Training in progress, step 500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f80a24ef27cb8d65adc7ffae4be6c2732033a5e9141dfd66815315f593ae70b8
+oid sha256:6b7bdfa9432865811566d801973f8536379093191662a7081831a5e5a10ab7ea
 size 3826461296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8da859acf7ac6600d1453a6ad96ad20e3865a29e481bed11e5055dfb249272fa
-size 2479123301
+oid sha256:98b8806bdda72b37431cd7a1864b5e940d2adca924c0255d88519f24424d35ce
+size 2479955235

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f0a73f4374b5e05c786b790825aa9c223b53f3ee4551182bcb497e6cf37794f
+oid sha256:0ff58b41c3672e659a0eb46d9ed11a0ca17415e7a2643a3ddfbaebb9f4e67f8f
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98e8d05c49d91a8f0b7f5e1dfd9876ebcb94dbdc34961d432fb69d2b41418c55
+oid sha256:04a7344de2b10f0c83d4bc41d4ac3ff0903cfb5c2b6ee1654e8dd79d5d353dd0
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16,
+  "epoch": 0.2,
   "eval_steps": 500,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -288,6 +288,76 @@
       "learning_rate": 4.216432865731463e-05,
       "loss": 0.9337,
       "step": 400
+    },
+    {
+      "epoch": 0.164,
+      "grad_norm": 19.447803497314453,
+      "learning_rate": 4.2081993569131834e-05,
+      "loss": 1.2047,
+      "step": 410
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 26.82716178894043,
+      "learning_rate": 4.188102893890675e-05,
+      "loss": 1.1294,
+      "step": 420
+    },
+    {
+      "epoch": 0.172,
+      "grad_norm": 12.995594024658203,
+      "learning_rate": 4.168006430868168e-05,
+      "loss": 1.0033,
+      "step": 430
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 21.796598434448242,
+      "learning_rate": 4.14790996784566e-05,
+      "loss": 0.8864,
+      "step": 440
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 13.911988258361816,
+      "learning_rate": 4.1278135048231516e-05,
+      "loss": 0.8974,
+      "step": 450
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 25.945011138916016,
+      "learning_rate": 4.1077170418006434e-05,
+      "loss": 1.261,
+      "step": 460
+    },
+    {
+      "epoch": 0.188,
+      "grad_norm": 19.943857192993164,
+      "learning_rate": 4.087620578778135e-05,
+      "loss": 1.0262,
+      "step": 470
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 23.558696746826172,
+      "learning_rate": 4.067524115755627e-05,
+      "loss": 0.9572,
+      "step": 480
+    },
+    {
+      "epoch": 0.196,
+      "grad_norm": 42.70231628417969,
+      "learning_rate": 4.047427652733119e-05,
+      "loss": 1.044,
+      "step": 490
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 16.41856575012207,
+      "learning_rate": 4.027331189710611e-05,
+      "loss": 1.0562,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -307,7 +377,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7213993175126016.0,
+  "total_flos": 9020891125518336.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:494a633dff0a175cc686333ee75294c5676e89507a1657f43bb2a04f0d770f70
+oid sha256:a61a9de7250209bad41a9d2af614e0cacba19d7115d8d918ae2499b5ad24f2b6
 size 6289