Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b9276134add1a9d62c5149512746492c7cbb4141b89af9bcfa8e2925e5a8b80
+oid sha256:ca0db966ae65eb1b520e8f3ae3d456f9d4e91465f627cd1c82756b33b1b419f1
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:160d95c0a28d6a6b7d233b51017579b3b47bd1fe3bb6272e145a55a01f6c0586
+oid sha256:36dade300cc644e90cbf7ee1611e18edf52418503670d90c67cd8931c193f11d
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c54b1263e33f4122f1c769808e699b240af8adf0df9054b3e4eff55c7874f1b1
+oid sha256:1c7e8c0f7bb988751ccd9907b573ddb354edc6c4d1478341caae7f6c4a40c442
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:621519582414cbcc961b30cff113e8b1e10923f26e46ef8e0ad7c29a35554318
+oid sha256:d403ac4d7711325e0c8bec676128002b741c5058ffa34f8bfc8e7d7e4547c436
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0012614206750352585,
+  "epoch": 0.002522841350070517,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 8.985,
       "eval_steps_per_second": 4.493,
       "step": 9
+    },
+    {
+      "epoch": 0.0016818942333803445,
+      "grad_norm": 2.783182382583618,
+      "learning_rate": 0.00012,
+      "loss": 1.9193,
+      "step": 12
+    },
+    {
+      "epoch": 0.002102367791725431,
+      "grad_norm": 2.446138381958008,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.6654,
+      "step": 15
+    },
+    {
+      "epoch": 0.002522841350070517,
+      "grad_norm": 1.4197582006454468,
+      "learning_rate": 0.00018,
+      "loss": 1.4818,
+      "step": 18
+    },
+    {
+      "epoch": 0.002522841350070517,
+      "eval_loss": 1.463165283203125,
+      "eval_runtime": 2674.6792,
+      "eval_samples_per_second": 8.986,
+      "eval_steps_per_second": 4.493,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.371275255585178e+16,
+  "total_flos": 1.0742550511170355e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null