Training in progress, step 800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28169bb183740976fb1e1012281faf4daaa901f0809070b5431b167a9aed9330
+oid sha256:73f8c1791b5ee7e58d663de47ee5fe8c35df4f1f6931e02c5c1c05ca2c095b6a
 size 579824888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bcc09d2987fc871b0f3d765698df5a7ddb67b242d4bf83d5e4d4194e97c62f1
+oid sha256:be87b0db9147168393b32986a7c8b1d815025dfeb0ce1175bbb3f22f44725ce1
 size 1159794763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecde0592a54835c0791d413df0b84cfe61c8375c6c53371a3a262f4a720ce7ee
+oid sha256:44dfb10fef84f1136d3eee8160822b0d721bb87ad12f498bd11540cf57bcb837
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bff1f3af0c59bc6ebaa29224579d5dfcd2f5ed0cc9dfc92a0a059a14be64f7bc
+oid sha256:eed2e2028bc81a04ee6b31f6b531dfb1c72a67f736dcd67eadafbd77d40b8d1c
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6,
+  "epoch": 0.8,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -146,6 +146,52 @@
       "eval_samples_per_second": 78.385,
       "eval_steps_per_second": 4.929,
       "step": 600
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 2.2103075981140137,
+      "learning_rate": 3.649468851314669e-05,
+      "loss": 21.8233,
+      "step": 650
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.6479830741882324,
+      "learning_rate": 2.7878659847348175e-05,
+      "loss": 21.7227,
+      "step": 700
+    },
+    {
+      "epoch": 0.7,
+      "eval_accuracy": 0.21617785614706886,
+      "eval_loss": 5.362000942230225,
+      "eval_runtime": 12.8392,
+      "eval_samples_per_second": 75.55,
+      "eval_steps_per_second": 4.751,
+      "step": 700
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.3954864740371704,
+      "learning_rate": 2.0015946888825077e-05,
+      "loss": 21.6333,
+      "step": 750
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.4790278673171997,
+      "learning_rate": 1.3174304897095113e-05,
+      "loss": 21.4768,
+      "step": 800
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.21887124010660555,
+      "eval_loss": 5.3149943351745605,
+      "eval_runtime": 12.5786,
+      "eval_samples_per_second": 77.115,
+      "eval_steps_per_second": 4.85,
+      "step": 800
     }
   ],
   "logging_steps": 50,
@@ -165,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.003509981904896e+17,
+  "total_flos": 1.338013309206528e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null