Training in progress, step 205, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a61688e024d8b1932cf10e8c7c4fd8bfa5735392d153178ec88aa005f437659
+oid sha256:92d85651c439ce48ea3d56c40d0425842d7994baed4a47aad62e36d94c4b23f1
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea23f453f8eabb264c21bbd0ca4d6a94ff11fc210c556dccdf6af0579fafbae7
+oid sha256:7bf193ed81f93c6475fd57733a56c1fe79c8c69f8b94c784383e191d9cc545dd
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81a4a5fe39569f33dbe40b2c3ef823b0ec30e90ec73a71b204af658d0ae7ceda
+oid sha256:1abed11a84ff2a3bab289ee4dbc5e653fda08a38f63ccae1554d6dac1565b7c1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71634941cfc460d54b5b983134e7f409c965008ba2b3dc0170fbbc05dbb2ca6c
+oid sha256:8250598c1a75cab0d8ccbc05b8ea5e24aa609b6e2d13838f6a479d4b06a86035
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2588159171789065,
+  "epoch": 0.2652863151083792,
   "eval_steps": 386,
-  "global_step": 200,
+  "global_step": 205,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1415,6 +1415,41 @@
       "learning_rate": 9.961803937075516e-05,
       "loss": 0.9766,
       "step": 200
+    },
+    {
+      "epoch": 0.260109996764801,
+      "grad_norm": 0.8204835057258606,
+      "learning_rate": 9.961293618920826e-05,
+      "loss": 0.8864,
+      "step": 201
+    },
+    {
+      "epoch": 0.26140407635069557,
+      "grad_norm": 0.9315406084060669,
+      "learning_rate": 9.960779927545883e-05,
+      "loss": 1.0388,
+      "step": 202
+    },
+    {
+      "epoch": 0.2626981559365901,
+      "grad_norm": 0.9286762475967407,
+      "learning_rate": 9.960262863299943e-05,
+      "loss": 0.9653,
+      "step": 203
+    },
+    {
+      "epoch": 0.26399223552248463,
+      "grad_norm": 0.8037816882133484,
+      "learning_rate": 9.959742426534566e-05,
+      "loss": 0.765,
+      "step": 204
+    },
+    {
+      "epoch": 0.2652863151083792,
+      "grad_norm": 0.9435904622077942,
+      "learning_rate": 9.9592186176036e-05,
+      "loss": 0.8889,
+      "step": 205
     }
   ],
   "logging_steps": 1,
@@ -1434,7 +1469,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.235874343387136e+17,
+  "total_flos": 2.2917712019718144e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null