Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb22093dabe281b9cbc4eb22aab4a8cf629244ccccad329a0521f9dd964d963e
+oid sha256:a3f7ee8792dd9cf0c928273870ab52cb64aff116c6a850cc17fb0f801a208234
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06c0bd56e48ea56e727bbc5767ef94a1a0aed786d16b0e478fa4fa52591ec340
+oid sha256:ffeafbaeb8b27e715a256d509047223bfb10dee18e019cc1736c070185ab83db
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d70227acf03aa0e9f6c4188369d5f8fc3ccfbaa5e5e7dc786509f886f3f7220
+oid sha256:d13e4ef893c536a59c5ca202a0f867f0e94596caf4c68d31ee7476794a1d4ac8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b80fcc7599efca0c6313d990c467c2eb3001742b23ddaadc22e3499c12cea79
+oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006539580812869895,
+  "epoch": 0.01307916162573979,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 85.648,
       "eval_steps_per_second": 42.824,
       "step": 50
+    },
+    {
+      "epoch": 0.007847496975443874,
+      "grad_norm": 18.687952041625977,
+      "learning_rate": 0.0002,
+      "loss": 12.9873,
+      "step": 60
+    },
+    {
+      "epoch": 0.009155413138017853,
+      "grad_norm": 8.790769577026367,
+      "learning_rate": 0.0002,
+      "loss": 12.423,
+      "step": 70
+    },
+    {
+      "epoch": 0.010463329300591831,
+      "grad_norm": 8.85031509399414,
+      "learning_rate": 0.0002,
+      "loss": 12.0676,
+      "step": 80
+    },
+    {
+      "epoch": 0.011771245463165811,
+      "grad_norm": 12.773844718933105,
+      "learning_rate": 0.0002,
+      "loss": 12.8019,
+      "step": 90
+    },
+    {
+      "epoch": 0.01307916162573979,
+      "grad_norm": 11.019274711608887,
+      "learning_rate": 0.0002,
+      "loss": 12.2702,
+      "step": 100
+    },
+    {
+      "epoch": 0.01307916162573979,
+      "eval_loss": 3.001326560974121,
+      "eval_runtime": 37.3516,
+      "eval_samples_per_second": 86.208,
+      "eval_steps_per_second": 43.104,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 386608712908800.0,
+  "total_flos": 775094167142400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null