Training in progress, step 20, checkpoint
Browse files
last-checkpoint/adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 67201802
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57506f2ec5f5fbf3795e5b55aca16c079cdeae6c931a76d683369e9c04454547
|
| 3 |
size 67201802
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 134433530
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a7c04278a39bd4e46b130581fdd7f5514c8ef922b45e41c167f8c8faddf737f
|
| 3 |
size 134433530
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e76a7a85a32d26c039a5707071a00913245aa032271177ed81e56c351754849
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2bc30782c80f39b95ece53e16ed533d0eb1d775796dc4d2c39691e355b142ab4
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "/content/results/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 10,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -22,13 +22,28 @@
|
|
| 22 |
"eval_samples_per_second": 0.762,
|
| 23 |
"eval_steps_per_second": 0.762,
|
| 24 |
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
}
|
| 26 |
],
|
| 27 |
"logging_steps": 10,
|
| 28 |
"max_steps": 4158,
|
| 29 |
"num_train_epochs": 1,
|
| 30 |
"save_steps": 10,
|
| 31 |
-
"total_flos":
|
| 32 |
"trial_name": null,
|
| 33 |
"trial_params": null
|
| 34 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.3644671440124512,
|
| 3 |
+
"best_model_checkpoint": "/content/results/checkpoint-20",
|
| 4 |
+
"epoch": 0.00481000481000481,
|
| 5 |
"eval_steps": 10,
|
| 6 |
+
"global_step": 20,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 22 |
"eval_samples_per_second": 0.762,
|
| 23 |
"eval_steps_per_second": 0.762,
|
| 24 |
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0,
|
| 28 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 29 |
+
"loss": 1.3393,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0,
|
| 34 |
+
"eval_jit_compilation_time": 1.867,
|
| 35 |
+
"eval_loss": 1.3644671440124512,
|
| 36 |
+
"eval_runtime": 55.1385,
|
| 37 |
+
"eval_samples_per_second": 0.762,
|
| 38 |
+
"eval_steps_per_second": 0.762,
|
| 39 |
+
"step": 20
|
| 40 |
}
|
| 41 |
],
|
| 42 |
"logging_steps": 10,
|
| 43 |
"max_steps": 4158,
|
| 44 |
"num_train_epochs": 1,
|
| 45 |
"save_steps": 10,
|
| 46 |
+
"total_flos": 690644086185984.0,
|
| 47 |
"trial_name": null,
|
| 48 |
"trial_params": null
|
| 49 |
}
|