Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81f014618393aba3b786559ab7e898762a7529f002d3495a0df431f20bc07501
+oid sha256:d7fd1dc9e6dee3c6e2c7c888960ce819968c50cd549b4c3a93aaf2348d2b5c54
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f23a48353215ee400ea9fb6dc9156a7282474d15ef9505fca2f247fc1df8a6c
+oid sha256:afa700ac347944422ce01b70af8c73d3e8b31a3d04ed3b2604f628584cc0119d
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bfb40a52c3b8fe25ca28ecea06885436d490a3dba0a15349fa317c01e5e48fa
+oid sha256:b783ebf522fd46f6505d994855f698ed643d7b120399b04ff114f6b536b5178f
 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": 0.1899335232668566,
+  "epoch": 0.2849002849002849,
   "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": 3.952,
       "eval_steps_per_second": 1.976,
       "step": 50
+    },
+    {
+      "epoch": 0.19373219373219372,
+      "grad_norm": 1.0411734580993652,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.1466,
+      "step": 51
+    },
+    {
+      "epoch": 0.19753086419753085,
+      "grad_norm": 1.2727152109146118,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.1484,
+      "step": 52
+    },
+    {
+      "epoch": 0.201329534662868,
+      "grad_norm": 1.522938847541809,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.1559,
+      "step": 53
+    },
+    {
+      "epoch": 0.20512820512820512,
+      "grad_norm": 1.072451114654541,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.1234,
+      "step": 54
+    },
+    {
+      "epoch": 0.20892687559354226,
+      "grad_norm": 2.466201066970825,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.1619,
+      "step": 55
+    },
+    {
+      "epoch": 0.2127255460588794,
+      "grad_norm": 2.4038662910461426,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.1967,
+      "step": 56
+    },
+    {
+      "epoch": 0.21652421652421652,
+      "grad_norm": 2.5965778827667236,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2216,
+      "step": 57
+    },
+    {
+      "epoch": 0.22032288698955366,
+      "grad_norm": 1.1259628534317017,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.1716,
+      "step": 58
+    },
+    {
+      "epoch": 0.2241215574548908,
+      "grad_norm": 1.1792726516723633,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.1462,
+      "step": 59
+    },
+    {
+      "epoch": 0.22792022792022792,
+      "grad_norm": 0.8546663522720337,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1117,
+      "step": 60
+    },
+    {
+      "epoch": 0.23171889838556506,
+      "grad_norm": 0.9426295161247253,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.1341,
+      "step": 61
+    },
+    {
+      "epoch": 0.2355175688509022,
+      "grad_norm": 1.6098453998565674,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.167,
+      "step": 62
+    },
+    {
+      "epoch": 0.23931623931623933,
+      "grad_norm": 1.1398288011550903,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1675,
+      "step": 63
+    },
+    {
+      "epoch": 0.24311490978157646,
+      "grad_norm": 1.3635776042938232,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.1591,
+      "step": 64
+    },
+    {
+      "epoch": 0.24691358024691357,
+      "grad_norm": 1.1154038906097412,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.1559,
+      "step": 65
+    },
+    {
+      "epoch": 0.25071225071225073,
+      "grad_norm": 0.870740532875061,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1289,
+      "step": 66
+    },
+    {
+      "epoch": 0.25451092117758783,
+      "grad_norm": 1.1247227191925049,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.1535,
+      "step": 67
+    },
+    {
+      "epoch": 0.258309591642925,
+      "grad_norm": 1.1654616594314575,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.1626,
+      "step": 68
+    },
+    {
+      "epoch": 0.2621082621082621,
+      "grad_norm": 1.496175765991211,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.1781,
+      "step": 69
+    },
+    {
+      "epoch": 0.26590693257359926,
+      "grad_norm": 2.098728895187378,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.1563,
+      "step": 70
+    },
+    {
+      "epoch": 0.26970560303893637,
+      "grad_norm": 0.9920639991760254,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.1556,
+      "step": 71
+    },
+    {
+      "epoch": 0.27350427350427353,
+      "grad_norm": 1.3341926336288452,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.2277,
+      "step": 72
+    },
+    {
+      "epoch": 0.27730294396961064,
+      "grad_norm": 1.2077915668487549,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.1837,
+      "step": 73
+    },
+    {
+      "epoch": 0.28110161443494774,
+      "grad_norm": 0.9270416498184204,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.1284,
+      "step": 74
+    },
+    {
+      "epoch": 0.2849002849002849,
+      "grad_norm": 1.1907814741134644,
+      "learning_rate": 0.0,
+      "loss": 0.2088,
+      "step": 75
+    },
+    {
+      "epoch": 0.2849002849002849,
+      "eval_loss": 0.14623484015464783,
+      "eval_runtime": 56.166,
+      "eval_samples_per_second": 3.953,
+      "eval_steps_per_second": 1.976,
+      "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": 7.46010452164608e+16,
+  "total_flos": 1.119015678246912e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null