Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a9be087ddd38ba7fc9dabd356b03ae674ecd4f9e7ca16de67de25f35ae98ee7
+oid sha256:4a3c20f10dd5c310dff2457946d5adda07b86ebf9ae1075c19bfc85c21a201cd
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a6dcbb75539080158a2a0cd44ce6cf06e4a7143ddfda1277c6c3518a1e82500
+oid sha256:06ac8233b1d594e17385b5ad1e880be7b7fd1508b520edbbe847f6c5dcffa0e1
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c54966f2465e62f3f23221c1b18d8d6c1829302b329b674439c498e34e1b28ba
+oid sha256:c8f9bfbb25b5742af971410f7969204872224492d0748212c97b7e3aec33a144
 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": 0.001415261233636042,
+  "epoch": 0.002830522467272084,
   "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": 276.014,
       "eval_steps_per_second": 138.162,
       "step": 3
+    },
+    {
+      "epoch": 0.0018870149781813894,
+      "grad_norm": 0.023581691086292267,
+      "learning_rate": 8e-05,
+      "loss": 10.3762,
+      "step": 4
+    },
+    {
+      "epoch": 0.0023587687227267368,
+      "grad_norm": 0.029611019417643547,
+      "learning_rate": 0.0001,
+      "loss": 10.3863,
+      "step": 5
+    },
+    {
+      "epoch": 0.002830522467272084,
+      "grad_norm": 0.024547450244426727,
+      "learning_rate": 0.00012,
+      "loss": 10.377,
+      "step": 6
+    },
+    {
+      "epoch": 0.002830522467272084,
+      "eval_loss": 10.383139610290527,
+      "eval_runtime": 3.3048,
+      "eval_samples_per_second": 270.213,
+      "eval_steps_per_second": 135.258,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 77585448960.0,
+  "total_flos": 155170897920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null