Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:823b261ef99b1e191a872a1cbd0e66bf08cb406a99a6b58f8f72266b82aac2f3
+oid sha256:0a8f7e4984002db3e6e3edcd0765593c41d05502a0580d65db70459e3367ca6a
 size 556856304

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3908c845b321034463b1730a374291100e15b1dff0852e4cbedc713d30402c95
+oid sha256:a6bab23454149a9c5e0a13a8391c8d13fcdcef9b942e6c6253f1f7a06a95f377
 size 21599060

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f22ee2bd42680b5f198191658fb24f22c66fd0968ab26c6e7ce687248687a73
+oid sha256:0f5adca46d5768b2528d11214bf50c169d41422785e8b729921c5399a7fed5df
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06842105263157895,
+  "epoch": 0.08771929824561403,
   "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": 55.704,
       "eval_steps_per_second": 27.852,
       "step": 39
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 6.921982765197754,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 7.4431,
+      "step": 40
+    },
+    {
+      "epoch": 0.07192982456140351,
+      "grad_norm": 5.440037727355957,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 6.0957,
+      "step": 41
+    },
+    {
+      "epoch": 0.07368421052631578,
+      "grad_norm": 6.525667667388916,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 7.1308,
+      "step": 42
+    },
+    {
+      "epoch": 0.07543859649122807,
+      "grad_norm": 6.312617301940918,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 6.5642,
+      "step": 43
+    },
+    {
+      "epoch": 0.07719298245614035,
+      "grad_norm": 6.488813400268555,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 5.9102,
+      "step": 44
+    },
+    {
+      "epoch": 0.07894736842105263,
+      "grad_norm": 6.369126319885254,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 6.7954,
+      "step": 45
+    },
+    {
+      "epoch": 0.08070175438596491,
+      "grad_norm": 5.541263103485107,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 6.9496,
+      "step": 46
+    },
+    {
+      "epoch": 0.0824561403508772,
+      "grad_norm": 5.264928340911865,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 6.3512,
+      "step": 47
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 5.724519729614258,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 6.058,
+      "step": 48
+    },
+    {
+      "epoch": 0.08596491228070176,
+      "grad_norm": 5.485682010650635,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 5.7932,
+      "step": 49
+    },
+    {
+      "epoch": 0.08771929824561403,
+      "grad_norm": 6.535744667053223,
+      "learning_rate": 0.0,
+      "loss": 6.6898,
+      "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": 2546502362726400.0,
+  "total_flos": 3264746618880000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null