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:b23b27be78527ca8d94cdc6064dbf55ef9428ed2d5fccf840f0d5b032e9cf96e
+oid sha256:98984ef9eb5fcc1eb8e3febbff3e0cfedacd4a33d8e62be0af7a80ebb721a2b1
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0519f3d246d7d718fbfd0ad44abd243b7de27d75dc511b5555bc75e9b99ff569
+oid sha256:8d492177efe94872466f85dfc60a43fea89f0e1947d42202bc2f06591111549c
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4975f04cc73623a7d831d10548ba7946cf5cebd8545c7386ad9f94aa368d0c8c
+oid sha256:a32c8349a05f0612cf16a973994c5e4c5024b7b8feede48d706acdfedcbca455
 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": 0.05684240443370755,
+  "epoch": 0.08526360665056132,
   "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": 11.151,
       "eval_steps_per_second": 5.583,
       "step": 50
+    },
+    {
+      "epoch": 0.057979252522381695,
+      "grad_norm": 5.924437046051025,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 12.278,
+      "step": 51
+    },
+    {
+      "epoch": 0.05911610061105585,
+      "grad_norm": 6.9019951820373535,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 12.2277,
+      "step": 52
+    },
+    {
+      "epoch": 0.06025294869973,
+      "grad_norm": 8.663328170776367,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 16.2151,
+      "step": 53
+    },
+    {
+      "epoch": 0.06138979678840415,
+      "grad_norm": 7.101144790649414,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 12.9355,
+      "step": 54
+    },
+    {
+      "epoch": 0.0625266448770783,
+      "grad_norm": 6.247992992401123,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 15.3862,
+      "step": 55
+    },
+    {
+      "epoch": 0.06366349296575245,
+      "grad_norm": 6.452046871185303,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 15.4312,
+      "step": 56
+    },
+    {
+      "epoch": 0.0648003410544266,
+      "grad_norm": 8.117711067199707,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 15.8753,
+      "step": 57
+    },
+    {
+      "epoch": 0.06593718914310075,
+      "grad_norm": 7.468315124511719,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 17.0208,
+      "step": 58
+    },
+    {
+      "epoch": 0.06707403723177491,
+      "grad_norm": 6.299598217010498,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 14.5744,
+      "step": 59
+    },
+    {
+      "epoch": 0.06821088532044906,
+      "grad_norm": 8.590055465698242,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 12.2129,
+      "step": 60
+    },
+    {
+      "epoch": 0.0693477334091232,
+      "grad_norm": 20.570341110229492,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 16.3481,
+      "step": 61
+    },
+    {
+      "epoch": 0.07048458149779736,
+      "grad_norm": 6.487506866455078,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 13.0091,
+      "step": 62
+    },
+    {
+      "epoch": 0.07162142958647151,
+      "grad_norm": 7.227597236633301,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 19.0134,
+      "step": 63
+    },
+    {
+      "epoch": 0.07275827767514566,
+      "grad_norm": 9.197311401367188,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 16.6898,
+      "step": 64
+    },
+    {
+      "epoch": 0.0738951257638198,
+      "grad_norm": 8.438094139099121,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 8.918,
+      "step": 65
+    },
+    {
+      "epoch": 0.07503197385249397,
+      "grad_norm": 8.239605903625488,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 15.4048,
+      "step": 66
+    },
+    {
+      "epoch": 0.07616882194116811,
+      "grad_norm": 6.532566547393799,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.6503,
+      "step": 67
+    },
+    {
+      "epoch": 0.07730567002984226,
+      "grad_norm": 7.610565185546875,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 13.7247,
+      "step": 68
+    },
+    {
+      "epoch": 0.07844251811851641,
+      "grad_norm": 7.103012561798096,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 13.4282,
+      "step": 69
+    },
+    {
+      "epoch": 0.07957936620719057,
+      "grad_norm": 7.29534912109375,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 14.6105,
+      "step": 70
+    },
+    {
+      "epoch": 0.08071621429586472,
+      "grad_norm": 7.118172645568848,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 15.4684,
+      "step": 71
+    },
+    {
+      "epoch": 0.08185306238453886,
+      "grad_norm": 8.032720565795898,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 12.0972,
+      "step": 72
+    },
+    {
+      "epoch": 0.08298991047321301,
+      "grad_norm": 5.702446937561035,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 14.8636,
+      "step": 73
+    },
+    {
+      "epoch": 0.08412675856188717,
+      "grad_norm": 6.32309627532959,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 14.2163,
+      "step": 74
+    },
+    {
+      "epoch": 0.08526360665056132,
+      "grad_norm": 6.813048362731934,
+      "learning_rate": 0.0,
+      "loss": 11.5691,
+      "step": 75
+    },
+    {
+      "epoch": 0.08526360665056132,
+      "eval_loss": 1.739717721939087,
+      "eval_runtime": 66.4587,
+      "eval_samples_per_second": 11.15,
+      "eval_steps_per_second": 5.582,
+      "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": 3056462708342784.0,
+  "total_flos": 4573317650448384.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null