Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73cd4e307afb1b93af96f534b74e1fdb650c784e0df7f30af8128b0a77d4d871
+oid sha256:b86f5ad33660fddfff5263e1fa06acf14bdf0b0b95fbcb733d06f4c0cb307df4
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ec2c4a92b1f877dabf703daed8e2e31088dfbfd57279a4dc9cdd2e6fcccd59e
+oid sha256:4afc71cec9aebc44a78c0bfbcc15870f9dfca4ffcfac2e4745d820134ac597d5
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6ef257eb7ff1c303d123acbae6f6510f62484eeaf16e641f1b0beef7381f6a
+oid sha256:ff2dfae3c6bd6c249bbd1ea727529189ba490dc8ff45314181f74050c12d0531
 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": 0.014234875444839857,
+  "epoch": 0.021352313167259787,
   "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": 387.73,
       "eval_steps_per_second": 193.865,
       "step": 6
+    },
+    {
+      "epoch": 0.0166073546856465,
+      "grad_norm": 0.04348461702466011,
+      "learning_rate": 0.00014,
+      "loss": 10.3802,
+      "step": 7
+    },
+    {
+      "epoch": 0.018979833926453145,
+      "grad_norm": 0.05182609334588051,
+      "learning_rate": 0.00016,
+      "loss": 10.3752,
+      "step": 8
+    },
+    {
+      "epoch": 0.021352313167259787,
+      "grad_norm": 0.04678908735513687,
+      "learning_rate": 0.00018,
+      "loss": 10.3739,
+      "step": 9
+    },
+    {
+      "epoch": 0.021352313167259787,
+      "eval_loss": 10.369029998779297,
+      "eval_runtime": 0.4202,
+      "eval_samples_per_second": 423.601,
+      "eval_steps_per_second": 211.801,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 77585448960.0,
+  "total_flos": 116378173440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null