Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:018e14b315fe7c2c4f3f3ecd8b30c12df557b1aac16e8d43200e427cde5012f9
+oid sha256:194586d3329b3915640ca629be211ec70f5b61a397ac703ca6f5434939582492
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:646034272609dc9d2c0541f1cb2326b461015d3659964f877ee677294404bf96
+oid sha256:1b0e76ee6269a9a9fabb2d984a5ea1939801a3483f6171f3a83c136b30abd349
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f98b2585ba496f632a735b8a7a739e3fb4531f5d994b75a9fec9af2a855a040b
+oid sha256:5a996d3bec7c1a1d5cfa47430ef266e5a8dd93e8eb7ea3732980f3263a8c33f9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c975e68baf84112bcf6e3bf3a6f55c44889e07688f04dbbc115884a58a2446b4
+oid sha256:8fba9b63cba9667080cabcc507a8b9f4b22657fbfa4fbd93588927df6c34fd73
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.5112262521588946,
+  "epoch": 1.7271157167530224,
   "eval_steps": 500,
-  "global_step": 3500,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -39,9 +39,9 @@
     {
       "epoch": 1.0,
       "eval_loss": 0.33670297265052795,
-      "eval_runtime": 28.3351,
-      "eval_samples_per_second": 16.658,
-      "eval_steps_per_second": 4.164,
+      "eval_runtime": 28.2248,
+      "eval_samples_per_second": 16.723,
+      "eval_steps_per_second": 4.181,
       "step": 2316
     },
     {
@@ -64,6 +64,13 @@
       "learning_rate": 9.93091537132988e-06,
       "loss": 0.3728,
       "step": 3500
+    },
+    {
+      "epoch": 1.7271157167530224,
+      "grad_norm": 0.9635007381439209,
+      "learning_rate": 8.491652274035695e-06,
+      "loss": 0.3675,
+      "step": 4000
     }
   ],
   "logging_steps": 500,
@@ -83,7 +90,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8524801509949440.0,
+  "total_flos": 9742717291069440.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0589186e917e79226308cded95843db5013776fee27e83a39d678ba03ec762d3
+oid sha256:d2d71d788b491a41c54d3b024285748be4a2e443d732e96343f48dd9941e304a
 size 5432