Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da34647703224a9f662b568e9c6ac938877f751c29ff7c900992680b81d9cfac
+oid sha256:921bb82ae17117b8621123cad231cc96b11b51415097c9afe198d94b22076dea
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caadb536e9ebbd0dc5e86b403b64c40a9bba1000243c7940de28e02b455bb0b7
+oid sha256:c5180a6a48f042324d7beea7da8cf40d05e7ca52e2c6f053e271ce03dee502e0
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d000b4df7c48eb60558df333b0b72870a8d302bfff400709f913ef5a3e459d94
+oid sha256:49ddb965365707e9cf823c0aae963aeebeb54a3819b41dd6759a3b8366ca82d3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
+oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.32193158953722334,
+  "epoch": 0.36217303822937624,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -170,6 +170,28 @@
       "eval_samples_per_second": 6.327,
       "eval_steps_per_second": 0.817,
       "step": 40
+    },
+    {
+      "epoch": 0.3380281690140845,
+      "grad_norm": 0.06008715555071831,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0047,
+      "step": 42
+    },
+    {
+      "epoch": 0.36217303822937624,
+      "grad_norm": 0.05889170616865158,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0063,
+      "step": 45
+    },
+    {
+      "epoch": 0.36217303822937624,
+      "eval_loss": 0.0061826580204069614,
+      "eval_runtime": 33.0232,
+      "eval_samples_per_second": 6.329,
+      "eval_steps_per_second": 0.818,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1992682951029555e+17,
+  "total_flos": 1.3501196529775411e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null