Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd800d3a54250e5a3a8503420f336a780a2471387a8c8b8aa9b2ed68f1609a5a
+oid sha256:14c56755326646089007a8d28de53621f05e3546b5e3b745dd908a50f63e5db8
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38fac1a61f9334a461badcb4e40410bfa2596401185407aae0ca1196ad1a8118
+oid sha256:2d4ad8742a18d98dbbf396ea3001b0d7c090b5a8c8971bec3058d3db9a8bfb4d
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2d8b97ca24cb0d141d9d3163bd9e91597cb59d10141b5e542107fbe6a2ed973
+oid sha256:b7b4a9a1e70602e378db11b8858260d969a98748357a815093eec0d227912861
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011145786892554615,
+  "epoch": 0.02229157378510923,
   "eval_steps": 5,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,221 @@
       "eval_samples_per_second": 6.616,
       "eval_steps_per_second": 0.83,
       "step": 25
+    },
+    {
+      "epoch": 0.0115916183682568,
+      "grad_norm": 8.244012832641602,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 3.1986,
+      "step": 26
+    },
+    {
+      "epoch": 0.012037449843958983,
+      "grad_norm": 0.592692494392395,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 3.2394,
+      "step": 27
+    },
+    {
+      "epoch": 0.012483281319661168,
+      "grad_norm": 27.265233993530273,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 3.6016,
+      "step": 28
+    },
+    {
+      "epoch": 0.012929112795363353,
+      "grad_norm": 0.6079114675521851,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 3.0391,
+      "step": 29
+    },
+    {
+      "epoch": 0.013374944271065538,
+      "grad_norm": 0.6926823258399963,
+      "learning_rate": 5e-05,
+      "loss": 2.9551,
+      "step": 30
+    },
+    {
+      "epoch": 0.013374944271065538,
+      "eval_loss": 1.5596755743026733,
+      "eval_runtime": 285.5845,
+      "eval_samples_per_second": 6.615,
+      "eval_steps_per_second": 0.83,
+      "step": 30
+    },
+    {
+      "epoch": 0.013820775746767721,
+      "grad_norm": 1.037886142730713,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 2.9686,
+      "step": 31
+    },
+    {
+      "epoch": 0.014266607222469906,
+      "grad_norm": 0.4959910213947296,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.9515,
+      "step": 32
+    },
+    {
+      "epoch": 0.014712438698172091,
+      "grad_norm": 0.8415336012840271,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 2.9902,
+      "step": 33
+    },
+    {
+      "epoch": 0.015158270173874276,
+      "grad_norm": 9.876391410827637,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 3.0443,
+      "step": 34
+    },
+    {
+      "epoch": 0.01560410164957646,
+      "grad_norm": 0.9276679158210754,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.9878,
+      "step": 35
+    },
+    {
+      "epoch": 0.01560410164957646,
+      "eval_loss": 1.551698923110962,
+      "eval_runtime": 285.4731,
+      "eval_samples_per_second": 6.617,
+      "eval_steps_per_second": 0.83,
+      "step": 35
+    },
+    {
+      "epoch": 0.016049933125278644,
+      "grad_norm": 0.8320974111557007,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 3.4585,
+      "step": 36
+    },
+    {
+      "epoch": 0.01649576460098083,
+      "grad_norm": 0.5846897959709167,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 3.0534,
+      "step": 37
+    },
+    {
+      "epoch": 0.016941596076683014,
+      "grad_norm": 0.558754026889801,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 3.2693,
+      "step": 38
+    },
+    {
+      "epoch": 0.017387427552385197,
+      "grad_norm": 0.6277199983596802,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 2.895,
+      "step": 39
+    },
+    {
+      "epoch": 0.017833259028087384,
+      "grad_norm": 58.99296569824219,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.2742,
+      "step": 40
+    },
+    {
+      "epoch": 0.017833259028087384,
+      "eval_loss": 1.547116994857788,
+      "eval_runtime": 285.366,
+      "eval_samples_per_second": 6.62,
+      "eval_steps_per_second": 0.831,
+      "step": 40
+    },
+    {
+      "epoch": 0.018279090503789567,
+      "grad_norm": 8.236936569213867,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 3.0018,
+      "step": 41
+    },
+    {
+      "epoch": 0.018724921979491754,
+      "grad_norm": 0.9785589575767517,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.8609,
+      "step": 42
+    },
+    {
+      "epoch": 0.019170753455193937,
+      "grad_norm": 10.383113861083984,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 3.2274,
+      "step": 43
+    },
+    {
+      "epoch": 0.01961658493089612,
+      "grad_norm": 0.4968133270740509,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 3.0423,
+      "step": 44
+    },
+    {
+      "epoch": 0.020062416406598307,
+      "grad_norm": 3.623450756072998,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.5747,
+      "step": 45
+    },
+    {
+      "epoch": 0.020062416406598307,
+      "eval_loss": 1.545439600944519,
+      "eval_runtime": 285.2282,
+      "eval_samples_per_second": 6.623,
+      "eval_steps_per_second": 0.831,
+      "step": 45
+    },
+    {
+      "epoch": 0.02050824788230049,
+      "grad_norm": 1.6544840335845947,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 3.0012,
+      "step": 46
+    },
+    {
+      "epoch": 0.020954079358002677,
+      "grad_norm": 0.5400304794311523,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 3.1082,
+      "step": 47
+    },
+    {
+      "epoch": 0.02139991083370486,
+      "grad_norm": 0.9255496263504028,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 3.3183,
+      "step": 48
+    },
+    {
+      "epoch": 0.021845742309407043,
+      "grad_norm": 1.5495226383209229,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 3.2117,
+      "step": 49
+    },
+    {
+      "epoch": 0.02229157378510923,
+      "grad_norm": 1.1511247158050537,
+      "learning_rate": 0.0,
+      "loss": 3.1134,
+      "step": 50
+    },
+    {
+      "epoch": 0.02229157378510923,
+      "eval_loss": 1.5448092222213745,
+      "eval_runtime": 285.2713,
+      "eval_samples_per_second": 6.622,
+      "eval_steps_per_second": 0.831,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -244,12 +459,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1516854942105600.0,
+  "total_flos": 3033709884211200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null