Training in progress, step 100
Browse files- all_results.json +16 -0
- config.json +1 -1
- eval_results.json +11 -0
- model.safetensors +1 -1
- preprocessor_config.json +14 -0
- runs/Mar18_15-27-23_9c311a5b3773/events.out.tfevents.1710777139.9c311a5b3773.3314.21 +3 -0
- runs/Mar18_16-06-19_9c311a5b3773/events.out.tfevents.1710777980.9c311a5b3773.3314.22 +3 -0
- runs/Mar18_16-51-36_9c311a5b3773/events.out.tfevents.1710780698.9c311a5b3773.175663.0 +3 -0
- train_results.json +8 -0
- trainer_state.json +1506 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.61,
|
| 3 |
+
"eval_accuracy": 0.8401525658807212,
|
| 4 |
+
"eval_f1": 0.8300860373682543,
|
| 5 |
+
"eval_loss": 0.5152533650398254,
|
| 6 |
+
"eval_precision": 0.8326625217058278,
|
| 7 |
+
"eval_recall": 0.8401525658807212,
|
| 8 |
+
"eval_runtime": 41.5803,
|
| 9 |
+
"eval_samples_per_second": 69.36,
|
| 10 |
+
"eval_steps_per_second": 8.682,
|
| 11 |
+
"total_flos": 2.2287694956200755e+18,
|
| 12 |
+
"train_loss": 0.2732895821850333,
|
| 13 |
+
"train_runtime": 1429.5622,
|
| 14 |
+
"train_samples_per_second": 358.711,
|
| 15 |
+
"train_steps_per_second": 22.454
|
| 16 |
+
}
|
config.json
CHANGED
|
@@ -38,5 +38,5 @@
|
|
| 38 |
"problem_type": "single_label_classification",
|
| 39 |
"qkv_bias": true,
|
| 40 |
"torch_dtype": "float32",
|
| 41 |
-
"transformers_version": "4.
|
| 42 |
}
|
|
|
|
| 38 |
"problem_type": "single_label_classification",
|
| 39 |
"qkv_bias": true,
|
| 40 |
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.39.0.dev0"
|
| 42 |
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.61,
|
| 3 |
+
"eval_accuracy": 0.8401525658807212,
|
| 4 |
+
"eval_f1": 0.8300860373682543,
|
| 5 |
+
"eval_loss": 0.5152533650398254,
|
| 6 |
+
"eval_precision": 0.8326625217058278,
|
| 7 |
+
"eval_recall": 0.8401525658807212,
|
| 8 |
+
"eval_runtime": 41.5803,
|
| 9 |
+
"eval_samples_per_second": 69.36,
|
| 10 |
+
"eval_steps_per_second": 8.682
|
| 11 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343239356
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37533831bd4454eece4c9e58d37e99dbcb12d932787fa67126bf9fdb7eabae8f
|
| 3 |
size 343239356
|
preprocessor_config.json
CHANGED
|
@@ -1,4 +1,18 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"do_normalize": true,
|
| 3 |
"do_rescale": true,
|
| 4 |
"do_resize": true,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_valid_processor_keys": [
|
| 3 |
+
"images",
|
| 4 |
+
"do_resize",
|
| 5 |
+
"size",
|
| 6 |
+
"resample",
|
| 7 |
+
"do_rescale",
|
| 8 |
+
"rescale_factor",
|
| 9 |
+
"do_normalize",
|
| 10 |
+
"image_mean",
|
| 11 |
+
"image_std",
|
| 12 |
+
"return_tensors",
|
| 13 |
+
"data_format",
|
| 14 |
+
"input_data_format"
|
| 15 |
+
],
|
| 16 |
"do_normalize": true,
|
| 17 |
"do_rescale": true,
|
| 18 |
"do_resize": true,
|
runs/Mar18_15-27-23_9c311a5b3773/events.out.tfevents.1710777139.9c311a5b3773.3314.21
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf8da78b31ec82b4130ab6869cf4497bea3a268b69f7e03c1ab9efdf51e57e86
|
| 3 |
+
size 560
|
runs/Mar18_16-06-19_9c311a5b3773/events.out.tfevents.1710777980.9c311a5b3773.3314.22
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9d64a813e3ef537dcb26823e2bc3876e5441054327691f52e866098a8c85c4a
|
| 3 |
+
size 4700
|
runs/Mar18_16-51-36_9c311a5b3773/events.out.tfevents.1710780698.9c311a5b3773.175663.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e7dd54f595722d5a95266c3b948b19757260d44ead65a25472066167ac1409c
|
| 3 |
+
size 7264
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.61,
|
| 3 |
+
"total_flos": 2.2287694956200755e+18,
|
| 4 |
+
"train_loss": 0.2732895821850333,
|
| 5 |
+
"train_runtime": 1429.5622,
|
| 6 |
+
"train_samples_per_second": 358.711,
|
| 7 |
+
"train_steps_per_second": 22.454
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1506 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5152533650398254,
|
| 3 |
+
"best_model_checkpoint": "./vit-lr-cosine-restarts/checkpoint-800",
|
| 4 |
+
"epoch": 5.607476635514018,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 1800,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"grad_norm": 5.076780319213867,
|
| 14 |
+
"learning_rate": 9.999998060388815e-05,
|
| 15 |
+
"loss": 1.3486,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06,
|
| 20 |
+
"grad_norm": 4.030631065368652,
|
| 21 |
+
"learning_rate": 9.999991355561956e-05,
|
| 22 |
+
"loss": 0.7525,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.09,
|
| 27 |
+
"grad_norm": 4.877225875854492,
|
| 28 |
+
"learning_rate": 9.999979861580028e-05,
|
| 29 |
+
"loss": 0.833,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.12,
|
| 34 |
+
"grad_norm": 7.290777683258057,
|
| 35 |
+
"learning_rate": 9.99996357845404e-05,
|
| 36 |
+
"loss": 0.9935,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.16,
|
| 41 |
+
"grad_norm": 5.126965522766113,
|
| 42 |
+
"learning_rate": 9.999942506199588e-05,
|
| 43 |
+
"loss": 0.7271,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.19,
|
| 48 |
+
"grad_norm": 6.139286518096924,
|
| 49 |
+
"learning_rate": 9.999916644836857e-05,
|
| 50 |
+
"loss": 0.8015,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.22,
|
| 55 |
+
"grad_norm": 4.372274398803711,
|
| 56 |
+
"learning_rate": 9.999885994390619e-05,
|
| 57 |
+
"loss": 0.8235,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.25,
|
| 62 |
+
"grad_norm": 4.294188976287842,
|
| 63 |
+
"learning_rate": 9.999850554890226e-05,
|
| 64 |
+
"loss": 0.6745,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.28,
|
| 69 |
+
"grad_norm": 5.877817153930664,
|
| 70 |
+
"learning_rate": 9.999810326369631e-05,
|
| 71 |
+
"loss": 0.6976,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.31,
|
| 76 |
+
"grad_norm": 4.55079984664917,
|
| 77 |
+
"learning_rate": 9.999765308867361e-05,
|
| 78 |
+
"loss": 0.5734,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.31,
|
| 83 |
+
"eval_accuracy": 0.7884882108183079,
|
| 84 |
+
"eval_f1": 0.7654615392142581,
|
| 85 |
+
"eval_loss": 0.6007876992225647,
|
| 86 |
+
"eval_precision": 0.763065724803555,
|
| 87 |
+
"eval_recall": 0.7884882108183079,
|
| 88 |
+
"eval_runtime": 39.2669,
|
| 89 |
+
"eval_samples_per_second": 73.446,
|
| 90 |
+
"eval_steps_per_second": 9.193,
|
| 91 |
+
"step": 100
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.34,
|
| 95 |
+
"grad_norm": 3.842815399169922,
|
| 96 |
+
"learning_rate": 9.999715502426537e-05,
|
| 97 |
+
"loss": 0.6458,
|
| 98 |
+
"step": 110
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.37,
|
| 102 |
+
"grad_norm": 8.019635200500488,
|
| 103 |
+
"learning_rate": 9.999660907094863e-05,
|
| 104 |
+
"loss": 0.6384,
|
| 105 |
+
"step": 120
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.4,
|
| 109 |
+
"grad_norm": 7.878860950469971,
|
| 110 |
+
"learning_rate": 9.999601522924635e-05,
|
| 111 |
+
"loss": 0.7051,
|
| 112 |
+
"step": 130
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.44,
|
| 116 |
+
"grad_norm": 2.1701011657714844,
|
| 117 |
+
"learning_rate": 9.999537349972733e-05,
|
| 118 |
+
"loss": 0.5199,
|
| 119 |
+
"step": 140
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.47,
|
| 123 |
+
"grad_norm": 4.154609680175781,
|
| 124 |
+
"learning_rate": 9.999468388300622e-05,
|
| 125 |
+
"loss": 0.5967,
|
| 126 |
+
"step": 150
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.5,
|
| 130 |
+
"grad_norm": 5.633548259735107,
|
| 131 |
+
"learning_rate": 9.999394637974358e-05,
|
| 132 |
+
"loss": 0.5481,
|
| 133 |
+
"step": 160
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.53,
|
| 137 |
+
"grad_norm": 3.171057939529419,
|
| 138 |
+
"learning_rate": 9.99931609906458e-05,
|
| 139 |
+
"loss": 0.6302,
|
| 140 |
+
"step": 170
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.56,
|
| 144 |
+
"grad_norm": 5.892911911010742,
|
| 145 |
+
"learning_rate": 9.999232771646514e-05,
|
| 146 |
+
"loss": 0.655,
|
| 147 |
+
"step": 180
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.59,
|
| 151 |
+
"grad_norm": 3.430375576019287,
|
| 152 |
+
"learning_rate": 9.999144655799976e-05,
|
| 153 |
+
"loss": 0.5747,
|
| 154 |
+
"step": 190
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.62,
|
| 158 |
+
"grad_norm": 5.8416056632995605,
|
| 159 |
+
"learning_rate": 9.999051751609367e-05,
|
| 160 |
+
"loss": 0.5602,
|
| 161 |
+
"step": 200
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.62,
|
| 165 |
+
"eval_accuracy": 0.7541608876560333,
|
| 166 |
+
"eval_f1": 0.7003949849463896,
|
| 167 |
+
"eval_loss": 0.784325361251831,
|
| 168 |
+
"eval_precision": 0.742547935218919,
|
| 169 |
+
"eval_recall": 0.7541608876560333,
|
| 170 |
+
"eval_runtime": 38.9694,
|
| 171 |
+
"eval_samples_per_second": 74.007,
|
| 172 |
+
"eval_steps_per_second": 9.264,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.65,
|
| 177 |
+
"grad_norm": 5.451653480529785,
|
| 178 |
+
"learning_rate": 9.998954059163672e-05,
|
| 179 |
+
"loss": 0.6803,
|
| 180 |
+
"step": 210
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.69,
|
| 184 |
+
"grad_norm": 6.584908485412598,
|
| 185 |
+
"learning_rate": 9.998851578556461e-05,
|
| 186 |
+
"loss": 0.7019,
|
| 187 |
+
"step": 220
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.72,
|
| 191 |
+
"grad_norm": 2.3256571292877197,
|
| 192 |
+
"learning_rate": 9.998744309885899e-05,
|
| 193 |
+
"loss": 0.4028,
|
| 194 |
+
"step": 230
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.75,
|
| 198 |
+
"grad_norm": 3.929255962371826,
|
| 199 |
+
"learning_rate": 9.998632253254729e-05,
|
| 200 |
+
"loss": 0.5235,
|
| 201 |
+
"step": 240
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.78,
|
| 205 |
+
"grad_norm": 4.65420389175415,
|
| 206 |
+
"learning_rate": 9.998515408770281e-05,
|
| 207 |
+
"loss": 0.6575,
|
| 208 |
+
"step": 250
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.81,
|
| 212 |
+
"grad_norm": 5.167401313781738,
|
| 213 |
+
"learning_rate": 9.998393776544475e-05,
|
| 214 |
+
"loss": 0.5393,
|
| 215 |
+
"step": 260
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.84,
|
| 219 |
+
"grad_norm": 3.1561028957366943,
|
| 220 |
+
"learning_rate": 9.998267356693811e-05,
|
| 221 |
+
"loss": 0.4725,
|
| 222 |
+
"step": 270
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.87,
|
| 226 |
+
"grad_norm": 4.633551597595215,
|
| 227 |
+
"learning_rate": 9.998136149339382e-05,
|
| 228 |
+
"loss": 0.4838,
|
| 229 |
+
"step": 280
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.9,
|
| 233 |
+
"grad_norm": 6.649106979370117,
|
| 234 |
+
"learning_rate": 9.99800015460686e-05,
|
| 235 |
+
"loss": 0.6252,
|
| 236 |
+
"step": 290
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.93,
|
| 240 |
+
"grad_norm": 6.892623424530029,
|
| 241 |
+
"learning_rate": 9.997859372626506e-05,
|
| 242 |
+
"loss": 0.7117,
|
| 243 |
+
"step": 300
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.93,
|
| 247 |
+
"eval_accuracy": 0.7659500693481276,
|
| 248 |
+
"eval_f1": 0.7754174880710092,
|
| 249 |
+
"eval_loss": 0.6221866011619568,
|
| 250 |
+
"eval_precision": 0.8158439426784209,
|
| 251 |
+
"eval_recall": 0.7659500693481276,
|
| 252 |
+
"eval_runtime": 38.9156,
|
| 253 |
+
"eval_samples_per_second": 74.109,
|
| 254 |
+
"eval_steps_per_second": 9.276,
|
| 255 |
+
"step": 300
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.97,
|
| 259 |
+
"grad_norm": 5.1511149406433105,
|
| 260 |
+
"learning_rate": 9.997713803533167e-05,
|
| 261 |
+
"loss": 0.5396,
|
| 262 |
+
"step": 310
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.0,
|
| 266 |
+
"grad_norm": 5.100913047790527,
|
| 267 |
+
"learning_rate": 9.997563447466271e-05,
|
| 268 |
+
"loss": 0.4868,
|
| 269 |
+
"step": 320
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.03,
|
| 273 |
+
"grad_norm": 5.780107498168945,
|
| 274 |
+
"learning_rate": 9.997408304569836e-05,
|
| 275 |
+
"loss": 0.4748,
|
| 276 |
+
"step": 330
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.06,
|
| 280 |
+
"grad_norm": 5.687930107116699,
|
| 281 |
+
"learning_rate": 9.997248374992462e-05,
|
| 282 |
+
"loss": 0.3881,
|
| 283 |
+
"step": 340
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.09,
|
| 287 |
+
"grad_norm": 3.1763672828674316,
|
| 288 |
+
"learning_rate": 9.997083658887336e-05,
|
| 289 |
+
"loss": 0.4268,
|
| 290 |
+
"step": 350
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.12,
|
| 294 |
+
"grad_norm": 2.4463164806365967,
|
| 295 |
+
"learning_rate": 9.996914156412227e-05,
|
| 296 |
+
"loss": 0.2806,
|
| 297 |
+
"step": 360
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.15,
|
| 301 |
+
"grad_norm": 3.662301778793335,
|
| 302 |
+
"learning_rate": 9.99673986772949e-05,
|
| 303 |
+
"loss": 0.4249,
|
| 304 |
+
"step": 370
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.18,
|
| 308 |
+
"grad_norm": 7.021162986755371,
|
| 309 |
+
"learning_rate": 9.996560793006067e-05,
|
| 310 |
+
"loss": 0.4093,
|
| 311 |
+
"step": 380
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.21,
|
| 315 |
+
"grad_norm": 4.5534539222717285,
|
| 316 |
+
"learning_rate": 9.996376932413478e-05,
|
| 317 |
+
"loss": 0.4531,
|
| 318 |
+
"step": 390
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.25,
|
| 322 |
+
"grad_norm": 2.38512921333313,
|
| 323 |
+
"learning_rate": 9.996188286127832e-05,
|
| 324 |
+
"loss": 0.4445,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.25,
|
| 329 |
+
"eval_accuracy": 0.7923023578363384,
|
| 330 |
+
"eval_f1": 0.7998929576261109,
|
| 331 |
+
"eval_loss": 0.5481300950050354,
|
| 332 |
+
"eval_precision": 0.8180996676834356,
|
| 333 |
+
"eval_recall": 0.7923023578363384,
|
| 334 |
+
"eval_runtime": 39.7555,
|
| 335 |
+
"eval_samples_per_second": 72.543,
|
| 336 |
+
"eval_steps_per_second": 9.081,
|
| 337 |
+
"step": 400
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 1.28,
|
| 341 |
+
"grad_norm": 4.16684103012085,
|
| 342 |
+
"learning_rate": 9.995994854329822e-05,
|
| 343 |
+
"loss": 0.3825,
|
| 344 |
+
"step": 410
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.31,
|
| 348 |
+
"grad_norm": 4.1305155754089355,
|
| 349 |
+
"learning_rate": 9.995796637204721e-05,
|
| 350 |
+
"loss": 0.4733,
|
| 351 |
+
"step": 420
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.34,
|
| 355 |
+
"grad_norm": 5.665832042694092,
|
| 356 |
+
"learning_rate": 9.99559363494239e-05,
|
| 357 |
+
"loss": 0.5294,
|
| 358 |
+
"step": 430
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.37,
|
| 362 |
+
"grad_norm": 4.365192413330078,
|
| 363 |
+
"learning_rate": 9.995385847737268e-05,
|
| 364 |
+
"loss": 0.4245,
|
| 365 |
+
"step": 440
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.4,
|
| 369 |
+
"grad_norm": 4.794129371643066,
|
| 370 |
+
"learning_rate": 9.995173275788385e-05,
|
| 371 |
+
"loss": 0.3817,
|
| 372 |
+
"step": 450
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.43,
|
| 376 |
+
"grad_norm": 5.548172950744629,
|
| 377 |
+
"learning_rate": 9.994955919299347e-05,
|
| 378 |
+
"loss": 0.4014,
|
| 379 |
+
"step": 460
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 1.46,
|
| 383 |
+
"grad_norm": 3.7581427097320557,
|
| 384 |
+
"learning_rate": 9.994733778478344e-05,
|
| 385 |
+
"loss": 0.3768,
|
| 386 |
+
"step": 470
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.5,
|
| 390 |
+
"grad_norm": 6.855079174041748,
|
| 391 |
+
"learning_rate": 9.994506853538152e-05,
|
| 392 |
+
"loss": 0.4268,
|
| 393 |
+
"step": 480
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.53,
|
| 397 |
+
"grad_norm": 4.8678483963012695,
|
| 398 |
+
"learning_rate": 9.994275144696124e-05,
|
| 399 |
+
"loss": 0.4195,
|
| 400 |
+
"step": 490
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.56,
|
| 404 |
+
"grad_norm": 2.5210819244384766,
|
| 405 |
+
"learning_rate": 9.994038652174203e-05,
|
| 406 |
+
"loss": 0.3471,
|
| 407 |
+
"step": 500
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 1.56,
|
| 411 |
+
"eval_accuracy": 0.8217753120665742,
|
| 412 |
+
"eval_f1": 0.8047594572379952,
|
| 413 |
+
"eval_loss": 0.5284826159477234,
|
| 414 |
+
"eval_precision": 0.8158080424554234,
|
| 415 |
+
"eval_recall": 0.8217753120665742,
|
| 416 |
+
"eval_runtime": 39.5975,
|
| 417 |
+
"eval_samples_per_second": 72.833,
|
| 418 |
+
"eval_steps_per_second": 9.117,
|
| 419 |
+
"step": 500
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.59,
|
| 423 |
+
"grad_norm": 3.7428205013275146,
|
| 424 |
+
"learning_rate": 9.993797376198904e-05,
|
| 425 |
+
"loss": 0.4145,
|
| 426 |
+
"step": 510
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.62,
|
| 430 |
+
"grad_norm": 4.127384185791016,
|
| 431 |
+
"learning_rate": 9.993551317001332e-05,
|
| 432 |
+
"loss": 0.3791,
|
| 433 |
+
"step": 520
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 1.65,
|
| 437 |
+
"grad_norm": 5.904128074645996,
|
| 438 |
+
"learning_rate": 9.993300474817171e-05,
|
| 439 |
+
"loss": 0.4183,
|
| 440 |
+
"step": 530
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.68,
|
| 444 |
+
"grad_norm": 3.835289478302002,
|
| 445 |
+
"learning_rate": 9.993044849886683e-05,
|
| 446 |
+
"loss": 0.3489,
|
| 447 |
+
"step": 540
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.71,
|
| 451 |
+
"grad_norm": 4.441788673400879,
|
| 452 |
+
"learning_rate": 9.992784442454718e-05,
|
| 453 |
+
"loss": 0.52,
|
| 454 |
+
"step": 550
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 1.74,
|
| 458 |
+
"grad_norm": 4.608953475952148,
|
| 459 |
+
"learning_rate": 9.9925192527707e-05,
|
| 460 |
+
"loss": 0.4983,
|
| 461 |
+
"step": 560
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.78,
|
| 465 |
+
"grad_norm": 3.4798424243927,
|
| 466 |
+
"learning_rate": 9.992249281088636e-05,
|
| 467 |
+
"loss": 0.3766,
|
| 468 |
+
"step": 570
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 1.81,
|
| 472 |
+
"grad_norm": 3.5282986164093018,
|
| 473 |
+
"learning_rate": 9.991974527667115e-05,
|
| 474 |
+
"loss": 0.2979,
|
| 475 |
+
"step": 580
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 1.84,
|
| 479 |
+
"grad_norm": 6.50264310836792,
|
| 480 |
+
"learning_rate": 9.991694992769305e-05,
|
| 481 |
+
"loss": 0.4602,
|
| 482 |
+
"step": 590
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.87,
|
| 486 |
+
"grad_norm": 1.7083078622817993,
|
| 487 |
+
"learning_rate": 9.991410676662952e-05,
|
| 488 |
+
"loss": 0.3144,
|
| 489 |
+
"step": 600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.87,
|
| 493 |
+
"eval_accuracy": 0.7961165048543689,
|
| 494 |
+
"eval_f1": 0.8022817302667706,
|
| 495 |
+
"eval_loss": 0.5565336346626282,
|
| 496 |
+
"eval_precision": 0.8311598226972493,
|
| 497 |
+
"eval_recall": 0.7961165048543689,
|
| 498 |
+
"eval_runtime": 38.759,
|
| 499 |
+
"eval_samples_per_second": 74.408,
|
| 500 |
+
"eval_steps_per_second": 9.314,
|
| 501 |
+
"step": 600
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.9,
|
| 505 |
+
"grad_norm": 5.729618549346924,
|
| 506 |
+
"learning_rate": 9.991121579620385e-05,
|
| 507 |
+
"loss": 0.4488,
|
| 508 |
+
"step": 610
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 1.93,
|
| 512 |
+
"grad_norm": 3.340083599090576,
|
| 513 |
+
"learning_rate": 9.99082770191851e-05,
|
| 514 |
+
"loss": 0.3636,
|
| 515 |
+
"step": 620
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.96,
|
| 519 |
+
"grad_norm": 2.685565710067749,
|
| 520 |
+
"learning_rate": 9.990529043838812e-05,
|
| 521 |
+
"loss": 0.2454,
|
| 522 |
+
"step": 630
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.99,
|
| 526 |
+
"grad_norm": 4.4097676277160645,
|
| 527 |
+
"learning_rate": 9.990225605667357e-05,
|
| 528 |
+
"loss": 0.413,
|
| 529 |
+
"step": 640
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.02,
|
| 533 |
+
"grad_norm": 3.5152175426483154,
|
| 534 |
+
"learning_rate": 9.989917387694786e-05,
|
| 535 |
+
"loss": 0.2442,
|
| 536 |
+
"step": 650
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.06,
|
| 540 |
+
"grad_norm": 3.326936960220337,
|
| 541 |
+
"learning_rate": 9.989604390216322e-05,
|
| 542 |
+
"loss": 0.206,
|
| 543 |
+
"step": 660
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.09,
|
| 547 |
+
"grad_norm": 5.301408767700195,
|
| 548 |
+
"learning_rate": 9.989286613531763e-05,
|
| 549 |
+
"loss": 0.305,
|
| 550 |
+
"step": 670
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.12,
|
| 554 |
+
"grad_norm": 4.104938507080078,
|
| 555 |
+
"learning_rate": 9.988964057945486e-05,
|
| 556 |
+
"loss": 0.2568,
|
| 557 |
+
"step": 680
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 2.15,
|
| 561 |
+
"grad_norm": 3.0700721740722656,
|
| 562 |
+
"learning_rate": 9.988636723766446e-05,
|
| 563 |
+
"loss": 0.2259,
|
| 564 |
+
"step": 690
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.18,
|
| 568 |
+
"grad_norm": 2.798845052719116,
|
| 569 |
+
"learning_rate": 9.988304611308174e-05,
|
| 570 |
+
"loss": 0.1702,
|
| 571 |
+
"step": 700
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.18,
|
| 575 |
+
"eval_accuracy": 0.8255894590846047,
|
| 576 |
+
"eval_f1": 0.8239856028376362,
|
| 577 |
+
"eval_loss": 0.5403878688812256,
|
| 578 |
+
"eval_precision": 0.8319658160543976,
|
| 579 |
+
"eval_recall": 0.8255894590846047,
|
| 580 |
+
"eval_runtime": 39.5591,
|
| 581 |
+
"eval_samples_per_second": 72.903,
|
| 582 |
+
"eval_steps_per_second": 9.126,
|
| 583 |
+
"step": 700
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 2.21,
|
| 587 |
+
"grad_norm": 0.7119998931884766,
|
| 588 |
+
"learning_rate": 9.987967720888777e-05,
|
| 589 |
+
"loss": 0.1882,
|
| 590 |
+
"step": 710
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.24,
|
| 594 |
+
"grad_norm": 4.365331649780273,
|
| 595 |
+
"learning_rate": 9.987626052830943e-05,
|
| 596 |
+
"loss": 0.3553,
|
| 597 |
+
"step": 720
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.27,
|
| 601 |
+
"grad_norm": 5.9306511878967285,
|
| 602 |
+
"learning_rate": 9.98727960746193e-05,
|
| 603 |
+
"loss": 0.3306,
|
| 604 |
+
"step": 730
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.31,
|
| 608 |
+
"grad_norm": 1.0953195095062256,
|
| 609 |
+
"learning_rate": 9.986928385113575e-05,
|
| 610 |
+
"loss": 0.1931,
|
| 611 |
+
"step": 740
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.34,
|
| 615 |
+
"grad_norm": 6.899849891662598,
|
| 616 |
+
"learning_rate": 9.986572386122291e-05,
|
| 617 |
+
"loss": 0.1806,
|
| 618 |
+
"step": 750
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.37,
|
| 622 |
+
"grad_norm": 1.6626615524291992,
|
| 623 |
+
"learning_rate": 9.986211610829065e-05,
|
| 624 |
+
"loss": 0.1701,
|
| 625 |
+
"step": 760
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.4,
|
| 629 |
+
"grad_norm": 4.0154709815979,
|
| 630 |
+
"learning_rate": 9.98584605957946e-05,
|
| 631 |
+
"loss": 0.2327,
|
| 632 |
+
"step": 770
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.43,
|
| 636 |
+
"grad_norm": 2.971966028213501,
|
| 637 |
+
"learning_rate": 9.98547573272361e-05,
|
| 638 |
+
"loss": 0.3,
|
| 639 |
+
"step": 780
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.46,
|
| 643 |
+
"grad_norm": 3.9327046871185303,
|
| 644 |
+
"learning_rate": 9.985100630616231e-05,
|
| 645 |
+
"loss": 0.3169,
|
| 646 |
+
"step": 790
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 2.49,
|
| 650 |
+
"grad_norm": 2.108839750289917,
|
| 651 |
+
"learning_rate": 9.984720753616604e-05,
|
| 652 |
+
"loss": 0.2557,
|
| 653 |
+
"step": 800
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 2.49,
|
| 657 |
+
"eval_accuracy": 0.8401525658807212,
|
| 658 |
+
"eval_f1": 0.8300860373682543,
|
| 659 |
+
"eval_loss": 0.5152533650398254,
|
| 660 |
+
"eval_precision": 0.8326625217058278,
|
| 661 |
+
"eval_recall": 0.8401525658807212,
|
| 662 |
+
"eval_runtime": 39.7502,
|
| 663 |
+
"eval_samples_per_second": 72.553,
|
| 664 |
+
"eval_steps_per_second": 9.082,
|
| 665 |
+
"step": 800
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 2.52,
|
| 669 |
+
"grad_norm": 2.910875082015991,
|
| 670 |
+
"learning_rate": 9.98433610208859e-05,
|
| 671 |
+
"loss": 0.4144,
|
| 672 |
+
"step": 810
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 2.55,
|
| 676 |
+
"grad_norm": 3.922912359237671,
|
| 677 |
+
"learning_rate": 9.98394667640062e-05,
|
| 678 |
+
"loss": 0.2054,
|
| 679 |
+
"step": 820
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 2.59,
|
| 683 |
+
"grad_norm": 4.223613739013672,
|
| 684 |
+
"learning_rate": 9.983552476925697e-05,
|
| 685 |
+
"loss": 0.2299,
|
| 686 |
+
"step": 830
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 2.62,
|
| 690 |
+
"grad_norm": 4.242312908172607,
|
| 691 |
+
"learning_rate": 9.983153504041402e-05,
|
| 692 |
+
"loss": 0.176,
|
| 693 |
+
"step": 840
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 2.65,
|
| 697 |
+
"grad_norm": 2.051708936691284,
|
| 698 |
+
"learning_rate": 9.98274975812988e-05,
|
| 699 |
+
"loss": 0.1621,
|
| 700 |
+
"step": 850
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 2.68,
|
| 704 |
+
"grad_norm": 4.030768871307373,
|
| 705 |
+
"learning_rate": 9.982341239577855e-05,
|
| 706 |
+
"loss": 0.2601,
|
| 707 |
+
"step": 860
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 2.71,
|
| 711 |
+
"grad_norm": 3.5723698139190674,
|
| 712 |
+
"learning_rate": 9.98192794877662e-05,
|
| 713 |
+
"loss": 0.2528,
|
| 714 |
+
"step": 870
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 2.74,
|
| 718 |
+
"grad_norm": 8.439871788024902,
|
| 719 |
+
"learning_rate": 9.981509886122034e-05,
|
| 720 |
+
"loss": 0.2787,
|
| 721 |
+
"step": 880
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 2.77,
|
| 725 |
+
"grad_norm": 1.1091142892837524,
|
| 726 |
+
"learning_rate": 9.981087052014534e-05,
|
| 727 |
+
"loss": 0.2204,
|
| 728 |
+
"step": 890
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 2.8,
|
| 732 |
+
"grad_norm": 6.232639312744141,
|
| 733 |
+
"learning_rate": 9.980659446859127e-05,
|
| 734 |
+
"loss": 0.1579,
|
| 735 |
+
"step": 900
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 2.8,
|
| 739 |
+
"eval_accuracy": 0.8217753120665742,
|
| 740 |
+
"eval_f1": 0.8250088481014233,
|
| 741 |
+
"eval_loss": 0.5866798162460327,
|
| 742 |
+
"eval_precision": 0.841958803508682,
|
| 743 |
+
"eval_recall": 0.8217753120665742,
|
| 744 |
+
"eval_runtime": 39.5043,
|
| 745 |
+
"eval_samples_per_second": 73.005,
|
| 746 |
+
"eval_steps_per_second": 9.138,
|
| 747 |
+
"step": 900
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 2.83,
|
| 751 |
+
"grad_norm": 7.044712543487549,
|
| 752 |
+
"learning_rate": 9.980227071065382e-05,
|
| 753 |
+
"loss": 0.3333,
|
| 754 |
+
"step": 910
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 2.87,
|
| 758 |
+
"grad_norm": 5.107402324676514,
|
| 759 |
+
"learning_rate": 9.979789925047447e-05,
|
| 760 |
+
"loss": 0.2788,
|
| 761 |
+
"step": 920
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 2.9,
|
| 765 |
+
"grad_norm": 3.1622753143310547,
|
| 766 |
+
"learning_rate": 9.979348009224032e-05,
|
| 767 |
+
"loss": 0.3464,
|
| 768 |
+
"step": 930
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 2.93,
|
| 772 |
+
"grad_norm": 6.17850399017334,
|
| 773 |
+
"learning_rate": 9.97890132401842e-05,
|
| 774 |
+
"loss": 0.3268,
|
| 775 |
+
"step": 940
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 2.96,
|
| 779 |
+
"grad_norm": 0.5498158931732178,
|
| 780 |
+
"learning_rate": 9.978449869858458e-05,
|
| 781 |
+
"loss": 0.2121,
|
| 782 |
+
"step": 950
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 2.99,
|
| 786 |
+
"grad_norm": 5.8213300704956055,
|
| 787 |
+
"learning_rate": 9.977993647176566e-05,
|
| 788 |
+
"loss": 0.1871,
|
| 789 |
+
"step": 960
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 3.02,
|
| 793 |
+
"grad_norm": 0.513097882270813,
|
| 794 |
+
"learning_rate": 9.97753265640973e-05,
|
| 795 |
+
"loss": 0.1037,
|
| 796 |
+
"step": 970
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 3.05,
|
| 800 |
+
"grad_norm": 5.008875846862793,
|
| 801 |
+
"learning_rate": 9.977066897999499e-05,
|
| 802 |
+
"loss": 0.1076,
|
| 803 |
+
"step": 980
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 3.08,
|
| 807 |
+
"grad_norm": 2.2303969860076904,
|
| 808 |
+
"learning_rate": 9.976596372391993e-05,
|
| 809 |
+
"loss": 0.0691,
|
| 810 |
+
"step": 990
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 3.12,
|
| 814 |
+
"grad_norm": 2.022919178009033,
|
| 815 |
+
"learning_rate": 9.976121080037899e-05,
|
| 816 |
+
"loss": 0.0815,
|
| 817 |
+
"step": 1000
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 3.12,
|
| 821 |
+
"eval_accuracy": 0.8401525658807212,
|
| 822 |
+
"eval_f1": 0.8350952876276385,
|
| 823 |
+
"eval_loss": 0.621809184551239,
|
| 824 |
+
"eval_precision": 0.8475972155785173,
|
| 825 |
+
"eval_recall": 0.8401525658807212,
|
| 826 |
+
"eval_runtime": 41.1855,
|
| 827 |
+
"eval_samples_per_second": 70.025,
|
| 828 |
+
"eval_steps_per_second": 8.765,
|
| 829 |
+
"step": 1000
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 3.15,
|
| 833 |
+
"grad_norm": 3.9770946502685547,
|
| 834 |
+
"learning_rate": 9.975641021392464e-05,
|
| 835 |
+
"loss": 0.0985,
|
| 836 |
+
"step": 1010
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 3.18,
|
| 840 |
+
"grad_norm": 1.0038492679595947,
|
| 841 |
+
"learning_rate": 9.975156196915505e-05,
|
| 842 |
+
"loss": 0.1406,
|
| 843 |
+
"step": 1020
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 3.21,
|
| 847 |
+
"grad_norm": 2.54162335395813,
|
| 848 |
+
"learning_rate": 9.974666607071404e-05,
|
| 849 |
+
"loss": 0.1524,
|
| 850 |
+
"step": 1030
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 3.24,
|
| 854 |
+
"grad_norm": 3.7266845703125,
|
| 855 |
+
"learning_rate": 9.974172252329104e-05,
|
| 856 |
+
"loss": 0.0771,
|
| 857 |
+
"step": 1040
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 3.27,
|
| 861 |
+
"grad_norm": 8.810432434082031,
|
| 862 |
+
"learning_rate": 9.973673133162115e-05,
|
| 863 |
+
"loss": 0.1663,
|
| 864 |
+
"step": 1050
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 3.3,
|
| 868 |
+
"grad_norm": 0.4533999562263489,
|
| 869 |
+
"learning_rate": 9.973169250048511e-05,
|
| 870 |
+
"loss": 0.0733,
|
| 871 |
+
"step": 1060
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 3.33,
|
| 875 |
+
"grad_norm": 0.25851675868034363,
|
| 876 |
+
"learning_rate": 9.972660603470927e-05,
|
| 877 |
+
"loss": 0.1261,
|
| 878 |
+
"step": 1070
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 3.36,
|
| 882 |
+
"grad_norm": 4.003190994262695,
|
| 883 |
+
"learning_rate": 9.97214719391656e-05,
|
| 884 |
+
"loss": 0.1786,
|
| 885 |
+
"step": 1080
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 3.4,
|
| 889 |
+
"grad_norm": 3.595621109008789,
|
| 890 |
+
"learning_rate": 9.971629021877172e-05,
|
| 891 |
+
"loss": 0.0972,
|
| 892 |
+
"step": 1090
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 3.43,
|
| 896 |
+
"grad_norm": 2.7062487602233887,
|
| 897 |
+
"learning_rate": 9.971106087849084e-05,
|
| 898 |
+
"loss": 0.1075,
|
| 899 |
+
"step": 1100
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 3.43,
|
| 903 |
+
"eval_accuracy": 0.8429264909847434,
|
| 904 |
+
"eval_f1": 0.8341860243029758,
|
| 905 |
+
"eval_loss": 0.6122580170631409,
|
| 906 |
+
"eval_precision": 0.8456371193220292,
|
| 907 |
+
"eval_recall": 0.8429264909847434,
|
| 908 |
+
"eval_runtime": 39.1852,
|
| 909 |
+
"eval_samples_per_second": 73.599,
|
| 910 |
+
"eval_steps_per_second": 9.213,
|
| 911 |
+
"step": 1100
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 3.46,
|
| 915 |
+
"grad_norm": 4.331242561340332,
|
| 916 |
+
"learning_rate": 9.97057839233318e-05,
|
| 917 |
+
"loss": 0.0529,
|
| 918 |
+
"step": 1110
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 3.49,
|
| 922 |
+
"grad_norm": 4.688290119171143,
|
| 923 |
+
"learning_rate": 9.970045935834904e-05,
|
| 924 |
+
"loss": 0.1567,
|
| 925 |
+
"step": 1120
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 3.52,
|
| 929 |
+
"grad_norm": 6.66792106628418,
|
| 930 |
+
"learning_rate": 9.96950871886426e-05,
|
| 931 |
+
"loss": 0.053,
|
| 932 |
+
"step": 1130
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 3.55,
|
| 936 |
+
"grad_norm": 13.5020170211792,
|
| 937 |
+
"learning_rate": 9.968966741935813e-05,
|
| 938 |
+
"loss": 0.1816,
|
| 939 |
+
"step": 1140
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 3.58,
|
| 943 |
+
"grad_norm": 2.9301021099090576,
|
| 944 |
+
"learning_rate": 9.968420005568684e-05,
|
| 945 |
+
"loss": 0.1387,
|
| 946 |
+
"step": 1150
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 3.61,
|
| 950 |
+
"grad_norm": 0.7428218126296997,
|
| 951 |
+
"learning_rate": 9.967868510286557e-05,
|
| 952 |
+
"loss": 0.2021,
|
| 953 |
+
"step": 1160
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 3.64,
|
| 957 |
+
"grad_norm": 5.887143611907959,
|
| 958 |
+
"learning_rate": 9.967312256617671e-05,
|
| 959 |
+
"loss": 0.1325,
|
| 960 |
+
"step": 1170
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 3.68,
|
| 964 |
+
"grad_norm": 0.15455959737300873,
|
| 965 |
+
"learning_rate": 9.966751245094823e-05,
|
| 966 |
+
"loss": 0.0623,
|
| 967 |
+
"step": 1180
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 3.71,
|
| 971 |
+
"grad_norm": 11.433218002319336,
|
| 972 |
+
"learning_rate": 9.966185476255371e-05,
|
| 973 |
+
"loss": 0.099,
|
| 974 |
+
"step": 1190
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 3.74,
|
| 978 |
+
"grad_norm": 1.5371123552322388,
|
| 979 |
+
"learning_rate": 9.965614950641225e-05,
|
| 980 |
+
"loss": 0.161,
|
| 981 |
+
"step": 1200
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 3.74,
|
| 985 |
+
"eval_accuracy": 0.8509015256588072,
|
| 986 |
+
"eval_f1": 0.8419411480198592,
|
| 987 |
+
"eval_loss": 0.6438868045806885,
|
| 988 |
+
"eval_precision": 0.8478228582682292,
|
| 989 |
+
"eval_recall": 0.8509015256588072,
|
| 990 |
+
"eval_runtime": 39.7116,
|
| 991 |
+
"eval_samples_per_second": 72.624,
|
| 992 |
+
"eval_steps_per_second": 9.091,
|
| 993 |
+
"step": 1200
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 3.77,
|
| 997 |
+
"grad_norm": 5.211598873138428,
|
| 998 |
+
"learning_rate": 9.965039668798855e-05,
|
| 999 |
+
"loss": 0.1748,
|
| 1000 |
+
"step": 1210
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 3.8,
|
| 1004 |
+
"grad_norm": 6.897021770477295,
|
| 1005 |
+
"learning_rate": 9.96445963127928e-05,
|
| 1006 |
+
"loss": 0.2178,
|
| 1007 |
+
"step": 1220
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 3.83,
|
| 1011 |
+
"grad_norm": 2.0479114055633545,
|
| 1012 |
+
"learning_rate": 9.963874838638084e-05,
|
| 1013 |
+
"loss": 0.0631,
|
| 1014 |
+
"step": 1230
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 3.86,
|
| 1018 |
+
"grad_norm": 0.7689093351364136,
|
| 1019 |
+
"learning_rate": 9.963285291435398e-05,
|
| 1020 |
+
"loss": 0.1147,
|
| 1021 |
+
"step": 1240
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 3.89,
|
| 1025 |
+
"grad_norm": 0.16739872097969055,
|
| 1026 |
+
"learning_rate": 9.96269099023591e-05,
|
| 1027 |
+
"loss": 0.1705,
|
| 1028 |
+
"step": 1250
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 3.93,
|
| 1032 |
+
"grad_norm": 0.712565004825592,
|
| 1033 |
+
"learning_rate": 9.962091935608861e-05,
|
| 1034 |
+
"loss": 0.0937,
|
| 1035 |
+
"step": 1260
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 3.96,
|
| 1039 |
+
"grad_norm": 9.288028717041016,
|
| 1040 |
+
"learning_rate": 9.961488128128047e-05,
|
| 1041 |
+
"loss": 0.1466,
|
| 1042 |
+
"step": 1270
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 3.99,
|
| 1046 |
+
"grad_norm": 1.646752119064331,
|
| 1047 |
+
"learning_rate": 9.960879568371813e-05,
|
| 1048 |
+
"loss": 0.0806,
|
| 1049 |
+
"step": 1280
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 4.02,
|
| 1053 |
+
"grad_norm": 0.14091795682907104,
|
| 1054 |
+
"learning_rate": 9.960266256923055e-05,
|
| 1055 |
+
"loss": 0.0882,
|
| 1056 |
+
"step": 1290
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 4.05,
|
| 1060 |
+
"grad_norm": 0.6831271052360535,
|
| 1061 |
+
"learning_rate": 9.959648194369227e-05,
|
| 1062 |
+
"loss": 0.0446,
|
| 1063 |
+
"step": 1300
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 4.05,
|
| 1067 |
+
"eval_accuracy": 0.8561026352288488,
|
| 1068 |
+
"eval_f1": 0.8516177334392149,
|
| 1069 |
+
"eval_loss": 0.6347180008888245,
|
| 1070 |
+
"eval_precision": 0.8514533351685835,
|
| 1071 |
+
"eval_recall": 0.8561026352288488,
|
| 1072 |
+
"eval_runtime": 39.1555,
|
| 1073 |
+
"eval_samples_per_second": 73.655,
|
| 1074 |
+
"eval_steps_per_second": 9.22,
|
| 1075 |
+
"step": 1300
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 4.08,
|
| 1079 |
+
"grad_norm": 0.6896274089813232,
|
| 1080 |
+
"learning_rate": 9.959025381302325e-05,
|
| 1081 |
+
"loss": 0.0551,
|
| 1082 |
+
"step": 1310
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 4.11,
|
| 1086 |
+
"grad_norm": 1.7469240427017212,
|
| 1087 |
+
"learning_rate": 9.958397818318904e-05,
|
| 1088 |
+
"loss": 0.0172,
|
| 1089 |
+
"step": 1320
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 4.14,
|
| 1093 |
+
"grad_norm": 1.5375361442565918,
|
| 1094 |
+
"learning_rate": 9.957765506020062e-05,
|
| 1095 |
+
"loss": 0.1115,
|
| 1096 |
+
"step": 1330
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 4.17,
|
| 1100 |
+
"grad_norm": 0.022675570100545883,
|
| 1101 |
+
"learning_rate": 9.95712844501145e-05,
|
| 1102 |
+
"loss": 0.0172,
|
| 1103 |
+
"step": 1340
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 4.21,
|
| 1107 |
+
"grad_norm": 0.012827737256884575,
|
| 1108 |
+
"learning_rate": 9.956486635903263e-05,
|
| 1109 |
+
"loss": 0.0473,
|
| 1110 |
+
"step": 1350
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 4.24,
|
| 1114 |
+
"grad_norm": 9.727991104125977,
|
| 1115 |
+
"learning_rate": 9.955840079310251e-05,
|
| 1116 |
+
"loss": 0.0425,
|
| 1117 |
+
"step": 1360
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 4.27,
|
| 1121 |
+
"grad_norm": 0.1388218253850937,
|
| 1122 |
+
"learning_rate": 9.955188775851703e-05,
|
| 1123 |
+
"loss": 0.0799,
|
| 1124 |
+
"step": 1370
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 4.3,
|
| 1128 |
+
"grad_norm": 6.434169769287109,
|
| 1129 |
+
"learning_rate": 9.95453272615146e-05,
|
| 1130 |
+
"loss": 0.1215,
|
| 1131 |
+
"step": 1380
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 4.33,
|
| 1135 |
+
"grad_norm": 0.04131891950964928,
|
| 1136 |
+
"learning_rate": 9.953871930837908e-05,
|
| 1137 |
+
"loss": 0.2098,
|
| 1138 |
+
"step": 1390
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 4.36,
|
| 1142 |
+
"grad_norm": 5.073083400726318,
|
| 1143 |
+
"learning_rate": 9.953206390543979e-05,
|
| 1144 |
+
"loss": 0.1209,
|
| 1145 |
+
"step": 1400
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 4.36,
|
| 1149 |
+
"eval_accuracy": 0.8453536754507628,
|
| 1150 |
+
"eval_f1": 0.8453570551603792,
|
| 1151 |
+
"eval_loss": 0.6838424801826477,
|
| 1152 |
+
"eval_precision": 0.8481646167581471,
|
| 1153 |
+
"eval_recall": 0.8453536754507628,
|
| 1154 |
+
"eval_runtime": 40.1161,
|
| 1155 |
+
"eval_samples_per_second": 71.891,
|
| 1156 |
+
"eval_steps_per_second": 8.999,
|
| 1157 |
+
"step": 1400
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 4.39,
|
| 1161 |
+
"grad_norm": 0.1268097162246704,
|
| 1162 |
+
"learning_rate": 9.952536105907148e-05,
|
| 1163 |
+
"loss": 0.0401,
|
| 1164 |
+
"step": 1410
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 4.42,
|
| 1168 |
+
"grad_norm": 0.3008650839328766,
|
| 1169 |
+
"learning_rate": 9.951861077569438e-05,
|
| 1170 |
+
"loss": 0.0539,
|
| 1171 |
+
"step": 1420
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 4.45,
|
| 1175 |
+
"grad_norm": 1.8736006021499634,
|
| 1176 |
+
"learning_rate": 9.951181306177408e-05,
|
| 1177 |
+
"loss": 0.0375,
|
| 1178 |
+
"step": 1430
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 4.49,
|
| 1182 |
+
"grad_norm": 0.02439166232943535,
|
| 1183 |
+
"learning_rate": 9.950496792382172e-05,
|
| 1184 |
+
"loss": 0.0783,
|
| 1185 |
+
"step": 1440
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 4.52,
|
| 1189 |
+
"grad_norm": 2.347705841064453,
|
| 1190 |
+
"learning_rate": 9.949807536839375e-05,
|
| 1191 |
+
"loss": 0.0744,
|
| 1192 |
+
"step": 1450
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 4.55,
|
| 1196 |
+
"grad_norm": 0.04086657613515854,
|
| 1197 |
+
"learning_rate": 9.94911354020921e-05,
|
| 1198 |
+
"loss": 0.0466,
|
| 1199 |
+
"step": 1460
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 4.58,
|
| 1203 |
+
"grad_norm": 1.9723145961761475,
|
| 1204 |
+
"learning_rate": 9.94841480315641e-05,
|
| 1205 |
+
"loss": 0.0459,
|
| 1206 |
+
"step": 1470
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 4.61,
|
| 1210 |
+
"grad_norm": 0.05683187022805214,
|
| 1211 |
+
"learning_rate": 9.947711326350247e-05,
|
| 1212 |
+
"loss": 0.1431,
|
| 1213 |
+
"step": 1480
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 4.64,
|
| 1217 |
+
"grad_norm": 3.9203383922576904,
|
| 1218 |
+
"learning_rate": 9.947003110464533e-05,
|
| 1219 |
+
"loss": 0.0488,
|
| 1220 |
+
"step": 1490
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 4.67,
|
| 1224 |
+
"grad_norm": 1.1523628234863281,
|
| 1225 |
+
"learning_rate": 9.946290156177625e-05,
|
| 1226 |
+
"loss": 0.006,
|
| 1227 |
+
"step": 1500
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 4.67,
|
| 1231 |
+
"eval_accuracy": 0.8394590846047156,
|
| 1232 |
+
"eval_f1": 0.8362644621553696,
|
| 1233 |
+
"eval_loss": 0.7756162285804749,
|
| 1234 |
+
"eval_precision": 0.8375320979339962,
|
| 1235 |
+
"eval_recall": 0.8394590846047156,
|
| 1236 |
+
"eval_runtime": 40.2425,
|
| 1237 |
+
"eval_samples_per_second": 71.666,
|
| 1238 |
+
"eval_steps_per_second": 8.971,
|
| 1239 |
+
"step": 1500
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 4.7,
|
| 1243 |
+
"grad_norm": 10.209505081176758,
|
| 1244 |
+
"learning_rate": 9.945572464172408e-05,
|
| 1245 |
+
"loss": 0.0775,
|
| 1246 |
+
"step": 1510
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 4.74,
|
| 1250 |
+
"grad_norm": 1.9617162942886353,
|
| 1251 |
+
"learning_rate": 9.944850035136317e-05,
|
| 1252 |
+
"loss": 0.0089,
|
| 1253 |
+
"step": 1520
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 4.77,
|
| 1257 |
+
"grad_norm": 4.741919994354248,
|
| 1258 |
+
"learning_rate": 9.944122869761312e-05,
|
| 1259 |
+
"loss": 0.0835,
|
| 1260 |
+
"step": 1530
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 4.8,
|
| 1264 |
+
"grad_norm": 8.549369812011719,
|
| 1265 |
+
"learning_rate": 9.943390968743899e-05,
|
| 1266 |
+
"loss": 0.0569,
|
| 1267 |
+
"step": 1540
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 4.83,
|
| 1271 |
+
"grad_norm": 0.6695631146430969,
|
| 1272 |
+
"learning_rate": 9.942654332785117e-05,
|
| 1273 |
+
"loss": 0.1164,
|
| 1274 |
+
"step": 1550
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 4.86,
|
| 1278 |
+
"grad_norm": 4.1318278312683105,
|
| 1279 |
+
"learning_rate": 9.94191296259054e-05,
|
| 1280 |
+
"loss": 0.042,
|
| 1281 |
+
"step": 1560
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 4.89,
|
| 1285 |
+
"grad_norm": 6.556665897369385,
|
| 1286 |
+
"learning_rate": 9.941166858870275e-05,
|
| 1287 |
+
"loss": 0.045,
|
| 1288 |
+
"step": 1570
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 4.92,
|
| 1292 |
+
"grad_norm": 13.292597770690918,
|
| 1293 |
+
"learning_rate": 9.940416022338966e-05,
|
| 1294 |
+
"loss": 0.0682,
|
| 1295 |
+
"step": 1580
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 4.95,
|
| 1299 |
+
"grad_norm": 7.545276165008545,
|
| 1300 |
+
"learning_rate": 9.939660453715789e-05,
|
| 1301 |
+
"loss": 0.1476,
|
| 1302 |
+
"step": 1590
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 4.98,
|
| 1306 |
+
"grad_norm": 4.052639961242676,
|
| 1307 |
+
"learning_rate": 9.93890015372445e-05,
|
| 1308 |
+
"loss": 0.0219,
|
| 1309 |
+
"step": 1600
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 4.98,
|
| 1313 |
+
"eval_accuracy": 0.8280166435506241,
|
| 1314 |
+
"eval_f1": 0.8270572625886861,
|
| 1315 |
+
"eval_loss": 0.8814780116081238,
|
| 1316 |
+
"eval_precision": 0.8368468785461194,
|
| 1317 |
+
"eval_recall": 0.8280166435506241,
|
| 1318 |
+
"eval_runtime": 39.3962,
|
| 1319 |
+
"eval_samples_per_second": 73.205,
|
| 1320 |
+
"eval_steps_per_second": 9.163,
|
| 1321 |
+
"step": 1600
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 5.02,
|
| 1325 |
+
"grad_norm": 0.7045537829399109,
|
| 1326 |
+
"learning_rate": 9.93813512309319e-05,
|
| 1327 |
+
"loss": 0.102,
|
| 1328 |
+
"step": 1610
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 5.05,
|
| 1332 |
+
"grad_norm": 0.47862136363983154,
|
| 1333 |
+
"learning_rate": 9.937365362554782e-05,
|
| 1334 |
+
"loss": 0.0198,
|
| 1335 |
+
"step": 1620
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 5.08,
|
| 1339 |
+
"grad_norm": 0.06051962450146675,
|
| 1340 |
+
"learning_rate": 9.936590872846529e-05,
|
| 1341 |
+
"loss": 0.029,
|
| 1342 |
+
"step": 1630
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 5.11,
|
| 1346 |
+
"grad_norm": 8.44522762298584,
|
| 1347 |
+
"learning_rate": 9.935811654710257e-05,
|
| 1348 |
+
"loss": 0.0077,
|
| 1349 |
+
"step": 1640
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 5.14,
|
| 1353 |
+
"grad_norm": 0.15062321722507477,
|
| 1354 |
+
"learning_rate": 9.935027708892333e-05,
|
| 1355 |
+
"loss": 0.011,
|
| 1356 |
+
"step": 1650
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 5.17,
|
| 1360 |
+
"grad_norm": 0.006027880124747753,
|
| 1361 |
+
"learning_rate": 9.93423903614364e-05,
|
| 1362 |
+
"loss": 0.0524,
|
| 1363 |
+
"step": 1660
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 5.2,
|
| 1367 |
+
"grad_norm": 0.09458424896001816,
|
| 1368 |
+
"learning_rate": 9.933445637219598e-05,
|
| 1369 |
+
"loss": 0.074,
|
| 1370 |
+
"step": 1670
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 5.23,
|
| 1374 |
+
"grad_norm": 4.973755836486816,
|
| 1375 |
+
"learning_rate": 9.932647512880151e-05,
|
| 1376 |
+
"loss": 0.1273,
|
| 1377 |
+
"step": 1680
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 5.26,
|
| 1381 |
+
"grad_norm": 5.976691246032715,
|
| 1382 |
+
"learning_rate": 9.931844663889766e-05,
|
| 1383 |
+
"loss": 0.007,
|
| 1384 |
+
"step": 1690
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 5.3,
|
| 1388 |
+
"grad_norm": 14.914401054382324,
|
| 1389 |
+
"learning_rate": 9.931037091017441e-05,
|
| 1390 |
+
"loss": 0.0616,
|
| 1391 |
+
"step": 1700
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 5.3,
|
| 1395 |
+
"eval_accuracy": 0.8155339805825242,
|
| 1396 |
+
"eval_f1": 0.7863981529949345,
|
| 1397 |
+
"eval_loss": 1.0824644565582275,
|
| 1398 |
+
"eval_precision": 0.8128168319440793,
|
| 1399 |
+
"eval_recall": 0.8155339805825242,
|
| 1400 |
+
"eval_runtime": 38.9135,
|
| 1401 |
+
"eval_samples_per_second": 74.113,
|
| 1402 |
+
"eval_steps_per_second": 9.277,
|
| 1403 |
+
"step": 1700
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 5.33,
|
| 1407 |
+
"grad_norm": 0.02390890195965767,
|
| 1408 |
+
"learning_rate": 9.930224795036694e-05,
|
| 1409 |
+
"loss": 0.009,
|
| 1410 |
+
"step": 1710
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 5.36,
|
| 1414 |
+
"grad_norm": 6.92083740234375,
|
| 1415 |
+
"learning_rate": 9.929407776725565e-05,
|
| 1416 |
+
"loss": 0.118,
|
| 1417 |
+
"step": 1720
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 5.39,
|
| 1421 |
+
"grad_norm": 0.024119729176163673,
|
| 1422 |
+
"learning_rate": 9.928586036866628e-05,
|
| 1423 |
+
"loss": 0.0051,
|
| 1424 |
+
"step": 1730
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 5.42,
|
| 1428 |
+
"grad_norm": 8.526777267456055,
|
| 1429 |
+
"learning_rate": 9.927759576246969e-05,
|
| 1430 |
+
"loss": 0.1098,
|
| 1431 |
+
"step": 1740
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 5.45,
|
| 1435 |
+
"grad_norm": 2.77993106842041,
|
| 1436 |
+
"learning_rate": 9.926928395658198e-05,
|
| 1437 |
+
"loss": 0.1047,
|
| 1438 |
+
"step": 1750
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 5.48,
|
| 1442 |
+
"grad_norm": 0.030404316261410713,
|
| 1443 |
+
"learning_rate": 9.926092495896446e-05,
|
| 1444 |
+
"loss": 0.0495,
|
| 1445 |
+
"step": 1760
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 5.51,
|
| 1449 |
+
"grad_norm": 0.07882791757583618,
|
| 1450 |
+
"learning_rate": 9.925251877762369e-05,
|
| 1451 |
+
"loss": 0.0609,
|
| 1452 |
+
"step": 1770
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 5.55,
|
| 1456 |
+
"grad_norm": 1.615186095237732,
|
| 1457 |
+
"learning_rate": 9.924406542061135e-05,
|
| 1458 |
+
"loss": 0.0399,
|
| 1459 |
+
"step": 1780
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 5.58,
|
| 1463 |
+
"grad_norm": 5.359433650970459,
|
| 1464 |
+
"learning_rate": 9.923556489602436e-05,
|
| 1465 |
+
"loss": 0.032,
|
| 1466 |
+
"step": 1790
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 5.61,
|
| 1470 |
+
"grad_norm": 1.139506459236145,
|
| 1471 |
+
"learning_rate": 9.922701721200479e-05,
|
| 1472 |
+
"loss": 0.0305,
|
| 1473 |
+
"step": 1800
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 5.61,
|
| 1477 |
+
"eval_accuracy": 0.840499306518724,
|
| 1478 |
+
"eval_f1": 0.8366786621950907,
|
| 1479 |
+
"eval_loss": 0.8289232850074768,
|
| 1480 |
+
"eval_precision": 0.8427815878781533,
|
| 1481 |
+
"eval_recall": 0.840499306518724,
|
| 1482 |
+
"eval_runtime": 40.1613,
|
| 1483 |
+
"eval_samples_per_second": 71.81,
|
| 1484 |
+
"eval_steps_per_second": 8.989,
|
| 1485 |
+
"step": 1800
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 5.61,
|
| 1489 |
+
"step": 1800,
|
| 1490 |
+
"total_flos": 2.2287694956200755e+18,
|
| 1491 |
+
"train_loss": 0.2732895821850333,
|
| 1492 |
+
"train_runtime": 1429.5622,
|
| 1493 |
+
"train_samples_per_second": 358.711,
|
| 1494 |
+
"train_steps_per_second": 22.454
|
| 1495 |
+
}
|
| 1496 |
+
],
|
| 1497 |
+
"logging_steps": 10,
|
| 1498 |
+
"max_steps": 32100,
|
| 1499 |
+
"num_input_tokens_seen": 0,
|
| 1500 |
+
"num_train_epochs": 100,
|
| 1501 |
+
"save_steps": 100,
|
| 1502 |
+
"total_flos": 2.2287694956200755e+18,
|
| 1503 |
+
"train_batch_size": 16,
|
| 1504 |
+
"trial_name": null,
|
| 1505 |
+
"trial_params": null
|
| 1506 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aab637bd8e8c36001550bf35ab0a6ca3623a95000dfa39cb3d55b23c77bd97fc
|
| 3 |
size 4920
|