Training in progress, epoch 6, 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 sha256:71e58c28154dffcb30f14b50844f6977937562e99cf1d10c140ff2f29744edc3
|
| 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:d25fd32e37629b8a81718aa4981261247ecec1e7d3a8fba9275fad1fd079af7c
|
| 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 sha256:2b00198c0a76d2b134e58977666d57ae1f7de5e2dfe7b151a00fd2e5abad3451
|
| 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 sha256:136c120d5cb1bfe293fa4c534feee6054bd3200d5f744d350104a8b80432a125
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "./opt_trained/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,
|
|
@@ -61,6 +61,14 @@
|
|
| 61 |
"eval_samples_per_second": 37.182,
|
| 62 |
"eval_steps_per_second": 9.295,
|
| 63 |
"step": 1005
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
}
|
| 65 |
],
|
| 66 |
"logging_steps": 500,
|
|
@@ -80,7 +88,7 @@
|
|
| 80 |
"attributes": {}
|
| 81 |
}
|
| 82 |
},
|
| 83 |
-
"total_flos":
|
| 84 |
"train_batch_size": 16,
|
| 85 |
"trial_name": null,
|
| 86 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.0030088424682617,
|
| 3 |
+
"best_model_checkpoint": "./opt_trained/checkpoint-1206",
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1206,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 61 |
"eval_samples_per_second": 37.182,
|
| 62 |
"eval_steps_per_second": 9.295,
|
| 63 |
"step": 1005
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 6.0,
|
| 67 |
+
"eval_loss": 1.0030088424682617,
|
| 68 |
+
"eval_runtime": 76.8319,
|
| 69 |
+
"eval_samples_per_second": 37.172,
|
| 70 |
+
"eval_steps_per_second": 9.293,
|
| 71 |
+
"step": 1206
|
| 72 |
}
|
| 73 |
],
|
| 74 |
"logging_steps": 500,
|
|
|
|
| 88 |
"attributes": {}
|
| 89 |
}
|
| 90 |
},
|
| 91 |
+
"total_flos": 4.059810657792e+16,
|
| 92 |
"train_batch_size": 16,
|
| 93 |
"trial_name": null,
|
| 94 |
"trial_params": null
|