Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2db7a836d3828d6dbe5d208237301a20329bf2c5f16fa592c38e71e72f69a2b6
+oid sha256:a69a31f0f5101aa463b688ddb3981a0de27e35c7d56ee6447bd5f72e4eb858aa
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0523db887ea76127cb28a94fa341f7e6d43b538f5eca548d7215ca2d8146e20
+oid sha256:3a26986f912ddb383f928e78f2d8ccf8794c4326cf8ed9b93f780150d4978ead
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6be89b2cd2a89bc9a357c462211278505e1756ffdfc78ecf89b3010a0b8981e
+oid sha256:e6bf19e75a59ee8c6a96e9c63d30b78c698cbfef05ceb7eb28dd7602d0b1a826
 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": 0.005934718100890208,
+  "epoch": 0.011869436201780416,
   "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": 31.862,
       "eval_steps_per_second": 16.006,
       "step": 3
+    },
+    {
+      "epoch": 0.00791295746785361,
+      "grad_norm": 2.6389150619506836,
+      "learning_rate": 8e-05,
+      "loss": 3.455,
+      "step": 4
+    },
+    {
+      "epoch": 0.009891196834817012,
+      "grad_norm": 2.1177756786346436,
+      "learning_rate": 0.0001,
+      "loss": 3.1793,
+      "step": 5
+    },
+    {
+      "epoch": 0.011869436201780416,
+      "grad_norm": 2.3191111087799072,
+      "learning_rate": 0.00012,
+      "loss": 3.1444,
+      "step": 6
+    },
+    {
+      "epoch": 0.011869436201780416,
+      "eval_loss": 3.2011735439300537,
+      "eval_runtime": 6.7027,
+      "eval_samples_per_second": 31.778,
+      "eval_steps_per_second": 15.964,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 554869274443776.0,
+  "total_flos": 1109738548887552.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null