Training in progress, step 68, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7509a38f253530a371c4f75f1b5dcbea50b136a890c57a3ee3bc66254766e63f
+oid sha256:0cbd533dccb77e0785bfd785c08160c33c48af3e1618c6fbf736240de3d65215
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:943bc6dada57397735ca818193ed0b16c7c4f3889837989d8dfbb6097b4a594f
+oid sha256:1dd6641d202d84fd9c4a931b1c22e5c8fda108a40e8f1b7c343a952a7374b7d4
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c543948a535496f0dde46e00d90041e4b64736cb4a715d793f78a309b0450ac5
+oid sha256:24d2bf6b77f8850a276f23712d3998c1486d4cad7b87b73826a884c0e5e13663
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9fa892ecd236e652150058649b13d9161331d85e374c4bec1d60ad6a556c3a9
+oid sha256:40aaba2d15c70d89033b94214bc8306c06d04f2fbceef0fdedf952808109d707
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013089509143407122,
+  "epoch": 0.01745267885787616,
   "eval_steps": 17,
-  "global_step": 51,
+  "global_step": 68,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -158,6 +158,49 @@
       "eval_samples_per_second": 13.278,
       "eval_steps_per_second": 1.661,
       "step": 51
+    },
+    {
+      "epoch": 0.013859480269489894,
+      "grad_norm": 0.3275759220123291,
+      "learning_rate": 8.73410738492077e-05,
+      "loss": 2.3057,
+      "step": 54
+    },
+    {
+      "epoch": 0.014629451395572667,
+      "grad_norm": 0.29645541310310364,
+      "learning_rate": 8.564642241456986e-05,
+      "loss": 2.3326,
+      "step": 57
+    },
+    {
+      "epoch": 0.015399422521655439,
+      "grad_norm": 0.3317429721355438,
+      "learning_rate": 8.386407858128706e-05,
+      "loss": 2.3392,
+      "step": 60
+    },
+    {
+      "epoch": 0.01616939364773821,
+      "grad_norm": 0.3201993405818939,
+      "learning_rate": 8.199842702516583e-05,
+      "loss": 2.3972,
+      "step": 63
+    },
+    {
+      "epoch": 0.01693936477382098,
+      "grad_norm": 0.3513089716434479,
+      "learning_rate": 8.005405736415126e-05,
+      "loss": 2.3498,
+      "step": 66
+    },
+    {
+      "epoch": 0.01745267885787616,
+      "eval_loss": 2.3205010890960693,
+      "eval_runtime": 493.7323,
+      "eval_samples_per_second": 13.293,
+      "eval_steps_per_second": 1.663,
+      "step": 68
     }
   ],
   "logging_steps": 3,
@@ -177,7 +220,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.41634467692544e+16,
+  "total_flos": 9.855498037336474e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null