Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:819ae226158fa856a8939fb1c49db5bf20818da2316abf351bc63b542cee0695
+oid sha256:ac7c99bcc089af874eedff7c8a225f5b1a2852c294a2ec48d1305e97bee9e356
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28b410e6336f62d1a177fe350031c6223541d1089e2d744f04ce6035ddd5daf3
+oid sha256:4fb55da73ae7f94d8f96ab5e47f869eb56dbb8c4280cb0d8084b59c0c98f707d
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9264abfa6d2cc5145363bf71d2fb16332b1ac4e60642a70827881d9a447c36a4
+oid sha256:af82c1f1d4ec999545a290f8875f59e0434314b9e98a3c2553c0c541daf4cdfa
 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": 0.0007174887892376681,
+  "epoch": 0.0014349775784753362,
   "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": 446.467,
       "eval_steps_per_second": 223.36,
       "step": 3
+    },
+    {
+      "epoch": 0.0009566517189835576,
+      "grad_norm": 1.2163171768188477,
+      "learning_rate": 8e-05,
+      "loss": 44.3973,
+      "step": 4
+    },
+    {
+      "epoch": 0.001195814648729447,
+      "grad_norm": 1.4012264013290405,
+      "learning_rate": 0.0001,
+      "loss": 44.4088,
+      "step": 5
+    },
+    {
+      "epoch": 0.0014349775784753362,
+      "grad_norm": 1.4006203413009644,
+      "learning_rate": 0.00012,
+      "loss": 44.4034,
+      "step": 6
+    },
+    {
+      "epoch": 0.0014349775784753362,
+      "eval_loss": 11.09300708770752,
+      "eval_runtime": 3.988,
+      "eval_samples_per_second": 441.57,
+      "eval_steps_per_second": 220.91,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2241331200.0,
+  "total_flos": 4482662400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null