Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:283afa3baa5e8fa4f6de2c39b1c86f7af0f20ab0c3471172a020080149e96b5d
+oid sha256:e01b1332e5d8080c66d9841bb5c7b323e109aca57192d35cb76be29d56513ea5
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cf67360110e8579f38370ecbca04d67fc1c12e9965f67398fe8530282f95fd4
+oid sha256:ab8a351790dab7c6dd8f30d7c2bbee4b07dfde3aa146973843f1617b9f8ed2ef
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f005639ce0865eae9775065c9fed38932da15f22f9e96d8e1fc81a298bdf6ae
+oid sha256:0e0cecd4fa0b346dabc60917e1b3ca1c91ce878034ad78d001aa7d9a1f75d88e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0001196911967124818,
+  "epoch": 0.0002393823934249636,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 22.906,
       "eval_steps_per_second": 11.453,
       "step": 3
+    },
+    {
+      "epoch": 0.00015958826228330906,
+      "grad_norm": 35.32827377319336,
+      "learning_rate": 8e-05,
+      "loss": 12.036,
+      "step": 4
+    },
+    {
+      "epoch": 0.00019948532785413634,
+      "grad_norm": 27.98809051513672,
+      "learning_rate": 0.0001,
+      "loss": 13.5756,
+      "step": 5
+    },
+    {
+      "epoch": 0.0002393823934249636,
+      "grad_norm": 30.70273780822754,
+      "learning_rate": 0.00012,
+      "loss": 9.3102,
+      "step": 6
+    },
+    {
+      "epoch": 0.0002393823934249636,
+      "eval_loss": 6.75634241104126,
+      "eval_runtime": 460.8268,
+      "eval_samples_per_second": 22.902,
+      "eval_steps_per_second": 11.451,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 786064805462016.0,
+  "total_flos": 1618368717127680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null