Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f782860e46be09076e1482c865aa9dd1d5f511293507052233fa2db2df03919
+oid sha256:a7a83d396ad160e5e5a044d1ae3213fc66af111c83fa37b6938ff157d177e7a0
 size 30322120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bad98557c6783dd4866d26414efa72fcbd339685b25fe8f4cfff85a75bd9a1c
+oid sha256:16376afc1fddc46799352e11feea556e6952677516c7af585a46b72b988610a9
 size 15768084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ccc19b6cc79f6792944bb183d23fb2ae518baee1ebed73538b3e3b120bc09b1
+oid sha256:d712c77120c67ed91988aaa635519cafd55c1a8cf6c5bd9894cf262d7fd97eb6
 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": 0.00043609405095032164,
+  "epoch": 0.0008721881019006433,
   "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": 2.217,
       "eval_steps_per_second": 1.109,
       "step": 3
+    },
+    {
+      "epoch": 0.0005814587346004289,
+      "grad_norm": 9.180171012878418,
+      "learning_rate": 8e-05,
+      "loss": 3.6817,
+      "step": 4
+    },
+    {
+      "epoch": 0.000726823418250536,
+      "grad_norm": 12.513172149658203,
+      "learning_rate": 0.0001,
+      "loss": 5.2037,
+      "step": 5
+    },
+    {
+      "epoch": 0.0008721881019006433,
+      "grad_norm": 6.623383045196533,
+      "learning_rate": 0.00012,
+      "loss": 2.7651,
+      "step": 6
+    },
+    {
+      "epoch": 0.0008721881019006433,
+      "eval_loss": 3.960355758666992,
+      "eval_runtime": 1307.1519,
+      "eval_samples_per_second": 2.216,
+      "eval_steps_per_second": 1.109,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 186369435500544.0,
+  "total_flos": 372738871001088.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null