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:f8a674e65fbae0eaa531071239721aea34ee18d60ba8393c32b9a68a7a3fc056
+oid sha256:d1108f7fb395438a13c45c08f013b21c73f9673e136398d65a938b7d0f89226a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cff6eb1ec9a8c21168614b5824ffe406880366027ed15fca88d03a8f58fa01bd
+oid sha256:0cd89b2f447c68cd7ec841b4c9d5e864bdddd6056bbc596881ce8680c77bca47
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40a6e54f9735ac650e1bce7d31fe07be9de05d82d7f44a83bbaaeae992231fe8
+oid sha256:b16e571b5200a459b1d8d0f1e526ee8e68933e666abc123060b4e85c87c58aaf
 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": 9.932788133629109e-05,
+  "epoch": 0.00019865576267258218,
   "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": 28.596,
       "eval_steps_per_second": 14.299,
       "step": 3
+    },
+    {
+      "epoch": 0.0001324371751150548,
+      "grad_norm": 0.6291266083717346,
+      "learning_rate": 8e-05,
+      "loss": 2.4232,
+      "step": 4
+    },
+    {
+      "epoch": 0.0001655464688938185,
+      "grad_norm": 0.7624912858009338,
+      "learning_rate": 0.0001,
+      "loss": 2.6784,
+      "step": 5
+    },
+    {
+      "epoch": 0.00019865576267258218,
+      "grad_norm": 0.6687327027320862,
+      "learning_rate": 0.00012,
+      "loss": 2.2124,
+      "step": 6
+    },
+    {
+      "epoch": 0.00019865576267258218,
+      "eval_loss": 2.883939743041992,
+      "eval_runtime": 443.4782,
+      "eval_samples_per_second": 28.676,
+      "eval_steps_per_second": 14.339,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 601108380647424.0,
+  "total_flos": 1202216761294848.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null