Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4856283095e861a9b4892d9ec3fbb2ef4ddc4c246bf11ceca3f9aad3a53ea733
+oid sha256:a52fede561c5b0071b97c88f7f1accfbd096449b7e3dfa04a2d96442205c54e2
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db2199488cfe02f909b52aeb318025f107ec7e7c7f4b8bcf01e9139a0997445a
+oid sha256:56a3dfab0a0748ebcb8a48cc9d467b8cb27f6fb930c7a0f252d18ac6338061ce
 size 180543866

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f0e1be4e6a2c004c12dfe8d6cd095be73a8bf7b2d4f7398921fda849246d025
+oid sha256:c8b8ba95982c7e1d308216fc72a1f7f09b31cf15039a4666dbb57145c56bfcaf
 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": 0.0005671506352087115,
+  "epoch": 0.001134301270417423,
   "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": 29.951,
       "eval_steps_per_second": 14.976,
       "step": 25
+    },
+    {
+      "epoch": 0.0005898366606170599,
+      "grad_norm": 1.7302452325820923,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 2.0632,
+      "step": 26
+    },
+    {
+      "epoch": 0.0006125226860254084,
+      "grad_norm": 1.7510278224945068,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.1041,
+      "step": 27
+    },
+    {
+      "epoch": 0.0006352087114337568,
+      "grad_norm": 1.4340311288833618,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 2.0235,
+      "step": 28
+    },
+    {
+      "epoch": 0.0006578947368421052,
+      "grad_norm": 1.4099208116531372,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 2.0296,
+      "step": 29
+    },
+    {
+      "epoch": 0.0006805807622504537,
+      "grad_norm": 1.4559657573699951,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.989,
+      "step": 30
+    },
+    {
+      "epoch": 0.0007032667876588021,
+      "grad_norm": 1.659051537513733,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.0203,
+      "step": 31
+    },
+    {
+      "epoch": 0.0007259528130671506,
+      "grad_norm": 2.0444107055664062,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 2.0082,
+      "step": 32
+    },
+    {
+      "epoch": 0.0007486388384754991,
+      "grad_norm": 2.0712087154388428,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 1.9541,
+      "step": 33
+    },
+    {
+      "epoch": 0.0007713248638838476,
+      "grad_norm": 1.8016096353530884,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 1.9549,
+      "step": 34
+    },
+    {
+      "epoch": 0.000794010889292196,
+      "grad_norm": 4.192699432373047,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 1.9673,
+      "step": 35
+    },
+    {
+      "epoch": 0.0008166969147005445,
+      "grad_norm": 3.760023355484009,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 1.9319,
+      "step": 36
+    },
+    {
+      "epoch": 0.0008393829401088929,
+      "grad_norm": 2.344935894012451,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 1.9,
+      "step": 37
+    },
+    {
+      "epoch": 0.0008620689655172414,
+      "grad_norm": 2.100687026977539,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 1.865,
+      "step": 38
+    },
+    {
+      "epoch": 0.0008847549909255898,
+      "grad_norm": 3.1228349208831787,
+      "learning_rate": 5e-05,
+      "loss": 1.8805,
+      "step": 39
+    },
+    {
+      "epoch": 0.0009074410163339383,
+      "grad_norm": 2.3817391395568848,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 1.8904,
+      "step": 40
+    },
+    {
+      "epoch": 0.0009301270417422867,
+      "grad_norm": 2.454270839691162,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 1.9163,
+      "step": 41
+    },
+    {
+      "epoch": 0.0009528130671506353,
+      "grad_norm": 2.8007712364196777,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.8889,
+      "step": 42
+    },
+    {
+      "epoch": 0.0009754990925589837,
+      "grad_norm": 3.751268148422241,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.7979,
+      "step": 43
+    },
+    {
+      "epoch": 0.000998185117967332,
+      "grad_norm": 2.9384889602661133,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 1.8534,
+      "step": 44
+    },
+    {
+      "epoch": 0.0010208711433756805,
+      "grad_norm": 2.206895589828491,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.8246,
+      "step": 45
+    },
+    {
+      "epoch": 0.001043557168784029,
+      "grad_norm": 2.771620512008667,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 1.7729,
+      "step": 46
+    },
+    {
+      "epoch": 0.0010662431941923776,
+      "grad_norm": 4.623754978179932,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 1.8095,
+      "step": 47
+    },
+    {
+      "epoch": 0.001088929219600726,
+      "grad_norm": 9.82066822052002,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.8858,
+      "step": 48
+    },
+    {
+      "epoch": 0.0011116152450090745,
+      "grad_norm": 15.103967666625977,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 2.0393,
+      "step": 49
+    },
+    {
+      "epoch": 0.001134301270417423,
+      "grad_norm": 14.861157417297363,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 2.1831,
+      "step": 50
+    },
+    {
+      "epoch": 0.001134301270417423,
+      "eval_loss": 2.4072601795196533,
+      "eval_runtime": 1241.41,
+      "eval_samples_per_second": 29.901,
+      "eval_steps_per_second": 14.951,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4894017925939200.0,
+  "total_flos": 9788035851878400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null