|
| 427 |
+
"eval_samples_per_second": 13.972,
|
| 428 |
+
"eval_steps_per_second": 0.351,
|
| 429 |
+
"step": 3000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.69,
|
| 433 |
+
"learning_rate": 1.644555002763958e-05,
|
| 434 |
+
"loss": 1.1604,
|
| 435 |
+
"step": 3100
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.69,
|
| 439 |
+
"eval_loss": 1.166330337524414,
|
| 440 |
+
"eval_runtime": 65.4697,
|
| 441 |
+
"eval_samples_per_second": 13.976,
|
| 442 |
+
"eval_steps_per_second": 0.351,
|
| 443 |
+
"step": 3100
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.71,
|
| 447 |
+
"learning_rate": 1.6169154228855724e-05,
|
| 448 |
+
"loss": 1.1554,
|
| 449 |
+
"step": 3200
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.71,
|
| 453 |
+
"eval_loss": 1.1642917394638062,
|
| 454 |
+
"eval_runtime": 65.458,
|
| 455 |
+
"eval_samples_per_second": 13.978,
|
| 456 |
+
"eval_steps_per_second": 0.351,
|
| 457 |
+
"step": 3200
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.73,
|
| 461 |
+
"learning_rate": 1.5892758430071865e-05,
|
| 462 |
+
"loss": 1.1534,
|
| 463 |
+
"step": 3300
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.73,
|
| 467 |
+
"eval_loss": 1.1629236936569214,
|
| 468 |
+
"eval_runtime": 65.4858,
|
| 469 |
+
"eval_samples_per_second": 13.972,
|
| 470 |
+
"eval_steps_per_second": 0.351,
|
| 471 |
+
"step": 3300
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.75,
|
| 475 |
+
"learning_rate": 1.5616362631288005e-05,
|
| 476 |
+
"loss": 1.1627,
|
| 477 |
+
"step": 3400
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.75,
|
| 481 |
+
"eval_loss": 1.1618852615356445,
|
| 482 |
+
"eval_runtime": 65.4438,
|
| 483 |
+
"eval_samples_per_second": 13.981,
|
| 484 |
+
"eval_steps_per_second": 0.351,
|
| 485 |
+
"step": 3400
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.77,
|
| 489 |
+
"learning_rate": 1.5339966832504146e-05,
|
| 490 |
+
"loss": 1.1575,
|
| 491 |
+
"step": 3500
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.77,
|
| 495 |
+
"eval_loss": 1.1608364582061768,
|
| 496 |
+
"eval_runtime": 65.4065,
|
| 497 |
+
"eval_samples_per_second": 13.989,
|
| 498 |
+
"eval_steps_per_second": 0.352,
|
| 499 |
+
"step": 3500
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.8,
|
| 503 |
+
"learning_rate": 1.5063571033720288e-05,
|
| 504 |
+
"loss": 1.1648,
|
| 505 |
+
"step": 3600
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.8,
|
| 509 |
+
"eval_loss": 1.159523844718933,
|
| 510 |
+
"eval_runtime": 65.4364,
|
| 511 |
+
"eval_samples_per_second": 13.983,
|
| 512 |
+
"eval_steps_per_second": 0.351,
|
| 513 |
+
"step": 3600
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.82,
|
| 517 |
+
"learning_rate": 1.4787175234936429e-05,
|
| 518 |
+
"loss": 1.1577,
|
| 519 |
+
"step": 3700
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.82,
|
| 523 |
+
"eval_loss": 1.1583499908447266,
|
| 524 |
+
"eval_runtime": 65.4227,
|
| 525 |
+
"eval_samples_per_second": 13.986,
|
| 526 |
+
"eval_steps_per_second": 0.352,
|
| 527 |
+
"step": 3700
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.84,
|
| 531 |
+
"learning_rate": 1.4510779436152571e-05,
|
| 532 |
+
"loss": 1.16,
|
| 533 |
+
"step": 3800
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.84,
|
| 537 |
+
"eval_loss": 1.1572628021240234,
|
| 538 |
+
"eval_runtime": 65.429,
|
| 539 |
+
"eval_samples_per_second": 13.985,
|
| 540 |
+
"eval_steps_per_second": 0.352,
|
| 541 |
+
"step": 3800
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.86,
|
| 545 |
+
"learning_rate": 1.4234383637368712e-05,
|
| 546 |
+
"loss": 1.1514,
|
| 547 |
+
"step": 3900
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 0.86,
|
| 551 |
+
"eval_loss": 1.156549096107483,
|
| 552 |
+
"eval_runtime": 65.3706,
|
| 553 |
+
"eval_samples_per_second": 13.997,
|
| 554 |
+
"eval_steps_per_second": 0.352,
|
| 555 |
+
"step": 3900
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.88,
|
| 559 |
+
"learning_rate": 1.3957987838584854e-05,
|
| 560 |
+
"loss": 1.1613,
|
| 561 |
+
"step": 4000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.88,
|
| 565 |
+
"eval_loss": 1.1555191278457642,
|
| 566 |
+
"eval_runtime": 65.3524,
|
| 567 |
+
"eval_samples_per_second": 14.001,
|
| 568 |
+
"eval_steps_per_second": 0.352,
|
| 569 |
+
"step": 4000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.91,
|
| 573 |
+
"learning_rate": 1.3681592039800995e-05,
|
| 574 |
+
"loss": 1.1546,
|
| 575 |
+
"step": 4100
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.91,
|
| 579 |
+
"eval_loss": 1.1544185876846313,
|
| 580 |
+
"eval_runtime": 65.3797,
|
| 581 |
+
"eval_samples_per_second": 13.995,
|
| 582 |
+
"eval_steps_per_second": 0.352,
|
| 583 |
+
"step": 4100
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.93,
|
| 587 |
+
"learning_rate": 1.3405196241017137e-05,
|
| 588 |
+
"loss": 1.1491,
|
| 589 |
+
"step": 4200
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.93,
|
| 593 |
+
"eval_loss": 1.1530828475952148,
|
| 594 |
+
"eval_runtime": 65.3838,
|
| 595 |
+
"eval_samples_per_second": 13.994,
|
| 596 |
+
"eval_steps_per_second": 0.352,
|
| 597 |
+
"step": 4200
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.95,
|
| 601 |
+
"learning_rate": 1.312880044223328e-05,
|
| 602 |
+
"loss": 1.1517,
|
| 603 |
+
"step": 4300
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.95,
|
| 607 |
+
"eval_loss": 1.152304768562317,
|
| 608 |
+
"eval_runtime": 65.3976,
|
| 609 |
+
"eval_samples_per_second": 13.991,
|
| 610 |
+
"eval_steps_per_second": 0.352,
|
| 611 |
+
"step": 4300
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.97,
|
| 615 |
+
"learning_rate": 1.285240464344942e-05,
|
| 616 |
+
"loss": 1.1519,
|
| 617 |
+
"step": 4400
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.97,
|
| 621 |
+
"eval_loss": 1.1511619091033936,
|
| 622 |
+
"eval_runtime": 65.3815,
|
| 623 |
+
"eval_samples_per_second": 13.995,
|
| 624 |
+
"eval_steps_per_second": 0.352,
|
| 625 |
+
"step": 4400
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.99,
|
| 629 |
+
"learning_rate": 1.2576008844665563e-05,
|
| 630 |
+
"loss": 1.1455,
|
| 631 |
+
"step": 4500
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.99,
|
| 635 |
+
"eval_loss": 1.1500450372695923,
|
| 636 |
+
"eval_runtime": 65.3586,
|
| 637 |
+
"eval_samples_per_second": 14.0,
|
| 638 |
+
"eval_steps_per_second": 0.352,
|
| 639 |
+
"step": 4500
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.02,
|
| 643 |
+
"learning_rate": 1.2299613045881703e-05,
|
| 644 |
+
"loss": 1.1257,
|
| 645 |
+
"step": 4600
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 1.02,
|
| 649 |
+
"eval_loss": 1.149997591972351,
|
| 650 |
+
"eval_runtime": 65.3761,
|
| 651 |
+
"eval_samples_per_second": 13.996,
|
| 652 |
+
"eval_steps_per_second": 0.352,
|
| 653 |
+
"step": 4600
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.04,
|
| 657 |
+
"learning_rate": 1.2023217247097844e-05,
|
| 658 |
+
"loss": 1.1252,
|
| 659 |
+
"step": 4700
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 1.04,
|
| 663 |
+
"eval_loss": 1.149656891822815,
|
| 664 |
+
"eval_runtime": 65.396,
|
| 665 |
+
"eval_samples_per_second": 13.992,
|
| 666 |
+
"eval_steps_per_second": 0.352,
|
| 667 |
+
"step": 4700
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.06,
|
| 671 |
+
"learning_rate": 1.1746821448313986e-05,
|
| 672 |
+
"loss": 1.1324,
|
| 673 |
+
"step": 4800
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 1.06,
|
| 677 |
+
"eval_loss": 1.1489354372024536,
|
| 678 |
+
"eval_runtime": 65.4189,
|
| 679 |
+
"eval_samples_per_second": 13.987,
|
| 680 |
+
"eval_steps_per_second": 0.352,
|
| 681 |
+
"step": 4800
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.08,
|
| 685 |
+
"learning_rate": 1.1470425649530129e-05,
|
| 686 |
+
"loss": 1.1194,
|
| 687 |
+
"step": 4900
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 1.08,
|
| 691 |
+
"eval_loss": 1.1480780839920044,
|
| 692 |
+
"eval_runtime": 65.3723,
|
| 693 |
+
"eval_samples_per_second": 13.997,
|
| 694 |
+
"eval_steps_per_second": 0.352,
|
| 695 |
+
"step": 4900
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.1,
|
| 699 |
+
"learning_rate": 1.119402985074627e-05,
|
| 700 |
+
"loss": 1.1201,
|
| 701 |
+
"step": 5000
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 1.1,
|
| 705 |
+
"eval_loss": 1.1470924615859985,
|
| 706 |
+
"eval_runtime": 65.3931,
|
| 707 |
+
"eval_samples_per_second": 13.992,
|
| 708 |
+
"eval_steps_per_second": 0.352,
|
| 709 |
+
"step": 5000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.13,
|
| 713 |
+
"learning_rate": 1.0917634051962412e-05,
|
| 714 |
+
"loss": 1.1206,
|
| 715 |
+
"step": 5100
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 1.13,
|
| 719 |
+
"eval_loss": 1.1463979482650757,
|
| 720 |
+
"eval_runtime": 65.3812,
|
| 721 |
+
"eval_samples_per_second": 13.995,
|
| 722 |
+
"eval_steps_per_second": 0.352,
|
| 723 |
+
"step": 5100
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.15,
|
| 727 |
+
"learning_rate": 1.0641238253178552e-05,
|
| 728 |
+
"loss": 1.1237,
|
| 729 |
+
"step": 5200
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.15,
|
| 733 |
+
"eval_loss": 1.1460208892822266,
|
| 734 |
+
"eval_runtime": 65.4045,
|
| 735 |
+
"eval_samples_per_second": 13.99,
|
| 736 |
+
"eval_steps_per_second": 0.352,
|
| 737 |
+
"step": 5200
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.17,
|
| 741 |
+
"learning_rate": 1.0364842454394693e-05,
|
| 742 |
+
"loss": 1.1252,
|
| 743 |
+
"step": 5300
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 1.17,
|
| 747 |
+
"eval_loss": 1.1448407173156738,
|
| 748 |
+
"eval_runtime": 65.3974,
|
| 749 |
+
"eval_samples_per_second": 13.991,
|
| 750 |
+
"eval_steps_per_second": 0.352,
|
| 751 |
+
"step": 5300
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.19,
|
| 755 |
+
"learning_rate": 1.0088446655610835e-05,
|
| 756 |
+
"loss": 1.1097,
|
| 757 |
+
"step": 5400
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 1.19,
|
| 761 |
+
"eval_loss": 1.144822597503662,
|
| 762 |
+
"eval_runtime": 65.4129,
|
| 763 |
+
"eval_samples_per_second": 13.988,
|
| 764 |
+
"eval_steps_per_second": 0.352,
|
| 765 |
+
"step": 5400
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.22,
|
| 769 |
+
"learning_rate": 9.812050856826976e-06,
|
| 770 |
+
"loss": 1.1136,
|
| 771 |
+
"step": 5500
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 1.22,
|
| 775 |
+
"eval_loss": 1.1438499689102173,
|
| 776 |
+
"eval_runtime": 65.3802,
|
| 777 |
+
"eval_samples_per_second": 13.995,
|
| 778 |
+
"eval_steps_per_second": 0.352,
|
| 779 |
+
"step": 5500
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.24,
|
| 783 |
+
"learning_rate": 9.535655058043118e-06,
|
| 784 |
+
"loss": 1.1188,
|
| 785 |
+
"step": 5600
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 1.24,
|
| 789 |
+
"eval_loss": 1.1431740522384644,
|
| 790 |
+
"eval_runtime": 65.408,
|
| 791 |
+
"eval_samples_per_second": 13.989,
|
| 792 |
+
"eval_steps_per_second": 0.352,
|
| 793 |
+
"step": 5600
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.26,
|
| 797 |
+
"learning_rate": 9.259259259259259e-06,
|
| 798 |
+
"loss": 1.1229,
|
| 799 |
+
"step": 5700
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 1.26,
|
| 803 |
+
"eval_loss": 1.1426993608474731,
|
| 804 |
+
"eval_runtime": 65.4152,
|
| 805 |
+
"eval_samples_per_second": 13.988,
|
| 806 |
+
"eval_steps_per_second": 0.352,
|
| 807 |
+
"step": 5700
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.28,
|
| 811 |
+
"learning_rate": 8.9828634604754e-06,
|
| 812 |
+
"loss": 1.1158,
|
| 813 |
+
"step": 5800
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 1.28,
|
| 817 |
+
"eval_loss": 1.142805814743042,
|
| 818 |
+
"eval_runtime": 65.389,
|
| 819 |
+
"eval_samples_per_second": 13.993,
|
| 820 |
+
"eval_steps_per_second": 0.352,
|
| 821 |
+
"step": 5800
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.3,
|
| 825 |
+
"learning_rate": 8.706467661691544e-06,
|
| 826 |
+
"loss": 1.1123,
|
| 827 |
+
"step": 5900
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 1.3,
|
| 831 |
+
"eval_loss": 1.141711950302124,
|
| 832 |
+
"eval_runtime": 65.4062,
|
| 833 |
+
"eval_samples_per_second": 13.99,
|
| 834 |
+
"eval_steps_per_second": 0.352,
|
| 835 |
+
"step": 5900
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.33,
|
| 839 |
+
"learning_rate": 8.430071862907685e-06,
|
| 840 |
+
"loss": 1.1088,
|
| 841 |
+
"step": 6000
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 1.33,
|
| 845 |
+
"eval_loss": 1.1413805484771729,
|
| 846 |
+
"eval_runtime": 65.3833,
|
| 847 |
+
"eval_samples_per_second": 13.994,
|
| 848 |
+
"eval_steps_per_second": 0.352,
|
| 849 |
+
"step": 6000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.35,
|
| 853 |
+
"learning_rate": 8.153676064123827e-06,
|
| 854 |
+
"loss": 1.1166,
|
| 855 |
+
"step": 6100
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 1.35,
|
| 859 |
+
"eval_loss": 1.1401617527008057,
|
| 860 |
+
"eval_runtime": 65.3721,
|
| 861 |
+
"eval_samples_per_second": 13.997,
|
| 862 |
+
"eval_steps_per_second": 0.352,
|
| 863 |
+
"step": 6100
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.37,
|
| 867 |
+
"learning_rate": 7.877280265339968e-06,
|
| 868 |
+
"loss": 1.1058,
|
| 869 |
+
"step": 6200
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 1.37,
|
| 873 |
+
"eval_loss": 1.139762282371521,
|
| 874 |
+
"eval_runtime": 65.366,
|
| 875 |
+
"eval_samples_per_second": 13.998,
|
| 876 |
+
"eval_steps_per_second": 0.352,
|
| 877 |
+
"step": 6200
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.39,
|
| 881 |
+
"learning_rate": 7.600884466556109e-06,
|
| 882 |
+
"loss": 1.1117,
|
| 883 |
+
"step": 6300
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 1.39,
|
| 887 |
+
"eval_loss": 1.139173984527588,
|
| 888 |
+
"eval_runtime": 65.3916,
|
| 889 |
+
"eval_samples_per_second": 13.993,
|
| 890 |
+
"eval_steps_per_second": 0.352,
|
| 891 |
+
"step": 6300
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.41,
|
| 895 |
+
"learning_rate": 7.3244886677722505e-06,
|
| 896 |
+
"loss": 1.1094,
|
| 897 |
+
"step": 6400
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.41,
|
| 901 |
+
"eval_loss": 1.138359546661377,
|
| 902 |
+
"eval_runtime": 65.3904,
|
| 903 |
+
"eval_samples_per_second": 13.993,
|
| 904 |
+
"eval_steps_per_second": 0.352,
|
| 905 |
+
"step": 6400
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.44,
|
| 909 |
+
"learning_rate": 7.048092868988391e-06,
|
| 910 |
+
"loss": 1.1086,
|
| 911 |
+
"step": 6500
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 1.44,
|
| 915 |
+
"eval_loss": 1.1380010843276978,
|
| 916 |
+
"eval_runtime": 65.4015,
|
| 917 |
+
"eval_samples_per_second": 13.991,
|
| 918 |
+
"eval_steps_per_second": 0.352,
|
| 919 |
+
"step": 6500
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.46,
|
| 923 |
+
"learning_rate": 6.771697070204533e-06,
|
| 924 |
+
"loss": 1.1123,
|
| 925 |
+
"step": 6600
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 1.46,
|
| 929 |
+
"eval_loss": 1.137791395187378,
|
| 930 |
+
"eval_runtime": 65.3778,
|
| 931 |
+
"eval_samples_per_second": 13.996,
|
| 932 |
+
"eval_steps_per_second": 0.352,
|
| 933 |
+
"step": 6600
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.48,
|
| 937 |
+
"learning_rate": 6.495301271420674e-06,
|
| 938 |
+
"loss": 1.1192,
|
| 939 |
+
"step": 6700
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 1.48,
|
| 943 |
+
"eval_loss": 1.137495994567871,
|
| 944 |
+
"eval_runtime": 65.4289,
|
| 945 |
+
"eval_samples_per_second": 13.985,
|
| 946 |
+
"eval_steps_per_second": 0.352,
|
| 947 |
+
"step": 6700
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.5,
|
| 951 |
+
"learning_rate": 6.2189054726368165e-06,
|
| 952 |
+
"loss": 1.1047,
|
| 953 |
+
"step": 6800
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 1.5,
|
| 957 |
+
"eval_loss": 1.1372565031051636,
|
| 958 |
+
"eval_runtime": 65.3657,
|
| 959 |
+
"eval_samples_per_second": 13.998,
|
| 960 |
+
"eval_steps_per_second": 0.352,
|
| 961 |
+
"step": 6800
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.52,
|
| 965 |
+
"learning_rate": 5.942509673852958e-06,
|
| 966 |
+
"loss": 1.1084,
|
| 967 |
+
"step": 6900
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 1.52,
|
| 971 |
+
"eval_loss": 1.136530876159668,
|
| 972 |
+
"eval_runtime": 65.37,
|
| 973 |
+
"eval_samples_per_second": 13.997,
|
| 974 |
+
"eval_steps_per_second": 0.352,
|
| 975 |
+
"step": 6900
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.55,
|
| 979 |
+
"learning_rate": 5.666113875069099e-06,
|
| 980 |
+
"loss": 1.1137,
|
| 981 |
+
"step": 7000
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 1.55,
|
| 985 |
+
"eval_loss": 1.1357197761535645,
|
| 986 |
+
"eval_runtime": 65.3617,
|
| 987 |
+
"eval_samples_per_second": 13.999,
|
| 988 |
+
"eval_steps_per_second": 0.352,
|
| 989 |
+
"step": 7000
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.57,
|
| 993 |
+
"learning_rate": 5.38971807628524e-06,
|
| 994 |
+
"loss": 1.1139,
|
| 995 |
+
"step": 7100
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 1.57,
|
| 999 |
+
"eval_loss": 1.1352890729904175,
|
| 1000 |
+
"eval_runtime": 65.3665,
|
| 1001 |
+
"eval_samples_per_second": 13.998,
|
| 1002 |
+
"eval_steps_per_second": 0.352,
|
| 1003 |
+
"step": 7100
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 1.59,
|
| 1007 |
+
"learning_rate": 5.1133222775013826e-06,
|
| 1008 |
+
"loss": 1.1122,
|
| 1009 |
+
"step": 7200
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 1.59,
|
| 1013 |
+
"eval_loss": 1.1347852945327759,
|
| 1014 |
+
"eval_runtime": 65.3678,
|
| 1015 |
+
"eval_samples_per_second": 13.998,
|
| 1016 |
+
"eval_steps_per_second": 0.352,
|
| 1017 |
+
"step": 7200
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.61,
|
| 1021 |
+
"learning_rate": 4.836926478717524e-06,
|
| 1022 |
+
"loss": 1.1148,
|
| 1023 |
+
"step": 7300
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 1.61,
|
| 1027 |
+
"eval_loss": 1.134663462638855,
|
| 1028 |
+
"eval_runtime": 65.381,
|
| 1029 |
+
"eval_samples_per_second": 13.995,
|
| 1030 |
+
"eval_steps_per_second": 0.352,
|
| 1031 |
+
"step": 7300
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.64,
|
| 1035 |
+
"learning_rate": 4.560530679933666e-06,
|
| 1036 |
+
"loss": 1.116,
|
| 1037 |
+
"step": 7400
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 1.64,
|
| 1041 |
+
"eval_loss": 1.134074330329895,
|
| 1042 |
+
"eval_runtime": 65.3847,
|
| 1043 |
+
"eval_samples_per_second": 13.994,
|
| 1044 |
+
"eval_steps_per_second": 0.352,
|
| 1045 |
+
"step": 7400
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 1.66,
|
| 1049 |
+
"learning_rate": 4.284134881149806e-06,
|
| 1050 |
+
"loss": 1.105,
|
| 1051 |
+
"step": 7500
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 1.66,
|
| 1055 |
+
"eval_loss": 1.1337759494781494,
|
| 1056 |
+
"eval_runtime": 65.3676,
|
| 1057 |
+
"eval_samples_per_second": 13.998,
|
| 1058 |
+
"eval_steps_per_second": 0.352,
|
| 1059 |
+
"step": 7500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.68,
|
| 1063 |
+
"learning_rate": 4.007739082365948e-06,
|
| 1064 |
+
"loss": 1.1155,
|
| 1065 |
+
"step": 7600
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 1.68,
|
| 1069 |
+
"eval_loss": 1.1333887577056885,
|
| 1070 |
+
"eval_runtime": 65.3814,
|
| 1071 |
+
"eval_samples_per_second": 13.995,
|
| 1072 |
+
"eval_steps_per_second": 0.352,
|
| 1073 |
+
"step": 7600
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 1.7,
|
| 1077 |
+
"learning_rate": 3.7313432835820893e-06,
|
| 1078 |
+
"loss": 1.1082,
|
| 1079 |
+
"step": 7700
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 1.7,
|
| 1083 |
+
"eval_loss": 1.1329772472381592,
|
| 1084 |
+
"eval_runtime": 65.3817,
|
| 1085 |
+
"eval_samples_per_second": 13.995,
|
| 1086 |
+
"eval_steps_per_second": 0.352,
|
| 1087 |
+
"step": 7700
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.72,
|
| 1091 |
+
"learning_rate": 3.4549474847982316e-06,
|
| 1092 |
+
"loss": 1.1145,
|
| 1093 |
+
"step": 7800
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 1.72,
|
| 1097 |
+
"eval_loss": 1.1328340768814087,
|
| 1098 |
+
"eval_runtime": 65.4303,
|
| 1099 |
+
"eval_samples_per_second": 13.984,
|
| 1100 |
+
"eval_steps_per_second": 0.352,
|
| 1101 |
+
"step": 7800
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.75,
|
| 1105 |
+
"learning_rate": 3.1785516860143727e-06,
|
| 1106 |
+
"loss": 1.1078,
|
| 1107 |
+
"step": 7900
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 1.75,
|
| 1111 |
+
"eval_loss": 1.1321594715118408,
|
| 1112 |
+
"eval_runtime": 65.5896,
|
| 1113 |
+
"eval_samples_per_second": 13.95,
|
| 1114 |
+
"eval_steps_per_second": 0.351,
|
| 1115 |
+
"step": 7900
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.77,
|
| 1119 |
+
"learning_rate": 2.902155887230514e-06,
|
| 1120 |
+
"loss": 1.1041,
|
| 1121 |
+
"step": 8000
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 1.77,
|
| 1125 |
+
"eval_loss": 1.1319067478179932,
|
| 1126 |
+
"eval_runtime": 65.4493,
|
| 1127 |
+
"eval_samples_per_second": 13.98,
|
| 1128 |
+
"eval_steps_per_second": 0.351,
|
| 1129 |
+
"step": 8000
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.79,
|
| 1133 |
+
"learning_rate": 2.6257600884466557e-06,
|
| 1134 |
+
"loss": 1.0935,
|
| 1135 |
+
"step": 8100
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 1.79,
|
| 1139 |
+
"eval_loss": 1.1322442293167114,
|
| 1140 |
+
"eval_runtime": 65.3072,
|
| 1141 |
+
"eval_samples_per_second": 14.011,
|
| 1142 |
+
"eval_steps_per_second": 0.352,
|
| 1143 |
+
"step": 8100
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.81,
|
| 1147 |
+
"learning_rate": 2.349364289662797e-06,
|
| 1148 |
+
"loss": 1.0906,
|
| 1149 |
+
"step": 8200
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 1.81,
|
| 1153 |
+
"eval_loss": 1.1326180696487427,
|
| 1154 |
+
"eval_runtime": 65.2969,
|
| 1155 |
+
"eval_samples_per_second": 14.013,
|
| 1156 |
+
"eval_steps_per_second": 0.352,
|
| 1157 |
+
"step": 8200
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.83,
|
| 1161 |
+
"learning_rate": 2.0729684908789387e-06,
|
| 1162 |
+
"loss": 1.1016,
|
| 1163 |
+
"step": 8300
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 1.83,
|
| 1167 |
+
"eval_loss": 1.132248878479004,
|
| 1168 |
+
"eval_runtime": 65.2925,
|
| 1169 |
+
"eval_samples_per_second": 14.014,
|
| 1170 |
+
"eval_steps_per_second": 0.352,
|
| 1171 |
+
"step": 8300
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.86,
|
| 1175 |
+
"learning_rate": 1.7965726920950804e-06,
|
| 1176 |
+
"loss": 1.0907,
|
| 1177 |
+
"step": 8400
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 1.86,
|
| 1181 |
+
"eval_loss": 1.1321300268173218,
|
| 1182 |
+
"eval_runtime": 65.2955,
|
| 1183 |
+
"eval_samples_per_second": 14.013,
|
| 1184 |
+
"eval_steps_per_second": 0.352,
|
| 1185 |
+
"step": 8400
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.88,
|
| 1189 |
+
"learning_rate": 1.5201768933112217e-06,
|
| 1190 |
+
"loss": 1.0908,
|
| 1191 |
+
"step": 8500
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 1.88,
|
| 1195 |
+
"eval_loss": 1.1320557594299316,
|
| 1196 |
+
"eval_runtime": 65.2825,
|
| 1197 |
+
"eval_samples_per_second": 14.016,
|
| 1198 |
+
"eval_steps_per_second": 0.352,
|
| 1199 |
+
"step": 8500
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.9,
|
| 1203 |
+
"learning_rate": 1.2437810945273632e-06,
|
| 1204 |
+
"loss": 1.0997,
|
| 1205 |
+
"step": 8600
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 1.9,
|
| 1209 |
+
"eval_loss": 1.131882667541504,
|
| 1210 |
+
"eval_runtime": 65.2854,
|
| 1211 |
+
"eval_samples_per_second": 14.015,
|
| 1212 |
+
"eval_steps_per_second": 0.352,
|
| 1213 |
+
"step": 8600
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.92,
|
| 1217 |
+
"learning_rate": 9.673852957435047e-07,
|
| 1218 |
+
"loss": 1.0856,
|
| 1219 |
+
"step": 8700
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 1.92,
|
| 1223 |
+
"eval_loss": 1.1319279670715332,
|
| 1224 |
+
"eval_runtime": 65.279,
|
| 1225 |
+
"eval_samples_per_second": 14.017,
|
| 1226 |
+
"eval_steps_per_second": 0.352,
|
| 1227 |
+
"step": 8700
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.94,
|
| 1231 |
+
"learning_rate": 6.909894969596462e-07,
|
| 1232 |
+
"loss": 1.0898,
|
| 1233 |
+
"step": 8800
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 1.94,
|
| 1237 |
+
"eval_loss": 1.1317994594573975,
|
| 1238 |
+
"eval_runtime": 65.2805,
|
| 1239 |
+
"eval_samples_per_second": 14.016,
|
| 1240 |
+
"eval_steps_per_second": 0.352,
|
| 1241 |
+
"step": 8800
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.97,
|
| 1245 |
+
"learning_rate": 4.145936981757878e-07,
|
| 1246 |
+
"loss": 1.0944,
|
| 1247 |
+
"step": 8900
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 1.97,
|
| 1251 |
+
"eval_loss": 1.1316641569137573,
|
| 1252 |
+
"eval_runtime": 65.3051,
|
| 1253 |
+
"eval_samples_per_second": 14.011,
|
| 1254 |
+
"eval_steps_per_second": 0.352,
|
| 1255 |
+
"step": 8900
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.99,
|
| 1259 |
+
"learning_rate": 1.3819789939192925e-07,
|
| 1260 |
+
"loss": 1.0875,
|
| 1261 |
+
"step": 9000
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 1.99,
|
| 1265 |
+
"eval_loss": 1.1316481828689575,
|
| 1266 |
+
"eval_runtime": 65.2846,
|
| 1267 |
+
"eval_samples_per_second": 14.016,
|
| 1268 |
+
"eval_steps_per_second": 0.352,
|
| 1269 |
+
"step": 9000
|
| 1270 |
+
}
|
| 1271 |
+
],
|
| 1272 |
+
"logging_steps": 100,
|
| 1273 |
+
"max_steps": 9050,
|
| 1274 |
+
"num_train_epochs": 2,
|
| 1275 |
+
"save_steps": 1000,
|
| 1276 |
+
"total_flos": 7.910691746781069e+18,
|
| 1277 |
+
"trial_name": null,
|
| 1278 |
+
"trial_params": null
|
| 1279 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:178958f0d1fb7cb7032e81cfa077acee6f8e5b4963605560964c080a0d9613d3
|
| 3 |
+
size 4600
|