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:b4c55491f2e9da2b15b641422b62da136441558b855cc27b2bbb9fb7de59a8f7
+oid sha256:d63c6e74c3470ac5c297d4bc4ba1d50016363410d6b8210719af24777011e492
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ebaa83872ff1e4d5b4e56f7553575945efae35d63e172b29a4197e30d3f3d44
+oid sha256:12baf2d8e0a12b3cd86f93557d324042f1bb2038041d14ceacc84345cbe78cb5
 size 102030196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f238ab1b4d0451f11666163c0e5fb9c2d363ffc446936a3d9521cc04dab565b1
+oid sha256:fc47c3a1464826449c4b706b5a992ed4ba8b7c1085ff4feb0c933558ef732feb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
+oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0006434661375945091,
+  "epoch": 0.0012869322751890182,
   "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": 4.236,
       "eval_steps_per_second": 4.236,
       "step": 3
+    },
+    {
+      "epoch": 0.0008579548501260121,
+      "grad_norm": 59.29423904418945,
+      "learning_rate": 6e-05,
+      "loss": 8.4669,
+      "step": 4
+    },
+    {
+      "epoch": 0.0010724435626575152,
+      "grad_norm": 43.15823745727539,
+      "learning_rate": 8e-05,
+      "loss": 5.8545,
+      "step": 5
+    },
+    {
+      "epoch": 0.0012869322751890182,
+      "grad_norm": 42.88001251220703,
+      "learning_rate": 0.0001,
+      "loss": 4.0161,
+      "step": 6
+    },
+    {
+      "epoch": 0.0012869322751890182,
+      "eval_loss": 1.5954408645629883,
+      "eval_runtime": 230.2213,
+      "eval_samples_per_second": 4.265,
+      "eval_steps_per_second": 4.265,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2300683084627968.0,
+  "total_flos": 4601366169255936.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null