Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08c8dfa6409cf0e41673fd2e6bec4829a2714c3a27387af5dac2434dee5f2968
+oid sha256:2d4a968b66836e725cac9a83ace7e662126e5fc296754449688b1bfddf82fd07
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55451ad3736ea9fdea0a3c49d7be68efecd307dc38896a7014636dc55fa6869c
+oid sha256:3d56ae489420e26ef83894805ff1728ef3d352fb2d0009bfe33122f2f025a971
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c1a4adb1b1ce84bf3c63fcc11644b695c4c5059b5073a8fbe3711b1a33b7ecf
+oid sha256:4f609db69d69d667281cf63cfd5fda478d6e1005e82a9604de65cd269795f5a1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beb167787cdd9594eed637547cf4a56f4a4d8ea359757a120c76bb5d91190782
+oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7017543859649122,
+  "epoch": 0.935672514619883,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 6.414,
       "eval_steps_per_second": 6.414,
       "step": 75
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 2.6566221714019775,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 2.3354,
+      "step": 76
+    },
+    {
+      "epoch": 0.7204678362573099,
+      "grad_norm": 2.7329909801483154,
+      "learning_rate": 3.053416295410026e-05,
+      "loss": 2.3228,
+      "step": 77
+    },
+    {
+      "epoch": 0.7298245614035088,
+      "grad_norm": 2.649616241455078,
+      "learning_rate": 2.8066019966134904e-05,
+      "loss": 2.2475,
+      "step": 78
+    },
+    {
+      "epoch": 0.7391812865497076,
+      "grad_norm": 2.667179584503174,
+      "learning_rate": 2.5685517452260567e-05,
+      "loss": 2.6119,
+      "step": 79
+    },
+    {
+      "epoch": 0.7485380116959064,
+      "grad_norm": 2.4291374683380127,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 2.3532,
+      "step": 80
+    },
+    {
+      "epoch": 0.7578947368421053,
+      "grad_norm": 2.347785472869873,
+      "learning_rate": 2.119892463932781e-05,
+      "loss": 2.5149,
+      "step": 81
+    },
+    {
+      "epoch": 0.7672514619883041,
+      "grad_norm": 2.5152335166931152,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.4291,
+      "step": 82
+    },
+    {
+      "epoch": 0.776608187134503,
+      "grad_norm": 2.509918212890625,
+      "learning_rate": 1.7096242744495837e-05,
+      "loss": 2.2923,
+      "step": 83
+    },
+    {
+      "epoch": 0.7859649122807018,
+      "grad_norm": 2.535485029220581,
+      "learning_rate": 1.5195190384357404e-05,
+      "loss": 2.2462,
+      "step": 84
+    },
+    {
+      "epoch": 0.7953216374269005,
+      "grad_norm": 2.524515151977539,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 2.3981,
+      "step": 85
+    },
+    {
+      "epoch": 0.8046783625730994,
+      "grad_norm": 2.53387713432312,
+      "learning_rate": 1.1705240714107302e-05,
+      "loss": 2.3842,
+      "step": 86
+    },
+    {
+      "epoch": 0.8140350877192982,
+      "grad_norm": 2.3665547370910645,
+      "learning_rate": 1.0120595370083318e-05,
+      "loss": 2.0239,
+      "step": 87
+    },
+    {
+      "epoch": 0.8233918128654971,
+      "grad_norm": 2.359243631362915,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 2.3947,
+      "step": 88
+    },
+    {
+      "epoch": 0.8327485380116959,
+      "grad_norm": 2.518428325653076,
+      "learning_rate": 7.281614543321269e-06,
+      "loss": 2.1668,
+      "step": 89
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 2.3977906703948975,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 2.2668,
+      "step": 90
+    },
+    {
+      "epoch": 0.8514619883040936,
+      "grad_norm": 2.6835556030273438,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 2.255,
+      "step": 91
+    },
+    {
+      "epoch": 0.8608187134502924,
+      "grad_norm": 2.503506898880005,
+      "learning_rate": 3.873830406168111e-06,
+      "loss": 2.2606,
+      "step": 92
+    },
+    {
+      "epoch": 0.8701754385964913,
+      "grad_norm": 2.585240125656128,
+      "learning_rate": 2.970427372400353e-06,
+      "loss": 2.1736,
+      "step": 93
+    },
+    {
+      "epoch": 0.87953216374269,
+      "grad_norm": 2.5094244480133057,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 2.3768,
+      "step": 94
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 2.3380393981933594,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 2.4361,
+      "step": 95
+    },
+    {
+      "epoch": 0.8982456140350877,
+      "grad_norm": 2.5652716159820557,
+      "learning_rate": 9.731931258429638e-07,
+      "loss": 2.1897,
+      "step": 96
+    },
+    {
+      "epoch": 0.9076023391812865,
+      "grad_norm": 2.379408836364746,
+      "learning_rate": 5.478104631726711e-07,
+      "loss": 2.397,
+      "step": 97
+    },
+    {
+      "epoch": 0.9169590643274854,
+      "grad_norm": 2.5933423042297363,
+      "learning_rate": 2.4359497401758024e-07,
+      "loss": 2.5667,
+      "step": 98
+    },
+    {
+      "epoch": 0.9263157894736842,
+      "grad_norm": 2.5865583419799805,
+      "learning_rate": 6.09172980904238e-08,
+      "loss": 2.4204,
+      "step": 99
+    },
+    {
+      "epoch": 0.935672514619883,
+      "grad_norm": 2.6614973545074463,
+      "learning_rate": 0.0,
+      "loss": 2.624,
+      "step": 100
+    },
+    {
+      "epoch": 0.935672514619883,
+      "eval_loss": 2.30788254737854,
+      "eval_runtime": 13.8631,
+      "eval_samples_per_second": 6.492,
+      "eval_steps_per_second": 6.492,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -578,12 +761,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.305621389377536e+16,
+  "total_flos": 1.738765926137856e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null