Training in progress, step 4510, 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 sha256:88ae95cf6aba11df6f0436ff95af06051bb0d7c7f153a760831e480ff299a469
|
| 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 sha256:0951a3afad114f4625c187e8311fc57a2e2d83caf224e43baa8c546c14babc0d
|
| 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:a8851f0d5ee0311d139af2ddee2d86a761b8a6a51c98d19fb544feed02c1c218
|
| 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": 34.
|
| 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,
|
|
@@ -8108,6 +8108,24 @@
|
|
| 8108 |
"mean_token_accuracy": 0.6552159339189529,
|
| 8109 |
"num_tokens": 16412619.0,
|
| 8110 |
"step": 4500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8111 |
}
|
| 8112 |
],
|
| 8113 |
"logging_steps": 5,
|
|
@@ -8127,7 +8145,7 @@
|
|
| 8127 |
"attributes": {}
|
| 8128 |
}
|
| 8129 |
},
|
| 8130 |
-
"total_flos": 8.
|
| 8131 |
"train_batch_size": 4,
|
| 8132 |
"trial_name": null,
|
| 8133 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 34.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4510,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8108 |
"mean_token_accuracy": 0.6552159339189529,
|
| 8109 |
"num_tokens": 16412619.0,
|
| 8110 |
"step": 4500
|
| 8111 |
+
},
|
| 8112 |
+
{
|
| 8113 |
+
"epoch": 34.65384615384615,
|
| 8114 |
+
"grad_norm": 0.0,
|
| 8115 |
+
"learning_rate": 2.748e-05,
|
| 8116 |
+
"loss": 1.8421,
|
| 8117 |
+
"mean_token_accuracy": 0.6334175139665603,
|
| 8118 |
+
"num_tokens": 16429807.0,
|
| 8119 |
+
"step": 4505
|
| 8120 |
+
},
|
| 8121 |
+
{
|
| 8122 |
+
"epoch": 34.69230769230769,
|
| 8123 |
+
"grad_norm": 0.0,
|
| 8124 |
+
"learning_rate": 2.7455000000000004e-05,
|
| 8125 |
+
"loss": 1.7888,
|
| 8126 |
+
"mean_token_accuracy": 0.6399717807769776,
|
| 8127 |
+
"num_tokens": 16447829.0,
|
| 8128 |
+
"step": 4510
|
| 8129 |
}
|
| 8130 |
],
|
| 8131 |
"logging_steps": 5,
|
|
|
|
| 8145 |
"attributes": {}
|
| 8146 |
}
|
| 8147 |
},
|
| 8148 |
+
"total_flos": 8.335397084332032e+17,
|
| 8149 |
"train_batch_size": 4,
|
| 8150 |
"trial_name": null,
|
| 8151 |
"trial_params": null
|