Training in progress, step 345, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c82180f14717620e0bf756c85b583676dc7d69114368727db88aae103d64aa3
+oid sha256:10742d0d8bf9f86583fe8f8e669e4185a674f714dc49ffdfb5d6b15de14bf150
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d94f089a1e467259428315e6e4ad483b5faaba1f2396f78d9eb6bf56641de7b9
+oid sha256:0d2f76262232ba65042a794500f554111ee7dc02d2d4b3bafbd2f6f6ab44d14c
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe6a98cf43c9788166599038375eb01cf5493b9863f02eb9463a77c771ad5463
+oid sha256:8ed11591e8f20b4787f4e6cf3c53a96e282f5ef0a7dd0a280b2e82dae9893e2c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5097543f48561dead5ef0816caa212645fb361fee6d0137dbeaac39adc3b6ec8
+oid sha256:b9bb8b24f4a9f7edc29066576ef36f9a38b3dc95e778ec0d2e8b280ebcd9c22d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.43998705920414105,
+  "epoch": 0.44645745713361373,
   "eval_steps": 386,
-  "global_step": 340,
+  "global_step": 345,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2395,6 +2395,41 @@
       "learning_rate": 9.857729325492329e-05,
       "loss": 1.0093,
       "step": 340
+    },
+    {
+      "epoch": 0.4412811387900356,
+      "grad_norm": 0.8646867275238037,
+      "learning_rate": 9.856751176922388e-05,
+      "loss": 0.9235,
+      "step": 341
+    },
+    {
+      "epoch": 0.4425752183759301,
+      "grad_norm": 0.7576479315757751,
+      "learning_rate": 9.85576972621137e-05,
+      "loss": 0.8323,
+      "step": 342
+    },
+    {
+      "epoch": 0.44386929796182467,
+      "grad_norm": 0.8257366418838501,
+      "learning_rate": 9.854784974026572e-05,
+      "loss": 0.8478,
+      "step": 343
+    },
+    {
+      "epoch": 0.4451633775477192,
+      "grad_norm": 0.8963577747344971,
+      "learning_rate": 9.853796921037534e-05,
+      "loss": 0.8943,
+      "step": 344
+    },
+    {
+      "epoch": 0.44645745713361373,
+      "grad_norm": 0.8696343898773193,
+      "learning_rate": 9.85280556791604e-05,
+      "loss": 0.991,
+      "step": 345
     }
   ],
   "logging_steps": 1,
@@ -2414,7 +2449,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.800986383758131e+17,
+  "total_flos": 3.8568832423428096e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null