Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69d1b9424194f2b72acccb5851f6868a3153e7b3806febc313397aa44849ab5d
+oid sha256:35ff6e996b906c18a2ba4e4215c41de305d53061820b1b6fa0bfe889b3644944
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:535a9bd21e8ebcc2a752fd85b5a4357b222308c113fcac22a4fedca4cfbb3278
+oid sha256:080eaf89a3066cade79c2b266e821b4ba394d86a5cfd63b7a43426f57d011169
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b5bc72d35a952567b178439a440ebd6225ccee20b3b5a9f8d26721e60808459
+oid sha256:2cb741a1b6c12fea007d9d6a85137f098d7e74d9ca251e354a6aa242a9cce0ef
 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": 0.001274426508071368,
+  "epoch": 0.002548853016142736,
   "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": 33.675,
       "eval_steps_per_second": 16.838,
       "step": 3
+    },
+    {
+      "epoch": 0.0016992353440951572,
+      "grad_norm": 1.2402433156967163,
+      "learning_rate": 8e-05,
+      "loss": 7.1005,
+      "step": 4
+    },
+    {
+      "epoch": 0.0021240441801189465,
+      "grad_norm": 1.4624475240707397,
+      "learning_rate": 0.0001,
+      "loss": 6.9481,
+      "step": 5
+    },
+    {
+      "epoch": 0.002548853016142736,
+      "grad_norm": 1.6787381172180176,
+      "learning_rate": 0.00012,
+      "loss": 7.2956,
+      "step": 6
+    },
+    {
+      "epoch": 0.002548853016142736,
+      "eval_loss": 1.7664850950241089,
+      "eval_runtime": 35.0121,
+      "eval_samples_per_second": 28.333,
+      "eval_steps_per_second": 14.167,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 275386013319168.0,
+  "total_flos": 550772026638336.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null