Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b2fee3e15feab3a0047553eccce557d475a1dcb3ac4d45283ac34edfe334ed6
+oid sha256:072b3dd49d46fcb9e3147b16e8fdd9164b9219ae1af8aabd23ad1604084a885d
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5038b2411afe299e69ebd276ab86120a5adb69c15d1c241b24e8c29ceeca4ee6
+oid sha256:f35b8477ed6a9c77283332c180b0530620ac017f4892dff4f636695967e163d5
 size 180543866

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:566d560e6b36fe4550a5847fef06f89ecba2d66c364128fc9977de8e9e411a5e
+oid sha256:286570ca2fb4fddd38a1df62beaeed45f57a3511cc38a9174e75b2d4f223b226
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04152823920265781,
+  "epoch": 0.06229235880398671,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 14.143,
       "eval_steps_per_second": 7.071,
       "step": 50
+    },
+    {
+      "epoch": 0.04235880398671096,
+      "grad_norm": 3.037964344024658,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.2274,
+      "step": 51
+    },
+    {
+      "epoch": 0.04318936877076412,
+      "grad_norm": 2.001744270324707,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 1.8772,
+      "step": 52
+    },
+    {
+      "epoch": 0.04401993355481727,
+      "grad_norm": 2.270850419998169,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 1.8247,
+      "step": 53
+    },
+    {
+      "epoch": 0.044850498338870434,
+      "grad_norm": 2.272608518600464,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.4002,
+      "step": 54
+    },
+    {
+      "epoch": 0.04568106312292359,
+      "grad_norm": 1.9296989440917969,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 2.2143,
+      "step": 55
+    },
+    {
+      "epoch": 0.046511627906976744,
+      "grad_norm": 1.6859852075576782,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 1.6857,
+      "step": 56
+    },
+    {
+      "epoch": 0.0473421926910299,
+      "grad_norm": 1.8581290245056152,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.6804,
+      "step": 57
+    },
+    {
+      "epoch": 0.04817275747508306,
+      "grad_norm": 1.8868964910507202,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 1.6223,
+      "step": 58
+    },
+    {
+      "epoch": 0.049003322259136214,
+      "grad_norm": 1.9600261449813843,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.6922,
+      "step": 59
+    },
+    {
+      "epoch": 0.04983388704318937,
+      "grad_norm": 1.9007118940353394,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.804,
+      "step": 60
+    },
+    {
+      "epoch": 0.050664451827242524,
+      "grad_norm": 1.7296816110610962,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 1.6008,
+      "step": 61
+    },
+    {
+      "epoch": 0.05149501661129568,
+      "grad_norm": 1.7615364789962769,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 1.5411,
+      "step": 62
+    },
+    {
+      "epoch": 0.05232558139534884,
+      "grad_norm": 1.64870023727417,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.531,
+      "step": 63
+    },
+    {
+      "epoch": 0.053156146179401995,
+      "grad_norm": 1.8037062883377075,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 1.7586,
+      "step": 64
+    },
+    {
+      "epoch": 0.05398671096345515,
+      "grad_norm": 1.8290114402770996,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 1.7702,
+      "step": 65
+    },
+    {
+      "epoch": 0.054817275747508304,
+      "grad_norm": 1.5939185619354248,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7454,
+      "step": 66
+    },
+    {
+      "epoch": 0.05564784053156146,
+      "grad_norm": 1.5866504907608032,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.5255,
+      "step": 67
+    },
+    {
+      "epoch": 0.05647840531561462,
+      "grad_norm": 1.9439473152160645,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 1.767,
+      "step": 68
+    },
+    {
+      "epoch": 0.057308970099667775,
+      "grad_norm": 1.8197013139724731,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.6518,
+      "step": 69
+    },
+    {
+      "epoch": 0.05813953488372093,
+      "grad_norm": 1.836192011833191,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 1.5788,
+      "step": 70
+    },
+    {
+      "epoch": 0.058970099667774084,
+      "grad_norm": 1.8220064640045166,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.8797,
+      "step": 71
+    },
+    {
+      "epoch": 0.059800664451827246,
+      "grad_norm": 1.953622579574585,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.8,
+      "step": 72
+    },
+    {
+      "epoch": 0.0606312292358804,
+      "grad_norm": 1.840462565422058,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 1.8579,
+      "step": 73
+    },
+    {
+      "epoch": 0.061461794019933555,
+      "grad_norm": 1.8298439979553223,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 1.8466,
+      "step": 74
+    },
+    {
+      "epoch": 0.06229235880398671,
+      "grad_norm": 1.7909139394760132,
+      "learning_rate": 0.0,
+      "loss": 1.7919,
+      "step": 75
+    },
+    {
+      "epoch": 0.06229235880398671,
+      "eval_loss": 1.9671133756637573,
+      "eval_runtime": 72.2963,
+      "eval_samples_per_second": 14.026,
+      "eval_steps_per_second": 7.013,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.003273674817536e+16,
+  "total_flos": 1.5195925660041216e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null