Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99131d181be6825a80640e8ee755979cc560509bcdbf24734c116afaf330e896
+oid sha256:bbb5d64611e9393823802e84b732b234bfbced5fbf177db8a8894d13eda15ea9
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b4bed8eb24650f4a94169bc31d5a1992c701bc46b4ad8bd1ed6e2b0062c0d5d
+oid sha256:b086b6d64d9ce798d2d28fefbfd0f84466871aaa0a37bd1b856d1912a4ab8645
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c0b1e9d6e4ac295ecdcaca5beaf8e0d5d3736f0f2c183da89335564b1e4a6b2
+oid sha256:79791411d71c1113ecebaa01b1bfad87290258ad79fdc9d6745b07f0639a2399
 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": 0.02197560707614548,
+  "epoch": 0.04395121415229096,
   "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": 18.166,
       "eval_steps_per_second": 9.093,
       "step": 50
+    },
+    {
+      "epoch": 0.026370728491374573,
+      "grad_norm": 8.649742126464844,
+      "learning_rate": 0.0002,
+      "loss": 0.3513,
+      "step": 60
+    },
+    {
+      "epoch": 0.03076584990660367,
+      "grad_norm": 11.820034980773926,
+      "learning_rate": 0.0002,
+      "loss": 0.4011,
+      "step": 70
+    },
+    {
+      "epoch": 0.03516097132183277,
+      "grad_norm": 4.739223957061768,
+      "learning_rate": 0.0002,
+      "loss": 0.3105,
+      "step": 80
+    },
+    {
+      "epoch": 0.039556092737061864,
+      "grad_norm": 3.959333896636963,
+      "learning_rate": 0.0002,
+      "loss": 0.3885,
+      "step": 90
+    },
+    {
+      "epoch": 0.04395121415229096,
+      "grad_norm": 7.995823860168457,
+      "learning_rate": 0.0002,
+      "loss": 0.4986,
+      "step": 100
+    },
+    {
+      "epoch": 0.04395121415229096,
+      "eval_loss": 0.08041178435087204,
+      "eval_runtime": 52.7416,
+      "eval_samples_per_second": 18.183,
+      "eval_steps_per_second": 9.101,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3070712667373568e+16,
+  "total_flos": 2.626358152790016e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null