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:b9cb96cbec5eca62afc5d8949c1432e36c659652fadc4699a0e555173c0f4682
+oid sha256:38333f77a54b3ca20876b401c8b375cc2051353a14161eb906f224d5acb5c68f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87da47363882ad422ed2648a4b63626acf0b2615aff5dd0af4079918b4cac1f7
+oid sha256:bc301f8d4a31eaf219d32235d0c3f5daa71b55775f530131382cf9505dad645d
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a5f891767aaacfb795fc4c851c74f7dcf55cd20474ec59a43d271975d0645cf
+oid sha256:d36cf02c5c091e1cf6b7a556033f9afe92924f5c6d18c68aeec7f759f6f16a6c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0007658133084607644,
+  "epoch": 0.0009818119339240568,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 0.3962,
       "step": 35
+    },
+    {
+      "epoch": 0.0007854495471392455,
+      "grad_norm": 0.7175095081329346,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4025,
+      "step": 40
+    },
+    {
+      "epoch": 0.0007854495471392455,
+      "eval_loss": 0.36656200885772705,
+      "eval_runtime": 1454.2635,
+      "eval_samples_per_second": 14.745,
+      "eval_steps_per_second": 7.373,
+      "step": 40
+    },
+    {
+      "epoch": 0.0008836307405316511,
+      "grad_norm": 0.8027252554893494,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3648,
+      "step": 45
+    },
+    {
+      "epoch": 0.0009818119339240568,
+      "grad_norm": 0.7240496873855591,
+      "learning_rate": 0.0,
+      "loss": 0.3809,
+      "step": 50
+    },
+    {
+      "epoch": 0.0009818119339240568,
+      "eval_loss": 0.3623235821723938,
+      "eval_runtime": 1454.581,
+      "eval_samples_per_second": 14.742,
+      "eval_steps_per_second": 7.371,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7213300567769088.0,
+  "total_flos": 9247821240729600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null