Training in progress, step 15000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c24a6fee6197a7d0e0dc60fd3a17ae12371f686c25f8c59baa4e0a84062e4f9b
+oid sha256:d77c6fe75d2e084ea0b2dfb28f34e36e3797890c2158cf82df6cb58bd03848de
 size 498612824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7bb4a03ac656611f593c1f2ba0d38c8cbf04d907421b2c50bbdccb383e90608
+oid sha256:63d9616b208a7a5c95c12618c0f196a6549f6659b7d07ac8dd3e3b8297204116
 size 997345931

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1729b2eea6571b9bf3c801be2729d60efb8e2cb8629926b7109ada2c3384ad31
+oid sha256:4629bc6a7a1bf6a97eb230e023069c9de195f733b6e1d5ac800948162494e8d7
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23c844bc341ec75b5cad5ad0be21d7c0eeee0623194498c334d6946af672123e
+oid sha256:b0415cc902581048eff49426d3b5977e3d3a9842950529c62d3aba0c1eceb6cc
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04b0bf137a45b36bdb178c3406191d51b6266f45964c2cad0b5dc4c8bc6aa400
+oid sha256:cb2202b9362ddcbf14d87d88a547d9ac58913b4d2ad37d69d76ff373475958bd
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 9000,
-  "best_metric": 0.04935265704989433,
-  "best_model_checkpoint": "./training_output/checkpoint-9000",
-  "epoch": 0.7,
+  "best_global_step": 15000,
+  "best_metric": 0.048726025968790054,
+  "best_model_checkpoint": "./training_output/checkpoint-15000",
+  "epoch": 0.75,
   "eval_steps": 1000,
-  "global_step": 14000,
+  "global_step": 15000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -330,6 +330,29 @@
       "eval_samples_per_second": 52.552,
       "eval_steps_per_second": 3.284,
       "step": 14000
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 0.1631036400794983,
+      "learning_rate": 5.501000000000001e-06,
+      "loss": 0.0197,
+      "step": 14500
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.4217091202735901,
+      "learning_rate": 5.001e-06,
+      "loss": 0.0256,
+      "step": 15000
+    },
+    {
+      "epoch": 0.75,
+      "eval_accuracy": 0.97195,
+      "eval_loss": 0.048726025968790054,
+      "eval_runtime": 380.4177,
+      "eval_samples_per_second": 52.574,
+      "eval_steps_per_second": 3.286,
+      "step": 15000
     }
   ],
   "logging_steps": 500,
@@ -349,7 +372,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.473421910016e+16,
+  "total_flos": 1.57866633216e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null