Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1498e68997d7efa80748284328828a3bb2095fd364da94d35c6ca3f4dea61555
+oid sha256:1a166fd1375d531101b7fe544fadf6ca75cb91e0259b33cdd526e64d4a2ffc1b
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f98f37933ae8e652c4d6bcea0f8ff8a8c6e3287d7990af1d665e7c9d3a2a080
+oid sha256:daac49d5d7c56d84fb7f9ba7c9dee83610088e5c7a7ae5db279cfd5b1e0f0781
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a91207079a4d06a2e0343a805bd4731bdce1f224f8753275a8c1594d4ff5d7d0
+oid sha256:2c595568d5a7bb7b9b57941fb29c461e3dc17e26eb6b784f3922a9394cd85bee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba2da34f28903361f0dc730c5c7c178c98918af7f2f4dbd9a9718ee70beb337c
+oid sha256:31c70338869ffec5aa6e537de1ea64302e45bfe61a54ec17491a7c787e89c12b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.303030303030303,
+  "epoch": 1.5627705627705628,
   "eval_steps": 15,
-  "global_step": 75,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 4.432,
       "eval_steps_per_second": 0.594,
       "step": 75
+    },
+    {
+      "epoch": 1.354978354978355,
+      "grad_norm": 0.8432238101959229,
+      "learning_rate": 6.286336541589224e-05,
+      "loss": 2.2449,
+      "step": 78
+    },
+    {
+      "epoch": 1.406926406926407,
+      "grad_norm": 0.9027056097984314,
+      "learning_rate": 6.004970048339226e-05,
+      "loss": 2.2785,
+      "step": 81
+    },
+    {
+      "epoch": 1.4588744588744589,
+      "grad_norm": 0.977626621723175,
+      "learning_rate": 5.7202446389173223e-05,
+      "loss": 2.1978,
+      "step": 84
+    },
+    {
+      "epoch": 1.5108225108225108,
+      "grad_norm": 1.0718011856079102,
+      "learning_rate": 5.433111952413495e-05,
+      "loss": 2.1774,
+      "step": 87
+    },
+    {
+      "epoch": 1.5627705627705628,
+      "grad_norm": 1.034270167350769,
+      "learning_rate": 5.144531673771363e-05,
+      "loss": 2.1726,
+      "step": 90
+    },
+    {
+      "epoch": 1.5627705627705628,
+      "eval_loss": 0.6731178164482117,
+      "eval_runtime": 21.8631,
+      "eval_samples_per_second": 4.437,
+      "eval_steps_per_second": 0.595,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -249,7 +292,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.86404668407808e+17,
+  "total_flos": 4.636856020893696e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null