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:a241e22ffac0d805eb071041b61b0d1cfda9d50bf01b003840aadee9bba31731
+oid sha256:43031206bc639aafce03d415ba3292655820852e068fa2f371f4e2512b23c73e
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc3ed6a0364fa228d53b0f466060fcc72a2c8f1485ff707c7e6b30c0f08b9e5f
+oid sha256:41fce71a2facbb3651cdba77548483c81a6d381c10c29ff4f49576779d5bfea1
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:559aa784b0078d433f070c2088ec5a3500d5f53f789fb7fe08d88a71ab7706b5
+oid sha256:873d11eb07e1b9a512c8142223f8a384b6b11253a60b55a45b0f30cc73620820
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009674922600619196,
+  "epoch": 0.01934984520123839,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 2.66,
       "eval_steps_per_second": 2.66,
       "step": 25
+    },
+    {
+      "epoch": 0.011609907120743035,
+      "grad_norm": 0.41392597556114197,
+      "learning_rate": 5e-05,
+      "loss": 1.3273,
+      "step": 30
+    },
+    {
+      "epoch": 0.013544891640866873,
+      "grad_norm": 0.47019708156585693,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.2684,
+      "step": 35
+    },
+    {
+      "epoch": 0.015479876160990712,
+      "grad_norm": 0.477716326713562,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2093,
+      "step": 40
+    },
+    {
+      "epoch": 0.01741486068111455,
+      "grad_norm": 0.4382253587245941,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.218,
+      "step": 45
+    },
+    {
+      "epoch": 0.01934984520123839,
+      "grad_norm": 0.4909341335296631,
+      "learning_rate": 0.0,
+      "loss": 1.3078,
+      "step": 50
+    },
+    {
+      "epoch": 0.01934984520123839,
+      "eval_loss": 1.281789779663086,
+      "eval_runtime": 108.7097,
+      "eval_samples_per_second": 2.649,
+      "eval_steps_per_second": 2.649,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -72,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1676905757540352.0,
+  "total_flos": 3318875978465280.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null