Training in progress, step 2830, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:650ed8c23d47b8ebd88f36b3cd829f02b4b679b60ee724adc0792a7246e65d92
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:283b1c188c528c3c10032eecad401f7029e1348b6b5910eeba421160b79bbfed
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bee856fe5329f3ad516744ee8fc431b07377f6fcc5bd5a8dafed331177b518b
|
| 3 |
size 14645
|
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 sha256:086b65d447fc5b1474eb59a6ae804b02b01e1add8bc0381b3ff9aada747c5b0a
|
| 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": 0.
|
| 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,
|
|
@@ -2838,6 +2838,16 @@
|
|
| 2838 |
"mean_token_accuracy": 0.7392091482877732,
|
| 2839 |
"num_tokens": 13115184.0,
|
| 2840 |
"step": 2820
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2841 |
}
|
| 2842 |
],
|
| 2843 |
"logging_steps": 10,
|
|
@@ -2857,7 +2867,7 @@
|
|
| 2857 |
"attributes": {}
|
| 2858 |
}
|
| 2859 |
},
|
| 2860 |
-
"total_flos": 6.
|
| 2861 |
"train_batch_size": 4,
|
| 2862 |
"trial_name": null,
|
| 2863 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.6037333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2830,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2838 |
"mean_token_accuracy": 0.7392091482877732,
|
| 2839 |
"num_tokens": 13115184.0,
|
| 2840 |
"step": 2820
|
| 2841 |
+
},
|
| 2842 |
+
{
|
| 2843 |
+
"entropy": 0.9755672253668308,
|
| 2844 |
+
"epoch": 0.6037333333333333,
|
| 2845 |
+
"grad_norm": 0.24116092920303345,
|
| 2846 |
+
"learning_rate": 8.203466957668215e-05,
|
| 2847 |
+
"loss": 1.0671576499938964,
|
| 2848 |
+
"mean_token_accuracy": 0.7598815195262432,
|
| 2849 |
+
"num_tokens": 13163748.0,
|
| 2850 |
+
"step": 2830
|
| 2851 |
}
|
| 2852 |
],
|
| 2853 |
"logging_steps": 10,
|
|
|
|
| 2867 |
"attributes": {}
|
| 2868 |
}
|
| 2869 |
},
|
| 2870 |
+
"total_flos": 6.238848191423693e+16,
|
| 2871 |
"train_batch_size": 4,
|
| 2872 |
"trial_name": null,
|
| 2873 |
"trial_params": null
|