Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2f2971439d88f6db0bc8827138b0e15bf7514b74aa28fdbbe00e3b10f7a2248
+oid sha256:dedc4283d74b96d3365730aade2d5ce973d88a3f30dbcfff941cbb89a7655559
 size 338298

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88254e9b0975f5d59302c648d167fdb1882638b5516bfcd2a47b8961fa05da7b
+oid sha256:ac3dd7fe23ff03c3e30af5c1cad2f92251d3a0191178e1d707204085e9c08e67
 size 418030

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dbb97c11c6f1318074260e982b59a91d8a5584bd279926c1beca30dfe95c3f0
+oid sha256:c4c0b0bf7901f8440d57c140f37d42ec44e25b28f62a126cb668b5c02dd5da3a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
+oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2755102040816326,
+  "epoch": 0.32142857142857145,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 610.543,
       "eval_steps_per_second": 155.411,
       "step": 54
+    },
+    {
+      "epoch": 0.29081632653061223,
+      "grad_norm": 0.22721412777900696,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 6.8316,
+      "step": 57
+    },
+    {
+      "epoch": 0.30612244897959184,
+      "grad_norm": 0.2554455101490021,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 6.8269,
+      "step": 60
+    },
+    {
+      "epoch": 0.32142857142857145,
+      "grad_norm": 0.1824101209640503,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 6.8329,
+      "step": 63
+    },
+    {
+      "epoch": 0.32142857142857145,
+      "eval_loss": 6.830348014831543,
+      "eval_runtime": 0.2768,
+      "eval_samples_per_second": 596.042,
+      "eval_steps_per_second": 151.72,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 519009140736.0,
+  "total_flos": 605510664192.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null