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:ba769a8518b703318fb50ec0f856f3debaabfac894332b3efbda487ff002a1ac
+oid sha256:4ed1e8e98a3b0d7bce1a489d41abc4051b77ab2faf969fe9e00495bff7c8e7a7
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fac0a59a674845a28b12987443b28a5b806173435f68d0abca5c63b68915c12
+oid sha256:0ec97a4bae5f4f421b91055d6bdc92e652cefa73fee36b383f4a4ff523b4765a
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:719020131bf833c90632c6b01b06c5301e1876ba50a1273eb06ec350ba411a1a
+oid sha256:f537d6df07787c716bf4621ea221744763bd88e92a07f95d1fa6f6a06d8ac757
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
+oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2634578847371754,
+  "epoch": 0.39518682710576314,
   "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": 42.45,
       "eval_steps_per_second": 21.352,
       "step": 26
+    },
+    {
+      "epoch": 0.27359088030398987,
+      "grad_norm": 2.240417718887329,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 0.2279,
+      "step": 27
+    },
+    {
+      "epoch": 0.28372387587080433,
+      "grad_norm": 1.6692705154418945,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.1103,
+      "step": 28
+    },
+    {
+      "epoch": 0.29385687143761874,
+      "grad_norm": 1.1334484815597534,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 0.107,
+      "step": 29
+    },
+    {
+      "epoch": 0.3039898670044332,
+      "grad_norm": 1.8195340633392334,
+      "learning_rate": 5e-05,
+      "loss": 0.0558,
+      "step": 30
+    },
+    {
+      "epoch": 0.3141228625712476,
+      "grad_norm": 1.8854806423187256,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 0.3479,
+      "step": 31
+    },
+    {
+      "epoch": 0.32425585813806207,
+      "grad_norm": 2.1316421031951904,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.1326,
+      "step": 32
+    },
+    {
+      "epoch": 0.3343888537048765,
+      "grad_norm": 2.0381174087524414,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.3254,
+      "step": 33
+    },
+    {
+      "epoch": 0.34452184927169094,
+      "grad_norm": 1.3313711881637573,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.1059,
+      "step": 34
+    },
+    {
+      "epoch": 0.3546548448385054,
+      "grad_norm": 0.8397698998451233,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0336,
+      "step": 35
+    },
+    {
+      "epoch": 0.3647878404053198,
+      "grad_norm": 1.6760809421539307,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.0713,
+      "step": 36
+    },
+    {
+      "epoch": 0.37492083597213427,
+      "grad_norm": 0.7013064622879028,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.0364,
+      "step": 37
+    },
+    {
+      "epoch": 0.3850538315389487,
+      "grad_norm": 0.7092528939247131,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.1465,
+      "step": 38
+    },
+    {
+      "epoch": 0.39518682710576314,
+      "grad_norm": 0.9758922457695007,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.1129,
+      "step": 39
+    },
+    {
+      "epoch": 0.39518682710576314,
+      "eval_loss": 0.10418615490198135,
+      "eval_runtime": 3.9348,
+      "eval_samples_per_second": 42.441,
+      "eval_steps_per_second": 21.348,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.713735840301056e+16,
+  "total_flos": 2.570603760451584e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null