Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c15fd40905c39b6a585d5ca0294c344111af19185eb1051b9c52136d9c770bc8
+oid sha256:664cb66582e86aefa0c4143dccdf257c3265e64503006391e7efcce9c1617a7c
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a30500e9376f12fe53d54c5520d3ac4105160e2363ddd2ea7e3ee5383a4e5b7
+oid sha256:dab2fe20abf7a9ff555011c8c2e7f4d1165b948742087a67e55abde6e0e9871d
 size 45276986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a55e9c336339d6fd13d64d8454d14449f18f5cdad9904b170065366b9868f8c6
+oid sha256:89dea70f47acd2b9f7ea2c5f0039833bb10d2c6ee456c9814feb8de96fd74cd3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06829946ff807c7143728448cc1bf384944e638865601317db4b29a92003bb11
+oid sha256:008d83c4f5ee0c3b0aa2ca88e92cb7f21d43acfd48a8bc37442b67fb3134fa7c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00011343012704174228,
+  "epoch": 0.00017014519056261342,
   "eval_steps": 2,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -125,6 +125,57 @@
       "eval_samples_per_second": 42.487,
       "eval_steps_per_second": 21.244,
       "step": 10
+    },
+    {
+      "epoch": 0.0001247731397459165,
+      "grad_norm": 1.8356683254241943,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.5877,
+      "step": 11
+    },
+    {
+      "epoch": 0.00013611615245009076,
+      "grad_norm": 2.1842660903930664,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.7213,
+      "step": 12
+    },
+    {
+      "epoch": 0.00013611615245009076,
+      "eval_loss": 2.6496598720550537,
+      "eval_runtime": 873.54,
+      "eval_samples_per_second": 42.494,
+      "eval_steps_per_second": 21.247,
+      "step": 12
+    },
+    {
+      "epoch": 0.00014745916515426498,
+      "grad_norm": 1.7997459173202515,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.5478,
+      "step": 13
+    },
+    {
+      "epoch": 0.0001588021778584392,
+      "grad_norm": 1.7971285581588745,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.5521,
+      "step": 14
+    },
+    {
+      "epoch": 0.0001588021778584392,
+      "eval_loss": 2.627178430557251,
+      "eval_runtime": 873.6543,
+      "eval_samples_per_second": 42.488,
+      "eval_steps_per_second": 21.244,
+      "step": 14
+    },
+    {
+      "epoch": 0.00017014519056261342,
+      "grad_norm": 1.5861200094223022,
+      "learning_rate": 0.0,
+      "loss": 2.5571,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -139,12 +190,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 481091030876160.0,
+  "total_flos": 721636546314240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null