Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a7a252009b5c1154a1ab66d27b5553fe5576110fd8217875b0430a7f964b005
+oid sha256:e7f87d67f69349a6842bfa4b3da70d1a3370ba02e217c2037c653b41f16e573d
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6db1555bdd12f27df80c37700352e7d9317a96599ba709ae349ccebd764a10b1
+oid sha256:20db4e8ecab7661787a112ca6c40d6fcb56d18faa8598542388c68b7888c5bca
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16f48a6b6d64b6c1b1d6b98606bbfb470d707c8dace80a06d6480a49bb4a4cdd
+oid sha256:ae39e1d5e6e5d0fe4d33b48aa6087a2c9c717bf5f6cce7541dbe8cda76344af2
 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": 0.08283288465520812,
+  "epoch": 0.12424932698281217,
   "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": 27.083,
       "eval_steps_per_second": 13.568,
       "step": 100
+    },
+    {
+      "epoch": 0.09111617312072894,
+      "grad_norm": 3.7265028953552246,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 3.8139,
+      "step": 110
+    },
+    {
+      "epoch": 0.09939946158624974,
+      "grad_norm": 3.8285229206085205,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 3.7093,
+      "step": 120
+    },
+    {
+      "epoch": 0.10768275005177055,
+      "grad_norm": 2.8003692626953125,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 3.6752,
+      "step": 130
+    },
+    {
+      "epoch": 0.11596603851729137,
+      "grad_norm": 3.7858400344848633,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 3.584,
+      "step": 140
+    },
+    {
+      "epoch": 0.12424932698281217,
+      "grad_norm": 3.6800522804260254,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 3.4246,
+      "step": 150
+    },
+    {
+      "epoch": 0.12424932698281217,
+      "eval_loss": 0.9045064449310303,
+      "eval_runtime": 18.8551,
+      "eval_samples_per_second": 26.995,
+      "eval_steps_per_second": 13.524,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6572359657914368e+16,
+  "total_flos": 2.4878898651070464e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null