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:d9eeef9a757ed4389d24342a990eb327f27a3ab9c383ceef67a7e2babdef4ec5
+oid sha256:0b64582593e2c693f12cf63a0849d889e3310df73dee62966918107d9e139cb2
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e12e31bd3ab2fea2180c168d38e7cff572713c620e8e3d39aeeb65fc40db1190
+oid sha256:7d67261182fdac1401f443b7ce9626087dc58474439c816f9a9abfb8babff4ef
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d93d600975602b7dc557ea6bf2be1af32b3a49c58755d50746f1058367b602f
+oid sha256:d68d2a8ec68d97e9f6781386cdc5d11673589bf128caf93d024b660045d53f99
 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": 0.003179650238473768,
+  "epoch": 0.006359300476947536,
   "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": 14.47,
       "eval_steps_per_second": 7.235,
       "step": 3
+    },
+    {
+      "epoch": 0.0042395336512983575,
+      "grad_norm": 0.7442638278007507,
+      "learning_rate": 8e-05,
+      "loss": 6.4499,
+      "step": 4
+    },
+    {
+      "epoch": 0.005299417064122946,
+      "grad_norm": 0.7729753851890564,
+      "learning_rate": 0.0001,
+      "loss": 6.1611,
+      "step": 5
+    },
+    {
+      "epoch": 0.006359300476947536,
+      "grad_norm": 0.7975832223892212,
+      "learning_rate": 0.00012,
+      "loss": 6.1086,
+      "step": 6
+    },
+    {
+      "epoch": 0.006359300476947536,
+      "eval_loss": 1.549599051475525,
+      "eval_runtime": 27.5431,
+      "eval_samples_per_second": 14.45,
+      "eval_steps_per_second": 7.225,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 977249545224192.0,
+  "total_flos": 1954499090448384.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null