Training in progress, step 9300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d33aa6465f9abb34233b6354f37a051718d38bdd7e741298841e4582d0f142d
+oid sha256:85beb4e63f2c5b59a9fb44c1941465e25467b6f51e0595870a1ed098da9eb3a9
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba5204466ae4487e214855180a1192547e4ac27af7a7f63f134519d46ee40145
+oid sha256:2bfa466e47344fdb4b82ac2e27349b5aa4a9780daa2a9dd909396e056672be06
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa880c1daade42489548428c80dfc7dd79b5600e67b13b79367956ccd4dd4f41
+oid sha256:e3cda8d8dfc43c49473f34af5d9dbd59701d7b0b55fa4d024a4a95d2b0775e60
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd7e7c0b78a68a269a0c2d97fdccfb6ac7781d12da5817b2cd744268907a9d68
+oid sha256:3e194f1dd757c906a836decafb805f1dccfe64bb4c1bfe3207704010eaaa32fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7424,
+  "epoch": 0.744,
   "eval_steps": 500,
-  "global_step": 9280,
+  "global_step": 9300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3255,6 +3255,13 @@
       "learning_rate": 1.7466396779212695e-05,
       "loss": 3.4381,
       "step": 9280
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 26.957141876220703,
+      "learning_rate": 1.7418463821296398e-05,
+      "loss": 3.4075,
+      "step": 9300
     }
   ],
   "logging_steps": 20,
@@ -3262,7 +3269,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 2.1951059416940544e+16,
+  "total_flos": 2.199570826395648e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null