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:f957e5edcf0ff7edcf880d4932568895bcc715076392b634ce9f352173191db8
+oid sha256:23ef621c8b616e5e304df0bd7cf91f1573ff3c738f325bb909db08731d6b8772
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8545bcb51c957caacd8363678a7c7538ab58dc9e929fe36b19607e90c786662
+oid sha256:90030f4ac1245cdf030cf76e09ab129dd56976981f9c1b26ec614206d195fea6
 size 42608388

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c81455e3b5fa4ac608032487865cd5d9aad1b7633e0d831b8d1e1e3f9ce6956
+oid sha256:2b9e29ca9f1840ccec759292965b44b25e81d2b6f5643637c96ef211cfb804af
 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": 4.8702879963635184e-05,
+  "epoch": 9.740575992727037e-05,
   "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": 7.698,
       "eval_steps_per_second": 7.698,
       "step": 3
+    },
+    {
+      "epoch": 6.493717328484691e-05,
+      "grad_norm": 9.130757331848145,
+      "learning_rate": 8e-05,
+      "loss": 3.286,
+      "step": 4
+    },
+    {
+      "epoch": 8.117146660605864e-05,
+      "grad_norm": 9.889158248901367,
+      "learning_rate": 0.0001,
+      "loss": 2.3931,
+      "step": 5
+    },
+    {
+      "epoch": 9.740575992727037e-05,
+      "grad_norm": 7.035650253295898,
+      "learning_rate": 0.00012,
+      "loss": 2.4323,
+      "step": 6
+    },
+    {
+      "epoch": 9.740575992727037e-05,
+      "eval_loss": NaN,
+      "eval_runtime": 1684.7423,
+      "eval_samples_per_second": 7.697,
+      "eval_steps_per_second": 7.697,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 603178974314496.0,
+  "total_flos": 1206357948628992.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null