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:d1415d706bec38defea36ead3cdc39d5ce811269ab784cb78fd8053c91723677
+oid sha256:a67ab2a4fdfaad74ee01f67f47483c2b7d15597b91d8bfe2603244b3761b6d33
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53cee3a01715dd1f667e94192ea5f8eac7153db9568942a543655321632bda88
+oid sha256:cb97331a651f2c5a16194269d485af461b8ba38a536ffb3fd0cd46dd78634241
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f740901ed64f5f8faba4c4399f748c6779503ac7c16ef83516dab3603a5a5402
+oid sha256:b5db0eb505891a65233cdcbbe5a0de714bf369879ab6d0e941ebb7e8bd026d21
 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": 0.01646090534979424,
+  "epoch": 0.024691358024691357,
   "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": 44.295,
       "eval_steps_per_second": 22.148,
       "step": 6
+    },
+    {
+      "epoch": 0.019204389574759947,
+      "grad_norm": 86.56372833251953,
+      "learning_rate": 0.00014,
+      "loss": 5.6625,
+      "step": 7
+    },
+    {
+      "epoch": 0.02194787379972565,
+      "grad_norm": 80.3042984008789,
+      "learning_rate": 0.00016,
+      "loss": 9.7957,
+      "step": 8
+    },
+    {
+      "epoch": 0.024691358024691357,
+      "grad_norm": 109.0301513671875,
+      "learning_rate": 0.00018,
+      "loss": 10.7531,
+      "step": 9
+    },
+    {
+      "epoch": 0.024691358024691357,
+      "eval_loss": 1.7538036108016968,
+      "eval_runtime": 3.5013,
+      "eval_samples_per_second": 43.984,
+      "eval_steps_per_second": 21.992,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 105274278936576.0,
+  "total_flos": 155718204260352.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null