Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78a93ace29ab2b6a3170340fc326b507648a88e3a4a9814f9219f24aa84bb792
+oid sha256:4d73babbb800d15e886c00142f5b95da30c96f214de6a1041c6ce5d1a02c9df3
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34d098cf060ea0b47b8cb9f75c134c13d9e4bbf9a1e98e6fb28a62f7f19c4f06
+oid sha256:617bd3df8f5f6c7d1ee2c08c45ac5fea5fed7017ff8b1360e6a45f36436b1142
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:464e6cdff3f8548ba79ace3859c72e6b06d1e045e69932eb75c584ad0e8918c8
+oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0016825574873808188,
+  "epoch": 0.0033651149747616375,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 243.535,
       "eval_steps_per_second": 121.929,
       "step": 3
+    },
+    {
+      "epoch": 0.002243409983174425,
+      "grad_norm": 0.016678154468536377,
+      "learning_rate": 8e-05,
+      "loss": 11.9328,
+      "step": 4
+    },
+    {
+      "epoch": 0.0028042624789680315,
+      "grad_norm": 0.018861737102270126,
+      "learning_rate": 0.0001,
+      "loss": 11.9248,
+      "step": 5
+    },
+    {
+      "epoch": 0.0033651149747616375,
+      "grad_norm": 0.009495808742940426,
+      "learning_rate": 0.00012,
+      "loss": 11.926,
+      "step": 6
+    },
+    {
+      "epoch": 0.0033651149747616375,
+      "eval_loss": 11.93128776550293,
+      "eval_runtime": 3.1316,
+      "eval_samples_per_second": 239.81,
+      "eval_steps_per_second": 120.065,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 384024576.0,
+  "total_flos": 738508800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null