Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d6589d8ccec56ae7cec491e45f338265163dfaa0514671c6886c318939ff16b
+oid sha256:a761600bb05eb0b51f0c1d08e8aeeceffca12c2825bb94d0096ef68b0832dd96
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:556e0e496c347bcacdc631fcc976d989f763173ce71a481c5e595eda55e7868c
+oid sha256:1df56f785bfec9725d3743268841438503c60ea39693fd8cdc39be1d60346c3d
 size 18810036

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96337aceb721df4a39beff9244b65d1cc5d873c4c0a7c3c253f42ec95bd3c737
+oid sha256:02b9b8da40beadd514dc13fdd3c8e1aeaa56dd6010eb05994d7dbf6d3136ef25
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4da44b1e728628aca7953c36b51c1a8e86ff48e7b0510da4dad905b7baf90075
+oid sha256:3cab7179b1ebf44623f4d0517c52f97f0dce3ae84201e614d4143af8990f5db8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90dbcef4627cf6dae532a9a8253b624934e88872fdcc33c4ca09154619960b47
+oid sha256:c01f94c1a1216692d538a3a245c0976803197608a15bc074c81b00028040b3e6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd8d65a02101282957e9ff4a7ca57ff66ccbed5b37662c0225e938e0c9443324
+oid sha256:d7305c81fb147bad2c0b7dfc4a6ccbc7d9927becb843ea17bee6a6dd2785e009
 size 15024

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": 0.5853658536585366,
+  "epoch": 0.7504690431519699,
   "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": 78.325,
       "eval_steps_per_second": 9.943,
       "step": 39
+    },
+    {
+      "epoch": 0.600375234521576,
+      "grad_norm": 1.6693542003631592,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6815,
+      "step": 40
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 2.4521377086639404,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.7027,
+      "step": 41
+    },
+    {
+      "epoch": 0.6303939962476548,
+      "grad_norm": 1.4812160730361938,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.7015,
+      "step": 42
+    },
+    {
+      "epoch": 0.6454033771106942,
+      "grad_norm": 2.221867799758911,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.6957,
+      "step": 43
+    },
+    {
+      "epoch": 0.6604127579737336,
+      "grad_norm": 3.274115800857544,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.7147,
+      "step": 44
+    },
+    {
+      "epoch": 0.6754221388367729,
+      "grad_norm": 1.3704664707183838,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6968,
+      "step": 45
+    },
+    {
+      "epoch": 0.6904315196998124,
+      "grad_norm": 1.5144388675689697,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.7031,
+      "step": 46
+    },
+    {
+      "epoch": 0.7054409005628518,
+      "grad_norm": 2.387979030609131,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.699,
+      "step": 47
+    },
+    {
+      "epoch": 0.7204502814258912,
+      "grad_norm": 1.8138819932937622,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.7033,
+      "step": 48
+    },
+    {
+      "epoch": 0.7354596622889306,
+      "grad_norm": 1.4316879510879517,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.6938,
+      "step": 49
+    },
+    {
+      "epoch": 0.7504690431519699,
+      "grad_norm": 2.234066963195801,
+      "learning_rate": 0.0,
+      "loss": 0.7067,
+      "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": 4.498754837151744e+16,
+  "total_flos": 5.7676344066048e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null