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:a91b73af0659e16889f6937036a2720450662f82be8ab1602829666712205fcf
+oid sha256:d33f72e9cd5583db0003cff54987aec8e5de9f0ad6d681950c2d55ff0c8dd5a5
 size 556856304

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de960fb84178c81229c5a2bf9d428d1738b6c6e775c68a04ffece116e39fdbad
+oid sha256:deb4e1e7fa23801b363a688ba5e7649c3e975e3bd05d985a6468b2d0f79c60b3
 size 21599060

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e1568a9e8418232f5cb6d15207f018fdd610216d44e9fd26dbeb423790da509
+oid sha256:830c0717e1a623f4428da5c6215b99cc10f0295b0807586eba37d260994f5fd2
 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": 0.00010412147505422994,
+  "epoch": 0.00020824295010845987,
   "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": 37.824,
       "eval_steps_per_second": 18.912,
       "step": 3
+    },
+    {
+      "epoch": 0.00013882863340563992,
+      "grad_norm": 2.3599693775177,
+      "learning_rate": 8e-05,
+      "loss": 5.1925,
+      "step": 4
+    },
+    {
+      "epoch": 0.0001735357917570499,
+      "grad_norm": 5.262383937835693,
+      "learning_rate": 0.0001,
+      "loss": 6.9685,
+      "step": 5
+    },
+    {
+      "epoch": 0.00020824295010845987,
+      "grad_norm": 2.1987497806549072,
+      "learning_rate": 0.00012,
+      "loss": 4.5352,
+      "step": 6
+    },
+    {
+      "epoch": 0.00020824295010845987,
+      "eval_loss": 1.2795846462249756,
+      "eval_runtime": 322.719,
+      "eval_samples_per_second": 37.593,
+      "eval_steps_per_second": 18.797,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 342798394982400.0,
+  "total_flos": 669273056870400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null