Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:195625db2fee46dc60d36163e21dff252b2b667e63e459f264072074e08a1e4b
+oid sha256:ef5614f0e850273f45b9eee54904763d4e386105bec005da5e3752804d9a7a22
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:836dfa4d9c917ce3883300b57248c842dc2b775221908288517ec922335da6d2
+oid sha256:43afc3f5f462576ddadb1d75486a4c30b5a4a4ccc5b29aeba031db8afbe59024
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d93d600975602b7dc557ea6bf2be1af32b3a49c58755d50746f1058367b602f
+oid sha256:d5095323b290578a89328d8247b6223badac2013fbf499b9514ebea4b896d297
 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": 0.004678362573099415,
+  "epoch": 0.00935672514619883,
   "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": 19.49,
       "eval_steps_per_second": 9.781,
       "step": 3
+    },
+    {
+      "epoch": 0.006237816764132553,
+      "grad_norm": 0.31834664940834045,
+      "learning_rate": 8e-05,
+      "loss": 1.4852,
+      "step": 4
+    },
+    {
+      "epoch": 0.007797270955165692,
+      "grad_norm": 0.3573683500289917,
+      "learning_rate": 0.0001,
+      "loss": 1.3656,
+      "step": 5
+    },
+    {
+      "epoch": 0.00935672514619883,
+      "grad_norm": 0.3832826614379883,
+      "learning_rate": 0.00012,
+      "loss": 1.583,
+      "step": 6
+    },
+    {
+      "epoch": 0.00935672514619883,
+      "eval_loss": 1.7191375494003296,
+      "eval_runtime": 13.9435,
+      "eval_samples_per_second": 19.436,
+      "eval_steps_per_second": 9.754,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 977239881547776.0,
+  "total_flos": 1913761434697728.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null