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:bf79143b43de7946ae41765d28672b49c87af81c5c3a11082807a51cc6eaf930
+oid sha256:6924471615dadc09cde5478f2c6ae7199eef81fb83b9a9ca2d83a3d6eba9c6e4
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66257d86ec2679933882031c1f680443efc3f693497c7734126f5cb46aff0a25
+oid sha256:6d75a1d9a17262369472b5f9ead778b4f35a9c06ddda1255c5e0e3bc4f5e1a35
 size 212298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c5c2489f942c0bfb1f653e1fc6bfc4d52b4ef6a98d19d8a41801976ad4c8d82
+oid sha256:f740901ed64f5f8faba4c4399f748c6779503ac7c16ef83516dab3603a5a5402
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c1fa12db6e65a79cc008f6035c457ab68bb8c45c7fe7a2790ea24e528e6b743
+oid sha256:a4b679dfcad285902b67d18379c2cc1ca0aebfc7646cb33fa82a3fb8ed15c820
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15007816571130797,
+  "epoch": 0.30015633142261594,
   "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": 120.339,
       "eval_steps_per_second": 60.466,
       "step": 9
+    },
+    {
+      "epoch": 0.20010422094841063,
+      "grad_norm": 0.028992891311645508,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 11.7632,
+      "step": 12
+    },
+    {
+      "epoch": 0.2501302761855133,
+      "grad_norm": 0.03157561272382736,
+      "learning_rate": 0.0001125,
+      "loss": 11.7637,
+      "step": 15
+    },
+    {
+      "epoch": 0.30015633142261594,
+      "grad_norm": 0.03268129751086235,
+      "learning_rate": 0.000135,
+      "loss": 11.7614,
+      "step": 18
+    },
+    {
+      "epoch": 0.30015633142261594,
+      "eval_loss": 11.761802673339844,
+      "eval_runtime": 1.7013,
+      "eval_samples_per_second": 119.322,
+      "eval_steps_per_second": 59.955,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 17003186749440.0,
+  "total_flos": 33596658155520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null