Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3948f3634ada5ae7c7de8e6d47d0044d8a54908518f3e3dd9df73fa28f350d02
+oid sha256:6a0aedd0cffd5fb61a630d8bd4880a59bcf9bf29b2fb34b474614d38e86b58d7
 size 144805440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7531ac50970f6bbbef732ee602ab57612eb67433db95a9c924e4d8a5ff15e720
+oid sha256:0cf9cbdc1e7b4c0cc677eef2b0878ae6bc4cc4ae4588bf0c8b68c4cacc1fe9ff
 size 74291604

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a65c7d81c66fb748eb12780de8de63775eeec185658fb414013d833d011ac1c9
+oid sha256:51b9dd86561e01021239d34cfcf3010c45ab7e7f7918d2b6c97b50424e9fe785
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.017747440273037544,
+  "epoch": 0.022753128555176336,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 0.1722,
       "step": 35
+    },
+    {
+      "epoch": 0.01820250284414107,
+      "grad_norm": 0.6138023138046265,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1248,
+      "step": 40
+    },
+    {
+      "epoch": 0.01820250284414107,
+      "eval_loss": 0.14828301966190338,
+      "eval_runtime": 193.2763,
+      "eval_samples_per_second": 4.791,
+      "eval_steps_per_second": 2.396,
+      "step": 40
+    },
+    {
+      "epoch": 0.020477815699658702,
+      "grad_norm": 12.502432823181152,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4113,
+      "step": 45
+    },
+    {
+      "epoch": 0.022753128555176336,
+      "grad_norm": 0.00241334387101233,
+      "learning_rate": 0.0,
+      "loss": 0.2781,
+      "step": 50
+    },
+    {
+      "epoch": 0.022753128555176336,
+      "eval_loss": 0.13595092296600342,
+      "eval_runtime": 193.1785,
+      "eval_samples_per_second": 4.793,
+      "eval_steps_per_second": 2.397,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.2631125277016064e+16,
+  "total_flos": 1.61937503551488e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null