Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e72c7e5be6cf5eb83c02530e1587de88d57a5f3ad792f869fb3c0851333e60f
+oid sha256:ce0203cbad67607029fd65bbbe7487529410845fe3c86485406e7761efee274c
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf71ea8cec1f12d8b2cc8304ee88814320bf52aa3811c4c394527f02fe00e197
+oid sha256:10b35a22b8a5cac1885bfd82956c2edaaedf1c4f1252eb88a801389ae2eba421
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc9ba646a412b1e567644e95b35454a2f3c483f2dee7ac4992f7d3c245d97e42
+oid sha256:667e71c033224f16044b20e9375dce709e5226baf79ff39eb2de2fcd18446b51
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1875,
+  "epoch": 0.2403846153846154,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,36 @@
       "eval_samples_per_second": 35.563,
       "eval_steps_per_second": 4.464,
       "step": 30
+    },
+    {
+      "epoch": 0.19230769230769232,
+      "grad_norm": 0.4777894616127014,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.1615,
+      "step": 40
+    },
+    {
+      "epoch": 0.19230769230769232,
+      "eval_loss": 2.1386547088623047,
+      "eval_runtime": 39.4608,
+      "eval_samples_per_second": 35.529,
+      "eval_steps_per_second": 4.46,
+      "step": 40
+    },
+    {
+      "epoch": 0.2403846153846154,
+      "grad_norm": 0.43009230494499207,
+      "learning_rate": 0.0,
+      "loss": 2.1359,
+      "step": 50
+    },
+    {
+      "epoch": 0.2403846153846154,
+      "eval_loss": 2.133580207824707,
+      "eval_runtime": 39.4346,
+      "eval_samples_per_second": 35.553,
+      "eval_steps_per_second": 4.463,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -74,12 +104,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.0386746822754304e+16,
+  "total_flos": 3.865635241485926e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null