Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ab35df2c6f42d94b1b765dd2d92defa45f055d1f9f3f69b3466f869f5b355ff
+oid sha256:5b671e81ca1faf222d1ea1ec15d031b7c25d5287d6df16c70e45a639050d85c3
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9477a14fbbd471626d75553c2acab50cb49b130123579171cbc54ada9829819
+oid sha256:b1aeda282bc04046d52f89196e74c839a96812009bdd3acf4655e7e4ebd85ae3
 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": 269.386,
       "eval_steps_per_second": 134.872,
       "step": 3
+    },
+    {
+      "epoch": 0.002243409983174425,
+      "grad_norm": 0.015789495781064034,
+      "learning_rate": 8e-05,
+      "loss": 11.9328,
+      "step": 4
+    },
+    {
+      "epoch": 0.0028042624789680315,
+      "grad_norm": 0.021245604380965233,
+      "learning_rate": 0.0001,
+      "loss": 11.9248,
+      "step": 5
+    },
+    {
+      "epoch": 0.0033651149747616375,
+      "grad_norm": 0.010077406652271748,
+      "learning_rate": 0.00012,
+      "loss": 11.926,
+      "step": 6
+    },
+    {
+      "epoch": 0.0033651149747616375,
+      "eval_loss": 11.931283950805664,
+      "eval_runtime": 2.8284,
+      "eval_samples_per_second": 265.525,
+      "eval_steps_per_second": 132.939,
+      "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