Training in progress, step 16000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d77c6fe75d2e084ea0b2dfb28f34e36e3797890c2158cf82df6cb58bd03848de
+oid sha256:60d5cc0f066a9ff7f9709202c6b1ea302b25d4fc82b916383dba6b74bf14639e
 size 498612824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63d9616b208a7a5c95c12618c0f196a6549f6659b7d07ac8dd3e3b8297204116
+oid sha256:529961f9c3d396e3bfd95d8632f4c919c1c8d7d7aebb25605e81bf65fca66018
 size 997345931

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4629bc6a7a1bf6a97eb230e023069c9de195f733b6e1d5ac800948162494e8d7
+oid sha256:e29be2623b9f70496e9bea6cd43302d895456299b445e94e0c3906aa73899453
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0415cc902581048eff49426d3b5977e3d3a9842950529c62d3aba0c1eceb6cc
+oid sha256:d9e8f14715c120c1b82640d08ff4b50ac8ef3a482a39de36f9dee0ad364309a0
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb2202b9362ddcbf14d87d88a547d9ac58913b4d2ad37d69d76ff373475958bd
+oid sha256:3bdd55dc4830a374b47a354ba8f1d6b80b053f25bf45716e5f0fe65d5ff8db6b
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 15000,
-  "best_metric": 0.048726025968790054,
-  "best_model_checkpoint": "./training_output/checkpoint-15000",
-  "epoch": 0.75,
+  "best_global_step": 16000,
+  "best_metric": 0.042671315371990204,
+  "best_model_checkpoint": "./training_output/checkpoint-16000",
+  "epoch": 0.8,
   "eval_steps": 1000,
-  "global_step": 15000,
+  "global_step": 16000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -353,6 +353,29 @@
       "eval_samples_per_second": 52.574,
       "eval_steps_per_second": 3.286,
       "step": 15000
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 0.054990075528621674,
+      "learning_rate": 4.501000000000001e-06,
+      "loss": 0.0176,
+      "step": 15500
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.00047703919699415565,
+      "learning_rate": 4.001e-06,
+      "loss": 0.0215,
+      "step": 16000
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.97645,
+      "eval_loss": 0.042671315371990204,
+      "eval_runtime": 380.4653,
+      "eval_samples_per_second": 52.567,
+      "eval_steps_per_second": 3.285,
+      "step": 16000
     }
   ],
   "logging_steps": 500,
@@ -372,7 +395,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.57866633216e+16,
+  "total_flos": 1.683910754304e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null