Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b1d802ec62c809d72ff62ecc47b8893f0bbf2eab44e42996da6a873c36798c8
+oid sha256:d2be6e792ce34b3308915cdc5c42ee775adbf714d92c3ad5146e2cde82cce630
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e9a545e0c9dc7489908c1290ec37c2440affe68c114d4078b5b81a69b30c2e0
+oid sha256:5db301bf2865329d8c2169cf69b75bfa73ef5739f8ead74d742c97bde9c48471
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bc95f8ef66804917a60b19acbb3aaab5647926085d4ddb008103acb36348fb2
+oid sha256:2bc49e406d40d15d4c77a549f46af25554828e4ccf4a2549a6e443a9a7b138dc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010471204188481676,
+  "epoch": 0.020942408376963352,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00018,
       "loss": 7.0334,
       "step": 9
+    },
+    {
+      "epoch": 0.012565445026178011,
+      "grad_norm": 1.8192013502120972,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 6.6012,
+      "step": 12
+    },
+    {
+      "epoch": 0.015706806282722512,
+      "grad_norm": 1.5765700340270996,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 6.1287,
+      "step": 15
+    },
+    {
+      "epoch": 0.016753926701570682,
+      "eval_loss": 1.506831407546997,
+      "eval_runtime": 57.3962,
+      "eval_samples_per_second": 7.021,
+      "eval_steps_per_second": 3.519,
+      "step": 16
+    },
+    {
+      "epoch": 0.018848167539267015,
+      "grad_norm": 2.498102903366089,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 5.9627,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3267323221770240.0,
+  "total_flos": 6534646443540480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null