Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:505ea2cdb0c21da771083d26a4e14952189e4b2d45d38e9743e29737b21da7bc
+oid sha256:669867dce5cac640f24024dba311ed70335457c74aa1ad66b4f157c9efb9a7ab
 size 604317736

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe3e568385666c24e2dc728be11733db52f3fa773e9719856cced99534fe7197
+oid sha256:be5dcd70260f6426617e07fc613053955f916894e1780ca347eb8f59ba47f4ab
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3aef7d20483b14af0dec3dd6e05dc978ec3e9677c14b2ba43d2e45951e4f80d
+oid sha256:04802b99b33b6f56b954f18cfba4aaae1ec7857780ef0227027e02fc45dacd00
 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": 0.0013162446527560981,
+  "epoch": 0.0016874931445591001,
   "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": 0.9516,
       "step": 35
+    },
+    {
+      "epoch": 0.0013499945156472803,
+      "grad_norm": 0.4973631799221039,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8305,
+      "step": 40
+    },
+    {
+      "epoch": 0.0013499945156472803,
+      "eval_loss": 0.8584612011909485,
+      "eval_runtime": 1067.8769,
+      "eval_samples_per_second": 11.683,
+      "eval_steps_per_second": 5.841,
+      "step": 40
+    },
+    {
+      "epoch": 0.0015187438301031903,
+      "grad_norm": 0.5161930322647095,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.9434,
+      "step": 45
+    },
+    {
+      "epoch": 0.0016874931445591001,
+      "grad_norm": 0.4835697114467621,
+      "learning_rate": 0.0,
+      "loss": 0.9551,
+      "step": 50
+    },
+    {
+      "epoch": 0.0016874931445591001,
+      "eval_loss": 0.8572389483451843,
+      "eval_runtime": 1567.7088,
+      "eval_samples_per_second": 7.958,
+      "eval_steps_per_second": 3.979,
+      "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": 9446658026766336.0,
+  "total_flos": 1.2174787715530752e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null