Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cab650935c0482531612b6d928e48d9dae71f5b0cc6d335d35ecfe4d2e682fd
+oid sha256:c4e90e0c96d09a55922d1ef08adc9faa7593a6ed4d2e6f7ac90ad144799584d4
 size 1521616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a23578b9d30499d14bd7284f3c7cc52614b791a0d9621c824b873601faa2d12f
+oid sha256:afb316f0fe1e459d42f500d5586d883a2471f08da8e70b9df870b0fbc677d919
 size 3108666

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2dacbc91d0d50e41b049f70a84d5b45ce05c0358d13151fa9f001452bc37899
+oid sha256:7927cb30dc5a5dd5bd3c0185ad7ae06fd9ac5b77bee0e6d0921b598afde5462e
 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": 0.03877096055054764,
+  "epoch": 0.05815644082582146,
   "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": 62.626,
       "eval_steps_per_second": 31.313,
       "step": 50
+    },
+    {
+      "epoch": 0.039546379761558594,
+      "grad_norm": 7.341830253601074,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 4.3773,
+      "step": 51
+    },
+    {
+      "epoch": 0.040321798972569545,
+      "grad_norm": 8.497244834899902,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 4.6826,
+      "step": 52
+    },
+    {
+      "epoch": 0.041097218183580496,
+      "grad_norm": 7.568642616271973,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 4.4897,
+      "step": 53
+    },
+    {
+      "epoch": 0.041872637394591454,
+      "grad_norm": 7.663918495178223,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 5.1256,
+      "step": 54
+    },
+    {
+      "epoch": 0.042648056605602405,
+      "grad_norm": 6.138592720031738,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 4.3068,
+      "step": 55
+    },
+    {
+      "epoch": 0.043423475816613356,
+      "grad_norm": 6.359229564666748,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 4.6431,
+      "step": 56
+    },
+    {
+      "epoch": 0.04419889502762431,
+      "grad_norm": 6.404804706573486,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 4.4604,
+      "step": 57
+    },
+    {
+      "epoch": 0.04497431423863526,
+      "grad_norm": 5.194124221801758,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 4.4148,
+      "step": 58
+    },
+    {
+      "epoch": 0.04574973344964622,
+      "grad_norm": 6.9789557456970215,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 4.5563,
+      "step": 59
+    },
+    {
+      "epoch": 0.04652515266065717,
+      "grad_norm": 6.215468406677246,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 4.6267,
+      "step": 60
+    },
+    {
+      "epoch": 0.04730057187166812,
+      "grad_norm": 5.669643878936768,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 4.3564,
+      "step": 61
+    },
+    {
+      "epoch": 0.04807599108267907,
+      "grad_norm": 6.695188045501709,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 4.6728,
+      "step": 62
+    },
+    {
+      "epoch": 0.04885141029369003,
+      "grad_norm": 6.3594069480896,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 4.4725,
+      "step": 63
+    },
+    {
+      "epoch": 0.04962682950470098,
+      "grad_norm": 6.124025344848633,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 4.7726,
+      "step": 64
+    },
+    {
+      "epoch": 0.05040224871571193,
+      "grad_norm": 6.306771755218506,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 4.7565,
+      "step": 65
+    },
+    {
+      "epoch": 0.05117766792672288,
+      "grad_norm": 6.299499034881592,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 4.1523,
+      "step": 66
+    },
+    {
+      "epoch": 0.05195308713773384,
+      "grad_norm": 5.291078567504883,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 4.4084,
+      "step": 67
+    },
+    {
+      "epoch": 0.05272850634874479,
+      "grad_norm": 7.21616268157959,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 4.2842,
+      "step": 68
+    },
+    {
+      "epoch": 0.05350392555975574,
+      "grad_norm": 5.060047626495361,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 4.4137,
+      "step": 69
+    },
+    {
+      "epoch": 0.054279344770766694,
+      "grad_norm": 5.063629627227783,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 4.4392,
+      "step": 70
+    },
+    {
+      "epoch": 0.05505476398177765,
+      "grad_norm": 4.903884410858154,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 4.3334,
+      "step": 71
+    },
+    {
+      "epoch": 0.0558301831927886,
+      "grad_norm": 6.626821517944336,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 4.8866,
+      "step": 72
+    },
+    {
+      "epoch": 0.056605602403799554,
+      "grad_norm": 5.395899772644043,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 4.1787,
+      "step": 73
+    },
+    {
+      "epoch": 0.057381021614810505,
+      "grad_norm": 5.96885347366333,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 4.9024,
+      "step": 74
+    },
+    {
+      "epoch": 0.05815644082582146,
+      "grad_norm": 6.069552898406982,
+      "learning_rate": 0.0,
+      "loss": 4.4114,
+      "step": 75
+    },
+    {
+      "epoch": 0.05815644082582146,
+      "eval_loss": 4.3782525062561035,
+      "eval_runtime": 17.3208,
+      "eval_samples_per_second": 62.699,
+      "eval_steps_per_second": 31.35,
+      "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": 29001724723200.0,
+  "total_flos": 43502587084800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null