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:a879c6bec8414e5a3f9ebd138e9f41c31a6b702284a7054bd27a44f9dc9cc3e0
+oid sha256:eed24b477fdf71608bbabb4783597c243d9214ed09504f9c40db1f89a398ad10
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32ea105b7b5f0c1a89a4bb00bc69cb657ae5ecb2d14ddfac62f1b710cf692cd9
+oid sha256:00bb604adff075916652553e6f756b485ce26d9245ee91577e1adacf02c29ca2
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05531349f6e2487143a7251afc8a645033108171aa1d481234785012b46d00ef
+oid sha256:e7b14d0c915e2c4063f110f3dbec036a026b529b8820509b2913f154771be18b
 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": 0.0008477569763334511,
+  "epoch": 0.0016955139526669022,
   "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": 17.568,
       "eval_steps_per_second": 8.784,
       "step": 3
+    },
+    {
+      "epoch": 0.0011303426351112682,
+      "grad_norm": 6.724841594696045,
+      "learning_rate": 8e-05,
+      "loss": 4.5783,
+      "step": 4
+    },
+    {
+      "epoch": 0.001412928293889085,
+      "grad_norm": 5.912840843200684,
+      "learning_rate": 0.0001,
+      "loss": 4.2418,
+      "step": 5
+    },
+    {
+      "epoch": 0.0016955139526669022,
+      "grad_norm": 5.554118633270264,
+      "learning_rate": 0.00012,
+      "loss": 3.4454,
+      "step": 6
+    },
+    {
+      "epoch": 0.0016955139526669022,
+      "eval_loss": 0.8012614846229553,
+      "eval_runtime": 84.8502,
+      "eval_samples_per_second": 17.56,
+      "eval_steps_per_second": 8.78,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1051603079528448.0,
+  "total_flos": 2103206159056896.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null