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:f77fea61e6f4766bcdb8a45e49a52433329b3d9bb6b0dda954e537c492105c53
+oid sha256:e244f74e1dfe7b078ac84b748981a70b33503702db0927817d376950cf371ea6
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e58bf94621de24d43805ce02672b32559d043cc7c728d25c85987c5576243a2
+oid sha256:15e0af881dd02dea0eb2b631800116aacc6dc07bd2c3010ceac3f1a47cd0cba1
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd179d5521367ea2d974e02c5577392adaf41662163e2589eb576b1d859facbe
+oid sha256:502bc21db2af3273cec5864b9184b9d7adb3ffa37452754c84f3c28a163c6ea7
 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": 0.11650485436893204,
+  "epoch": 0.23300970873786409,
   "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": 2.09,
       "eval_steps_per_second": 1.14,
       "step": 3
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "grad_norm": 17.89618682861328,
+      "learning_rate": 8e-05,
+      "loss": 7.6277,
+      "step": 4
+    },
+    {
+      "epoch": 0.1941747572815534,
+      "grad_norm": 22.238508224487305,
+      "learning_rate": 0.0001,
+      "loss": 6.5102,
+      "step": 5
+    },
+    {
+      "epoch": 0.23300970873786409,
+      "grad_norm": 17.981592178344727,
+      "learning_rate": 0.00012,
+      "loss": 5.852,
+      "step": 6
+    },
+    {
+      "epoch": 0.23300970873786409,
+      "eval_loss": 4.704180717468262,
+      "eval_runtime": 5.1699,
+      "eval_samples_per_second": 2.128,
+      "eval_steps_per_second": 1.161,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4451323701362688.0,
+  "total_flos": 8902647402725376.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null