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:b60bf794915008224e43813c817a77d441dcc95457c12cce0e3f0870f0fcfa14
+oid sha256:5d9f9f866c23a668c02a0ba1ebdcd38b0ba9337ccff85651adc36e20c6f0ce00
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfb8757bd5af249366bfa83fcb1ca5663501abb9cc4aebdd0f6e443f7b991eb1
+oid sha256:43300016a86339335341a47c02e7b9f54ecd8ef8bb4c4bd04440ccc6b4a421df
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57c112d728db58d29f71bf4e1a6ae26adace414e49ebf93dab769a4c16e64e9b
+oid sha256:98034a841a8af8a89a4f252e5ef6fd9b07235038469ab65e4215a2b643097c02
 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": 0.001170389154393836,
+  "epoch": 0.002340778308787672,
   "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": 18.68,
       "eval_steps_per_second": 9.34,
       "step": 3
+    },
+    {
+      "epoch": 0.0015605188725251145,
+      "grad_norm": 3.2878363132476807,
+      "learning_rate": 8e-05,
+      "loss": 2.84,
+      "step": 4
+    },
+    {
+      "epoch": 0.0019506485906563933,
+      "grad_norm": 4.44495964050293,
+      "learning_rate": 0.0001,
+      "loss": 3.7476,
+      "step": 5
+    },
+    {
+      "epoch": 0.002340778308787672,
+      "grad_norm": 3.2834181785583496,
+      "learning_rate": 0.00012,
+      "loss": 2.8451,
+      "step": 6
+    },
+    {
+      "epoch": 0.002340778308787672,
+      "eval_loss": 0.7554607391357422,
+      "eval_runtime": 57.8765,
+      "eval_samples_per_second": 18.66,
+      "eval_steps_per_second": 9.33,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1007785126920192.0,
+  "total_flos": 2059386998489088.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null