Training in progress, step 8, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e7f6c35736d2991aee8b53cdede0e8f5f34646bdcf99182f590c7456a216962
+oid sha256:e77f3e5d1289bba64d0fe9d2b1eb1b3bbc31b8fab083e6c9fc03003a927967cd
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccdb656e810fb19eff4bd49fce82d8b7b2d87ce4fecf1c53c4d6f99a97755c42
+oid sha256:a58d0ffe0e12c31a8e225eb979c810b76c5a6019aa5dee8426d03333ec1a6d33
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89f72fd87d2a203f08872f7f09157a532c2c679a7b1eb56f5d5e55083ec72c14
+oid sha256:698a2a174d63a3686e64f723632c723119c5cfbfc1884cf988ecbf3863d7db38
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
+oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010767160161507403,
+  "epoch": 0.021534320323014805,
   "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": 7.88,
       "eval_steps_per_second": 7.88,
       "step": 4
+    },
+    {
+      "epoch": 0.013458950201884253,
+      "grad_norm": 1.9561946392059326,
+      "learning_rate": 0.0001,
+      "loss": 0.7364,
+      "step": 5
+    },
+    {
+      "epoch": 0.016150740242261104,
+      "grad_norm": 1.8313077688217163,
+      "learning_rate": 0.00012,
+      "loss": 0.6385,
+      "step": 6
+    },
+    {
+      "epoch": 0.018842530282637954,
+      "grad_norm": 1.4374486207962036,
+      "learning_rate": 0.00014,
+      "loss": 0.4741,
+      "step": 7
+    },
+    {
+      "epoch": 0.021534320323014805,
+      "grad_norm": 1.279863715171814,
+      "learning_rate": 0.00016,
+      "loss": 0.3742,
+      "step": 8
+    },
+    {
+      "epoch": 0.021534320323014805,
+      "eval_loss": 0.3805864155292511,
+      "eval_runtime": 10.1128,
+      "eval_samples_per_second": 7.812,
+      "eval_steps_per_second": 7.812,
+      "step": 8
     }
   ],
   "logging_steps": 1,
@@ -70,7 +106,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1576510477565952.0,
+  "total_flos": 3431228686467072.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null