Training in progress, epoch 9, 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 500979600
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36d1741f1c2fdfc1389a2054eac709f84a531e3af46a79b487f335e795223ebb
|
| 3 |
size 500979600
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1002078330
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a4132076705e8c6d24d8425e81772d9bf33bee1eaec44d5be4091c1caeb53bb
|
| 3 |
size 1002078330
|
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 sha256:79f99c3423a1a837c0044fd54e06d7d82d98d4715055617568b6a0802f4f5619
|
| 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:c248f64379de1457aeba2dcf4a115bd43fe65fcd6c7b097c336db9e1a90ff441
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "./opt_trained3/checkpoint-
|
| 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,
|
|
@@ -71,6 +71,14 @@
|
|
| 71 |
"eval_samples_per_second": 50.368,
|
| 72 |
"eval_steps_per_second": 12.592,
|
| 73 |
"step": 120
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 74 |
}
|
| 75 |
],
|
| 76 |
"logging_steps": 500,
|
|
@@ -90,7 +98,7 @@
|
|
| 90 |
"attributes": {}
|
| 91 |
}
|
| 92 |
},
|
| 93 |
-
"total_flos":
|
| 94 |
"train_batch_size": 24,
|
| 95 |
"trial_name": null,
|
| 96 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.670530378818512,
|
| 3 |
+
"best_model_checkpoint": "./opt_trained3/checkpoint-135",
|
| 4 |
+
"epoch": 9.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 135,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 71 |
"eval_samples_per_second": 50.368,
|
| 72 |
"eval_steps_per_second": 12.592,
|
| 73 |
"step": 120
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 9.0,
|
| 77 |
+
"eval_loss": 0.670530378818512,
|
| 78 |
+
"eval_runtime": 5.9504,
|
| 79 |
+
"eval_samples_per_second": 50.417,
|
| 80 |
+
"eval_steps_per_second": 12.604,
|
| 81 |
+
"step": 135
|
| 82 |
}
|
| 83 |
],
|
| 84 |
"logging_steps": 500,
|
|
|
|
| 98 |
"attributes": {}
|
| 99 |
}
|
| 100 |
},
|
| 101 |
+
"total_flos": 5009450520960000.0,
|
| 102 |
"train_batch_size": 24,
|
| 103 |
"trial_name": null,
|
| 104 |
"trial_params": null
|