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:d84c5282d2e7d0ea3e973a0de05a139cfe0836c081b0b609b73befb1e9ca9d55
+oid sha256:a04e8bb8ca37343ae64f873ddb2a3c1debddf4a496a3715aad43175c6b6e3c86
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f163fa89b8936796c1a5ff858c90cb3dd3f92b5a94b3c40954f8f939bafba7f1
+oid sha256:8624c05f7f5baebb6b8b938c423bfc1e1a0ed2ed8df3fe16d3e7c86f7866ca82
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd2ce6a4f1c3bbfd52ba9fa4db11b93d339684c3f272b90507a5f2e93b00fd41
+oid sha256:a7a0aebc905166ccbc9d1081d60c28e85b370977f92a8aa1f6448c9b38434493
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab86422507560fe36df503fcec7bf779ca3831d87874f9d53f9874da7847a7db
+oid sha256:ff6d5658d989a948ad877d27db387126f74d0183667eec54026eabc036c44fcd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e694f0cc15b61b63c49f9899e4c048e19a381c3dd62c34081641acb74888e30
+oid sha256:96b874fd4e830f52d3783b56aa0b46683c0937e1faf35468cbc01f8690b42a3d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:815478db4ee9ed16b0245cb6f7a08d04a58049917227d5c8d036f71c90ba2fa4
+oid sha256:c685c1c7e4ceeca5adc48e02a99ae9aa59a62b5c4321750b5293d5da9fe8e86b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.33557046979865773,
+  "epoch": 0.6711409395973155,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 15.624,
       "eval_steps_per_second": 4.062,
       "step": 25
+    },
+    {
+      "epoch": 0.348993288590604,
+      "grad_norm": 0.16195999085903168,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.7858,
+      "step": 26
+    },
+    {
+      "epoch": 0.3624161073825503,
+      "grad_norm": 0.1427437961101532,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.7842,
+      "step": 27
+    },
+    {
+      "epoch": 0.37583892617449666,
+      "grad_norm": 0.1225617453455925,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.7713,
+      "step": 28
+    },
+    {
+      "epoch": 0.38926174496644295,
+      "grad_norm": 0.1048019751906395,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.7604,
+      "step": 29
+    },
+    {
+      "epoch": 0.40268456375838924,
+      "grad_norm": 0.10601115971803665,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.7612,
+      "step": 30
+    },
+    {
+      "epoch": 0.4161073825503356,
+      "grad_norm": 0.10506386309862137,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.7592,
+      "step": 31
+    },
+    {
+      "epoch": 0.42953020134228187,
+      "grad_norm": 0.11626201122999191,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.7672,
+      "step": 32
+    },
+    {
+      "epoch": 0.4429530201342282,
+      "grad_norm": 0.10783777385950089,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.755,
+      "step": 33
+    },
+    {
+      "epoch": 0.4563758389261745,
+      "grad_norm": 0.11628258228302002,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.7495,
+      "step": 34
+    },
+    {
+      "epoch": 0.4697986577181208,
+      "grad_norm": 0.10531030595302582,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.7676,
+      "step": 35
+    },
+    {
+      "epoch": 0.48322147651006714,
+      "grad_norm": 0.10979268699884415,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.793,
+      "step": 36
+    },
+    {
+      "epoch": 0.4966442953020134,
+      "grad_norm": 0.11333921551704407,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.7676,
+      "step": 37
+    },
+    {
+      "epoch": 0.5100671140939598,
+      "grad_norm": 0.12159935384988785,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.7693,
+      "step": 38
+    },
+    {
+      "epoch": 0.5234899328859061,
+      "grad_norm": 0.11211013048887253,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.7542,
+      "step": 39
+    },
+    {
+      "epoch": 0.5369127516778524,
+      "grad_norm": 0.1045965701341629,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.7526,
+      "step": 40
+    },
+    {
+      "epoch": 0.5503355704697986,
+      "grad_norm": 0.10266979038715363,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.7718,
+      "step": 41
+    },
+    {
+      "epoch": 0.5637583892617449,
+      "grad_norm": 0.09563658386468887,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.722,
+      "step": 42
+    },
+    {
+      "epoch": 0.5771812080536913,
+      "grad_norm": 0.09837043285369873,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.7262,
+      "step": 43
+    },
+    {
+      "epoch": 0.5906040268456376,
+      "grad_norm": 0.09940379858016968,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.7409,
+      "step": 44
+    },
+    {
+      "epoch": 0.6040268456375839,
+      "grad_norm": 0.10937907546758652,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.7488,
+      "step": 45
+    },
+    {
+      "epoch": 0.6174496644295302,
+      "grad_norm": 0.102512888610363,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.7414,
+      "step": 46
+    },
+    {
+      "epoch": 0.6308724832214765,
+      "grad_norm": 0.10500387847423553,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.7486,
+      "step": 47
+    },
+    {
+      "epoch": 0.6442953020134228,
+      "grad_norm": 0.10852666199207306,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.7587,
+      "step": 48
+    },
+    {
+      "epoch": 0.6577181208053692,
+      "grad_norm": 0.11192145198583603,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.7629,
+      "step": 49
+    },
+    {
+      "epoch": 0.6711409395973155,
+      "grad_norm": 0.12789976596832275,
+      "learning_rate": 1e-05,
+      "loss": 0.7869,
+      "step": 50
+    },
+    {
+      "epoch": 0.6711409395973155,
+      "eval_loss": 0.7637184858322144,
+      "eval_runtime": 3.1762,
+      "eval_samples_per_second": 15.742,
+      "eval_steps_per_second": 4.093,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,12 +395,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.65595793275093e+17,
+  "total_flos": 5.31191586550186e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null