Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca5e23c465228e2b947fff5c9e13ca8a54c2b22dc69f94042cacc4bc4f4f0534
+oid sha256:36a71e70334049c9a54db9db2807ff2536b6373595d85458e2bc3f9492bb0e74
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1a0ec82ac04b4d9ccc96de767aae12fe7a52e37224939fd9e1f89a7025538e2
+oid sha256:4750cee02caf4858154f8ff03db879d28cbbf5119a720e436f88e8235b985932
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28ac6d6f63baafad9d2ceaf3fa4ec8c598a9cbcf87a4705844a1b79a5682c033
+oid sha256:da8d67ac4277b1edc8f723aa57ce85839d906a360f3a682adfd5c16b396c10dc
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e64c3ed8e79844386b92c479a002b11c813cfc5e611c42a50454b3e0c8c9d9b
+oid sha256:f029bbeabc91129fd39e4485c9b2d4dcdf33d32bc2c75aeb8610aa61e7abc0a2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.5997500390563975,
+  "epoch": 1.7997187939384471,
   "eval_steps": 500,
-  "global_step": 800,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -71,6 +71,13 @@
       "learning_rate": 9.466666666666667e-05,
       "loss": 1.3325,
       "step": 800
+    },
+    {
+      "epoch": 1.7997187939384471,
+      "grad_norm": 0.11473137885332108,
+      "learning_rate": 9.4e-05,
+      "loss": 1.3273,
+      "step": 900
     }
   ],
   "logging_steps": 100,
@@ -90,7 +97,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2485906126350582e+18,
+  "total_flos": 1.4046655838232248e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null