Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e830957ac14db3a9074c9d4201c9207500b7bc106f894e3e93d3ff83b141254e
+oid sha256:4bd395ff392de10dbf507363089228065f3921ee4afb771ab2083ad0ecf8111d
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:095ef47cee3fe623a1cab782aabc0865174f6863144a23ad426d06bea2581852
+oid sha256:13268935b511018fb3808abe4e253fde7d3a2a35f79c40f0735522529c299f06
 size 127788180

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c146388a3e375aff2b63de7d9a527540be61e69f806a75222257789592fb97ff
+oid sha256:2ae74989a289f237870432c4bfbed9d0140c66c5599ca6162057c3e918720333
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41a785ff17fa78518f56867cd303b6ba59257cf76b3fcae729747c3054010b8f
+oid sha256:6f553c3f2a57a3b0a91a846090b6b148022ac8a2f86073705977ee1d8d0d6fa2
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
+oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.47515705311250717,
+  "epoch": 0.7127355796687607,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 5.578,
       "eval_steps_per_second": 1.406,
       "step": 26
+    },
+    {
+      "epoch": 0.4934323243860651,
+      "grad_norm": 0.2927595376968384,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0162,
+      "step": 27
+    },
+    {
+      "epoch": 0.5117075956596231,
+      "grad_norm": 0.1291339248418808,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0014,
+      "step": 28
+    },
+    {
+      "epoch": 0.5299828669331811,
+      "grad_norm": 0.24390743672847748,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.01,
+      "step": 29
+    },
+    {
+      "epoch": 0.548258138206739,
+      "grad_norm": 0.07123029232025146,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0007,
+      "step": 30
+    },
+    {
+      "epoch": 0.566533409480297,
+      "grad_norm": 0.03508315980434418,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0004,
+      "step": 31
+    },
+    {
+      "epoch": 0.584808680753855,
+      "grad_norm": 0.33584150671958923,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0116,
+      "step": 32
+    },
+    {
+      "epoch": 0.6030839520274129,
+      "grad_norm": 0.18450838327407837,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0017,
+      "step": 33
+    },
+    {
+      "epoch": 0.6213592233009708,
+      "grad_norm": 0.30941474437713623,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0089,
+      "step": 34
+    },
+    {
+      "epoch": 0.6396344945745288,
+      "grad_norm": 0.3536520004272461,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0024,
+      "step": 35
+    },
+    {
+      "epoch": 0.6579097658480868,
+      "grad_norm": 0.3076607882976532,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0032,
+      "step": 36
+    },
+    {
+      "epoch": 0.6761850371216448,
+      "grad_norm": 0.09125807881355286,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.005,
+      "step": 37
+    },
+    {
+      "epoch": 0.6944603083952028,
+      "grad_norm": 0.09541966021060944,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0006,
+      "step": 38
+    },
+    {
+      "epoch": 0.7127355796687607,
+      "grad_norm": 0.042761899530887604,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0003,
+      "step": 39
+    },
+    {
+      "epoch": 0.7127355796687607,
+      "eval_loss": 0.005322535987943411,
+      "eval_runtime": 66.1258,
+      "eval_samples_per_second": 5.58,
+      "eval_steps_per_second": 1.406,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.056272233502081e+18,
+  "total_flos": 1.5844083502531215e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null