Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0015db75b00059c3f110e70095a6c6d7d36d96cd2d6563588ae4d5dd02d91712
+oid sha256:566ccbae4847bf755e8ffdcbe370491dcef6e53c6c881f74c2586b6688e121b0
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55e660754751563d5fea2d94b32d11bfb3c3e16890918e7783da0230afc62f13
+oid sha256:fbf82d87a34dbdcccefce1546f659382b3f536a89da8746a5ef8940cc8caa5dd
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59dfd7e3c5f47e9c59dd82d5934b354dca1792ccd6d53d936783c3e96fc445c8
+oid sha256:fda5437f05e2eaed0597b85f69532d5c06b3025917ba7357f9b3d1d946872746
 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": 0.001282188267977348,
+  "epoch": 0.001923282401966022,
   "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": 51.303,
       "eval_steps_per_second": 25.665,
       "step": 6
+    },
+    {
+      "epoch": 0.0014958863126402393,
+      "grad_norm": 4.81810188293457,
+      "learning_rate": 0.00014,
+      "loss": 3.5625,
+      "step": 7
+    },
+    {
+      "epoch": 0.0017095843573031308,
+      "grad_norm": 5.296993255615234,
+      "learning_rate": 0.00016,
+      "loss": 3.2156,
+      "step": 8
+    },
+    {
+      "epoch": 0.001923282401966022,
+      "grad_norm": 4.5458083152771,
+      "learning_rate": 0.00018,
+      "loss": 2.9665,
+      "step": 9
+    },
+    {
+      "epoch": 0.001923282401966022,
+      "eval_loss": 2.9628167152404785,
+      "eval_runtime": 39.5428,
+      "eval_samples_per_second": 49.845,
+      "eval_steps_per_second": 24.935,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 53422898282496.0,
+  "total_flos": 80134347423744.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null