Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90771bc3e40a6dff1cf2eb79b7b1c1c822c7798893018318d6cdfe647152e120
+oid sha256:8a973c937668cf72261d5b50815b1a6ce137524fee08ea5ffc1677ad93696fc7
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1530c86ce1f8ba52479255444aca6ad3cb9d0dec246662302d3700e4a19a5499
+oid sha256:70413df3c5453e15114575a1411a7a6558d90f1aae702ecb5d5c847f96c4c2b2
 size 501028338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e530f1b21e6744a0cf36a8fe08347c58f3b9d879634a50ea15adbcbf7076b2f
+oid sha256:8269368413165814a4034deba6289bdc53a41273ac7335b3b55dcfdfdd18a5df
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003369839932603201,
+  "epoch": 0.005054759898904802,
   "eval_steps": 2,
-  "global_step": 4,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,28 @@
       "eval_samples_per_second": 5.733,
       "eval_steps_per_second": 2.867,
       "step": 4
+    },
+    {
+      "epoch": 0.004212299915754001,
+      "grad_norm": 26.322071075439453,
+      "learning_rate": 0.0001,
+      "loss": 17.8213,
+      "step": 5
+    },
+    {
+      "epoch": 0.005054759898904802,
+      "grad_norm": 29.4674072265625,
+      "learning_rate": 0.00012,
+      "loss": 17.2315,
+      "step": 6
+    },
+    {
+      "epoch": 0.005054759898904802,
+      "eval_loss": 3.23167085647583,
+      "eval_runtime": 87.097,
+      "eval_samples_per_second": 5.741,
+      "eval_steps_per_second": 2.87,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -78,7 +100,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2539115878809600.0,
+  "total_flos": 3808673818214400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null