Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:628dd037aed20dc2b3a91431730c20c702f77b37976597a8c01ee28401142765
+oid sha256:bf2b4f5eff67f45410237416c4cccc74bd41ca5a511e3d9ac899173a97cd6f56
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1ccc07e802293dcd4f5b9086e83b35f0009160a73e7497dd112f0c4e18b165d
+oid sha256:8f79429790de6bada6cadc827665b017692fc33daee136383414f5a43400f49c
 size 81730196

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e79f6ba8fb7ffd48989487f6e68f93db591e92af3a69e568722794c031540f83
+oid sha256:dc0d6a68d922e782698a018376b53b85027f73e542c47378e687b580096f86bd
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecf7ec282beb1f61e959b9e912d5b9b4c3128e903769f4f35493243fd1bdc61b
+oid sha256:57c230e4a3d3176d8f4a84949e99fccf4bc6db16aab7ec60a204be03a7a4d58c
 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": 0.1453529000698812,
+  "epoch": 0.2180293501048218,
   "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": 11.814,
       "eval_steps_per_second": 2.961,
       "step": 26
+    },
+    {
+      "epoch": 0.1509433962264151,
+      "grad_norm": 0.4914432764053345,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.8609,
+      "step": 27
+    },
+    {
+      "epoch": 0.15653389238294899,
+      "grad_norm": 0.35133427381515503,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.8361,
+      "step": 28
+    },
+    {
+      "epoch": 0.16212438853948288,
+      "grad_norm": 0.3233548104763031,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.8291,
+      "step": 29
+    },
+    {
+      "epoch": 0.16771488469601678,
+      "grad_norm": 0.4606425166130066,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.855,
+      "step": 30
+    },
+    {
+      "epoch": 0.17330538085255065,
+      "grad_norm": 0.7441600561141968,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.8387,
+      "step": 31
+    },
+    {
+      "epoch": 0.17889587700908455,
+      "grad_norm": 0.3128848373889923,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.8219,
+      "step": 32
+    },
+    {
+      "epoch": 0.18448637316561844,
+      "grad_norm": 0.33925583958625793,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.8055,
+      "step": 33
+    },
+    {
+      "epoch": 0.19007686932215234,
+      "grad_norm": 0.6340675950050354,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.8227,
+      "step": 34
+    },
+    {
+      "epoch": 0.19566736547868624,
+      "grad_norm": 0.7749468684196472,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.8204,
+      "step": 35
+    },
+    {
+      "epoch": 0.20125786163522014,
+      "grad_norm": 0.3163313865661621,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.7955,
+      "step": 36
+    },
+    {
+      "epoch": 0.206848357791754,
+      "grad_norm": 0.3138035833835602,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.8125,
+      "step": 37
+    },
+    {
+      "epoch": 0.2124388539482879,
+      "grad_norm": 0.3796585500240326,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.7958,
+      "step": 38
+    },
+    {
+      "epoch": 0.2180293501048218,
+      "grad_norm": 0.34551334381103516,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.7706,
+      "step": 39
+    },
+    {
+      "epoch": 0.2180293501048218,
+      "eval_loss": 1.7951258420944214,
+      "eval_runtime": 101.982,
+      "eval_samples_per_second": 11.816,
+      "eval_steps_per_second": 2.961,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.4368258410256794e+17,
+  "total_flos": 8.155238761538519e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null