Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ead1015358f53d8b26266b949b4cb122cc003c02da0bdcb89e6918a0d42c095
+oid sha256:4275ed8c59bb14540d0badec4aede052c20924fab1795598608f7d12e88a8912
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdecb82c67077d09331ad0661f24d23c62cea924ea11fb27fde9ad33756f07dc
+oid sha256:31c420554c81b81381fce9f5da1cfdbc8eba10ad6393a9bdfcdafd5a4ff582f3
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:910ad6e66382619ec0777db80aa80cdb3bca0ea1814521679c8c0a2928e71c4d
+oid sha256:e9697c65e7e415a76c27a2584401385c8ade4b1aff580109a38b555858692664
 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": 0.008908685968819599,
+  "epoch": 0.013363028953229399,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -65,6 +65,35 @@
       "eval_samples_per_second": 13.764,
       "eval_steps_per_second": 6.882,
       "step": 6
+    },
+    {
+      "epoch": 0.010393466963622866,
+      "grad_norm": 10.377184867858887,
+      "learning_rate": 0.00014,
+      "loss": 9.6,
+      "step": 7
+    },
+    {
+      "epoch": 0.011878247958426132,
+      "grad_norm": 21.33673667907715,
+      "learning_rate": 0.00016,
+      "loss": 9.8471,
+      "step": 8
+    },
+    {
+      "epoch": 0.013363028953229399,
+      "grad_norm": 15.13981819152832,
+      "learning_rate": 0.00018,
+      "loss": 6.9279,
+      "step": 9
+    },
+    {
+      "epoch": 0.013363028953229399,
+      "eval_loss": 1.2549283504486084,
+      "eval_runtime": 18.303,
+      "eval_samples_per_second": 15.517,
+      "eval_steps_per_second": 7.758,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -84,7 +113,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1899734583214080.0,
+  "total_flos": 2849601874821120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null