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:fa08a4096aafeaa2bf1ed6944fac878f3f5959aa95f91461a601247a82d5f2ca
+oid sha256:48488aa8be640fd61cfe535f77c3431a5d526046e72ff4ff26d925e924a341b5
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e635b245b1cc8a0337ac22e80934bd1789c559a01266ecca4afdff544ddacecc
+oid sha256:79ba2f96298e02f6c1dc2f3c07106e76323a8ccda782cbeb726696941ce43f8e
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd3acbef01f966bd1f7d345be9f8aa68242b07cc3d63832fbe0274ad1778ffa4
+oid sha256:d8cc330a79fd720d64a2e46161cee2bfc8976c23b0235a144073fb971c9bb68c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa0fde01e60897f55f4ebaca5a490a1a483a2c53b2ae8e7543860a62c5b3298c
+oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01287128712871287,
+  "epoch": 0.019306930693069307,
   "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": 63.345,
       "eval_steps_per_second": 31.71,
       "step": 26
+    },
+    {
+      "epoch": 0.013366336633663366,
+      "grad_norm": 0.6701183915138245,
+      "learning_rate": 3.083613409639764e-05,
+      "loss": 2.6973,
+      "step": 27
+    },
+    {
+      "epoch": 0.013861386138613862,
+      "grad_norm": 0.6425264477729797,
+      "learning_rate": 2.8910861626005776e-05,
+      "loss": 2.3563,
+      "step": 28
+    },
+    {
+      "epoch": 0.014356435643564357,
+      "grad_norm": 0.6737343072891235,
+      "learning_rate": 2.6961477393196126e-05,
+      "loss": 2.4938,
+      "step": 29
+    },
+    {
+      "epoch": 0.01485148514851485,
+      "grad_norm": 0.6865612268447876,
+      "learning_rate": 2.5e-05,
+      "loss": 2.5242,
+      "step": 30
+    },
+    {
+      "epoch": 0.015346534653465346,
+      "grad_norm": 0.6353932023048401,
+      "learning_rate": 2.303852260680388e-05,
+      "loss": 2.565,
+      "step": 31
+    },
+    {
+      "epoch": 0.015841584158415842,
+      "grad_norm": 0.6973043084144592,
+      "learning_rate": 2.1089138373994223e-05,
+      "loss": 2.4031,
+      "step": 32
+    },
+    {
+      "epoch": 0.016336633663366337,
+      "grad_norm": 1.4028022289276123,
+      "learning_rate": 1.9163865903602374e-05,
+      "loss": 3.0209,
+      "step": 33
+    },
+    {
+      "epoch": 0.016831683168316833,
+      "grad_norm": 0.6376410722732544,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 2.6413,
+      "step": 34
+    },
+    {
+      "epoch": 0.017326732673267328,
+      "grad_norm": 0.584199845790863,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 2.3657,
+      "step": 35
+    },
+    {
+      "epoch": 0.01782178217821782,
+      "grad_norm": 0.5928731560707092,
+      "learning_rate": 1.3650237506511331e-05,
+      "loss": 2.247,
+      "step": 36
+    },
+    {
+      "epoch": 0.018316831683168316,
+      "grad_norm": 0.6492427587509155,
+      "learning_rate": 1.1937535882101281e-05,
+      "loss": 2.4935,
+      "step": 37
+    },
+    {
+      "epoch": 0.01881188118811881,
+      "grad_norm": 0.7328959107398987,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 2.4119,
+      "step": 38
+    },
+    {
+      "epoch": 0.019306930693069307,
+      "grad_norm": 0.55412757396698,
+      "learning_rate": 8.763798791745411e-06,
+      "loss": 2.355,
+      "step": 39
+    },
+    {
+      "epoch": 0.019306930693069307,
+      "eval_loss": 2.5016350746154785,
+      "eval_runtime": 13.3692,
+      "eval_samples_per_second": 63.654,
+      "eval_steps_per_second": 31.864,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 812139530944512.0,
+  "total_flos": 1227801495601152.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null