Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cf4d9e783998b87097e584219f0e28763e3bb9d1df44966538ed481f8205a56
+oid sha256:169b5157c1f2169d7ddf19760727c7853ef916dabe014979c10565e11bb8b53a
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80493b4e33f691949823fb8e2bdbd7554e1587cb84961dff45b2612953a16c6e
+oid sha256:b34110dce25b2501eaf3960e0b541ce604c8a97402c36129ce4a8f2c8422d00e
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beeab73a951277b8a8e724d489435ec916dfebe12851695aedc37604e9674822
+oid sha256:7b9dfe10278dbf1849e02c4b4451b95c95e574528793482dfb0b228be8ccb8c9
 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": 2.929,
       "eval_steps_per_second": 1.465,
       "step": 25
+    },
+    {
+      "epoch": 0.0011091558683943902,
+      "grad_norm": 2.535912275314331,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 3.8808,
+      "step": 26
+    },
+    {
+      "epoch": 0.0011518157094864822,
+      "grad_norm": 2.5588672161102295,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.8454,
+      "step": 27
+    },
+    {
+      "epoch": 0.001194475550578574,
+      "grad_norm": 2.523439884185791,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 2.9184,
+      "step": 28
+    },
+    {
+      "epoch": 0.001237135391670666,
+      "grad_norm": 2.095428943634033,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 2.7021,
+      "step": 29
+    },
+    {
+      "epoch": 0.0012797952327627579,
+      "grad_norm": 2.7387797832489014,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 3.2581,
+      "step": 30
+    },
+    {
+      "epoch": 0.00132245507385485,
+      "grad_norm": 2.6308884620666504,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.7427,
+      "step": 31
+    },
+    {
+      "epoch": 0.0013651149149469417,
+      "grad_norm": 2.636615037918091,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 3.285,
+      "step": 32
+    },
+    {
+      "epoch": 0.0014077747560390338,
+      "grad_norm": 2.369776487350464,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 3.0001,
+      "step": 33
+    },
+    {
+      "epoch": 0.0014504345971311256,
+      "grad_norm": 2.6059372425079346,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 3.2904,
+      "step": 34
+    },
+    {
+      "epoch": 0.0014930944382232176,
+      "grad_norm": 2.669086456298828,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 3.2649,
+      "step": 35
+    },
+    {
+      "epoch": 0.0015357542793153094,
+      "grad_norm": 2.914031505584717,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 3.3064,
+      "step": 36
+    },
+    {
+      "epoch": 0.0015784141204074015,
+      "grad_norm": 2.5457451343536377,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 3.0397,
+      "step": 37
+    },
+    {
+      "epoch": 0.0016210739614994933,
+      "grad_norm": 2.2913217544555664,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 3.371,
+      "step": 38
+    },
+    {
+      "epoch": 0.0016637338025915853,
+      "grad_norm": 2.8556880950927734,
+      "learning_rate": 5e-05,
+      "loss": 3.2176,
+      "step": 39
+    },
+    {
+      "epoch": 0.0017063936436836774,
+      "grad_norm": 2.8370909690856934,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 2.9915,
+      "step": 40
+    },
+    {
+      "epoch": 0.0017490534847757692,
+      "grad_norm": 2.672523260116577,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 2.6975,
+      "step": 41
+    },
+    {
+      "epoch": 0.0017917133258678612,
+      "grad_norm": 3.1466898918151855,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 3.7516,
+      "step": 42
+    },
+    {
+      "epoch": 0.001834373166959953,
+      "grad_norm": 2.774160861968994,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 3.1729,
+      "step": 43
+    },
+    {
+      "epoch": 0.001877033008052045,
+      "grad_norm": 3.153118133544922,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 3.5701,
+      "step": 44
+    },
+    {
+      "epoch": 0.001919692849144137,
+      "grad_norm": 2.9490132331848145,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.1243,
+      "step": 45
+    },
+    {
+      "epoch": 0.001962352690236229,
+      "grad_norm": 2.9602949619293213,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 3.3011,
+      "step": 46
+    },
+    {
+      "epoch": 0.0020050125313283208,
+      "grad_norm": 3.293994188308716,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 3.8062,
+      "step": 47
+    },
+    {
+      "epoch": 0.0020476723724204126,
+      "grad_norm": 3.6145431995391846,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.4406,
+      "step": 48
+    },
+    {
+      "epoch": 0.002090332213512505,
+      "grad_norm": 3.6309499740600586,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 3.7389,
+      "step": 49
+    },
+    {
+      "epoch": 0.0021329920546045967,
+      "grad_norm": 6.612607955932617,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 4.4957,
+      "step": 50
+    },
+    {
+      "epoch": 0.0021329920546045967,
+      "eval_loss": 0.36898791790008545,
+      "eval_runtime": 6736.9928,
+      "eval_samples_per_second": 2.93,
+      "eval_steps_per_second": 1.465,
+      "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