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:ebedb82f8f80f1d83184422667e7ca02340a20c0414db33f19cababf31c0edaf
+oid sha256:156851059b77c4d7020160b80d5becc95df67c510d798077699cdb4c8917146c
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f226bf7ef13778cfee789ebaa17bfb88e7252f92210cc18a9977de1c2a1982d3
+oid sha256:b33af5b48ccb00c224f465ac6d92ed128c008ed363a96d4beae550320a50cdc9
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5224358fefc4a6c20673e2c295e1dbc37dff7b6514472d01bd9b5aa0159f5f9
+oid sha256:3295d9b8e6727a0572a17fcd9e9c0c197ca020ea3fd15f4c9bf4d70bd654e602
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
+oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.025303110173958882,
+  "epoch": 0.0316288877174486,
   "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": 7.126,
       "eval_steps_per_second": 0.892,
       "step": 36
+    },
+    {
+      "epoch": 0.027411702688455455,
+      "grad_norm": 0.1926659792661667,
+      "learning_rate": 3.824798160583012e-05,
+      "loss": 0.7353,
+      "step": 39
+    },
+    {
+      "epoch": 0.02952029520295203,
+      "grad_norm": 0.20542505383491516,
+      "learning_rate": 3.5959278669726935e-05,
+      "loss": 0.8628,
+      "step": 42
+    },
+    {
+      "epoch": 0.0316288877174486,
+      "grad_norm": 0.1803169548511505,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 0.8016,
+      "step": 45
+    },
+    {
+      "epoch": 0.0316288877174486,
+      "eval_loss": 0.7604277729988098,
+      "eval_runtime": 336.9862,
+      "eval_samples_per_second": 7.113,
+      "eval_steps_per_second": 0.89,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.519755283136512e+16,
+  "total_flos": 1.189969410392064e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null