Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90c26a85e38465a485240c658909a17687699416af3e79f864da8043bd0f62fc
+oid sha256:596da61471f7acd22dfed810279a826afb7b67f26080e0055da80a685e50ae03
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f80c9ff111119d40461ca73630d31c5328cada50105f577839c77ebc90090796
+oid sha256:3a70f332281dffbc44dd442c0eb6fba71dece1c53fc85584adbaed85acee7fe1
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a5c53b4ddb1f83c87db0874b9ca8a72613eb4fb4e16a727f1e944d64a00fe7b
+oid sha256:72223fd40b61c72a4df43aea9c90ca091d8f4c0b5e6bb74b51346988ac0956d2
 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": 9.1022,
       "step": 25
+    },
+    {
+      "epoch": 0.012714713613301546,
+      "grad_norm": 3.8149141971211387e+18,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 8.8296,
+      "step": 26
+    },
+    {
+      "epoch": 0.013203741059966991,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00018,
+      "loss": 9.8113,
+      "step": 27
+    },
+    {
+      "epoch": 0.013692768506632435,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 9.417,
+      "step": 28
+    },
+    {
+      "epoch": 0.014181795953297879,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00019333333333333333,
+      "loss": 9.168,
+      "step": 29
+    },
+    {
+      "epoch": 0.014670823399963322,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0002,
+      "loss": 10.644,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -209,7 +244,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.51119918989312e+16,
+  "total_flos": 6.613439027871744e+16,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null