Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a51d9fc8751b9325823f7138e39e953dfd9b8379677be45c23e8f3c49740ab18
+oid sha256:ebfbc8205e61ffeb3cdd441b9812f5498ecb4deb2bac7465d220552acf30bf4e
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:186149bff317b1c34bae21f13ce701b31792f3406dc1321a455e9175a162ba72
+oid sha256:79f865cd5a23b2b296762c72638cee2c2d58ce31d4cf0f3be51fb11e1e2d4d79
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be463459f76491a4eadd327e6ecb5088de2aff9e12586ed0f1238525fca20cab
+oid sha256:426900dc4576c7b69ffe288dfe5ab8d765b6f0781fda217e5145137633ca7b0d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd8212ec5ec3406d74a7f927b717dd30ea8a06115ee6582e14976f7b84b4b58
+oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.21299254526091588,
+  "epoch": 0.3194888178913738,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 20.036,
       "eval_steps_per_second": 10.018,
       "step": 100
+    },
+    {
+      "epoch": 0.23429179978700745,
+      "grad_norm": 1.3918311595916748,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 1.2214,
+      "step": 110
+    },
+    {
+      "epoch": 0.25559105431309903,
+      "grad_norm": 1.0303548574447632,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 1.0175,
+      "step": 120
+    },
+    {
+      "epoch": 0.27689030883919064,
+      "grad_norm": 1.4731521606445312,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 1.1181,
+      "step": 130
+    },
+    {
+      "epoch": 0.29818956336528224,
+      "grad_norm": 1.2414261102676392,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 1.1889,
+      "step": 140
+    },
+    {
+      "epoch": 0.3194888178913738,
+      "grad_norm": 1.6876599788665771,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 1.2897,
+      "step": 150
+    },
+    {
+      "epoch": 0.3194888178913738,
+      "eval_loss": 1.076661229133606,
+      "eval_runtime": 9.8889,
+      "eval_samples_per_second": 20.023,
+      "eval_steps_per_second": 10.011,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.20578299887616e+16,
+  "total_flos": 4.820547768680448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null