Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8177036542e0a92bf699dcaf0d502f1fab05b8f7f1a560a89b531b0108d51eac
+oid sha256:94971f99e97ec0550e2a125b660b0ea6317e0e0438890f713cc221db742ac5c9
 size 228140600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7849e9d3441b409ecd91cadbf47f4b399d4571e62cf4ba3cd4b7c40dbe86fc9
+oid sha256:edca4fea10b8d375c396ebc7d99110615ebdde61385d29cf83b7cde67514baa9
 size 116472340

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28aa984a8995e23145e5379ede84981a1e489c4cf41652e1960df7f446e10019
+oid sha256:eabfcd1b25a9d15bb11d9c2889384891cc1a9db7b0c9fa8eb6b8ffe55907bbf9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
+oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12371134020618557,
+  "epoch": 0.15463917525773196,
   "eval_steps": 9,
-  "global_step": 36,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,35 @@
       "eval_samples_per_second": 6.805,
       "eval_steps_per_second": 0.861,
       "step": 36
+    },
+    {
+      "epoch": 0.13402061855670103,
+      "grad_norm": 2.198150634765625,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 2.795,
+      "step": 39
+    },
+    {
+      "epoch": 0.14432989690721648,
+      "grad_norm": 1.8142603635787964,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 2.7169,
+      "step": 42
+    },
+    {
+      "epoch": 0.15463917525773196,
+      "grad_norm": 1.9104666709899902,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.8454,
+      "step": 45
+    },
+    {
+      "epoch": 0.15463917525773196,
+      "eval_loss": 0.720156729221344,
+      "eval_runtime": 72.0724,
+      "eval_samples_per_second": 6.799,
+      "eval_steps_per_second": 0.86,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2808770639888384e+17,
+  "total_flos": 1.5782235252719616e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null