Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1ed777b14b8fc94aa6765d162f4ad2a8f39657193c66ecd8d09af6b76be936c
+oid sha256:3ff2715ae5ad266f6a321332f52654547d92979eb5b73cf08f9521c5a6e6c9ad
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbb7708b0ffc6fc2e7e862e0dcc698d294b5aff29f67e1c082843d72ec1bc51c
+oid sha256:0c768d54cf6862125a542e6c27c1423bc85ed8624457d097da258a7cb229ec03
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d6592a6ee630db08a9825b7a8de69d83be5485d8b50ac75c3b5952c7a9fc409
+oid sha256:32e39b58f8dd1428862d10b2ca179766f5915d74ecb29dc037da3881ece550f5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001537082105802485,
+  "epoch": 0.00307416421160497,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 4.58,
       "eval_steps_per_second": 4.58,
       "step": 3
+    },
+    {
+      "epoch": 0.0020494428077366465,
+      "grad_norm": 0.8441597819328308,
+      "learning_rate": 8e-05,
+      "loss": 0.9886,
+      "step": 4
+    },
+    {
+      "epoch": 0.0025618035096708082,
+      "grad_norm": 0.9734748005867004,
+      "learning_rate": 0.0001,
+      "loss": 0.9814,
+      "step": 5
+    },
+    {
+      "epoch": 0.00307416421160497,
+      "grad_norm": 0.8902590870857239,
+      "learning_rate": 0.00012,
+      "loss": 0.7274,
+      "step": 6
+    },
+    {
+      "epoch": 0.00307416421160497,
+      "eval_loss": 1.1203179359436035,
+      "eval_runtime": 89.7709,
+      "eval_samples_per_second": 4.578,
+      "eval_steps_per_second": 4.578,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2097116079980544.0,
+  "total_flos": 4194232159961088.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null