Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3afc7018e29c21d30dec35657ae34358d0fb0f9abb809f70cd7e6ccbec83bdfb
+oid sha256:7689b08d14537942ac21d66a0b9a9e1c0bc6d8567239ca48808b3f8bdf024a38
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41f89c1bb53ccdc38897acac4e2172a0d936cde38f6e445661d7b718e3fd6156
+oid sha256:c8f50d66e4593336e9c9bcc13471097326b803c637c6a78a47bfb3c80402557d
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83e1d42fa3a43f0b49fecc1fb9869481eef60e0607192a6ff7e39173952f7302
+oid sha256:81feec53929608a3d2b539f66e29270211cb35072ffa9c1bcebaa955f7bdc514
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.11214953271028037,
+  "epoch": 0.16822429906542055,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 30.415,
       "eval_steps_per_second": 15.868,
       "step": 6
+    },
+    {
+      "epoch": 0.1308411214953271,
+      "grad_norm": 1.3398456573486328,
+      "learning_rate": 0.00014,
+      "loss": 2.3719,
+      "step": 7
+    },
+    {
+      "epoch": 0.14953271028037382,
+      "grad_norm": 1.376936912536621,
+      "learning_rate": 0.00016,
+      "loss": 1.7642,
+      "step": 8
+    },
+    {
+      "epoch": 0.16822429906542055,
+      "grad_norm": 1.6025842428207397,
+      "learning_rate": 0.00018,
+      "loss": 1.9801,
+      "step": 9
+    },
+    {
+      "epoch": 0.16822429906542055,
+      "eval_loss": 2.127096652984619,
+      "eval_runtime": 0.7449,
+      "eval_samples_per_second": 30.878,
+      "eval_steps_per_second": 16.11,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1155977655091200.0,
+  "total_flos": 1710846929534976.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null