Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1831417af28ad4e8431cf68f5ff7cb340c7b0b38a1160114ca637e3215a236cb
+oid sha256:df2bbc3cf162bf3f7e6feac9e7dafa8931381498d73a06b4dff98aeea41e8777
 size 33572288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2f8f4d8a7f3b700a709fcb1e5fb6c8b3d685349784cfabec0f62be130078fbf
+oid sha256:e504f721274dde3e8e6a217acf096aebdc7ec57005119912d178d7ab109ff8ad
 size 17190970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:195d4c400c94c012e035f8ad146f414c04945c5ea9b6f10c156783198ebe3350
+oid sha256:f7cec7fa95fb16b09232bf47470bd56c852288bce7d205fc837860a8a1d8db12
 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": 0.006518196632265073,
+  "epoch": 0.013036393264530146,
   "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": 2.82,
       "eval_steps_per_second": 1.41,
       "step": 3
+    },
+    {
+      "epoch": 0.008690928843020097,
+      "grad_norm": 33.71705627441406,
+      "learning_rate": 8e-05,
+      "loss": 22.7458,
+      "step": 4
+    },
+    {
+      "epoch": 0.010863661053775122,
+      "grad_norm": 26.417665481567383,
+      "learning_rate": 0.0001,
+      "loss": 19.5417,
+      "step": 5
+    },
+    {
+      "epoch": 0.013036393264530146,
+      "grad_norm": 31.988718032836914,
+      "learning_rate": 0.00012,
+      "loss": 24.3794,
+      "step": 6
+    },
+    {
+      "epoch": 0.013036393264530146,
+      "eval_loss": 4.7808332443237305,
+      "eval_runtime": 67.3901,
+      "eval_samples_per_second": 2.879,
+      "eval_steps_per_second": 1.439,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 540955694333952.0,
+  "total_flos": 1081911388667904.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null