Training in progress, step 126, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f91b9eb503e262a419a8e975e953e7bcca72a35dc06fee59902a6adab2f8ff
+oid sha256:147e782becda787d99b94c6bad69cb906d223a40d2f601334f7ea8de17fce6dd
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fd6fcfc1ebe7217b086b12aa800d8aae24472a9c434aa144077bbbd44c309d2
+oid sha256:bfa0e82589a6f6cf44074215e2637567697993387b493da2d57c2aa0b564fab8
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24e3375c2f720f0c65cc29bc53ac2cc46c2d57ec6af442de3b981a1027556d64
+oid sha256:21a8cef57846ad22e38262ff905e75360e27250c498704a126d5649a9db3dc6a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95c99427ab0e3f179e8260c56d2a524955cd643e000ed1c4e3ac111dee56d825
+oid sha256:9fde2add4ac526f9d88b4a85a5e304b22d4aa9bf06cf799f89fbf1fa68e0bf83
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09473684210526316,
+  "epoch": 0.18947368421052632,
   "eval_steps": 63,
-  "global_step": 63,
+  "global_step": 126,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -65,6 +65,56 @@
       "eval_samples_per_second": 55.578,
       "eval_steps_per_second": 27.789,
       "step": 63
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 2.9531033039093018,
+      "learning_rate": 0.0001672300890261317,
+      "loss": 1.1114,
+      "step": 70
+    },
+    {
+      "epoch": 0.12030075187969924,
+      "grad_norm": 0.9415179491043091,
+      "learning_rate": 0.00015721166601221698,
+      "loss": 1.1491,
+      "step": 80
+    },
+    {
+      "epoch": 0.13533834586466165,
+      "grad_norm": 3.9636647701263428,
+      "learning_rate": 0.00014625382902408356,
+      "loss": 1.2552,
+      "step": 90
+    },
+    {
+      "epoch": 0.15037593984962405,
+      "grad_norm": 4.649128437042236,
+      "learning_rate": 0.00013453650544213076,
+      "loss": 1.6334,
+      "step": 100
+    },
+    {
+      "epoch": 0.16541353383458646,
+      "grad_norm": 2.313530445098877,
+      "learning_rate": 0.00012225209339563145,
+      "loss": 1.763,
+      "step": 110
+    },
+    {
+      "epoch": 0.18045112781954886,
+      "grad_norm": 3.655144453048706,
+      "learning_rate": 0.00010960230259076818,
+      "loss": 1.0297,
+      "step": 120
+    },
+    {
+      "epoch": 0.18947368421052632,
+      "eval_loss": 1.267545223236084,
+      "eval_runtime": 2.5163,
+      "eval_samples_per_second": 55.637,
+      "eval_steps_per_second": 27.818,
+      "step": 126
     }
   ],
   "logging_steps": 10,
@@ -84,7 +134,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 414308534059008.0,
+  "total_flos": 819026592792576.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null