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:a57cd36b2b2e91bb1891659b584469e512746bbf470503c0a1c6fe2f10df3bdc
+oid sha256:66d257e136df696d694e44783ede8271d52e1699cfb142db096fcb096d70ab92
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf40f4d45673af09e766aae58e42ac5a81e5f7ff1026883db3c7e2a4c39f9f35
+oid sha256:99126e5eadc5e761ad26987495aa7255ab86077f96aa79160f712372b64cc801
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fb746a2cbe53536f2027997265749960d455a437d0bd9d034e7e698176471da
+oid sha256:a9faa6cb684be5595c1c20af30ced447ff9782687a9b75ca33680014c5813e18
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00e109233a3b1e419ded7000144e17009baf641c96b8b80074559f67fdb254c2
+oid sha256:cc4d5354d3354bfb34ed485735d77438781eeab899ee5b6df564f1d5f189a89c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28dd9ee23a77065f17377e0cd1f2e4a49c85b2e93a804b61999ab6c7eda5b84e
+oid sha256:21a6a88a88e4bf1a33e8f65963ec436860c7d1406d61f2c1e1ef4592916d736d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:249d8647f12c0d9ee4d80686a6b43c3ca35a27ab8c0d69cef8a3467c2d10b644
+oid sha256:b5ae130613028d6497091f6723e1547bd46f1f05226c53ab5654468473d846b5
 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": 0.02554849423562099,
+  "epoch": 0.05109698847124198,
   "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": 50.552,
       "eval_steps_per_second": 13.143,
       "step": 25
+    },
+    {
+      "epoch": 0.02657043400504583,
+      "grad_norm": 0.1043691635131836,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.9928,
+      "step": 26
+    },
+    {
+      "epoch": 0.027592373774470668,
+      "grad_norm": 0.11791103333234787,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.9532,
+      "step": 27
+    },
+    {
+      "epoch": 0.028614313543895507,
+      "grad_norm": 0.09145063906908035,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.0049,
+      "step": 28
+    },
+    {
+      "epoch": 0.029636253313320347,
+      "grad_norm": 0.08089277148246765,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.9995,
+      "step": 29
+    },
+    {
+      "epoch": 0.030658193082745186,
+      "grad_norm": 0.08104592561721802,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.9722,
+      "step": 30
+    },
+    {
+      "epoch": 0.03168013285217002,
+      "grad_norm": 0.07853035628795624,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.9928,
+      "step": 31
+    },
+    {
+      "epoch": 0.032702072621594865,
+      "grad_norm": 0.09031016379594803,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.9555,
+      "step": 32
+    },
+    {
+      "epoch": 0.03372401239101971,
+      "grad_norm": 0.12751440703868866,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.0578,
+      "step": 33
+    },
+    {
+      "epoch": 0.03474595216044454,
+      "grad_norm": 0.10279670357704163,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.0634,
+      "step": 34
+    },
+    {
+      "epoch": 0.035767891929869386,
+      "grad_norm": 0.1316157430410385,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.0977,
+      "step": 35
+    },
+    {
+      "epoch": 0.03678983169929422,
+      "grad_norm": 0.16540181636810303,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.0971,
+      "step": 36
+    },
+    {
+      "epoch": 0.037811771468719065,
+      "grad_norm": 0.22142651677131653,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.1435,
+      "step": 37
+    },
+    {
+      "epoch": 0.0388337112381439,
+      "grad_norm": 0.10041386634111404,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.9938,
+      "step": 38
+    },
+    {
+      "epoch": 0.03985565100756874,
+      "grad_norm": 0.07974253594875336,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.9398,
+      "step": 39
+    },
+    {
+      "epoch": 0.04087759077699358,
+      "grad_norm": 0.07795632630586624,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.0004,
+      "step": 40
+    },
+    {
+      "epoch": 0.04189953054641842,
+      "grad_norm": 0.08004100620746613,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.0619,
+      "step": 41
+    },
+    {
+      "epoch": 0.04292147031584326,
+      "grad_norm": 0.08127743005752563,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.0346,
+      "step": 42
+    },
+    {
+      "epoch": 0.0439434100852681,
+      "grad_norm": 0.07527384161949158,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.9316,
+      "step": 43
+    },
+    {
+      "epoch": 0.044965349854692936,
+      "grad_norm": 0.08304384350776672,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.0297,
+      "step": 44
+    },
+    {
+      "epoch": 0.04598728962411778,
+      "grad_norm": 0.08190393447875977,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.9401,
+      "step": 45
+    },
+    {
+      "epoch": 0.047009229393542615,
+      "grad_norm": 0.0957888811826706,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.0054,
+      "step": 46
+    },
+    {
+      "epoch": 0.04803116916296746,
+      "grad_norm": 0.11726554483175278,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.0758,
+      "step": 47
+    },
+    {
+      "epoch": 0.0490531089323923,
+      "grad_norm": 0.14844173192977905,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.0277,
+      "step": 48
+    },
+    {
+      "epoch": 0.050075048701817136,
+      "grad_norm": 0.1817873865365982,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.1578,
+      "step": 49
+    },
+    {
+      "epoch": 0.05109698847124198,
+      "grad_norm": 0.24012449383735657,
+      "learning_rate": 1e-05,
+      "loss": 1.2365,
+      "step": 50
+    },
+    {
+      "epoch": 0.05109698847124198,
+      "eval_loss": 1.0246226787567139,
+      "eval_runtime": 0.9822,
+      "eval_samples_per_second": 50.906,
+      "eval_steps_per_second": 13.235,
+      "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": 4.16708196040704e+16,
+  "total_flos": 8.33416392081408e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null