Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b07794a4766223bc04ee621df668181809a9680efb7f3402e9062c1d647bca82
+oid sha256:b5918f923e94a1c71c1343bdcf10beeef3df1b930ad244fba32fd7f174ba907d
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:600a58d2b953c32b2ed9d106d83156d177ccdf78fe0147dc9a9c11b343b6fb6a
+oid sha256:3efa0ed49bd9be95076d7069e5e9edf45f6b79f66e0033c9a85e8f6d1f88f0b2
 size 1386414411

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cd45c472c02f69686aade1ec7cee7512c8dba6e6bde5e0bd023fd4f8f2f3548
+oid sha256:536f3bf5d8d9a338dc3c13d4a9497341d1858e9170a623670fdf984c7300d07b
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09714a2ef70dd987c21ebd404103aea88be622e980ab90fe03c4cb22a4d6d0de
+oid sha256:feac55dc4e1aa4e2fb9533ef48c19881a76f1225ae029d1ded10aa6105f9d143
 size 14917

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d607aeebc80b296b5bbc4bdd6acb23e9a6ea5c0feecf9462250a533d1c816c4
+oid sha256:a05fb06c8f2309f7e205252b1a3311f0b9687d7493c125c7e1233cf078e7b73e
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16666666666666666,
+  "epoch": 0.3333333333333333,
   "eval_steps": 200,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -96,6 +96,103 @@
       "learning_rate": 9.634541575171929e-05,
       "loss": 77.5796,
       "step": 500
+    },
+    {
+      "epoch": 0.18333333333333332,
+      "grad_norm": 30660.970703125,
+      "learning_rate": 9.524135262330098e-05,
+      "loss": 77.067,
+      "step": 550
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 55290.8203125,
+      "learning_rate": 9.399989299389661e-05,
+      "loss": 75.4663,
+      "step": 600
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.24998188196442597,
+      "eval_loss": 4.73757791519165,
+      "eval_runtime": 8.0417,
+      "eval_samples_per_second": 62.176,
+      "eval_steps_per_second": 1.99,
+      "step": 600
+    },
+    {
+      "epoch": 0.21666666666666667,
+      "grad_norm": 28325.5859375,
+      "learning_rate": 9.262480713559808e-05,
+      "loss": 76.2754,
+      "step": 650
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 354199.03125,
+      "learning_rate": 9.112027113896262e-05,
+      "loss": 76.0095,
+      "step": 700
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1301901.625,
+      "learning_rate": 8.949085423036296e-05,
+      "loss": 76.6464,
+      "step": 750
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 118610.0,
+      "learning_rate": 8.774150489539707e-05,
+      "loss": 78.2808,
+      "step": 800
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "eval_accuracy": 0.22522578989738337,
+      "eval_loss": 5.033573150634766,
+      "eval_runtime": 7.5988,
+      "eval_samples_per_second": 65.8,
+      "eval_steps_per_second": 2.106,
+      "step": 800
+    },
+    {
+      "epoch": 0.2833333333333333,
+      "grad_norm": 22132.029296875,
+      "learning_rate": 8.587753585050004e-05,
+      "loss": 79.5805,
+      "step": 850
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 10536.388671875,
+      "learning_rate": 8.390460790839882e-05,
+      "loss": 77.5871,
+      "step": 900
+    },
+    {
+      "epoch": 0.31666666666666665,
+      "grad_norm": 15219.642578125,
+      "learning_rate": 8.182871278641009e-05,
+      "loss": 77.6208,
+      "step": 950
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 92554.859375,
+      "learning_rate": 7.965615490979163e-05,
+      "loss": 78.9266,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "eval_accuracy": 0.2367096863914945,
+      "eval_loss": 4.885761737823486,
+      "eval_runtime": 7.9133,
+      "eval_samples_per_second": 63.185,
+      "eval_steps_per_second": 2.022,
+      "step": 1000
     }
   ],
   "logging_steps": 50,