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:d54ae07b5843e5bd379379f541b073c7aef630001f4499fbd216078a704231bb
+oid sha256:40494549b4406533c299da8e3ab999981b74e5a0bd30c23b2f04d314fe13e73b
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:092a1d44c7294b99c9d98715571605721f1f81905864afb7868d17f2cc69f26c
+oid sha256:4f6d0ca3794e9368c336148eabf7afb8822908d6bc23f9eba14aea311c4ce121
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:353bc68ec7c1c1f7f88aa08ec0a672f82cf829385fb27bbfd3564b4629669fd7
+oid sha256:8dc7e1a295df9114854a507bc86161f7e5b05bc4a28d6ca3047f1dd8fbca7a6e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d899d9a97a2b6486c53b9cbe1ddab8c7978ac7055694e6eba93d71f787e4a1fd
+oid sha256:de473c64a67af75120ec0d8a1c740afb01d291e49d2f33af7e7c4ee244fb7a79
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c98819d670d0a414ee366314b44443cad8530cb213ba9a4318c72d720e2cbc6a
+oid sha256:8acbfea744d5ea54c135b6a4eef1e1d01ebb338447cb93af37c7c135a7d57b76
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ba426c5150f1687b1785c0888f36e77c2c3a18e21234f812bb0c1d88d673c7f
+oid sha256:8e29fb16948f9473df9b05bc121381462a35ca15693f4bb3a074782ba0dafd8f
 size 15024

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": 0.11286681715575621,
+  "epoch": 0.22573363431151242,
   "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": 889.453,
       "eval_steps_per_second": 111.926,
       "step": 25
+    },
+    {
+      "epoch": 0.11738148984198646,
+      "grad_norm": 0.3440849781036377,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 10.3604,
+      "step": 26
+    },
+    {
+      "epoch": 0.12189616252821671,
+      "grad_norm": 0.46047431230545044,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 10.3535,
+      "step": 27
+    },
+    {
+      "epoch": 0.12641083521444696,
+      "grad_norm": 0.4075244069099426,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 10.3506,
+      "step": 28
+    },
+    {
+      "epoch": 0.1309255079006772,
+      "grad_norm": 0.3751038610935211,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 10.3532,
+      "step": 29
+    },
+    {
+      "epoch": 0.13544018058690746,
+      "grad_norm": 0.4397486448287964,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 10.3374,
+      "step": 30
+    },
+    {
+      "epoch": 0.1399548532731377,
+      "grad_norm": 0.5865473747253418,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 10.3264,
+      "step": 31
+    },
+    {
+      "epoch": 0.14446952595936793,
+      "grad_norm": 0.4633133113384247,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 10.3369,
+      "step": 32
+    },
+    {
+      "epoch": 0.1489841986455982,
+      "grad_norm": 0.5107329487800598,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 10.3342,
+      "step": 33
+    },
+    {
+      "epoch": 0.15349887133182843,
+      "grad_norm": 0.47929638624191284,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 10.34,
+      "step": 34
+    },
+    {
+      "epoch": 0.1580135440180587,
+      "grad_norm": 0.4484359920024872,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 10.3541,
+      "step": 35
+    },
+    {
+      "epoch": 0.16252821670428894,
+      "grad_norm": 0.42778682708740234,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 10.353,
+      "step": 36
+    },
+    {
+      "epoch": 0.1670428893905192,
+      "grad_norm": 0.4300452768802643,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 10.3391,
+      "step": 37
+    },
+    {
+      "epoch": 0.17155756207674944,
+      "grad_norm": 0.45499032735824585,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 10.3304,
+      "step": 38
+    },
+    {
+      "epoch": 0.17607223476297967,
+      "grad_norm": 0.5377456545829773,
+      "learning_rate": 5e-05,
+      "loss": 10.3295,
+      "step": 39
+    },
+    {
+      "epoch": 0.18058690744920994,
+      "grad_norm": 0.49316221475601196,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 10.3386,
+      "step": 40
+    },
+    {
+      "epoch": 0.18510158013544017,
+      "grad_norm": 0.5076413750648499,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 10.3365,
+      "step": 41
+    },
+    {
+      "epoch": 0.18961625282167044,
+      "grad_norm": 0.4477654993534088,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3443,
+      "step": 42
+    },
+    {
+      "epoch": 0.19413092550790068,
+      "grad_norm": 0.5417852997779846,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 10.3234,
+      "step": 43
+    },
+    {
+      "epoch": 0.1986455981941309,
+      "grad_norm": 0.4367150366306305,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 10.3257,
+      "step": 44
+    },
+    {
+      "epoch": 0.20316027088036118,
+      "grad_norm": 0.45080235600471497,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3438,
+      "step": 45
+    },
+    {
+      "epoch": 0.2076749435665914,
+      "grad_norm": 0.5051379203796387,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 10.3313,
+      "step": 46
+    },
+    {
+      "epoch": 0.21218961625282168,
+      "grad_norm": 0.44620585441589355,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 10.3198,
+      "step": 47
+    },
+    {
+      "epoch": 0.21670428893905191,
+      "grad_norm": 0.40200865268707275,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3412,
+      "step": 48
+    },
+    {
+      "epoch": 0.22121896162528218,
+      "grad_norm": 0.4732573330402374,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 10.3381,
+      "step": 49
+    },
+    {
+      "epoch": 0.22573363431151242,
+      "grad_norm": 0.5160777568817139,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 10.3322,
+      "step": 50
+    },
+    {
+      "epoch": 0.22573363431151242,
+      "eval_loss": 10.320771217346191,
+      "eval_runtime": 0.8387,
+      "eval_samples_per_second": 890.713,
+      "eval_steps_per_second": 112.084,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 10692014899200.0,
+  "total_flos": 21384029798400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null