Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29577600c2a2affc4b1cbd34a27f2272546d7430ef06c98a31d7a42880314429
+oid sha256:e55a7a2800b11cf228e53ec4da7c02921ac6b50070abc0c356385c62a60209cd
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95cb1592b923c4200460d7b40644001506a0e567129ce9f7a8166296a3678402
+oid sha256:cea7fec12f6abd90de3b923e4424b11d10589b6961349f4d28737e695588c195
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b774edba0a453c1e2ef2968a8991164309bfa632655c3c16684413a8dee343a2
+oid sha256:b35cfe9f5e5f782238d2a3b603736aaf8ebd4736e7c2ce4d888cdf269bffaf77
 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": 0.00023535410987114363,
+  "epoch": 0.00047070821974228727,
   "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": 14.763,
       "eval_steps_per_second": 7.381,
       "step": 3
+    },
+    {
+      "epoch": 0.0003138054798281915,
+      "grad_norm": 0.8401862382888794,
+      "learning_rate": 8e-05,
+      "loss": 1.9984,
+      "step": 4
+    },
+    {
+      "epoch": 0.00039225684978523936,
+      "grad_norm": 0.746632993221283,
+      "learning_rate": 0.0001,
+      "loss": 2.2822,
+      "step": 5
+    },
+    {
+      "epoch": 0.00047070821974228727,
+      "grad_norm": 0.830866277217865,
+      "learning_rate": 0.00012,
+      "loss": 2.1672,
+      "step": 6
+    },
+    {
+      "epoch": 0.00047070821974228727,
+      "eval_loss": 2.1076629161834717,
+      "eval_runtime": 363.7362,
+      "eval_samples_per_second": 14.758,
+      "eval_steps_per_second": 7.379,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1108895921602560.0,
+  "total_flos": 2376205546291200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null