Upload 8 files
Browse files- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +44 -0
- training_args.bin +3 -0
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:452a1db43297cf6475a5b3c80721fe8c2b94eca0884dca6fa6f103db60f01b52
|
| 3 |
+
size 33661637
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b388c49819d70d539656b87f2aea94ea2a512987b6f78aae915aab6fdada8c8
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f81ed21cd77141ef96eb5ba8894e38264c867c2905da82f5f6597a0b6ed4aa9
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.3832016885280609,
|
| 3 |
+
"best_model_checkpoint": "./lora-html/checkpoint-100",
|
| 4 |
+
"epoch": 5.2631578947368425,
|
| 5 |
+
"global_step": 100,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 2.63,
|
| 12 |
+
"learning_rate": 0.00014399999999999998,
|
| 13 |
+
"loss": 1.0623,
|
| 14 |
+
"step": 50
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 2.63,
|
| 18 |
+
"eval_loss": 0.5735694766044617,
|
| 19 |
+
"eval_runtime": 2.0662,
|
| 20 |
+
"eval_samples_per_second": 9.68,
|
| 21 |
+
"eval_steps_per_second": 1.452,
|
| 22 |
+
"step": 50
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 5.26,
|
| 26 |
+
"learning_rate": 0.000294,
|
| 27 |
+
"loss": 0.4702,
|
| 28 |
+
"step": 100
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 5.26,
|
| 32 |
+
"eval_loss": 0.3832016885280609,
|
| 33 |
+
"eval_runtime": 2.2136,
|
| 34 |
+
"eval_samples_per_second": 9.035,
|
| 35 |
+
"eval_steps_per_second": 1.355,
|
| 36 |
+
"step": 100
|
| 37 |
+
}
|
| 38 |
+
],
|
| 39 |
+
"max_steps": 100,
|
| 40 |
+
"num_train_epochs": 6,
|
| 41 |
+
"total_flos": 3.135836567764992e+16,
|
| 42 |
+
"trial_name": null,
|
| 43 |
+
"trial_params": null
|
| 44 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a9019be1ca636e4fc0d09b0580417776cf6c8066af4844147f82034d4ab6d27
|
| 3 |
+
size 3899
|