Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:786d0db22e2f9c4216fec157eba2a4c9eba27fa14025cc278887f78b6bd1fefa
+oid sha256:09394ae7dbdfee9ae805e60a54c66fecddc6e2e0772bb68c685416cf977ac0b9
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e1ea9c46b799b7fb9a718678e7d7fbe542725f82c64b237fe0bc98210f681be
+oid sha256:253b44427539527e6bcc9175fa60a0cf1c0743a03236d68945228bf5d9b293a9
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
+oid sha256:3a2809375c44051deea8394ef4e524b537561ea599f6f054cbc21229ed9516f2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
+oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0027063599458728013,
+  "epoch": 0.003469692238298463,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 181.333,
       "eval_steps_per_second": 90.667,
       "step": 39
+    },
+    {
+      "epoch": 0.0027757537906387703,
+      "grad_norm": 0.004865317139774561,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 11.9324,
+      "step": 40
+    },
+    {
+      "epoch": 0.00284514763540474,
+      "grad_norm": 0.00657661585137248,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 11.9362,
+      "step": 41
+    },
+    {
+      "epoch": 0.002914541480170709,
+      "grad_norm": 0.0071084885857999325,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 11.9319,
+      "step": 42
+    },
+    {
+      "epoch": 0.0029839353249366783,
+      "grad_norm": 0.011165489442646503,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 11.9326,
+      "step": 43
+    },
+    {
+      "epoch": 0.0030533291697026474,
+      "grad_norm": 0.006960089784115553,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 11.9312,
+      "step": 44
+    },
+    {
+      "epoch": 0.003122723014468617,
+      "grad_norm": 0.006921164225786924,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 11.9338,
+      "step": 45
+    },
+    {
+      "epoch": 0.003192116859234586,
+      "grad_norm": 0.0057137347757816315,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 11.9312,
+      "step": 46
+    },
+    {
+      "epoch": 0.0032615107040005554,
+      "grad_norm": 0.008974261581897736,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 11.9339,
+      "step": 47
+    },
+    {
+      "epoch": 0.0033309045487665244,
+      "grad_norm": 0.0074746268801391125,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 11.9307,
+      "step": 48
+    },
+    {
+      "epoch": 0.003400298393532494,
+      "grad_norm": 0.008818883448839188,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 11.9301,
+      "step": 49
+    },
+    {
+      "epoch": 0.003469692238298463,
+      "grad_norm": 0.009604895487427711,
+      "learning_rate": 0.0,
+      "loss": 11.9287,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8803024896.0,
+  "total_flos": 11254874112.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null