Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56848eb639accec7bef847b301ab2abea16d0955406230d8693429c8cbdc303b
+oid sha256:988a7a3626c2bb4dd44b88a73511539ba8dd35430220e95483bd47565f57cdf1
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2fb9d3825c162f9f52571138781d57b294bec0944be3db7e05be3772fee042b
+oid sha256:0b2b52bd6ad55e8c14435661f6bd50b5505ca385bf87f318fa30a9440943916d
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdc6b3923e158a46524ef942acb9e1e15e79ef0241c59ce127009613bf7b23bf
+oid sha256:942af8987e356e19a3198ec111fa703c2d54a92114bb8091448dcaa07a5fe22e
 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": 0.00015083525019797127,
+  "epoch": 0.00030167050039594254,
   "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": 7.147,
       "eval_steps_per_second": 3.574,
       "step": 3
+    },
+    {
+      "epoch": 0.00020111366693062834,
+      "grad_norm": 0.4316411018371582,
+      "learning_rate": 8e-05,
+      "loss": 1.7962,
+      "step": 4
+    },
+    {
+      "epoch": 0.00025139208366328547,
+      "grad_norm": 0.34983840584754944,
+      "learning_rate": 0.0001,
+      "loss": 2.1419,
+      "step": 5
+    },
+    {
+      "epoch": 0.00030167050039594254,
+      "grad_norm": 0.28104010224342346,
+      "learning_rate": 0.00012,
+      "loss": 1.8218,
+      "step": 6
+    },
+    {
+      "epoch": 0.00030167050039594254,
+      "eval_loss": 1.7353360652923584,
+      "eval_runtime": 1159.2615,
+      "eval_samples_per_second": 7.224,
+      "eval_steps_per_second": 3.613,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 653488517283840.0,
+  "total_flos": 1350542935719936.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null