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:b605b9a9e73dbca9cca9981cbbee4b5f38c55fc78d32337b316f2613ddaef568
+oid sha256:27da663b856624c8e3266daa6c25985528db3b40cfa5981f97117a02ce95a225
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a1568be9a23eddd7bf73606fd9afe011dba7bb39db577009fa3d56812be95e9
+oid sha256:28f1c80d24e6d6bb8ba233ec96f27d597017ce08a598ac532194e8b131fd57b3
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccbf59ef5b2583c555b98f9534763fb6ca41915f4f652736aefb0651cebb5a4f
+oid sha256:c73ea161f3b32784f2ed5d1c6a790d0b5111ddef4b2735c68b8061d2a1774541
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f02484c7518b82e433da31ed87354bae0a573dd0d86a00bc994b55000f5531ac
+oid sha256:c172862c80d877bda9cc5957d37104ca7252637d066dd8348737b1818f965608
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b305932358b7fb9c9a3168dc5506aadd293240264c644599ed13ada4d58e6899
+oid sha256:dfd320a7751c52cf98a8bb0266cc8ffc9b466c21edde2f1d31ea7053c56d3e82
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee7b516c65424fd5e74f65ec02a4183be1c890c8c4424a5a60faea8d5012621b
+oid sha256:506ffb6c950f3b03e5ab6a07a66009867a7bcda30cc6c1332e74400b44e4919a
 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": 0.031625553447185324,
+  "epoch": 0.06325110689437065,
   "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": 12.293,
       "eval_steps_per_second": 3.196,
       "step": 25
+    },
+    {
+      "epoch": 0.03289057558507274,
+      "grad_norm": 37.96943283081055,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 5.7969,
+      "step": 26
+    },
+    {
+      "epoch": 0.03415559772296015,
+      "grad_norm": 1.5687322616577148,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.7264,
+      "step": 27
+    },
+    {
+      "epoch": 0.03542061986084757,
+      "grad_norm": 1.1628891229629517,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.8082,
+      "step": 28
+    },
+    {
+      "epoch": 0.036685641998734975,
+      "grad_norm": 0.8394140005111694,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.9195,
+      "step": 29
+    },
+    {
+      "epoch": 0.03795066413662239,
+      "grad_norm": 0.9346224665641785,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.9093,
+      "step": 30
+    },
+    {
+      "epoch": 0.0392156862745098,
+      "grad_norm": 0.9901193976402283,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.0222,
+      "step": 31
+    },
+    {
+      "epoch": 0.04048070841239722,
+      "grad_norm": 0.9796273112297058,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.9273,
+      "step": 32
+    },
+    {
+      "epoch": 0.04174573055028463,
+      "grad_norm": 0.9287394881248474,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.9015,
+      "step": 33
+    },
+    {
+      "epoch": 0.043010752688172046,
+      "grad_norm": 0.9738181233406067,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.7521,
+      "step": 34
+    },
+    {
+      "epoch": 0.044275774826059454,
+      "grad_norm": 1.0583573579788208,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.0511,
+      "step": 35
+    },
+    {
+      "epoch": 0.04554079696394687,
+      "grad_norm": 1.0245318412780762,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.1022,
+      "step": 36
+    },
+    {
+      "epoch": 0.04680581910183428,
+      "grad_norm": 1.2444181442260742,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 2.0539,
+      "step": 37
+    },
+    {
+      "epoch": 0.0480708412397217,
+      "grad_norm": 24.339767456054688,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 3.6826,
+      "step": 38
+    },
+    {
+      "epoch": 0.04933586337760911,
+      "grad_norm": 0.6691582202911377,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.6845,
+      "step": 39
+    },
+    {
+      "epoch": 0.05060088551549652,
+      "grad_norm": 0.7083836793899536,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.776,
+      "step": 40
+    },
+    {
+      "epoch": 0.05186590765338393,
+      "grad_norm": 0.7264069318771362,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.8355,
+      "step": 41
+    },
+    {
+      "epoch": 0.05313092979127135,
+      "grad_norm": 0.7508512139320374,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.8773,
+      "step": 42
+    },
+    {
+      "epoch": 0.05439595192915876,
+      "grad_norm": 0.7919434905052185,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.8648,
+      "step": 43
+    },
+    {
+      "epoch": 0.055660974067046176,
+      "grad_norm": 0.8442027568817139,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.7584,
+      "step": 44
+    },
+    {
+      "epoch": 0.056925996204933584,
+      "grad_norm": 0.8228534460067749,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.9638,
+      "step": 45
+    },
+    {
+      "epoch": 0.058191018342821,
+      "grad_norm": 0.8046168088912964,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.8872,
+      "step": 46
+    },
+    {
+      "epoch": 0.05945604048070841,
+      "grad_norm": 0.8686741590499878,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.89,
+      "step": 47
+    },
+    {
+      "epoch": 0.06072106261859583,
+      "grad_norm": 0.9693074226379395,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.9709,
+      "step": 48
+    },
+    {
+      "epoch": 0.06198608475648324,
+      "grad_norm": 1.1496561765670776,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.0629,
+      "step": 49
+    },
+    {
+      "epoch": 0.06325110689437065,
+      "grad_norm": 1.4522725343704224,
+      "learning_rate": 1e-05,
+      "loss": 2.1552,
+      "step": 50
+    },
+    {
+      "epoch": 0.06325110689437065,
+      "eval_loss": 1.9020295143127441,
+      "eval_runtime": 4.0552,
+      "eval_samples_per_second": 12.33,
+      "eval_steps_per_second": 3.206,
+      "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": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null