Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad727b2e0fb69a17b5a7722ca719597e336e020d6e695250b6fe3212bfd9d431
+oid sha256:7260b7b072f1608a7e3e661f22f900461d76570f396a7e38743eb3d4778cb9cb
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69dfb319da9877ebfbc88a1d9a0e995d22f85a1f1fd5bf5ce4284c4314bcfc09
+oid sha256:cd2aaa0867fbd56b92459f6375c98bb985dadc2d21e921d96b07c7340d972f08
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d44b4c2939ff17bcfa7216556067440798f6d3d905dfa73c6ecaa290f650fdf5
+oid sha256:2524d0bbcba4740cd7bcb7b38bf3a617d1bce7003e9fd41727db5747210a9ac1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd8212ec5ec3406d74a7f927b717dd30ea8a06115ee6582e14976f7b84b4b58
+oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3367003367003367,
+  "epoch": 0.5050505050505051,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 25.278,
       "eval_steps_per_second": 12.74,
       "step": 100
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 7.069131243042648e-05,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 0.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.40404040404040403,
+      "grad_norm": 6.735725037287921e-05,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.4377104377104377,
+      "grad_norm": 6.0173402744112536e-05,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 0.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.4713804713804714,
+      "grad_norm": 6.178388866828755e-05,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 0.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.5050505050505051,
+      "grad_norm": 5.9491336287464947e-05,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 0.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.5050505050505051,
+      "eval_loss": 2.176878297177609e-06,
+      "eval_runtime": 4.9547,
+      "eval_samples_per_second": 25.228,
+      "eval_steps_per_second": 12.715,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1121827078144e+16,
+  "total_flos": 3.1682740617216e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null