Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d25ebe37203fab0f1f9f0b4e446da035b43b9686ba03902efb952df23824c7d
+oid sha256:374da347622d668269859b72eea6f2d0b4a91b341a780d5b61734db381dfaa05
 size 161533160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6ebb6c65daaf13a13d5ad4ba2eef62702dc6afe14c5108f3872ae914e6a5136
+oid sha256:e87be9e7a373870535fef2fa6152f10c18656b3e076faafdcd2eb3a7235ee483
 size 323292202

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a5666ca01619bd62acfd9039576fd98e2c6aac3986385a325913fa57b46962f
+oid sha256:8f8f252de09a4793e5f13e772318938c884d18658b3687d3f2f6915920086464
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016556291390728478,
+  "epoch": 0.033112582781456956,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,28 @@
       "eval_samples_per_second": 3.185,
       "eval_steps_per_second": 3.185,
       "step": 100
+    },
+    {
+      "epoch": 0.024834437086092714,
+      "grad_norm": 2.393519878387451,
+      "learning_rate": 8.222958057395145e-06,
+      "loss": 1.1353,
+      "step": 150
+    },
+    {
+      "epoch": 0.033112582781456956,
+      "grad_norm": 2.5604305267333984,
+      "learning_rate": 1.0982339955849891e-05,
+      "loss": 1.0539,
+      "step": 200
+    },
+    {
+      "epoch": 0.033112582781456956,
+      "eval_loss": 1.0201358795166016,
+      "eval_runtime": 1896.3026,
+      "eval_samples_per_second": 3.185,
+      "eval_steps_per_second": 3.185,
+      "step": 200
     }
   ],
   "logging_steps": 50,
@@ -49,7 +71,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 799936871399424.0,
+  "total_flos": 1563083893899264.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null