Training in progress, step 8, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eace9bb02363ee5ee56cc7a194d894b2b78ee3dd3894681bb154f8289d74145c
+oid sha256:f6bf84be1aae5b8b7946457e506504c6c2630fdef4fb88e2464690ae66e14367
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe85beab3c592316b8c837fa51bd79f1ff3e864bd6705b7c042e527cd482d963
+oid sha256:a8cb4d027701d26930a17df48eb5d041515507f70e9aee259cd342d19580d93b
 size 263088

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7873e222d9efb8cccaf41bdb9709cd5fee4a4127dbd5e3c024e4e1a78b58bf1
+oid sha256:738162faf052e4c539199a028fb652e4005a183b04a94b3c028ce4724481c2e6
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d631543250820de7c55909f23c02d0e6bad6599d8a326595be28c0408855554
+oid sha256:42db7237a248957f8ca1684b4d9fc99ed0496fe869a62d0c7eff835c4c03f07d
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a07f6da6d74e7a4c75d1066ca8d629f744fc12be88b613f604b5919a6b11e746
+oid sha256:2c4ce4d091756f12bab6bdc9cd40c04605bb3ee460b6a7d0066229771ebb2eb2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.30917874396135264,
+  "epoch": 0.6183574879227053,
   "eval_steps": 4,
-  "global_step": 4,
+  "global_step": 8,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -51,6 +51,42 @@
       "eval_samples_per_second": 248.368,
       "eval_steps_per_second": 62.092,
       "step": 4
+    },
+    {
+      "epoch": 0.3864734299516908,
+      "grad_norm": 31.669504165649414,
+      "learning_rate": 8.274303669726426e-05,
+      "loss": 353.9269,
+      "step": 5
+    },
+    {
+      "epoch": 0.463768115942029,
+      "grad_norm": 32.336524963378906,
+      "learning_rate": 7.077075065009433e-05,
+      "loss": 353.4835,
+      "step": 6
+    },
+    {
+      "epoch": 0.5410628019323671,
+      "grad_norm": 31.395036697387695,
+      "learning_rate": 5.7115741913664264e-05,
+      "loss": 353.1369,
+      "step": 7
+    },
+    {
+      "epoch": 0.6183574879227053,
+      "grad_norm": 31.216983795166016,
+      "learning_rate": 4.288425808633575e-05,
+      "loss": 352.7697,
+      "step": 8
+    },
+    {
+      "epoch": 0.6183574879227053,
+      "eval_loss": 11.021666526794434,
+      "eval_runtime": 0.3549,
+      "eval_samples_per_second": 247.956,
+      "eval_steps_per_second": 61.989,
+      "step": 8
     }
   ],
   "logging_steps": 1,
@@ -70,7 +106,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5324685705216.0,
+  "total_flos": 10649371410432.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null