Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ab15b4c66f04efff59161484dafc587e1c7f9dc257a2c41d6deb25f0d5889ba
+oid sha256:6e204e1f4f4ca327bf85888c327e4df6ec352656c5df4cfb58d787b556a92b0c
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:063fa671c64d3eb04110aad678efa35a1ffa7f90ba61480663cc354117840d62
+oid sha256:50d579d678d59d0e0169e50fc11280350ef86d25773900c1d6dca9ebf9f51c57
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08880825848fb5c66058f1ae60796a975d8eba319a67488da7b6f3895e178231
+oid sha256:d718a2f23bf1ddb91d46af5556d066c63ac28c306ad34f3b1009475aee7b05c2
 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": 0.009889064976228209,
+  "epoch": 0.012678288431061807,
   "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": 56.37,
       "eval_steps_per_second": 28.202,
       "step": 39
+    },
+    {
+      "epoch": 0.010142630744849446,
+      "grad_norm": 4.151251792907715,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 1.9259,
+      "step": 40
+    },
+    {
+      "epoch": 0.01039619651347068,
+      "grad_norm": 3.8641293048858643,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 1.8639,
+      "step": 41
+    },
+    {
+      "epoch": 0.010649762282091918,
+      "grad_norm": 4.853936672210693,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 2.2364,
+      "step": 42
+    },
+    {
+      "epoch": 0.010903328050713154,
+      "grad_norm": 4.689719200134277,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 1.9994,
+      "step": 43
+    },
+    {
+      "epoch": 0.01115689381933439,
+      "grad_norm": 4.530834674835205,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 1.9659,
+      "step": 44
+    },
+    {
+      "epoch": 0.011410459587955626,
+      "grad_norm": 4.6177825927734375,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 1.8617,
+      "step": 45
+    },
+    {
+      "epoch": 0.011664025356576862,
+      "grad_norm": 4.972818374633789,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 1.9799,
+      "step": 46
+    },
+    {
+      "epoch": 0.011917591125198098,
+      "grad_norm": 5.976642608642578,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 2.0939,
+      "step": 47
+    },
+    {
+      "epoch": 0.012171156893819335,
+      "grad_norm": 3.2281494140625,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 1.5168,
+      "step": 48
+    },
+    {
+      "epoch": 0.01242472266244057,
+      "grad_norm": 4.77769660949707,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 2.4263,
+      "step": 49
+    },
+    {
+      "epoch": 0.012678288431061807,
+      "grad_norm": 4.587887763977051,
+      "learning_rate": 0.0,
+      "loss": 1.9408,
+      "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": 1945674228695040.0,
+  "total_flos": 2484099801415680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null