Training in progress, step 8370, 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:d8ef172578a42d0b44c089180147000913e5c0920d9ba7b17d29489b776b0302
|
| 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:afcedd03d85cb0ce50613605e2f09ea5df1ef5b1666c9d82dca13497cb2e66d3
|
| 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 sha256:110ff4542a5778f6138edc4f996fed7325a17ae7c8874e6f39900a69910fc263
|
| 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": 64.
|
| 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,
|
|
@@ -15056,6 +15056,24 @@
|
|
| 15056 |
"mean_token_accuracy": 0.648283451795578,
|
| 15057 |
"num_tokens": 30490316.0,
|
| 15058 |
"step": 8360
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15059 |
}
|
| 15060 |
],
|
| 15061 |
"logging_steps": 5,
|
|
@@ -15075,7 +15093,7 @@
|
|
| 15075 |
"attributes": {}
|
| 15076 |
}
|
| 15077 |
},
|
| 15078 |
-
"total_flos": 1.
|
| 15079 |
"train_batch_size": 4,
|
| 15080 |
"trial_name": null,
|
| 15081 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 64.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8370,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15056 |
"mean_token_accuracy": 0.648283451795578,
|
| 15057 |
"num_tokens": 30490316.0,
|
| 15058 |
"step": 8360
|
| 15059 |
+
},
|
| 15060 |
+
{
|
| 15061 |
+
"epoch": 64.34615384615384,
|
| 15062 |
+
"grad_norm": 0.0,
|
| 15063 |
+
"learning_rate": 8.18e-06,
|
| 15064 |
+
"loss": 1.7349,
|
| 15065 |
+
"mean_token_accuracy": 0.6548443913459778,
|
| 15066 |
+
"num_tokens": 30509159.0,
|
| 15067 |
+
"step": 8365
|
| 15068 |
+
},
|
| 15069 |
+
{
|
| 15070 |
+
"epoch": 64.38461538461539,
|
| 15071 |
+
"grad_norm": 0.0,
|
| 15072 |
+
"learning_rate": 8.155e-06,
|
| 15073 |
+
"loss": 1.788,
|
| 15074 |
+
"mean_token_accuracy": 0.6422168552875519,
|
| 15075 |
+
"num_tokens": 30526994.0,
|
| 15076 |
+
"step": 8370
|
| 15077 |
}
|
| 15078 |
],
|
| 15079 |
"logging_steps": 5,
|
|
|
|
| 15093 |
"attributes": {}
|
| 15094 |
}
|
| 15095 |
},
|
| 15096 |
+
"total_flos": 1.5477946779038515e+18,
|
| 15097 |
"train_batch_size": 4,
|
| 15098 |
"trial_name": null,
|
| 15099 |
"trial_params": null
|