Training in progress, step 6270, 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 sha256:314f2a5e64d5115dac48a255478d174cde2dd5e04a593b668d2e3dd8245f2bff
|
| 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 sha256:0852c8f46075a8157671b37f2cc4f77818afc267bfe8942859e55eacc8de5bca
|
| 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 sha256:71d23011c78f5f21d1e63814cdc204cda9b819a8434aca9a35ae422e421a056b
|
| 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": 48.
|
| 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,
|
|
@@ -11276,6 +11276,24 @@
|
|
| 11276 |
"mean_token_accuracy": 0.6539576113224029,
|
| 11277 |
"num_tokens": 22829928.0,
|
| 11278 |
"step": 6260
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11279 |
}
|
| 11280 |
],
|
| 11281 |
"logging_steps": 5,
|
|
@@ -11295,7 +11313,7 @@
|
|
| 11295 |
"attributes": {}
|
| 11296 |
}
|
| 11297 |
},
|
| 11298 |
-
"total_flos": 1.
|
| 11299 |
"train_batch_size": 4,
|
| 11300 |
"trial_name": null,
|
| 11301 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 48.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6270,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11276 |
"mean_token_accuracy": 0.6539576113224029,
|
| 11277 |
"num_tokens": 22829928.0,
|
| 11278 |
"step": 6260
|
| 11279 |
+
},
|
| 11280 |
+
{
|
| 11281 |
+
"epoch": 48.19230769230769,
|
| 11282 |
+
"grad_norm": 0.0,
|
| 11283 |
+
"learning_rate": 1.868e-05,
|
| 11284 |
+
"loss": 1.7318,
|
| 11285 |
+
"mean_token_accuracy": 0.651011449098587,
|
| 11286 |
+
"num_tokens": 22848013.0,
|
| 11287 |
+
"step": 6265
|
| 11288 |
+
},
|
| 11289 |
+
{
|
| 11290 |
+
"epoch": 48.23076923076923,
|
| 11291 |
+
"grad_norm": 0.0,
|
| 11292 |
+
"learning_rate": 1.8655e-05,
|
| 11293 |
+
"loss": 1.705,
|
| 11294 |
+
"mean_token_accuracy": 0.6651150584220886,
|
| 11295 |
+
"num_tokens": 22866785.0,
|
| 11296 |
+
"step": 6270
|
| 11297 |
}
|
| 11298 |
],
|
| 11299 |
"logging_steps": 5,
|
|
|
|
| 11313 |
"attributes": {}
|
| 11314 |
}
|
| 11315 |
},
|
| 11316 |
+
"total_flos": 1.1591028515708928e+18,
|
| 11317 |
"train_batch_size": 4,
|
| 11318 |
"trial_name": null,
|
| 11319 |
"trial_params": null
|