Training in progress, step 1210, 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 sha256:97baa2f5771e59f574599e036a1ed725dbe5768e10211ab00f12b08e955e53a1
|
| 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 sha256:06f9b90899425084c24863a0d5fcfb63961eda7432aa211016bb09ddcbf0a144
|
| 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 sha256:2e92e81b0901c1569b797e725d19696c8d2c89e8dca844c28f2640752b32eeb5
|
| 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": 9.
|
| 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,
|
|
@@ -2168,6 +2168,24 @@
|
|
| 2168 |
"mean_token_accuracy": 0.6364401876926422,
|
| 2169 |
"num_tokens": 4376472.0,
|
| 2170 |
"step": 1200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2171 |
}
|
| 2172 |
],
|
| 2173 |
"logging_steps": 5,
|
|
@@ -2187,7 +2205,7 @@
|
|
| 2187 |
"attributes": {}
|
| 2188 |
}
|
| 2189 |
},
|
| 2190 |
-
"total_flos": 2.
|
| 2191 |
"train_batch_size": 4,
|
| 2192 |
"trial_name": null,
|
| 2193 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 9.307692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1210,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2168 |
"mean_token_accuracy": 0.6364401876926422,
|
| 2169 |
"num_tokens": 4376472.0,
|
| 2170 |
"step": 1200
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 9.26923076923077,
|
| 2174 |
+
"grad_norm": 0.0,
|
| 2175 |
+
"learning_rate": 4.398e-05,
|
| 2176 |
+
"loss": 1.7567,
|
| 2177 |
+
"mean_token_accuracy": 0.6473460882902146,
|
| 2178 |
+
"num_tokens": 4394898.0,
|
| 2179 |
+
"step": 1205
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 9.307692307692308,
|
| 2183 |
+
"grad_norm": 0.0,
|
| 2184 |
+
"learning_rate": 4.3955e-05,
|
| 2185 |
+
"loss": 1.6926,
|
| 2186 |
+
"mean_token_accuracy": 0.6541574269533157,
|
| 2187 |
+
"num_tokens": 4413886.0,
|
| 2188 |
+
"step": 1210
|
| 2189 |
}
|
| 2190 |
],
|
| 2191 |
"logging_steps": 5,
|
|
|
|
| 2205 |
"attributes": {}
|
| 2206 |
}
|
| 2207 |
},
|
| 2208 |
+
"total_flos": 2.2373934688714752e+17,
|
| 2209 |
"train_batch_size": 4,
|
| 2210 |
"trial_name": null,
|
| 2211 |
"trial_params": null
|