Training in progress, step 189, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6374035612a146da1a109a61d39346ef90aa723c35c9a39d002c6f436b99e0f
+oid sha256:5543dc40d49fc0154d1b16abbd286f2bf0435f7123acf10691f9d6b1017c2791
 size 556856304

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6043626bc4eaab3e567d8a690d89b2ba48bc4982f9614315e27098e503a238c6
+oid sha256:7eb23728351eea2a4fcb946b6be3c1b458e8fd969358c4a1d12dc9144fbd38ab
 size 21599060

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd90097bda2ff98046f4b0422fd3c485b996e564d7a8ece2d680b303573e27b6
+oid sha256:de37dd82cd0cf834d417f7b96248455ecd73827e4ae89369877d8120c7f0f3a8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fde2add4ac526f9d88b4a85a5e304b22d4aa9bf06cf799f89fbf1fa68e0bf83
+oid sha256:65558e26afbfb87dd1928966282919939bdee4084add607d42e008ed52d680cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005899290680525318,
+  "epoch": 0.008848936020787977,
   "eval_steps": 63,
-  "global_step": 126,
+  "global_step": 189,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -115,6 +115,56 @@
       "eval_samples_per_second": 58.901,
       "eval_steps_per_second": 29.457,
       "step": 126
+    },
+    {
+      "epoch": 0.006086569749748344,
+      "grad_norm": 3.45941424369812,
+      "learning_rate": 9.679484224283449e-05,
+      "loss": 3.886,
+      "step": 130
+    },
+    {
+      "epoch": 0.006554767422805909,
+      "grad_norm": 2.8132386207580566,
+      "learning_rate": 8.404001049666211e-05,
+      "loss": 3.7394,
+      "step": 140
+    },
+    {
+      "epoch": 0.007022965095863473,
+      "grad_norm": 4.228970050811768,
+      "learning_rate": 7.154724133689677e-05,
+      "loss": 4.0529,
+      "step": 150
+    },
+    {
+      "epoch": 0.007491162768921039,
+      "grad_norm": 3.7364513874053955,
+      "learning_rate": 5.952166568776062e-05,
+      "loss": 4.2573,
+      "step": 160
+    },
+    {
+      "epoch": 0.007959360441978603,
+      "grad_norm": 2.4087815284729004,
+      "learning_rate": 4.8160743168947496e-05,
+      "loss": 3.9108,
+      "step": 170
+    },
+    {
+      "epoch": 0.008427558115036168,
+      "grad_norm": 3.435811758041382,
+      "learning_rate": 3.7651019814126654e-05,
+      "loss": 3.9131,
+      "step": 180
+    },
+    {
+      "epoch": 0.008848936020787977,
+      "eval_loss": 1.9433419704437256,
+      "eval_runtime": 76.3299,
+      "eval_samples_per_second": 58.915,
+      "eval_steps_per_second": 29.464,
+      "step": 189
     }
   ],
   "logging_steps": 10,
@@ -134,7 +184,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4146228205977600.0,
+  "total_flos": 6203018575872000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null