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:ea336ed4d52564e21b6c0cdd91a7b11df83a05fb722a1cc6297090b176f80520
+oid sha256:7ef5379668c99b968c4bcb60184dd146809d97ddfe90d2d51a303e9d10f48ce9
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97de53943b1a6fe00b581c695cd7c2eee826a1b788dccc3dbe9440dcadf27346
+oid sha256:c4ff918aa82d9658ea4b9b36ac8d0b51406293f2951a34eae4d6e1f144319a49
 size 160172858

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a8f33a31a12e65db9870d40bbb9d66edfe40f1dc6aa3433fec5ee98dca66971
+oid sha256:1fc55e46f74fe1e2e19c9e192915616355e27c05ef750c64fd8b2b37786c93c3
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f512eb7cabd3ec7770303d18fe69984e8ff8f7c3825fa2bf0e1bb589a6f365e2
+oid sha256:c2f78b0455452857cdb1835c39eb64ab9332e969a942073abdb8307a1f1fcb3d
 size 14512

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": 0.0032258064516129032,
+  "epoch": 0.004838709677419355,
   "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": 15.226,
       "eval_steps_per_second": 7.613,
       "step": 6
+    },
+    {
+      "epoch": 0.003763440860215054,
+      "grad_norm": 0.46053290367126465,
+      "learning_rate": 0.00014,
+      "loss": 1.0607,
+      "step": 7
+    },
+    {
+      "epoch": 0.004301075268817204,
+      "grad_norm": 0.4400120973587036,
+      "learning_rate": 0.00016,
+      "loss": 1.1322,
+      "step": 8
+    },
+    {
+      "epoch": 0.004838709677419355,
+      "grad_norm": 0.5260744690895081,
+      "learning_rate": 0.00018,
+      "loss": 0.8884,
+      "step": 9
+    },
+    {
+      "epoch": 0.004838709677419355,
+      "eval_loss": 0.9314318895339966,
+      "eval_runtime": 50.6945,
+      "eval_samples_per_second": 15.465,
+      "eval_steps_per_second": 7.733,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1954499090448384.0,
+  "total_flos": 2931748635672576.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null