Training in progress, step 760, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89c68cd6a438b933914a04b6f5f131ead842b1d7581b44de6aaefbdd24e5b716
+oid sha256:e972db55cd134690c9776d7893074e87cc2bd702fb87941b5d9e6c8c25cc391a
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6f463d62884edf4be3d7052906d7e49a09c5aded8637fd7076342e70d2d5b58
+oid sha256:3e4cfccb1919ca19e17954935be00b0f7b6ec907798e5af06806f56a57bf04d5
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46997f094839d5a72cf41bb76c4ba6e1f48d2860bbee1aff38dc49eeca98851b
+oid sha256:5c76e2dcee376ec4154d62bae58a27df8cbfd5e72fd952966f6a9399f9bf9b0f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b50c27db27104c6ec65d23e9ee9b2125ae74a4486b331a13d6f8605dd5fb4916
+oid sha256:5570930358297cc1f2e27061c5b07167b82267528b2685d4e93682b90397c561
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.977030087350372,
+  "epoch": 0.9835004852798447,
   "eval_steps": 386,
-  "global_step": 755,
+  "global_step": 760,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5308,6 +5308,41 @@
       "learning_rate": 9.178697246126607e-05,
       "loss": 0.855,
       "step": 755
+    },
+    {
+      "epoch": 0.9783241669362666,
+      "grad_norm": 0.894588828086853,
+      "learning_rate": 9.176431874630941e-05,
+      "loss": 0.8531,
+      "step": 756
+    },
+    {
+      "epoch": 0.9796182465221611,
+      "grad_norm": 0.7806453704833984,
+      "learning_rate": 9.174163663548329e-05,
+      "loss": 0.9423,
+      "step": 757
+    },
+    {
+      "epoch": 0.9809123261080557,
+      "grad_norm": 0.8258002400398254,
+      "learning_rate": 9.171892614420942e-05,
+      "loss": 0.6763,
+      "step": 758
+    },
+    {
+      "epoch": 0.9822064056939501,
+      "grad_norm": 0.7445089221000671,
+      "learning_rate": 9.169618728792886e-05,
+      "loss": 0.7886,
+      "step": 759
+    },
+    {
+      "epoch": 0.9835004852798447,
+      "grad_norm": 0.8452383279800415,
+      "learning_rate": 9.167342008210192e-05,
+      "loss": 1.0001,
+      "step": 760
     }
   ],
   "logging_steps": 1,
@@ -5327,7 +5362,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.440425646286438e+17,
+  "total_flos": 8.496322504871117e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null