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:c1dbe096fa30e46c98206b1775a738b06c9f8d68f8ac7ce16cb2eb560df2a9fa
+oid sha256:1e1df190c4160825ea3a5b170c868688c30480839bb163ad395699e030883083
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bff2d66d09f15c16f152e345bc504598818f2243122abf5260ac3aa5d9a2f47b
+oid sha256:273a51d1a661bde2b80d5d839bf42ece2c900bdf9bb6a7f77639cf58afa06855
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40a6e54f9735ac650e1bce7d31fe07be9de05d82d7f44a83bbaaeae992231fe8
+oid sha256:b16e571b5200a459b1d8d0f1e526ee8e68933e666abc123060b4e85c87c58aaf
 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": 2.6644107988569676e-05,
+  "epoch": 5.328821597713935e-05,
   "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": 27.101,
       "eval_steps_per_second": 13.551,
       "step": 3
+    },
+    {
+      "epoch": 3.5525477318092904e-05,
+      "grad_norm": 34.76826477050781,
+      "learning_rate": 8e-05,
+      "loss": 9.7859,
+      "step": 4
+    },
+    {
+      "epoch": 4.440684664761613e-05,
+      "grad_norm": 30.317312240600586,
+      "learning_rate": 0.0001,
+      "loss": 11.2434,
+      "step": 5
+    },
+    {
+      "epoch": 5.328821597713935e-05,
+      "grad_norm": 21.470661163330078,
+      "learning_rate": 0.00012,
+      "loss": 8.105,
+      "step": 6
+    },
+    {
+      "epoch": 5.328821597713935e-05,
+      "eval_loss": 2.286210536956787,
+      "eval_runtime": 1749.226,
+      "eval_samples_per_second": 27.103,
+      "eval_steps_per_second": 13.552,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 569617680433152.0,
+  "total_flos": 1139235360866304.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null