Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00767ca69b10be067be2941298081f40c94987a843dd942bafbf5acda91befcc
+oid sha256:232bcc9858ce0d5c28e9aa298360eed5c7cf48195fa14f61cbf351cd02e615fe
 size 104902272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78572e5f2a8bec6263f5ab969a5779e4ac3a319ff4961a1cdb9d5f27a98240c6
+oid sha256:7b5f1a00c2c51f65d8628c1656aaae70ebd16e629157f10e5672ebcc305be65c
 size 53622996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca3c0186b3a13958bb603ba3c5cd1a680924c7f463ca3b8c4723827c05c83c3f
+oid sha256:74f2e0e81975bb9790d426cf1e81631aed9cf6bad42c0428d645bae0c8dcc89d
 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": 0.0034403669724770644,
+  "epoch": 0.006880733944954129,
   "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": 13.794,
       "eval_steps_per_second": 6.897,
       "step": 3
+    },
+    {
+      "epoch": 0.0045871559633027525,
+      "grad_norm": 1.2741070985794067,
+      "learning_rate": 8e-05,
+      "loss": 9.1738,
+      "step": 4
+    },
+    {
+      "epoch": 0.005733944954128441,
+      "grad_norm": 0.6461805105209351,
+      "learning_rate": 0.0001,
+      "loss": 6.9995,
+      "step": 5
+    },
+    {
+      "epoch": 0.006880733944954129,
+      "grad_norm": 0.6756094694137573,
+      "learning_rate": 0.00012,
+      "loss": 7.2973,
+      "step": 6
+    },
+    {
+      "epoch": 0.006880733944954129,
+      "eval_loss": 1.7852340936660767,
+      "eval_runtime": 26.7166,
+      "eval_samples_per_second": 13.774,
+      "eval_steps_per_second": 6.887,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1882395078819840.0,
+  "total_flos": 3764790157639680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null