Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75a6cf38fef33765a1f5520bedfaac160cbb9223015e7a3ab3786bd8ceaa432e
+oid sha256:c3458b1c788586fb9c34a610545b1a3d8f52bc0a66dc193ccd31e105065a9a90
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59d1dc215800f312848df48efb337364e9be3d58be6fd5a6b494aaa343453313
+oid sha256:b887cbcf5af4c529c39d41f4fdc0940a1f8b3ca1b02a94ace29737bd618856d7
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbd18a87b1347fb9cc79cc3548bb35011c7972900ba3127f9f74a79279cd6e26
+oid sha256:2f533f534d4800805436810cfc9380e579dd299a63eee9349424167eb9af0e4a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0410958904109589,
+  "epoch": 0.0821917808219178,
   "eval_steps": 6,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -222,6 +222,213 @@
       "learning_rate": 6.91341716182545e-05,
       "loss": 0.7425,
       "step": 25
+    },
+    {
+      "epoch": 0.042739726027397264,
+      "grad_norm": 1.6898382902145386,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.7092,
+      "step": 26
+    },
+    {
+      "epoch": 0.04438356164383562,
+      "grad_norm": 1.588605523109436,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 0.7136,
+      "step": 27
+    },
+    {
+      "epoch": 0.046027397260273974,
+      "grad_norm": 2.993543863296509,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.7542,
+      "step": 28
+    },
+    {
+      "epoch": 0.04767123287671233,
+      "grad_norm": 2.4193227291107178,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 0.7245,
+      "step": 29
+    },
+    {
+      "epoch": 0.049315068493150684,
+      "grad_norm": 0.8837425708770752,
+      "learning_rate": 5e-05,
+      "loss": 0.6908,
+      "step": 30
+    },
+    {
+      "epoch": 0.049315068493150684,
+      "eval_loss": 0.7084067463874817,
+      "eval_runtime": 401.4002,
+      "eval_samples_per_second": 1.916,
+      "eval_steps_per_second": 0.481,
+      "step": 30
+    },
+    {
+      "epoch": 0.05095890410958904,
+      "grad_norm": 1.4400691986083984,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 0.6718,
+      "step": 31
+    },
+    {
+      "epoch": 0.0526027397260274,
+      "grad_norm": 1.405909538269043,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.7016,
+      "step": 32
+    },
+    {
+      "epoch": 0.054246575342465755,
+      "grad_norm": 1.128387689590454,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.7065,
+      "step": 33
+    },
+    {
+      "epoch": 0.05589041095890411,
+      "grad_norm": 0.8258553147315979,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.68,
+      "step": 34
+    },
+    {
+      "epoch": 0.057534246575342465,
+      "grad_norm": 1.6371694803237915,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.7027,
+      "step": 35
+    },
+    {
+      "epoch": 0.05917808219178082,
+      "grad_norm": 1.7670177221298218,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.7175,
+      "step": 36
+    },
+    {
+      "epoch": 0.05917808219178082,
+      "eval_loss": 0.7042004466056824,
+      "eval_runtime": 401.6237,
+      "eval_samples_per_second": 1.915,
+      "eval_steps_per_second": 0.481,
+      "step": 36
+    },
+    {
+      "epoch": 0.060821917808219175,
+      "grad_norm": 4.805910110473633,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.7525,
+      "step": 37
+    },
+    {
+      "epoch": 0.06246575342465754,
+      "grad_norm": 2.293574810028076,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.7078,
+      "step": 38
+    },
+    {
+      "epoch": 0.06410958904109589,
+      "grad_norm": 1.8330103158950806,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.6966,
+      "step": 39
+    },
+    {
+      "epoch": 0.06575342465753424,
+      "grad_norm": 2.2366013526916504,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6836,
+      "step": 40
+    },
+    {
+      "epoch": 0.06739726027397261,
+      "grad_norm": 1.588487982749939,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.6875,
+      "step": 41
+    },
+    {
+      "epoch": 0.06904109589041096,
+      "grad_norm": 0.7167198061943054,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.695,
+      "step": 42
+    },
+    {
+      "epoch": 0.06904109589041096,
+      "eval_loss": 0.6984082460403442,
+      "eval_runtime": 401.5322,
+      "eval_samples_per_second": 1.915,
+      "eval_steps_per_second": 0.481,
+      "step": 42
+    },
+    {
+      "epoch": 0.07068493150684932,
+      "grad_norm": 1.4269287586212158,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.6566,
+      "step": 43
+    },
+    {
+      "epoch": 0.07232876712328767,
+      "grad_norm": 1.8338453769683838,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.7158,
+      "step": 44
+    },
+    {
+      "epoch": 0.07397260273972603,
+      "grad_norm": 1.369246244430542,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7047,
+      "step": 45
+    },
+    {
+      "epoch": 0.07561643835616438,
+      "grad_norm": 0.5873619318008423,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.6859,
+      "step": 46
+    },
+    {
+      "epoch": 0.07726027397260274,
+      "grad_norm": 0.5974377989768982,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.7013,
+      "step": 47
+    },
+    {
+      "epoch": 0.0789041095890411,
+      "grad_norm": 1.1578266620635986,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.6891,
+      "step": 48
+    },
+    {
+      "epoch": 0.0789041095890411,
+      "eval_loss": 0.7000875473022461,
+      "eval_runtime": 401.4631,
+      "eval_samples_per_second": 1.915,
+      "eval_steps_per_second": 0.481,
+      "step": 48
+    },
+    {
+      "epoch": 0.08054794520547945,
+      "grad_norm": 2.2058608531951904,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.7191,
+      "step": 49
+    },
+    {
+      "epoch": 0.0821917808219178,
+      "grad_norm": 1.0864945650100708,
+      "learning_rate": 0.0,
+      "loss": 0.7048,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -236,12 +443,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.119015678246912e+17,
+  "total_flos": 2.238031356493824e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null