Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36a71e70334049c9a54db9db2807ff2536b6373595d85458e2bc3f9492bb0e74
+oid sha256:d7b5956a1400bb4823586487e9e768ad8fa618ee4e83b5a436c694ee8216a1ff
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4750cee02caf4858154f8ff03db879d28cbbf5119a720e436f88e8235b985932
+oid sha256:a0938e573b6b73ec9c08d57a0aef1f85c771c5581375908232264d165e2db686
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da8d67ac4277b1edc8f723aa57ce85839d906a360f3a682adfd5c16b396c10dc
+oid sha256:02601105c0c4df0318c4868e79578c3b36513ed8185d08e441cb859a2824848d
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f029bbeabc91129fd39e4485c9b2d4dcdf33d32bc2c75aeb8610aa61e7abc0a2
+oid sha256:efb43817746a1d78c70529e1f403376494698487f2f0fffda582fc02bc229de3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.7997187939384471,
+  "epoch": 1.9996875488204968,
   "eval_steps": 500,
-  "global_step": 900,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -78,6 +78,21 @@
       "learning_rate": 9.4e-05,
       "loss": 1.3273,
       "step": 900
+    },
+    {
+      "epoch": 1.9996875488204968,
+      "grad_norm": 0.11462998390197754,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 1.3257,
+      "step": 1000
+    },
+    {
+      "epoch": 1.9996875488204968,
+      "eval_loss": 1.1889395713806152,
+      "eval_runtime": 780.6658,
+      "eval_samples_per_second": 19.883,
+      "eval_steps_per_second": 2.486,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -97,7 +112,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4046655838232248e+18,
+  "total_flos": 1.5607405550113915e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null