Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:495d3244df0d5c425b1057ec38c0263268b229bbab30df9f00d22f3106346f3e
+oid sha256:82eaf68cb2b7738118e0fe2db0a695219566f54d44c7b0fbaf0cb57dee99cf8d
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a99b509f62716c94c46b0bbfb1991353248b4bfc2c7e8b697ad5f0af49f7bb22
+oid sha256:1f1bcfe34c8daeff7460447a9d3a8946825d8dab5df0c066b20d6d05d485cdbf
 size 160284754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1da65c6fd85f4aa14aa34f294c78fa464be27f768771994054ee1aa907752aba
+oid sha256:4555e4c65e128e3c73410113c546065354d2476ccf2887955b4785922a9a9a7c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab098d97568c94b26c087e3ff4fd649c3aaa775049e6dbf18e927dde2c5feee8
+oid sha256:06829946ff807c7143728448cc1bf384944e638865601317db4b29a92003bb11
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010040160642570281,
+  "epoch": 0.020080321285140562,
   "eval_steps": 2,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -66,6 +66,65 @@
       "learning_rate": 0.0001,
       "loss": 5.6022,
       "step": 5
+    },
+    {
+      "epoch": 0.012048192771084338,
+      "grad_norm": 1.1300783157348633,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 6.2136,
+      "step": 6
+    },
+    {
+      "epoch": 0.012048192771084338,
+      "eval_loss": 1.5139317512512207,
+      "eval_runtime": 24.4198,
+      "eval_samples_per_second": 8.6,
+      "eval_steps_per_second": 4.3,
+      "step": 6
+    },
+    {
+      "epoch": 0.014056224899598393,
+      "grad_norm": 0.7629399299621582,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 5.591,
+      "step": 7
+    },
+    {
+      "epoch": 0.01606425702811245,
+      "grad_norm": 0.991378664970398,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 5.6169,
+      "step": 8
+    },
+    {
+      "epoch": 0.01606425702811245,
+      "eval_loss": 1.4971964359283447,
+      "eval_runtime": 24.1606,
+      "eval_samples_per_second": 8.692,
+      "eval_steps_per_second": 4.346,
+      "step": 8
+    },
+    {
+      "epoch": 0.018072289156626505,
+      "grad_norm": 1.3900601863861084,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 5.0918,
+      "step": 9
+    },
+    {
+      "epoch": 0.020080321285140562,
+      "grad_norm": 1.6595548391342163,
+      "learning_rate": 5e-05,
+      "loss": 5.4715,
+      "step": 10
+    },
+    {
+      "epoch": 0.020080321285140562,
+      "eval_loss": 1.4780693054199219,
+      "eval_runtime": 24.0817,
+      "eval_samples_per_second": 8.72,
+      "eval_steps_per_second": 4.36,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -85,7 +144,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1791624166244352.0,
+  "total_flos": 3501810870386688.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null