Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d313059b45d865ac1762a583ec400ea36589e519bddaa42409b4ddbc65e4a24
+oid sha256:69e2391ae33ca96af19ca2ace841dcda574fc1790b53792580d65d3c9e3026ce
 size 438032472

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60939877eb10186c82cb742ececcd86b3b89dcf23d63cc34abe9190235e49c56
+oid sha256:43f0443fe1f70c7a42de40f82586eb67ee731508f7158f8ba6d83bc10d863a3b
 size 876185978

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb70df0ad07747f808cfdb28d3f00ff5a1cfdb2f6a944e3debcc3c5e5f27b429
+oid sha256:c26edcd7164d1d17c537fa422a9cdc58f953d55d66feed6db98fc01a04f19406
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec9786334357a4fb2218d9067b799b12938c6b355b5990de5c82cd4cb64ba426
+oid sha256:352d1cb8705a18d1870fdd06ca30240b7780be1ac5622a15d434bd83b9f8b0e9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3857233226299286,
-  "best_model_checkpoint": "results/checkpoint-1000",
-  "epoch": 0.09552010698251982,
+  "best_metric": 0.3843745291233063,
+  "best_model_checkpoint": "results/checkpoint-1500",
+  "epoch": 0.14328016047377973,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,21 @@
       "eval_samples_per_second": 236.622,
       "eval_steps_per_second": 3.701,
       "step": 1000
+    },
+    {
+      "epoch": 0.14328016047377973,
+      "grad_norm": 3.55123233795166,
+      "learning_rate": 4.641799598815551e-05,
+      "loss": 0.4412,
+      "step": 1500
+    },
+    {
+      "epoch": 0.14328016047377973,
+      "eval_loss": 0.3843745291233063,
+      "eval_runtime": 108.5384,
+      "eval_samples_per_second": 240.938,
+      "eval_steps_per_second": 3.768,
+      "step": 1500
     }
   ],
   "logging_steps": 500,
@@ -56,7 +71,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6842736140288e+16,
+  "total_flos": 2.5264104210432e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null