Training in progress, epoch 3, 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:aa7f89e99a450ce748bcd5fa73e058fb60ddae4d1ec2e538d0dac52525ce0c6b
|
| 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:d1db75657c647a9527e5e149a0de8f73a90e243a0696776e3a6f20371509c905
|
| 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 sha256:73cd336dbfdad89399bec06133db2c08a18807b2944b35f34c3ce633cafc07c1
|
| 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:cc7789bd524a50ae91576dd3944cbc7b88e44f5f7d025656e2190fd21374ec1e
|
| 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,
|
|
@@ -38,6 +38,14 @@
|
|
| 38 |
"eval_samples_per_second": 13.817,
|
| 39 |
"eval_steps_per_second": 1.733,
|
| 40 |
"step": 603
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
}
|
| 42 |
],
|
| 43 |
"logging_steps": 500,
|
|
@@ -57,7 +65,7 @@
|
|
| 57 |
"attributes": {}
|
| 58 |
}
|
| 59 |
},
|
| 60 |
-
"total_flos":
|
| 61 |
"train_batch_size": 12,
|
| 62 |
"trial_name": null,
|
| 63 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 6.1056413650512695,
|
| 3 |
"best_model_checkpoint": "./opt_trained1/checkpoint-201",
|
| 4 |
+
"epoch": 3.9956656346749226,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 804,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 38 |
"eval_samples_per_second": 13.817,
|
| 39 |
"eval_steps_per_second": 1.733,
|
| 40 |
"step": 603
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 3.9956656346749226,
|
| 44 |
+
"eval_loss": 8.359700202941895,
|
| 45 |
+
"eval_runtime": 155.7968,
|
| 46 |
+
"eval_samples_per_second": 13.819,
|
| 47 |
+
"eval_steps_per_second": 1.733,
|
| 48 |
+
"step": 804
|
| 49 |
}
|
| 50 |
],
|
| 51 |
"logging_steps": 500,
|
|
|
|
| 65 |
"attributes": {}
|
| 66 |
}
|
| 67 |
},
|
| 68 |
+
"total_flos": 5.446962393985843e+16,
|
| 69 |
"train_batch_size": 12,
|
| 70 |
"trial_name": null,
|
| 71 |
"trial_params": null
|