Training in progress, epoch 1, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1324830880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34d30cd2d3ba0a118bc44f9ffe1d61ae733ab7391c3505d0fc6142257dd9d870
|
| 3 |
size 1324830880
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2649896030
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68bd918839235450e7016529117061462575bd438ab59c7e4f497daf14c0a307
|
| 3 |
size 2649896030
|
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 sha256:7951b102fa0035de952f0290adc9e70cb93d5096767428189697cc1180764452
|
| 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 sha256:1f2bebcb74fda4a7dc9be8feacd74ba4435f508244bde8e9024e695137478735
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 6.1056413650512695,
|
| 3 |
"best_model_checkpoint": "./opt_trained1/checkpoint-201",
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -15,6 +15,14 @@
|
|
| 15 |
"eval_samples_per_second": 13.809,
|
| 16 |
"eval_steps_per_second": 1.732,
|
| 17 |
"step": 201
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
}
|
| 19 |
],
|
| 20 |
"logging_steps": 500,
|
|
@@ -34,7 +42,7 @@
|
|
| 34 |
"attributes": {}
|
| 35 |
}
|
| 36 |
},
|
| 37 |
-
"total_flos":
|
| 38 |
"train_batch_size": 12,
|
| 39 |
"trial_name": null,
|
| 40 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 6.1056413650512695,
|
| 3 |
"best_model_checkpoint": "./opt_trained1/checkpoint-201",
|
| 4 |
+
"epoch": 1.9956656346749226,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 402,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 15 |
"eval_samples_per_second": 13.809,
|
| 16 |
"eval_steps_per_second": 1.732,
|
| 17 |
"step": 201
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.9956656346749226,
|
| 21 |
+
"eval_loss": 8.50473690032959,
|
| 22 |
+
"eval_runtime": 155.7389,
|
| 23 |
+
"eval_samples_per_second": 13.824,
|
| 24 |
+
"eval_steps_per_second": 1.734,
|
| 25 |
+
"step": 402
|
| 26 |
}
|
| 27 |
],
|
| 28 |
"logging_steps": 500,
|
|
|
|
| 42 |
"attributes": {}
|
| 43 |
}
|
| 44 |
},
|
| 45 |
+
"total_flos": 2.7234811969929216e+16,
|
| 46 |
"train_batch_size": 12,
|
| 47 |
"trial_name": null,
|
| 48 |
"trial_params": null
|