Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11161298f6d1c00e5f97d5a4c8d6a5f3711d6eb947378c1f5bfeff00fb151711
+oid sha256:084b254081faec9380ea542a323464dfa83cb5d431cbeb4cf1add968b3373b6b
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dc3e4d51570e3b8d25833919f3804b1c18f21e13c75470b9dbe9e5eda72ffc7
+oid sha256:7d1ab14446b88427b0169aa606fb0ce2331a012b1205fada3b05d6c498141668
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:762b7684bf0a16e62a37a4bd38b0fffc86eeb37c4d57faed65bdf98d2576ee3e
+oid sha256:b35c8e31723066aef0ea0dfb2c5b6fe2e13cec12317c048b86f03568518e1162
 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": 0.0008925914906277894,
+  "epoch": 0.0017851829812555787,
   "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": 8.232,
       "eval_steps_per_second": 4.116,
       "step": 3
+    },
+    {
+      "epoch": 0.0011901219875037191,
+      "grad_norm": 2.846064805984497,
+      "learning_rate": 8e-05,
+      "loss": 4.558,
+      "step": 4
+    },
+    {
+      "epoch": 0.001487652484379649,
+      "grad_norm": 1.77438223361969,
+      "learning_rate": 0.0001,
+      "loss": 3.2527,
+      "step": 5
+    },
+    {
+      "epoch": 0.0017851829812555787,
+      "grad_norm": 2.6561055183410645,
+      "learning_rate": 0.00012,
+      "loss": 4.8197,
+      "step": 6
+    },
+    {
+      "epoch": 0.0017851829812555787,
+      "eval_loss": 3.7654619216918945,
+      "eval_runtime": 171.8954,
+      "eval_samples_per_second": 8.238,
+      "eval_steps_per_second": 4.119,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1080837210636288.0,
+  "total_flos": 1904332228263936.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null