Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06a115e38f76c066aa6dab799814af39d6f610795d333a401c495fdf20a486da
+oid sha256:0b6a734d5e6d8c648ed67d3cc0634152c9c8eff1cb73426d7a666f7db630f9d8
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30acc7bafc4445827bf1ba39f95c1621dcfc1e4bc83b140f92eb0c067b99e4d0
+oid sha256:bd780a39cf221cd161fa9e8fc29e820fc2bc64b05b7b2f8b7bdf6c4d1b444118
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:631dfb2aa9ae256eca5748a1b2ab04547dfc14e5e8346db748407ed5d049499d
+oid sha256:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:764cf599d0b83c5d302be0978d09e435a466a8511dc1f7e86d5ee3704818d46f
+oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001266490765171504,
+  "epoch": 0.002532981530343008,
   "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": 14.756,
       "eval_steps_per_second": 14.756,
       "step": 3
+    },
+    {
+      "epoch": 0.0016886543535620053,
+      "grad_norm": 7.560422897338867,
+      "learning_rate": 4e-05,
+      "loss": 7.5846,
+      "step": 4
+    },
+    {
+      "epoch": 0.0021108179419525065,
+      "grad_norm": 5.9173455238342285,
+      "learning_rate": 6e-05,
+      "loss": 6.8106,
+      "step": 5
+    },
+    {
+      "epoch": 0.002532981530343008,
+      "grad_norm": 5.743566036224365,
+      "learning_rate": 8e-05,
+      "loss": 5.7917,
+      "step": 6
+    },
+    {
+      "epoch": 0.002532981530343008,
+      "eval_loss": 6.941962718963623,
+      "eval_runtime": 34.2264,
+      "eval_samples_per_second": 14.579,
+      "eval_steps_per_second": 14.579,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 554869274443776.0,
+  "total_flos": 1109738548887552.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null