Training in progress, step 84, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d678ddcd815c64cb34bb5e65c89513607ba053e4a6c9e16f79264ea3c082326
+oid sha256:1b6fb9b08c2e10e053f3d81ad8d2e0e24099462e2b5a2472f9154ee3481f0255
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:905a59ce198902d98f99592337983373607e49d00ff43b167d36922497a116a4
+oid sha256:760dba386ee4560fcbe21cb431d3d8086e73cb0d13b223b37fde2ea0eec443fa
 size 51613348

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e576a0cf5d4d2361e5146f1dceac71aa1a3d4db54e3485b22fbce47c7516e942
+oid sha256:0d87bc4656c379289d41186281c9cbad1876e328c641d66e6bd6c9c084caea09
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3101e5b327a48ff01ba2c03545970ed09eef14c8b179cc52c21d8ec3e72950f1
+oid sha256:200db5d515f7fe0d1c4e0bac456fe6b9042173a9f2b890836ad8c5bd6dfb4d2e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006291899179806,
+  "epoch": 0.012583798359612,
   "eval_steps": 42,
-  "global_step": 42,
+  "global_step": 84,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -121,6 +121,112 @@
       "eval_samples_per_second": 35.888,
       "eval_steps_per_second": 4.488,
       "step": 42
+    },
+    {
+      "epoch": 0.006741320549792143,
+      "grad_norm": 0.13759616017341614,
+      "learning_rate": 4.937319780454559e-05,
+      "loss": 1.1133,
+      "step": 45
+    },
+    {
+      "epoch": 0.007190741919778285,
+      "grad_norm": 0.14887671172618866,
+      "learning_rate": 4.926169550509787e-05,
+      "loss": 1.1339,
+      "step": 48
+    },
+    {
+      "epoch": 0.007640163289764428,
+      "grad_norm": 0.13235358893871307,
+      "learning_rate": 4.914121772213898e-05,
+      "loss": 1.0057,
+      "step": 51
+    },
+    {
+      "epoch": 0.00808958465975057,
+      "grad_norm": 0.14951473474502563,
+      "learning_rate": 4.9011809025775486e-05,
+      "loss": 1.0919,
+      "step": 54
+    },
+    {
+      "epoch": 0.008539006029736713,
+      "grad_norm": 0.1409119963645935,
+      "learning_rate": 4.887351729005726e-05,
+      "loss": 1.143,
+      "step": 57
+    },
+    {
+      "epoch": 0.008988427399722857,
+      "grad_norm": 0.13198496401309967,
+      "learning_rate": 4.8726393675266716e-05,
+      "loss": 1.0853,
+      "step": 60
+    },
+    {
+      "epoch": 0.009437848769709,
+      "grad_norm": 0.15319645404815674,
+      "learning_rate": 4.8570492608992325e-05,
+      "loss": 1.0534,
+      "step": 63
+    },
+    {
+      "epoch": 0.009887270139695143,
+      "grad_norm": 0.1532219797372818,
+      "learning_rate": 4.8405871765993433e-05,
+      "loss": 1.1016,
+      "step": 66
+    },
+    {
+      "epoch": 0.010336691509681285,
+      "grad_norm": 0.14198264479637146,
+      "learning_rate": 4.82325920468638e-05,
+      "loss": 1.029,
+      "step": 69
+    },
+    {
+      "epoch": 0.010786112879667428,
+      "grad_norm": 0.12415461987257004,
+      "learning_rate": 4.805071755550177e-05,
+      "loss": 1.1565,
+      "step": 72
+    },
+    {
+      "epoch": 0.01123553424965357,
+      "grad_norm": 0.1350441873073578,
+      "learning_rate": 4.7860315575395316e-05,
+      "loss": 1.1276,
+      "step": 75
+    },
+    {
+      "epoch": 0.011684955619639713,
+      "grad_norm": 0.12075574696063995,
+      "learning_rate": 4.766145654473095e-05,
+      "loss": 1.0753,
+      "step": 78
+    },
+    {
+      "epoch": 0.012134376989625857,
+      "grad_norm": 0.11550460755825043,
+      "learning_rate": 4.745421403033548e-05,
+      "loss": 1.0078,
+      "step": 81
+    },
+    {
+      "epoch": 0.012583798359612,
+      "grad_norm": 0.12455905228853226,
+      "learning_rate": 4.72386647004603e-05,
+      "loss": 1.0373,
+      "step": 84
+    },
+    {
+      "epoch": 0.012583798359612,
+      "eval_loss": 1.1157194375991821,
+      "eval_runtime": 312.8234,
+      "eval_samples_per_second": 35.94,
+      "eval_steps_per_second": 4.495,
+      "step": 84
     }
   ],
   "logging_steps": 3,
@@ -140,7 +246,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3438839322312704e+16,
+  "total_flos": 2.765900651220173e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null