Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d571c3a8eab6a750c1b1766683368d199ff123aa287ad8f192a93d2356ee7a8
+oid sha256:6f6d22668b55a13258d65f3e8a38e8cebac8fd3a9b9407028d74dcbbed279168
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab667f6e70cfc59dc7c436e76f82b73435149572f267b3409d867c0c19b83e83
+oid sha256:da41a437667e4609ef84623d1a5e4b00621bb5e24386a8ac597995e599afdaf3
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:652365ff63294ffff01ffedb52e831cc2560ab06b5699bca21d63e81dd0efbe7
+oid sha256:2edc13c60910e9acd555e90579b2ee1807926bb393c7c79b1e24163c3f5bfc9f
 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": 0.003973408726216856,
+  "epoch": 0.005094113751560072,
   "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": 28.601,
       "eval_steps_per_second": 14.301,
       "step": 39
+    },
+    {
+      "epoch": 0.004075291001248058,
+      "grad_norm": 2.2403550148010254,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1941,
+      "step": 40
+    },
+    {
+      "epoch": 0.004177173276279259,
+      "grad_norm": 1.1056747436523438,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.1054,
+      "step": 41
+    },
+    {
+      "epoch": 0.004279055551310461,
+      "grad_norm": 0.17147065699100494,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0343,
+      "step": 42
+    },
+    {
+      "epoch": 0.004380937826341662,
+      "grad_norm": 0.2568279802799225,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.0375,
+      "step": 43
+    },
+    {
+      "epoch": 0.0044828201013728634,
+      "grad_norm": 0.33789515495300293,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0438,
+      "step": 44
+    },
+    {
+      "epoch": 0.004584702376404065,
+      "grad_norm": 0.9882907271385193,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0627,
+      "step": 45
+    },
+    {
+      "epoch": 0.0046865846514352666,
+      "grad_norm": 0.8271799087524414,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0217,
+      "step": 46
+    },
+    {
+      "epoch": 0.004788466926466468,
+      "grad_norm": 0.8588903546333313,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.0656,
+      "step": 47
+    },
+    {
+      "epoch": 0.00489034920149767,
+      "grad_norm": 0.18504083156585693,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.0376,
+      "step": 48
+    },
+    {
+      "epoch": 0.004992231476528871,
+      "grad_norm": 0.46786996722221375,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.0398,
+      "step": 49
+    },
+    {
+      "epoch": 0.005094113751560072,
+      "grad_norm": 0.7483496069908142,
+      "learning_rate": 0.0,
+      "loss": 0.068,
+      "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": 1.124688709287936e+16,
+  "total_flos": 1.4419086016512e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null