Training in progress, step 840, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18afb835fc2c9c4f3afcb3ecf7dbb69ff2904f7c2e5267b1ec89d823c6f13831
+oid sha256:84ebecbf2ca75ad57ca7b58af0e968ef2090cf0cbf2d9de997a064b018738921
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78f3ab059899ae2c71ef5081007e22a22a8da9e06227771e5fedd9a3e46c680e
+oid sha256:b00e7236a16f54612acd3cd1712b00ba0e0a5ebd702d01df069c98828b504973
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e834e73ffab4e160c76a1bd779c86741b71aae87806079182876f96744bbaa3c
+oid sha256:9305dad521301e27731e7687a716b13bb515e0747793e6ae9190a1ac95e77259
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c69edcabc9c28bd555c4b26934528197e9fe7c072456052ac7530e1d13d44f8a
+oid sha256:ab189b99109032b154209762c91c1d401e345f9b0f9b7ebe3392ef6b914baeeb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0805564542219346,
+  "epoch": 1.0870268521514073,
   "eval_steps": 386,
-  "global_step": 835,
+  "global_step": 840,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5876,6 +5876,41 @@
       "learning_rate": 8.988624162896057e-05,
       "loss": 0.8475,
       "step": 835
+    },
+    {
+      "epoch": 1.0818505338078293,
+      "grad_norm": 0.9945587515830994,
+      "learning_rate": 8.986136654557784e-05,
+      "loss": 0.8112,
+      "step": 836
+    },
+    {
+      "epoch": 1.0831446133937237,
+      "grad_norm": 0.8039492964744568,
+      "learning_rate": 8.983646436015692e-05,
+      "loss": 0.6536,
+      "step": 837
+    },
+    {
+      "epoch": 1.0844386929796181,
+      "grad_norm": 0.8176629543304443,
+      "learning_rate": 8.981153508962899e-05,
+      "loss": 0.7452,
+      "step": 838
+    },
+    {
+      "epoch": 1.0857327725655128,
+      "grad_norm": 0.945672869682312,
+      "learning_rate": 8.978657875094368e-05,
+      "loss": 0.7925,
+      "step": 839
+    },
+    {
+      "epoch": 1.0870268521514073,
+      "grad_norm": 0.9550118446350098,
+      "learning_rate": 8.976159536106894e-05,
+      "loss": 0.8496,
+      "step": 840
     }
   ],
   "logging_steps": 1,
@@ -5895,7 +5930,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.334076672908984e+17,
+  "total_flos": 9.389973531493663e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null