Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:826d8f4988014c35c94fb884f9f61f6af1d13dacf99f7531919548fe889810b9
+oid sha256:ad913310e1589817dc80faff9d0734dff6ac4b956d97bf6696d4e4373704f347
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79f0ecf696ea3830dadcc56ebee824fa66c5c31da7d45ba2f4e2d6bea66cafaa
+oid sha256:b688ebf97c3b5140692bfe732017ff54db8bc5389696c5b4685bbc5c9e78013e
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:104b09cc6df95f3b0d5e3d0e48bc90e51a986bbda4ae0fd0e8e48388960641a8
+oid sha256:c20ce01a6ab099e169bfbba7f0d7e683fd5547e6ce53b20d7b9dcf1cddb0e519
 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": 0.12560386473429952,
+  "epoch": 0.1610305958132045,
   "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": 23.049,
       "eval_steps_per_second": 11.613,
       "step": 39
+    },
+    {
+      "epoch": 0.1288244766505636,
+      "grad_norm": 2.555748701095581,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.7752,
+      "step": 40
+    },
+    {
+      "epoch": 0.1320450885668277,
+      "grad_norm": 2.8646492958068848,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 0.6029,
+      "step": 41
+    },
+    {
+      "epoch": 0.13526570048309178,
+      "grad_norm": 3.072885274887085,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.7051,
+      "step": 42
+    },
+    {
+      "epoch": 0.13848631239935588,
+      "grad_norm": 2.487110137939453,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 0.4773,
+      "step": 43
+    },
+    {
+      "epoch": 0.14170692431561996,
+      "grad_norm": 2.7830471992492676,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 0.5362,
+      "step": 44
+    },
+    {
+      "epoch": 0.14492753623188406,
+      "grad_norm": 2.803068161010742,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.57,
+      "step": 45
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 3.0086348056793213,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 0.6742,
+      "step": 46
+    },
+    {
+      "epoch": 0.15136876006441224,
+      "grad_norm": 3.5830721855163574,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 0.6125,
+      "step": 47
+    },
+    {
+      "epoch": 0.15458937198067632,
+      "grad_norm": 2.493169069290161,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 0.5324,
+      "step": 48
+    },
+    {
+      "epoch": 0.15780998389694043,
+      "grad_norm": 2.481688976287842,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 0.516,
+      "step": 49
+    },
+    {
+      "epoch": 0.1610305958132045,
+      "grad_norm": 3.480961322784424,
+      "learning_rate": 0.0,
+      "loss": 0.6306,
+      "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": 7843197292118016.0,
+  "total_flos": 1.0121668013850624e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null