Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e6c315b39d443cc773c362027346865cb3cd9024065a68da192d469b8027cb1
+oid sha256:03a0566fbf83223060a3b42aa8f10b70ec9ed4c5186affa252a19530d44f466d
 size 104902272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d69ecd8a76ea16e1ade4b800f7e970f6171e96e8aa2410283e76d8ffc37c95a
+oid sha256:3d7db7ba423ddc3c6042ac9299c16f2c3e96a7f991edf44dad41e878b8e798dc
 size 53622996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a30ab6aba457b62b3b46ef063f965a22dbd99e339a0860a0336ca542d741ea12
+oid sha256:e9ed846b2bb081072beb0e1e599903d467ecadde55da795aeb29726cded6d617
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
+oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0970752955818295,
+  "epoch": 0.12445550715619166,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 13.165,
       "eval_steps_per_second": 6.582,
       "step": 39
+    },
+    {
+      "epoch": 0.09956440572495333,
+      "grad_norm": 0.899815559387207,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 4.6769,
+      "step": 40
+    },
+    {
+      "epoch": 0.10205351586807716,
+      "grad_norm": 0.9126536846160889,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 4.5519,
+      "step": 41
+    },
+    {
+      "epoch": 0.104542626011201,
+      "grad_norm": 0.9206661581993103,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 4.4688,
+      "step": 42
+    },
+    {
+      "epoch": 0.10703173615432483,
+      "grad_norm": 0.9055898785591125,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 4.5955,
+      "step": 43
+    },
+    {
+      "epoch": 0.10952084629744867,
+      "grad_norm": 0.8516914248466492,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 4.4511,
+      "step": 44
+    },
+    {
+      "epoch": 0.11200995644057249,
+      "grad_norm": 0.920841634273529,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 4.6116,
+      "step": 45
+    },
+    {
+      "epoch": 0.11449906658369632,
+      "grad_norm": 0.9671267867088318,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 4.7746,
+      "step": 46
+    },
+    {
+      "epoch": 0.11698817672682016,
+      "grad_norm": 0.9318122267723083,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 4.8963,
+      "step": 47
+    },
+    {
+      "epoch": 0.119477286869944,
+      "grad_norm": 0.8927145600318909,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 4.582,
+      "step": 48
+    },
+    {
+      "epoch": 0.12196639701306783,
+      "grad_norm": 0.8922162652015686,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 4.6308,
+      "step": 49
+    },
+    {
+      "epoch": 0.12445550715619166,
+      "grad_norm": 0.8940671682357788,
+      "learning_rate": 0.0,
+      "loss": 4.6593,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.447113602465792e+16,
+  "total_flos": 3.1373251313664e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null