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:ae3f17c679bc8768ca431be0bf0e2125b63918e9bbe7280c61707694b0be2315
+oid sha256:a4951d9c9d0b9b88eb6f965b83a8f61cc364dc55ebb908f977986449557d27c0
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09305e2436e4c6dec4a67280b74976b96a42122dd991932a5022b134e53e1671
+oid sha256:32a5aea81b788651b82cc60ff2cb25010e6a38228a18667b9e9b93ff2d8e95fc
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d1ca0d26190b1d4e36bc64722c1d3a15d4fbcf10b0297979d5b1a5e865c30f2
+oid sha256:acb51c4fb3a634956d61a25a3ca8fe7d5dc2947935cdb108666d882979263988
 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": 0.008207934336525308,
+  "epoch": 0.016415868673050615,
   "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": 24.741,
       "eval_steps_per_second": 12.37,
       "step": 3
+    },
+    {
+      "epoch": 0.01094391244870041,
+      "grad_norm": 1.6363928318023682,
+      "learning_rate": 8e-05,
+      "loss": 9.9866,
+      "step": 4
+    },
+    {
+      "epoch": 0.013679890560875513,
+      "grad_norm": 1.4630907773971558,
+      "learning_rate": 0.0001,
+      "loss": 8.2748,
+      "step": 5
+    },
+    {
+      "epoch": 0.016415868673050615,
+      "grad_norm": 1.7034509181976318,
+      "learning_rate": 0.00012,
+      "loss": 8.8614,
+      "step": 6
+    },
+    {
+      "epoch": 0.016415868673050615,
+      "eval_loss": 2.269967555999756,
+      "eval_runtime": 6.2348,
+      "eval_samples_per_second": 24.7,
+      "eval_steps_per_second": 12.35,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 610774925967360.0,
+  "total_flos": 1099394866741248.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null