Training in progress, step 3500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d205a10ec746a2e621f265219dffa86a02638edbf5ec5a1fc74c7ff8891fb23d
+oid sha256:b97d4789449a829ba6967c26f88e6fb1d82de78eaecc34cb1d82a6d35e1e894a
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff8e69d6b3e91fe72610a7572602e11de1cb107ec8f2a123491d5e62d0998954
+oid sha256:47b1eca478433de5f9c62dea463f61950fd620b0be021230d58e0ae99dadfcca
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f848050763f228c45f41876f788201e463cbdcc748427dc62e8abf982f465e5e
+oid sha256:4d7f6140254e7b0fc70eb6194d0d97925be55a60fce52d6b728d7ec8079bd94d
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1ac3ef405adcd631e67f3a0c40ddc7e7d705d69b4fbe06bc5a1701aae09096a
+oid sha256:4aa17ebc8dd2b45de60c809b3e54b378786946552985dbb94de64b75faaaabf3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.798937665989689,
+  "epoch": 6.998906420871739,
   "eval_steps": 500,
-  "global_step": 3400,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -293,6 +293,21 @@
       "learning_rate": 7.733333333333333e-05,
       "loss": 1.2685,
       "step": 3400
+    },
+    {
+      "epoch": 6.998906420871739,
+      "grad_norm": 0.16717413067817688,
+      "learning_rate": 7.666666666666667e-05,
+      "loss": 1.2713,
+      "step": 3500
+    },
+    {
+      "epoch": 6.998906420871739,
+      "eval_loss": 1.1368179321289062,
+      "eval_runtime": 780.0179,
+      "eval_samples_per_second": 19.9,
+      "eval_steps_per_second": 2.488,
+      "step": 3500
     }
   ],
   "logging_steps": 100,
@@ -312,7 +327,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.306494079176016e+18,
+  "total_flos": 5.462569050364183e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null