Training in progress, step 2500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72c474249d7bd26bb3d3aa6fd8b2d6dd47ce56d95d1b9fadabf9d80386985d01
+oid sha256:2340c7a13fcc15a4fda30b781dcdf5814248b70a557cceb00cec2f44eb668d85
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1978aa37200b580896dfce75674a0fdeece3a680adae62e1ae6a6bb0ac597530
+oid sha256:acb984a3c9a86fe26e521dcd305e60cdc81de818654c36a99208a9f0e9f40934
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e0045739043a1f47643b813cbabc473141dd79658dbb66a9080e37f01080f2a
+oid sha256:5604d9d3a71fe29d2132679abbb8924b3bc48dbd5eff5e533842e7eebc6c2195
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3177e3b1e883a4ce813e19b5686aa0ddb9fc95274cac4bd31c26b3f7510095a7
+oid sha256:0fca4557dc47ae840f038455c2e5db6fca05342b3edaa84049dd9e7e99b58e9a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8635578583765112,
+  "epoch": 1.079447322970639,
   "eval_steps": 500,
-  "global_step": 2000,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,6 +35,21 @@
       "learning_rate": 1.4248704663212436e-05,
       "loss": 0.4194,
       "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.33670297265052795,
+      "eval_runtime": 28.2248,
+      "eval_samples_per_second": 16.723,
+      "eval_steps_per_second": 4.181,
+      "step": 2316
+    },
+    {
+      "epoch": 1.079447322970639,
+      "grad_norm": 3.1095924377441406,
+      "learning_rate": 1.280944156591825e-05,
+      "loss": 0.4036,
+      "step": 2500
     }
   ],
   "logging_steps": 500,
@@ -54,7 +69,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4871663124480000.0,
+  "total_flos": 6088969947709440.0,
   "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