Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74b83c398995fef387d0350ca1e4893c6fc44073c2616fc4bc311c836150f281
+oid sha256:dfe2de6b119d5661289c0fe0865d04e57a54fee53e7eab157cee9f1c1d1f40e3
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:073a51b6579761614dba08aa7cb28e9a07d5411c8ab8d6770884b28157ec7bcc
+oid sha256:89aada9da7b0524ac1f466805def21bd9c201bc8b696fd048c061ce046f4c2be
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b8d766a2c89ca827fd88604c04645a44e7deecf9ec62a527d0adcbef8aac440
+oid sha256:9f6c4b7c059825c4bc8cb721af1bd8b0f04e3482c208d61c6dee52f9e48a542b
 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": 0.06377759607522486,
+  "epoch": 0.08176614881439084,
   "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": 1.0695,
       "step": 35
+    },
+    {
+      "epoch": 0.06541291905151267,
+      "grad_norm": 2.8147099018096924,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.1374,
+      "step": 40
+    },
+    {
+      "epoch": 0.06541291905151267,
+      "eval_loss": 1.01498281955719,
+      "eval_runtime": 25.1622,
+      "eval_samples_per_second": 10.253,
+      "eval_steps_per_second": 5.127,
+      "step": 40
+    },
+    {
+      "epoch": 0.07358953393295176,
+      "grad_norm": 3.164930820465088,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0507,
+      "step": 45
+    },
+    {
+      "epoch": 0.08176614881439084,
+      "grad_norm": 3.7304253578186035,
+      "learning_rate": 0.0,
+      "loss": 1.2695,
+      "step": 50
+    },
+    {
+      "epoch": 0.08176614881439084,
+      "eval_loss": 1.0039623975753784,
+      "eval_runtime": 24.9829,
+      "eval_samples_per_second": 10.327,
+      "eval_steps_per_second": 5.164,
+      "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": 8004335107571712.0,
+  "total_flos": 1.02619680866304e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null