Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:164935e21fad69c552c1909708c3eb377bcfc209b7b671f71dd3edf5bbdced42
+oid sha256:80665225e82ae9bb2a1fc60b54b7bd47451d8ce5f89a1646e176cddd83a354eb
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24456457356a1fcfeacffe0d1b35309f6f4a8759df8cc9e143db0a5a6047f90c
+oid sha256:04adc7be1f48589e66619349e3b0f0cd52d7ae3792750b5e1f349d78f2c8f9df
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97a06efdf9c0a3412c2213f750b599184601a81c1b554150f5baece32506b39e
+oid sha256:3c5c2489f942c0bfb1f653e1fc6bfc4d52b4ef6a98d19d8a41801976ad4c8d82
 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": 0.00051440329218107,
+  "epoch": 0.00102880658436214,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -36,6 +36,35 @@
       "eval_samples_per_second": 44.607,
       "eval_steps_per_second": 22.304,
       "step": 3
+    },
+    {
+      "epoch": 0.0006858710562414266,
+      "grad_norm": 73.80441284179688,
+      "learning_rate": 8e-05,
+      "loss": 17.9721,
+      "step": 4
+    },
+    {
+      "epoch": 0.0008573388203017832,
+      "grad_norm": 51.07341766357422,
+      "learning_rate": 0.0001,
+      "loss": 15.2132,
+      "step": 5
+    },
+    {
+      "epoch": 0.00102880658436214,
+      "grad_norm": 73.77809143066406,
+      "learning_rate": 0.00012,
+      "loss": 18.699,
+      "step": 6
+    },
+    {
+      "epoch": 0.00102880658436214,
+      "eval_loss": 4.13886833190918,
+      "eval_runtime": 53.0262,
+      "eval_samples_per_second": 46.317,
+      "eval_steps_per_second": 23.158,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -55,7 +84,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 26318569734144.0,
+  "total_flos": 52637139468288.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null