Training in progress, step 1110, 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 sha256:2fa77cdc09a38c6d04df3fa509596a32a1c3a35094ccbf11f249bcd5982f3ce4
|
| 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 sha256:2165031fe1a80343379e73710a164891819c16b81190509c9d5c4522be6409c4
|
| 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 sha256:8ce16ffd942d45b89b03798ef5c25913228d1152985bf26fe3a92d9ca52caf7e
|
| 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": 8.
|
| 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,
|
|
@@ -1988,6 +1988,24 @@
|
|
| 1988 |
"mean_token_accuracy": 0.6398821622133255,
|
| 1989 |
"num_tokens": 4011349.0,
|
| 1990 |
"step": 1100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1991 |
}
|
| 1992 |
],
|
| 1993 |
"logging_steps": 5,
|
|
@@ -2007,7 +2025,7 @@
|
|
| 2007 |
"attributes": {}
|
| 2008 |
}
|
| 2009 |
},
|
| 2010 |
-
"total_flos": 2.
|
| 2011 |
"train_batch_size": 4,
|
| 2012 |
"trial_name": null,
|
| 2013 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 8.538461538461538,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1110,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1988 |
"mean_token_accuracy": 0.6398821622133255,
|
| 1989 |
"num_tokens": 4011349.0,
|
| 1990 |
"step": 1100
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 8.5,
|
| 1994 |
+
"grad_norm": 0.0,
|
| 1995 |
+
"learning_rate": 4.448e-05,
|
| 1996 |
+
"loss": 1.784,
|
| 1997 |
+
"mean_token_accuracy": 0.6396127253770828,
|
| 1998 |
+
"num_tokens": 4029422.0,
|
| 1999 |
+
"step": 1105
|
| 2000 |
+
},
|
| 2001 |
+
{
|
| 2002 |
+
"epoch": 8.538461538461538,
|
| 2003 |
+
"grad_norm": 0.0,
|
| 2004 |
+
"learning_rate": 4.4455e-05,
|
| 2005 |
+
"loss": 1.7972,
|
| 2006 |
+
"mean_token_accuracy": 0.6439882755279541,
|
| 2007 |
+
"num_tokens": 4047081.0,
|
| 2008 |
+
"step": 1110
|
| 2009 |
}
|
| 2010 |
],
|
| 2011 |
"logging_steps": 5,
|
|
|
|
| 2025 |
"attributes": {}
|
| 2026 |
}
|
| 2027 |
},
|
| 2028 |
+
"total_flos": 2.0519441894375424e+17,
|
| 2029 |
"train_batch_size": 4,
|
| 2030 |
"trial_name": null,
|
| 2031 |
"trial_params": null
|