Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68e432ff3408dc5bba0dfb5cd5721d8944be4ffb93d772d854c70e2381e8d173
+oid sha256:a96a12628b3e0170d420e6c480f3112fd0b4aa7e7e665c9447fb9a39a2fc8908
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83589cd3dee88aa88b308b8cf3b1d44b9bbe6e0a83a82892eb84b211c4fc4fa4
+oid sha256:a8b052e5a8ff99b128943144629d0c75360af506a32296070193695b49a665a6
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90507dcf4d39b7dfe3254777cbe8ff4e49c392485a00c9ad55a285ad440e8b26
+oid sha256:2790fbe4c7b99ec49d4b4c03b9ab968ac7530589725905d8485c8345302070f4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
+oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1593625498007968,
+  "epoch": 0.3187250996015936,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 9.306,
       "eval_steps_per_second": 4.671,
       "step": 25
+    },
+    {
+      "epoch": 0.1657370517928287,
+      "grad_norm": 0.44654762744903564,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.0428,
+      "step": 26
+    },
+    {
+      "epoch": 0.17211155378486057,
+      "grad_norm": 0.4134571850299835,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0506,
+      "step": 27
+    },
+    {
+      "epoch": 0.17848605577689244,
+      "grad_norm": 0.24441246688365936,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.0159,
+      "step": 28
+    },
+    {
+      "epoch": 0.1848605577689243,
+      "grad_norm": 0.44964155554771423,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.054,
+      "step": 29
+    },
+    {
+      "epoch": 0.19123505976095617,
+      "grad_norm": 0.22025738656520844,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0233,
+      "step": 30
+    },
+    {
+      "epoch": 0.19760956175298805,
+      "grad_norm": 0.5241214632987976,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.0493,
+      "step": 31
+    },
+    {
+      "epoch": 0.20398406374501993,
+      "grad_norm": 0.7061783671379089,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.0439,
+      "step": 32
+    },
+    {
+      "epoch": 0.2103585657370518,
+      "grad_norm": 1.2703156471252441,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.0372,
+      "step": 33
+    },
+    {
+      "epoch": 0.21673306772908366,
+      "grad_norm": 0.614372193813324,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 0.0617,
+      "step": 34
+    },
+    {
+      "epoch": 0.22310756972111553,
+      "grad_norm": 0.6067790389060974,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0296,
+      "step": 35
+    },
+    {
+      "epoch": 0.2294820717131474,
+      "grad_norm": 0.2267586588859558,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.022,
+      "step": 36
+    },
+    {
+      "epoch": 0.2358565737051793,
+      "grad_norm": 0.16750691831111908,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.017,
+      "step": 37
+    },
+    {
+      "epoch": 0.24223107569721117,
+      "grad_norm": 0.482281357049942,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 0.0178,
+      "step": 38
+    },
+    {
+      "epoch": 0.24860557768924302,
+      "grad_norm": 1.8239290714263916,
+      "learning_rate": 5e-05,
+      "loss": 0.2721,
+      "step": 39
+    },
+    {
+      "epoch": 0.2549800796812749,
+      "grad_norm": 0.316111296415329,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 0.0421,
+      "step": 40
+    },
+    {
+      "epoch": 0.2613545816733068,
+      "grad_norm": 0.2607780992984772,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 0.0442,
+      "step": 41
+    },
+    {
+      "epoch": 0.26772908366533865,
+      "grad_norm": 0.34263813495635986,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0468,
+      "step": 42
+    },
+    {
+      "epoch": 0.27410358565737053,
+      "grad_norm": 0.23391367495059967,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0463,
+      "step": 43
+    },
+    {
+      "epoch": 0.2804780876494024,
+      "grad_norm": 0.1930956095457077,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.039,
+      "step": 44
+    },
+    {
+      "epoch": 0.2868525896414343,
+      "grad_norm": 0.19257277250289917,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0351,
+      "step": 45
+    },
+    {
+      "epoch": 0.2932270916334661,
+      "grad_norm": 0.2096574753522873,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.0425,
+      "step": 46
+    },
+    {
+      "epoch": 0.299601593625498,
+      "grad_norm": 0.18197529017925262,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.0397,
+      "step": 47
+    },
+    {
+      "epoch": 0.30597609561752986,
+      "grad_norm": 0.18108899891376495,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0401,
+      "step": 48
+    },
+    {
+      "epoch": 0.31235059760956174,
+      "grad_norm": 0.21128466725349426,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.0355,
+      "step": 49
+    },
+    {
+      "epoch": 0.3187250996015936,
+      "grad_norm": 0.20305347442626953,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 0.0345,
+      "step": 50
+    },
+    {
+      "epoch": 0.3187250996015936,
+      "eval_loss": 0.04450911656022072,
+      "eval_runtime": 28.4605,
+      "eval_samples_per_second": 9.311,
+      "eval_steps_per_second": 4.673,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.6502401196032e+16,
+  "total_flos": 1.33004802392064e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null