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:b24b8598cdd3bf76390c6536e2614deb94222cebe2f8d2eab467ec6270b11033
+oid sha256:5af87d658ccf46306447c62ae3d066dfa6ef4687119288bf64b7c5096308cca3
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3c6921ed0d7bcdb1e35e202fd258587e28ae1db1554a4de7b24b51de6ed691f
+oid sha256:ddec1fe8ff6b92dec81a4c516a13b01cd4d307f19c57e7bfddd6daa0fc8516ff
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d0e63554d1f0c98cbd7a7acd8454d464bfe744537ebf1b761c5fa0c423e5747
+oid sha256:c92d6d1e1b87396b0e067b3d5724aa6108c00b67b400cf4276964e62941d80b5
 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": 0.0021227666725632407,
+  "epoch": 0.004245533345126481,
   "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": 15.891,
       "eval_steps_per_second": 7.959,
       "step": 3
+    },
+    {
+      "epoch": 0.0028303555634176542,
+      "grad_norm": 0.6546880602836609,
+      "learning_rate": 8e-05,
+      "loss": 0.9462,
+      "step": 4
+    },
+    {
+      "epoch": 0.0035379444542720678,
+      "grad_norm": 0.6106970310211182,
+      "learning_rate": 0.0001,
+      "loss": 0.9038,
+      "step": 5
+    },
+    {
+      "epoch": 0.004245533345126481,
+      "grad_norm": 0.4324353039264679,
+      "learning_rate": 0.00012,
+      "loss": 0.6771,
+      "step": 6
+    },
+    {
+      "epoch": 0.004245533345126481,
+      "eval_loss": 0.9147760272026062,
+      "eval_runtime": 37.5096,
+      "eval_samples_per_second": 15.863,
+      "eval_steps_per_second": 7.945,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 187536499015680.0,
+  "total_flos": 400077864566784.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null