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:e7afee5b77c973a47a8e24a0dacbef308c512bfc5dc8975af7b9672f75571233
+oid sha256:aa9ac750196de913e98e8a37e0e35b38fe6524c64a0da8abe97e54b85c3a7f28
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7fc17d267c2d1260cf74c7f48be0b25e1fcb556c094b2116a3d6c7183396855
+oid sha256:0b65587ad600575a9e608cc7a3945515d559a60cabd0833e69b3cfeaa6d89ac2
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:192f0b407dbacf0c2b575154416f6b58ccc968389aba4b372a0f03a786ad6139
+oid sha256:8698664741532736c8338ceeee4c7726d838b00c383d3de8ee8b8c18b52e285b
 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": 0.006418828563787109,
+  "epoch": 0.009628242845680663,
   "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": 6.971,
       "eval_steps_per_second": 3.486,
       "step": 6
+    },
+    {
+      "epoch": 0.007488633324418294,
+      "grad_norm": 22.19415283203125,
+      "learning_rate": 0.00014,
+      "loss": 12.868,
+      "step": 7
+    },
+    {
+      "epoch": 0.008558438085049478,
+      "grad_norm": 32.429786682128906,
+      "learning_rate": 0.00016,
+      "loss": 8.5214,
+      "step": 8
+    },
+    {
+      "epoch": 0.009628242845680663,
+      "grad_norm": 23.76179313659668,
+      "learning_rate": 0.00018,
+      "loss": 4.399,
+      "step": 9
+    },
+    {
+      "epoch": 0.009628242845680663,
+      "eval_loss": 2.3507754802703857,
+      "eval_runtime": 56.3965,
+      "eval_samples_per_second": 6.986,
+      "eval_steps_per_second": 3.493,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1387173186109440.0,
+  "total_flos": 1988281566756864.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null