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:c5d3f1be5d57d2f4b78d7d04f00b2f77bd37d9b5fdc0c95d8cc49f0eca67ae1c
+oid sha256:822c578f50f300ceeb35d1c3b82df3d82e7f81f6d7fd5c0daf65dd176a69078a
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d53a6adeec212d7a729a3bf761d857a3eeeff5cda1255d3f3f9f0ee63b45d74e
+oid sha256:da59b0cebc254da91420c8d630b99628027a2658f1baee38f40b706d4a9e746d
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7905a562e3922e49c02b13a62a655eca4805e88aae4026f1bfc339b1c47ffff
+oid sha256:8b39a79df42874b54e01731649d4c9656970ca1cb57dc8dfa52f950eff5cbdb5
 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": 0.0010664960273022983,
+  "epoch": 0.0021329920546045967,
   "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": 5.899,
       "eval_steps_per_second": 2.949,
       "step": 25
+    },
+    {
+      "epoch": 0.0011091558683943902,
+      "grad_norm": 3.144263982772827,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 3.8628,
+      "step": 26
+    },
+    {
+      "epoch": 0.0011518157094864822,
+      "grad_norm": 2.507157325744629,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.8496,
+      "step": 27
+    },
+    {
+      "epoch": 0.001194475550578574,
+      "grad_norm": 2.559713125228882,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 2.8976,
+      "step": 28
+    },
+    {
+      "epoch": 0.001237135391670666,
+      "grad_norm": 2.1491596698760986,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 2.703,
+      "step": 29
+    },
+    {
+      "epoch": 0.0012797952327627579,
+      "grad_norm": 2.6858789920806885,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 3.2626,
+      "step": 30
+    },
+    {
+      "epoch": 0.00132245507385485,
+      "grad_norm": 2.5397956371307373,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.7342,
+      "step": 31
+    },
+    {
+      "epoch": 0.0013651149149469417,
+      "grad_norm": 2.6062099933624268,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 3.3048,
+      "step": 32
+    },
+    {
+      "epoch": 0.0014077747560390338,
+      "grad_norm": 2.4756972789764404,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 2.9948,
+      "step": 33
+    },
+    {
+      "epoch": 0.0014504345971311256,
+      "grad_norm": 2.7714602947235107,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 3.2915,
+      "step": 34
+    },
+    {
+      "epoch": 0.0014930944382232176,
+      "grad_norm": 2.65149188041687,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 3.2514,
+      "step": 35
+    },
+    {
+      "epoch": 0.0015357542793153094,
+      "grad_norm": 2.8307254314422607,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 3.299,
+      "step": 36
+    },
+    {
+      "epoch": 0.0015784141204074015,
+      "grad_norm": 2.442545175552368,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 3.0294,
+      "step": 37
+    },
+    {
+      "epoch": 0.0016210739614994933,
+      "grad_norm": 2.2670016288757324,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 3.3772,
+      "step": 38
+    },
+    {
+      "epoch": 0.0016637338025915853,
+      "grad_norm": 2.8332643508911133,
+      "learning_rate": 5e-05,
+      "loss": 3.2163,
+      "step": 39
+    },
+    {
+      "epoch": 0.0017063936436836774,
+      "grad_norm": 2.668203830718994,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 2.9927,
+      "step": 40
+    },
+    {
+      "epoch": 0.0017490534847757692,
+      "grad_norm": 2.528712034225464,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 2.7003,
+      "step": 41
+    },
+    {
+      "epoch": 0.0017917133258678612,
+      "grad_norm": 3.2600278854370117,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 3.7579,
+      "step": 42
+    },
+    {
+      "epoch": 0.001834373166959953,
+      "grad_norm": 2.814138412475586,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 3.1766,
+      "step": 43
+    },
+    {
+      "epoch": 0.001877033008052045,
+      "grad_norm": 3.453101873397827,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 3.5888,
+      "step": 44
+    },
+    {
+      "epoch": 0.001919692849144137,
+      "grad_norm": 2.941481828689575,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.1291,
+      "step": 45
+    },
+    {
+      "epoch": 0.001962352690236229,
+      "grad_norm": 3.0425057411193848,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 3.3131,
+      "step": 46
+    },
+    {
+      "epoch": 0.0020050125313283208,
+      "grad_norm": 3.546339750289917,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 3.8228,
+      "step": 47
+    },
+    {
+      "epoch": 0.0020476723724204126,
+      "grad_norm": 3.8112733364105225,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.4266,
+      "step": 48
+    },
+    {
+      "epoch": 0.002090332213512505,
+      "grad_norm": 3.7606093883514404,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 3.7293,
+      "step": 49
+    },
+    {
+      "epoch": 0.0021329920546045967,
+      "grad_norm": 6.579668045043945,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 4.5136,
+      "step": 50
+    },
+    {
+      "epoch": 0.0021329920546045967,
+      "eval_loss": 0.3695688843727112,
+      "eval_runtime": 3346.9603,
+      "eval_samples_per_second": 5.898,
+      "eval_steps_per_second": 2.949,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.303407560635187e+16,
+  "total_flos": 6.590380257784627e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null