Training in progress, step 600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bae43b52627ec635e8138665a3a76fb67c1c6817b62a6b5533adc30466d1216
+oid sha256:0b60bd2b618a69841c9638940c605adda6c4341ba295b93f3a6e133859850d9b
 size 579748776

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4caadb553679cfc495bfa78dbf95efbd0038757efc70a680411a31a089ef9238
+oid sha256:f82169ccf1b0127e9b22314f600b128025f5b62090d5a9708b8fcba2a47577d6
 size 1159627083

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02b94dfa6d7836c5c68f2d2549fc9be186c2691c198e846c097e4aae3ccf90e6
+oid sha256:b88b1c42229400fab90420f6e5c036d698ae72e0815465d44c9b14b967936d62
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a903f2c82e7b21fcfdd55b988513d1f4b97daf80c782473ccecc104f23b4dd7c
+oid sha256:a24f1bcbda0bf3e5430414e8c982c53ac11d90f165724ef0b93f5942d606b3a0
 size 14917

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81bef68395366893911697d5372e508b6e708198d9017941b12c0581628d2a93
+oid sha256:4be5aafe091abf14e9046be44e4c580810411461427a26c13cdf5ca05ae54bc2
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15,
+  "epoch": 0.3,
   "eval_steps": 100,
-  "global_step": 300,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,117 @@
       "eval_samples_per_second": 64.571,
       "eval_steps_per_second": 2.13,
       "step": 300
+    },
+    {
+      "epoch": 0.1625,
+      "grad_norm": 54.86927032470703,
+      "learning_rate": 9.783313076097283e-05,
+      "loss": 101.6082,
+      "step": 325
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 14.090791702270508,
+      "learning_rate": 9.717209048767277e-05,
+      "loss": 100.8465,
+      "step": 350
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 42.630802154541016,
+      "learning_rate": 9.642604291892226e-05,
+      "loss": 99.9092,
+      "step": 375
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 12.524935722351074,
+      "learning_rate": 9.559633248286604e-05,
+      "loss": 99.0524,
+      "step": 400
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.15310791228876244,
+      "eval_loss": 6.214518070220947,
+      "eval_runtime": 7.3913,
+      "eval_samples_per_second": 65.618,
+      "eval_steps_per_second": 2.165,
+      "step": 400
+    },
+    {
+      "epoch": 0.2125,
+      "grad_norm": 22.39153480529785,
+      "learning_rate": 9.468445437379055e-05,
+      "loss": 98.4639,
+      "step": 425
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 20.86402702331543,
+      "learning_rate": 9.369205185768272e-05,
+      "loss": 97.6668,
+      "step": 450
+    },
+    {
+      "epoch": 0.2375,
+      "grad_norm": 15.403814315795898,
+      "learning_rate": 9.262091331095375e-05,
+      "loss": 97.1439,
+      "step": 475
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 18.481685638427734,
+      "learning_rate": 9.147296899766376e-05,
+      "loss": 96.6031,
+      "step": 500
+    },
+    {
+      "epoch": 0.25,
+      "eval_accuracy": 0.1584204706678313,
+      "eval_loss": 6.100996494293213,
+      "eval_runtime": 7.4101,
+      "eval_samples_per_second": 65.451,
+      "eval_steps_per_second": 2.159,
+      "step": 500
+    },
+    {
+      "epoch": 0.2625,
+      "grad_norm": 19.892127990722656,
+      "learning_rate": 9.025028759105558e-05,
+      "loss": 96.2492,
+      "step": 525
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 20.713096618652344,
+      "learning_rate": 8.895507244566574e-05,
+      "loss": 96.3436,
+      "step": 550
+    },
+    {
+      "epoch": 0.2875,
+      "grad_norm": 12.466355323791504,
+      "learning_rate": 8.758965762673064e-05,
+      "loss": 96.5737,
+      "step": 575
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 21.678146362304688,
+      "learning_rate": 8.615650370404327e-05,
+      "loss": 95.9314,
+      "step": 600
+    },
+    {
+      "epoch": 0.3,
+      "eval_accuracy": 0.163982449674087,
+      "eval_loss": 5.986855983734131,
+      "eval_runtime": 7.6235,
+      "eval_samples_per_second": 63.619,
+      "eval_steps_per_second": 2.099,
+      "step": 600
     }
   ],
   "logging_steps": 25,
@@ -138,7 +249,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.006672071458816e+17,
+  "total_flos": 4.013344142917632e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null