Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d92dae7e245d877d6936348499ccb2405aff67e62816a5cd966d554aedf7394
+oid sha256:2c5798691fceeef7587674007a21c62b7b7eb99d4deed37780c5a29fea43dcb8
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97a5420631f0e7ac77207094637bd8ae806d837b6dc9a624773974736332a1bb
+oid sha256:322aacf33dc28e0df8985460823e1a407a74d726f6da0c77ced6ea43e45417b4
 size 1003002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c99d856f4b0fd798f0682438819be33ce60061bf9a2f48fb0c01c526e16fde06
+oid sha256:8285489f68000ec4600333ccee281bca8dd48450423899eaa09a26dab85569a3
 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": 0.014035087719298246,
+  "epoch": 0.028070175438596492,
   "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": 38.378,
       "eval_steps_per_second": 38.378,
       "step": 3
+    },
+    {
+      "epoch": 0.01871345029239766,
+      "grad_norm": 10.393665313720703,
+      "learning_rate": 8e-05,
+      "loss": 7.893,
+      "step": 4
+    },
+    {
+      "epoch": 0.023391812865497075,
+      "grad_norm": 10.401045799255371,
+      "learning_rate": 0.0001,
+      "loss": 7.6955,
+      "step": 5
+    },
+    {
+      "epoch": 0.028070175438596492,
+      "grad_norm": 12.121800422668457,
+      "learning_rate": 0.00012,
+      "loss": 6.9641,
+      "step": 6
+    },
+    {
+      "epoch": 0.028070175438596492,
+      "eval_loss": 7.324780464172363,
+      "eval_runtime": 1.2063,
+      "eval_samples_per_second": 37.305,
+      "eval_steps_per_second": 37.305,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 814485602304.0,
+  "total_flos": 1628971204608.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null