Training in progress, step 3920, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9fe74d7cfe12aee6890166fc046c3b1e990810bb679c95e48dc56901d6dcbb8
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec92fbdf58b3219cd25d78abca90360bc99cf875e630f52c1a82592297a6bd31
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a324f5da75ced0785694b3a4d31b40aeb0ef82cae858b53d242580d4880654e5
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 30.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -7046,6 +7046,24 @@
|
|
| 7046 |
"mean_token_accuracy": 0.6612500458955765,
|
| 7047 |
"num_tokens": 14260761.0,
|
| 7048 |
"step": 3910
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7049 |
}
|
| 7050 |
],
|
| 7051 |
"logging_steps": 5,
|
|
@@ -7065,7 +7083,7 @@
|
|
| 7065 |
"attributes": {}
|
| 7066 |
}
|
| 7067 |
},
|
| 7068 |
-
"total_flos": 7.
|
| 7069 |
"train_batch_size": 4,
|
| 7070 |
"trial_name": null,
|
| 7071 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 30.153846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3920,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7046 |
"mean_token_accuracy": 0.6612500458955765,
|
| 7047 |
"num_tokens": 14260761.0,
|
| 7048 |
"step": 3910
|
| 7049 |
+
},
|
| 7050 |
+
{
|
| 7051 |
+
"epoch": 30.115384615384617,
|
| 7052 |
+
"grad_norm": 0.0,
|
| 7053 |
+
"learning_rate": 3.0430000000000002e-05,
|
| 7054 |
+
"loss": 1.7619,
|
| 7055 |
+
"mean_token_accuracy": 0.6461090564727783,
|
| 7056 |
+
"num_tokens": 14278765.0,
|
| 7057 |
+
"step": 3915
|
| 7058 |
+
},
|
| 7059 |
+
{
|
| 7060 |
+
"epoch": 30.153846153846153,
|
| 7061 |
+
"grad_norm": 0.0,
|
| 7062 |
+
"learning_rate": 3.0405e-05,
|
| 7063 |
+
"loss": 1.7833,
|
| 7064 |
+
"mean_token_accuracy": 0.6493801504373551,
|
| 7065 |
+
"num_tokens": 14296313.0,
|
| 7066 |
+
"step": 3920
|
| 7067 |
}
|
| 7068 |
],
|
| 7069 |
"logging_steps": 5,
|
|
|
|
| 7083 |
"attributes": {}
|
| 7084 |
}
|
| 7085 |
},
|
| 7086 |
+
"total_flos": 7.245011465566618e+17,
|
| 7087 |
"train_batch_size": 4,
|
| 7088 |
"trial_name": null,
|
| 7089 |
"trial_params": null
|