Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfadfb52e9cece92efbfcdd07d95bd0bd03c43ac4e187c3b0bdb2e0801fe7fb5
+oid sha256:53f2f3446a19634c906c9137244712d5a2609909611892760d48690b617313f8
 size 684272496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c4bfe670460a6c3e6f99e0af0a50034f8c671ee01067c8497c4e845ee37eb41
+oid sha256:94e44a3abfc1262f53fe89de4ddd92295861ad567c79f8beded210a2854535f9
 size 81730196

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82d58cdefbfa206272ae0f49b7c1ab4333ed43fed8f691ed4fab228d76a03af4
+oid sha256:23b1cdc93839cf3d1839ae8fbc0a092fe54b0e38a1fa2ef42fb2cb7ea1f38aa8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5b1b3e059101187bfc3dbbbf83ace53384f686f1746265194c4a97e6f99011f
+oid sha256:1f9c8d472a9fcb528aad7900cb24b90313f284110ca432406a71ead59cbde1f3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f6de54275f346101ff8b49b7b00b2a5e3c3f833bea127dd1d85c05840e8e91e
+oid sha256:8245d8d3d3816dd284f4381705afc1ac7d7e6002a14fe01153bec7adf5280188
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7088bfeda8ca84a250864306b44e2cb8f6e645d52ec0d290b01d09803cdac7f4
+oid sha256:e01e0573ae2aa58b2e2ae712e76a15ee28e34fab0d7c2da6f89be4395d3de6b5
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.047337278106508875,
+  "epoch": 0.07100591715976332,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 19.925,
       "eval_steps_per_second": 2.514,
       "step": 6
+    },
+    {
+      "epoch": 0.055226824457593686,
+      "grad_norm": 7.916440963745117,
+      "learning_rate": 0.00014,
+      "loss": 1.1182,
+      "step": 7
+    },
+    {
+      "epoch": 0.0631163708086785,
+      "grad_norm": 4.70343017578125,
+      "learning_rate": 0.00016,
+      "loss": 0.7454,
+      "step": 8
+    },
+    {
+      "epoch": 0.07100591715976332,
+      "grad_norm": 2.260014533996582,
+      "learning_rate": 0.00018,
+      "loss": 0.3618,
+      "step": 9
+    },
+    {
+      "epoch": 0.07100591715976332,
+      "eval_loss": 0.2835359275341034,
+      "eval_runtime": 10.7491,
+      "eval_samples_per_second": 19.909,
+      "eval_steps_per_second": 2.512,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.1366013018701824e+16,
+  "total_flos": 4.704901952805274e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null