Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37e6dd4c68876dc0008299e0f12d5cbea1bb4f8e695f2d9694d4d8b9ec46a089
+oid sha256:2f294deb0acaf5fa2e5f9d497230122ffdcb95c899309b335237bd3e10f0c3b6
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23cb2486344c9d56175c01a97e523b28bcad0becd8bf8cfe500fc6ea19680ecf
+oid sha256:e852674f370eb61e8ae81eb11d59597c5487a3bc4d4397cd6806ed777402ad0d
 size 313998650

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca0c2cc2fe9da84ef169e69c35803a5d3c75f4bd626a379eb08f2f7158086110
+oid sha256:3b10ba552649461620dbe891d8d8feec865c974519169d2d4bc45d08da5cd1fd
 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": 0.0008438533720380747,
+  "epoch": 0.0016877067440761494,
   "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": 8.983,
       "eval_steps_per_second": 4.492,
       "step": 25
+    },
+    {
+      "epoch": 0.0008776075069195976,
+      "grad_norm": 1.2517900466918945,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.49,
+      "step": 26
+    },
+    {
+      "epoch": 0.0009113616418011207,
+      "grad_norm": 1.1255788803100586,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.4652,
+      "step": 27
+    },
+    {
+      "epoch": 0.0009451157766826436,
+      "grad_norm": 1.3350865840911865,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.5945,
+      "step": 28
+    },
+    {
+      "epoch": 0.0009788699115641666,
+      "grad_norm": 1.255922555923462,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.4186,
+      "step": 29
+    },
+    {
+      "epoch": 0.0010126240464456897,
+      "grad_norm": 1.1698178052902222,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.4548,
+      "step": 30
+    },
+    {
+      "epoch": 0.0010463781813272125,
+      "grad_norm": 1.1624618768692017,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.5209,
+      "step": 31
+    },
+    {
+      "epoch": 0.0010801323162087356,
+      "grad_norm": 1.9189029932022095,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.5466,
+      "step": 32
+    },
+    {
+      "epoch": 0.0011138864510902586,
+      "grad_norm": 1.1308246850967407,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.445,
+      "step": 33
+    },
+    {
+      "epoch": 0.0011476405859717816,
+      "grad_norm": 1.261982798576355,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 0.4534,
+      "step": 34
+    },
+    {
+      "epoch": 0.0011813947208533045,
+      "grad_norm": 1.2305161952972412,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.4823,
+      "step": 35
+    },
+    {
+      "epoch": 0.0012151488557348275,
+      "grad_norm": 1.3532754182815552,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.4471,
+      "step": 36
+    },
+    {
+      "epoch": 0.0012489029906163505,
+      "grad_norm": 1.5262309312820435,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.5651,
+      "step": 37
+    },
+    {
+      "epoch": 0.0012826571254978736,
+      "grad_norm": 1.0819740295410156,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 0.5211,
+      "step": 38
+    },
+    {
+      "epoch": 0.0013164112603793964,
+      "grad_norm": 1.3941339254379272,
+      "learning_rate": 5e-05,
+      "loss": 0.46,
+      "step": 39
+    },
+    {
+      "epoch": 0.0013501653952609194,
+      "grad_norm": 1.6077882051467896,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 0.5456,
+      "step": 40
+    },
+    {
+      "epoch": 0.0013839195301424425,
+      "grad_norm": 1.1812937259674072,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 0.4872,
+      "step": 41
+    },
+    {
+      "epoch": 0.0014176736650239655,
+      "grad_norm": 1.304977536201477,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.4647,
+      "step": 42
+    },
+    {
+      "epoch": 0.0014514277999054883,
+      "grad_norm": 1.7109375,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.5107,
+      "step": 43
+    },
+    {
+      "epoch": 0.0014851819347870114,
+      "grad_norm": 1.3880994319915771,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.4708,
+      "step": 44
+    },
+    {
+      "epoch": 0.0015189360696685344,
+      "grad_norm": 1.2330398559570312,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.4897,
+      "step": 45
+    },
+    {
+      "epoch": 0.0015526902045500575,
+      "grad_norm": 1.0758552551269531,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.4025,
+      "step": 46
+    },
+    {
+      "epoch": 0.0015864443394315803,
+      "grad_norm": 1.2690551280975342,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.5129,
+      "step": 47
+    },
+    {
+      "epoch": 0.0016201984743131033,
+      "grad_norm": 1.5134022235870361,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.3607,
+      "step": 48
+    },
+    {
+      "epoch": 0.0016539526091946264,
+      "grad_norm": 1.6051034927368164,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.5501,
+      "step": 49
+    },
+    {
+      "epoch": 0.0016877067440761494,
+      "grad_norm": 4.110562324523926,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 0.7889,
+      "step": 50
+    },
+    {
+      "epoch": 0.0016877067440761494,
+      "eval_loss": 0.4801631271839142,
+      "eval_runtime": 2778.0051,
+      "eval_samples_per_second": 8.981,
+      "eval_steps_per_second": 4.491,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0083160855412736e+16,
+  "total_flos": 2.0017309481435136e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null