Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f5a095cf3ad017d16420db072122a607f00b84e2095c7abded3801eb1483f30
+oid sha256:8ea1383aa6972f950a496bbf127ae3c176a695185d404c17bb87a32f44442f7b
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acc942411b3a58ba0a3723700c420b2091d69d60991d4d5af2102eaecded568c
+oid sha256:2af92d072fbbb7f76c05ab9fc41518bc10498cd0de1dae24e1ac690438d36f3f
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18f07a103b5a7ce383958d3ccdcdfd49b4b76cd4196ae0465111ebece710f20e
+oid sha256:f2c7b6cb315312c6c82b23cb21e455823073a3e69e8631d21018c71ee2b3e5c9
 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": 0.0030943785456420837,
+  "epoch": 0.006188757091284167,
   "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": 15.256,
       "eval_steps_per_second": 7.647,
       "step": 3
+    },
+    {
+      "epoch": 0.0041258380608561115,
+      "grad_norm": 1.3186827898025513,
+      "learning_rate": 8e-05,
+      "loss": 10.0087,
+      "step": 4
+    },
+    {
+      "epoch": 0.005157297576070139,
+      "grad_norm": 1.2354528903961182,
+      "learning_rate": 0.0001,
+      "loss": 8.5305,
+      "step": 5
+    },
+    {
+      "epoch": 0.006188757091284167,
+      "grad_norm": 1.6300536394119263,
+      "learning_rate": 0.00012,
+      "loss": 9.3115,
+      "step": 6
+    },
+    {
+      "epoch": 0.006188757091284167,
+      "eval_loss": 2.355851173400879,
+      "eval_runtime": 27.0062,
+      "eval_samples_per_second": 15.145,
+      "eval_steps_per_second": 7.591,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1189078577971200.0,
+  "total_flos": 2293222971801600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null