Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3950845c2f51b1328e58e9169572a7c4a3ef6e00b28c43cb5b11383bf89e299e
+oid sha256:fe4bbd4b2af70a6a7dfad23961d0806044434c2044cbff65e98a1168d5e33e96
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb2ff07ed57d2c969030046f636f8f692a9924ef77abaf02607e737d00d30d6b
+oid sha256:2d7610f6c31f6c195d1617c119ab83678c9883c2cd1cbb7926d2580d272ba4ad
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c46a9041bc76fb74c1eb6e3c3aba7745904ff75fbb300564ecb7f564d26082ff
+oid sha256:6d50e9dcbcf5cae7f0b94ed81f513ff8871f9e6f54116aaa09f004cc015eebf0
 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": 0.0031496062992125984,
+  "epoch": 0.006299212598425197,
   "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": 3.953,
       "eval_steps_per_second": 1.977,
       "step": 25
+    },
+    {
+      "epoch": 0.003275590551181102,
+      "grad_norm": 1.4434717893600464,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.4383,
+      "step": 26
+    },
+    {
+      "epoch": 0.0034015748031496064,
+      "grad_norm": 1.187625765800476,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.4064,
+      "step": 27
+    },
+    {
+      "epoch": 0.00352755905511811,
+      "grad_norm": 1.288070797920227,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.3957,
+      "step": 28
+    },
+    {
+      "epoch": 0.0036535433070866144,
+      "grad_norm": 1.3888908624649048,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.4349,
+      "step": 29
+    },
+    {
+      "epoch": 0.003779527559055118,
+      "grad_norm": 1.2192840576171875,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.3789,
+      "step": 30
+    },
+    {
+      "epoch": 0.003905511811023622,
+      "grad_norm": 1.7539172172546387,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.4327,
+      "step": 31
+    },
+    {
+      "epoch": 0.004031496062992126,
+      "grad_norm": 1.2005337476730347,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.416,
+      "step": 32
+    },
+    {
+      "epoch": 0.00415748031496063,
+      "grad_norm": 1.3382314443588257,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.4181,
+      "step": 33
+    },
+    {
+      "epoch": 0.004283464566929134,
+      "grad_norm": 1.445595622062683,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 0.4458,
+      "step": 34
+    },
+    {
+      "epoch": 0.004409448818897638,
+      "grad_norm": 1.3078209161758423,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.3524,
+      "step": 35
+    },
+    {
+      "epoch": 0.004535433070866142,
+      "grad_norm": 1.3248423337936401,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.4059,
+      "step": 36
+    },
+    {
+      "epoch": 0.0046614173228346455,
+      "grad_norm": 1.2014515399932861,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.3862,
+      "step": 37
+    },
+    {
+      "epoch": 0.00478740157480315,
+      "grad_norm": 1.251442313194275,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 0.4217,
+      "step": 38
+    },
+    {
+      "epoch": 0.004913385826771654,
+      "grad_norm": 1.549546480178833,
+      "learning_rate": 5e-05,
+      "loss": 0.3972,
+      "step": 39
+    },
+    {
+      "epoch": 0.005039370078740157,
+      "grad_norm": 1.5308916568756104,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 0.4102,
+      "step": 40
+    },
+    {
+      "epoch": 0.0051653543307086614,
+      "grad_norm": 1.7657283544540405,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 0.4259,
+      "step": 41
+    },
+    {
+      "epoch": 0.005291338582677166,
+      "grad_norm": 1.9394474029541016,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.384,
+      "step": 42
+    },
+    {
+      "epoch": 0.005417322834645669,
+      "grad_norm": 1.7663687467575073,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.3748,
+      "step": 43
+    },
+    {
+      "epoch": 0.005543307086614173,
+      "grad_norm": 1.4035406112670898,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.3698,
+      "step": 44
+    },
+    {
+      "epoch": 0.005669291338582677,
+      "grad_norm": 1.6968581676483154,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.4055,
+      "step": 45
+    },
+    {
+      "epoch": 0.005795275590551181,
+      "grad_norm": 1.6501572132110596,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.376,
+      "step": 46
+    },
+    {
+      "epoch": 0.005921259842519685,
+      "grad_norm": 1.4387761354446411,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.3797,
+      "step": 47
+    },
+    {
+      "epoch": 0.006047244094488189,
+      "grad_norm": 2.231095552444458,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.409,
+      "step": 48
+    },
+    {
+      "epoch": 0.0061732283464566926,
+      "grad_norm": 2.0894861221313477,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.4164,
+      "step": 49
+    },
+    {
+      "epoch": 0.006299212598425197,
+      "grad_norm": 2.8405890464782715,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 0.4957,
+      "step": 50
+    },
+    {
+      "epoch": 0.006299212598425197,
+      "eval_loss": 0.46602168679237366,
+      "eval_runtime": 1691.0057,
+      "eval_samples_per_second": 3.953,
+      "eval_steps_per_second": 1.977,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.73005226082304e+16,
+  "total_flos": 7.46010452164608e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null