Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:974300d3350641abe014d6704cfb1d6cc56d9da823eea827210d60c36e9c839c
+oid sha256:27143de200dcd7dd6333b34817bd3ebe89abd6d1c1b5ce0ed42ecd8ea334f31f
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7b2f8af1c94128cb81f2b9a1064ef3c89ceb55b87a9cd805b44259dc9bc6b9
+oid sha256:b9227174b827248911bfd55fbea33636654f11ce07ab16a4d51074f68518cafd
 size 263088

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a031850dcc26dc8454e6c1fbc0d19befa80e7355b1e30146694d0bf31825a6a
+oid sha256:041e36e3c63dabfbb6e7d5573efecf709c639e3b8a104c7746cf31c9f4387091
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52094c62ca4dfa395c723cb1dad56301ac75db9f4f2f84c819898935fadfe03b
+oid sha256:061d0692fa8b539252cb5e5cc70a1ba2787f7f56c4ebcd691f0f3c1c7c15066b
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c1b8c1c878192032a23ccb4c7aaa7be63cc77e4e3f2996e96e2c66766dd6f5a
+oid sha256:43dca3ecd2ab47e84f0307855ded82435ba1673dc93e9b6f6d6bea2853047334
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b098097ca88434e884de8a24fad42e21ad1a6774b281de953474de0fabd1388
+oid sha256:1e922b1e29817b9be2afe815bd82603354841818005001da4aa22780ae5012a2
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f0e8493ff99f9af37458df108b6e2a227e9c9ca45eb35eb386b03431532946a
+oid sha256:4435e50107632056c980bf5ca683b30daf6a7049b63cba2514277d76468ff4af
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc510ca170c2ba4c1dea7186091866709a9add8c6dcc9db187644258b5087781
+oid sha256:35fe1b3fc01d2378ec9105ebaa2a9c3b381a9de368f76b148e172a17484465f8
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c96f059ace7e0d8e1a14825dec084b13ba116dfabee3c8fdf4dc7768571690f7
+oid sha256:4f9eb59e5a76de855e9a75a5d2894e26ce2cdf8f8cf68a12da5845f2358c76a6
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a201fa589c2696efa6aab64148eb4ea48b21acf46b4c392e53104c46a68f2e5d
+oid sha256:13a1a5a2d900e135b3cdfbf0d13da3726612a93b102df4fd225802b9fb4baec9
 size 15984

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": 0.00032928134346788137,
+  "epoch": 0.0006585626869357627,
   "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": 639.258,
       "eval_steps_per_second": 79.944,
       "step": 3
+    },
+    {
+      "epoch": 0.00043904179129050847,
+      "grad_norm": 3.233558177947998,
+      "learning_rate": 8e-05,
+      "loss": 44.4412,
+      "step": 4
+    },
+    {
+      "epoch": 0.0005488022391131356,
+      "grad_norm": 3.275294303894043,
+      "learning_rate": 0.0001,
+      "loss": 44.4168,
+      "step": 5
+    },
+    {
+      "epoch": 0.0006585626869357627,
+      "grad_norm": 3.2577297687530518,
+      "learning_rate": 0.00012,
+      "loss": 44.4082,
+      "step": 6
+    },
+    {
+      "epoch": 0.0006585626869357627,
+      "eval_loss": 11.081639289855957,
+      "eval_runtime": 24.0515,
+      "eval_samples_per_second": 638.006,
+      "eval_steps_per_second": 79.787,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 998378569728.0,
+  "total_flos": 1996757139456.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null