Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5992a86747cef14f63762668b2ac2fbf9e23ce5e8bb74133abf9d11c202cc4f4
+oid sha256:8793f46feb5de8084edfe2d09eb7051d2e0cf0226d4c35f19c7f3b706f020162
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c1e8f5f88992d2a779e848ba59169c2a7ac5ded2dac15a4d2e66d46ef348edf
+oid sha256:81abc551906a3c2b0ee0bcf4e2f4b1fae525647218995a2d644aa121904655c5
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc695d50fa9c7a7b39e7508c0827b13b4400b02508b8aa483545d12dba8b4308
+oid sha256:42700a3931f169d1a7cb24ca5c5bfdf8c30401d4efdc7d55be9e5bed753e25b1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cbe95d5ecd33771846042e20aabf210775f4e6a78ced16f0764898d40abeba5
+oid sha256:cedaf8893734b19717a3bbbc716629d55965a18bdde504cf46d9182fcb60eb14
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012225686166636102,
+  "epoch": 0.014670823399963322,
   "eval_steps": 34,
-  "global_step": 25,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -190,6 +190,41 @@
       "learning_rate": 0.0001666666666666667,
       "loss": 0.9764,
       "step": 25
+    },
+    {
+      "epoch": 0.012714713613301546,
+      "grad_norm": 0.6190416812896729,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 0.9819,
+      "step": 26
+    },
+    {
+      "epoch": 0.013203741059966991,
+      "grad_norm": 0.4747830927371979,
+      "learning_rate": 0.00018,
+      "loss": 0.9395,
+      "step": 27
+    },
+    {
+      "epoch": 0.013692768506632435,
+      "grad_norm": 0.9486120343208313,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 0.9669,
+      "step": 28
+    },
+    {
+      "epoch": 0.014181795953297879,
+      "grad_norm": 0.4615766108036041,
+      "learning_rate": 0.00019333333333333333,
+      "loss": 0.9341,
+      "step": 29
+    },
+    {
+      "epoch": 0.014670823399963322,
+      "grad_norm": 0.46146905422210693,
+      "learning_rate": 0.0002,
+      "loss": 1.0082,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -209,7 +244,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.109738548887552e+17,
+  "total_flos": 1.3316862586650624e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null