Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:755724b0631bfa5b087014e3dbf8d0215f850b25f24fa70503b4f276adfa500a
+oid sha256:b9d8770789ae188d824f935c833fb6154c1771f2523b9a265607cc8de617fa66
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a51d610e51dde111b8baafea1bc86bdb7a626fb9789e73914b9d918f5d1e8f11
+oid sha256:5fd2126e28877d7c02fcd7f4f072709b258592af91f236684f0d81b18d896347
 size 1001863522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e05f8d69b932da2eb0a0218c5401beec260093f7ac541477b6236d01606fe88
+oid sha256:52d95415a130ba4a535d63832f8606bf6d417c27a3808eb72adcfe868d9ffd10
 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": 0.09115770282588878,
+  "epoch": 0.18231540565177756,
   "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": 6.431,
       "eval_steps_per_second": 3.229,
       "step": 25
+    },
+    {
+      "epoch": 0.09480401093892434,
+      "grad_norm": 1.8341199159622192,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 9.8156,
+      "step": 26
+    },
+    {
+      "epoch": 0.09845031905195989,
+      "grad_norm": 1.9661328792572021,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 10.0505,
+      "step": 27
+    },
+    {
+      "epoch": 0.10209662716499544,
+      "grad_norm": 2.0087292194366455,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 9.4768,
+      "step": 28
+    },
+    {
+      "epoch": 0.105742935278031,
+      "grad_norm": 2.208437442779541,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 9.5623,
+      "step": 29
+    },
+    {
+      "epoch": 0.10938924339106655,
+      "grad_norm": 2.0323190689086914,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 10.4219,
+      "step": 30
+    },
+    {
+      "epoch": 0.11303555150410209,
+      "grad_norm": 1.9072842597961426,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 9.1549,
+      "step": 31
+    },
+    {
+      "epoch": 0.11668185961713765,
+      "grad_norm": 2.2138895988464355,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 10.4151,
+      "step": 32
+    },
+    {
+      "epoch": 0.1203281677301732,
+      "grad_norm": 2.239079236984253,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 10.1372,
+      "step": 33
+    },
+    {
+      "epoch": 0.12397447584320875,
+      "grad_norm": 2.131258964538574,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 9.4423,
+      "step": 34
+    },
+    {
+      "epoch": 0.1276207839562443,
+      "grad_norm": 2.1453845500946045,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 9.3926,
+      "step": 35
+    },
+    {
+      "epoch": 0.13126709206927986,
+      "grad_norm": 3.005169153213501,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 9.9575,
+      "step": 36
+    },
+    {
+      "epoch": 0.1349134001823154,
+      "grad_norm": 2.2520599365234375,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 10.8131,
+      "step": 37
+    },
+    {
+      "epoch": 0.13855970829535097,
+      "grad_norm": 2.4393112659454346,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 12.2067,
+      "step": 38
+    },
+    {
+      "epoch": 0.1422060164083865,
+      "grad_norm": 2.4657881259918213,
+      "learning_rate": 5e-05,
+      "loss": 11.86,
+      "step": 39
+    },
+    {
+      "epoch": 0.14585232452142205,
+      "grad_norm": 2.2421562671661377,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 11.2129,
+      "step": 40
+    },
+    {
+      "epoch": 0.14949863263445762,
+      "grad_norm": 2.500739812850952,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 10.8666,
+      "step": 41
+    },
+    {
+      "epoch": 0.15314494074749316,
+      "grad_norm": 2.3504726886749268,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3909,
+      "step": 42
+    },
+    {
+      "epoch": 0.15679124886052873,
+      "grad_norm": 2.4648520946502686,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 12.7165,
+      "step": 43
+    },
+    {
+      "epoch": 0.16043755697356427,
+      "grad_norm": 4.018390655517578,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 12.8443,
+      "step": 44
+    },
+    {
+      "epoch": 0.1640838650865998,
+      "grad_norm": 2.460999011993408,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 13.6509,
+      "step": 45
+    },
+    {
+      "epoch": 0.16773017319963537,
+      "grad_norm": 3.274535655975342,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 11.1371,
+      "step": 46
+    },
+    {
+      "epoch": 0.17137648131267091,
+      "grad_norm": 3.133227586746216,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 11.5938,
+      "step": 47
+    },
+    {
+      "epoch": 0.17502278942570648,
+      "grad_norm": 3.6370604038238525,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 13.0006,
+      "step": 48
+    },
+    {
+      "epoch": 0.17866909753874202,
+      "grad_norm": 4.2182936668396,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 12.1576,
+      "step": 49
+    },
+    {
+      "epoch": 0.18231540565177756,
+      "grad_norm": 5.010047912597656,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 12.5341,
+      "step": 50
+    },
+    {
+      "epoch": 0.18231540565177756,
+      "eval_loss": 1.2788481712341309,
+      "eval_runtime": 36.0057,
+      "eval_samples_per_second": 6.416,
+      "eval_steps_per_second": 3.222,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.3785926656e+16,
+  "total_flos": 1.27571853312e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null