Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c78b215bb9d89ff3fa839ec707db622f34754f79e4d6a5f0cb291735dad0db4
+oid sha256:d704dfd3184c1bfc6795d409e2b0c2e3c5faa4206c29f4492853cfb3ea8789c7
 size 5752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f991a7bd6f13f0336faa87369ab5559d55fe1a5603d67a855c49416168c3e25
+oid sha256:26c3035dd15b0481c26fadd027785430b3e56b0e32a23a5e0b3fd4f152502b15
 size 15814

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9264abfa6d2cc5145363bf71d2fb16332b1ac4e60642a70827881d9a447c36a4
+oid sha256:af82c1f1d4ec999545a290f8875f59e0434314b9e98a3c2553c0c541daf4cdfa
 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": 0.001905366783105748,
+  "epoch": 0.003810733566211496,
   "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": 189.73,
       "eval_steps_per_second": 95.008,
       "step": 3
+    },
+    {
+      "epoch": 0.0025404890441409972,
+      "grad_norm": 3.1553656299365684e-05,
+      "learning_rate": 8e-05,
+      "loss": 46.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.0031756113051762463,
+      "grad_norm": 3.737325459951535e-05,
+      "learning_rate": 0.0001,
+      "loss": 46.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.003810733566211496,
+      "grad_norm": 3.1286661396734416e-05,
+      "learning_rate": 0.00012,
+      "loss": 46.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.003810733566211496,
+      "eval_loss": 11.5,
+      "eval_runtime": 3.627,
+      "eval_samples_per_second": 182.795,
+      "eval_steps_per_second": 91.535,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 69730074624.0,
+  "total_flos": 129498710016.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null