Training in progress, epoch 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71581f82e6862d692176414092b0e8e6764e17449a2329441b4ae88e3739269d
+oid sha256:105ec62e27b1b8f7aa153564669d99fdcae0cce994dd95aba51fb7cde2a103e5
 size 146815928

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c391e45498ded4e2e57b61dddbfa94dbac874ad6c82d5a4eab31f0717e8f5808
+oid sha256:ef9fef5576f86effc4c65cf9d7c9f62d32e18f35dd03d4c5d7d232b608e9b596
 size 74680890

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:952a271550edb332dcf42e7bd768d2235aafa919742890d7287782b6398dcfe0
+oid sha256:06f6baef321f45542655ea7e7bc0542f19585c5e699e115b35512d8ecf429cda
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4822723ae3261c98ea16adc0ab752d38bf2ec1968c2933f8124d383bce7b609
+oid sha256:4b9f54317f5921d87d4ee06afedabceb6dc4bda58df9df55b7d20d07603bdb24
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
+  "epoch": 6.0,
   "eval_steps": 500,
-  "global_step": 1750,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -166,6 +166,42 @@
       "eval_samples_per_second": 2.111,
       "eval_steps_per_second": 0.528,
       "step": 1750
+    },
+    {
+      "epoch": 5.142857142857143,
+      "grad_norm": 0.6160484552383423,
+      "learning_rate": 0.00011333333333333334,
+      "loss": 0.1886,
+      "step": 1800
+    },
+    {
+      "epoch": 5.428571428571429,
+      "grad_norm": 0.41531217098236084,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 0.1814,
+      "step": 1900
+    },
+    {
+      "epoch": 5.714285714285714,
+      "grad_norm": 0.43082195520401,
+      "learning_rate": 0.0001,
+      "loss": 0.1783,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.5060862302780151,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 0.1732,
+      "step": 2100
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.23785410821437836,
+      "eval_runtime": 331.866,
+      "eval_samples_per_second": 2.109,
+      "eval_steps_per_second": 0.527,
+      "step": 2100
     }
   ],
   "logging_steps": 100,
@@ -185,7 +221,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.283075383839949e+16,
+  "total_flos": 5.136567526804685e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null