Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:202ff70d3d0582ff4a65726e7a5077a3471af8e13bc55a5f77537e8da117c127
+oid sha256:9c5d5d0e5375785d13a300896163a0aed4e68fef0c36411eb25a925f1fbb478a
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:082a9e642cd4df32e787d30cd28f6e93ee7b00c9b99f6abf4f0c4f72168d2591
+oid sha256:e08a97e1365d6ab6032836c390f54d528a81f14aeb56dc372e9cc577f14d45c0
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52b2a86efcede2ab0d8f6498ece5e6861b2e6f409af1126535691abe18451e7e
+oid sha256:56ca4cd06fc697d08a6cd7c230ceef659a899bd45c131af511e54b94e556b863
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5562ea51c3bd8b1e1b1abebcd552dac4d59434cd2f1fb795249ae8423eb06372
+oid sha256:24e0f3673394386439e3f0b52a2d7d726ebb81dc5015c9eb0eae1f375ee4e808
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d35c02576f0b8a545cb31f19b8b96a16c89598222141ae35a88f6db841464403
+oid sha256:d316a2056d50afb3271f7c8914716b86276dc6b0ab396536dcdc7c42a03977f1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31325c1b80bce04a9ddded74026d541038fe85a38c08694334f9fb3e60ac77be
+oid sha256:76eb9635e3579f2810973f16f71d82ba4b56c309f3627285ade87ad4b0c7bbd0
 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": 0.062315002336812586,
+  "epoch": 0.12463000467362517,
   "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": 37.924,
       "eval_steps_per_second": 9.86,
       "step": 25
+    },
+    {
+      "epoch": 0.06480760243028509,
+      "grad_norm": 0.09114177525043488,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.886,
+      "step": 26
+    },
+    {
+      "epoch": 0.0673002025237576,
+      "grad_norm": 0.09418703615665436,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.9273,
+      "step": 27
+    },
+    {
+      "epoch": 0.0697928026172301,
+      "grad_norm": 0.09414679557085037,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.9459,
+      "step": 28
+    },
+    {
+      "epoch": 0.0722854027107026,
+      "grad_norm": 0.10642877221107483,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.9734,
+      "step": 29
+    },
+    {
+      "epoch": 0.07477800280417511,
+      "grad_norm": 0.1117902398109436,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.0237,
+      "step": 30
+    },
+    {
+      "epoch": 0.0772706028976476,
+      "grad_norm": 0.12783116102218628,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.0062,
+      "step": 31
+    },
+    {
+      "epoch": 0.07976320299112011,
+      "grad_norm": 0.13062702119350433,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.0148,
+      "step": 32
+    },
+    {
+      "epoch": 0.08225580308459261,
+      "grad_norm": 0.14114302396774292,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.0211,
+      "step": 33
+    },
+    {
+      "epoch": 0.08474840317806512,
+      "grad_norm": 0.15735821425914764,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.0175,
+      "step": 34
+    },
+    {
+      "epoch": 0.08724100327153762,
+      "grad_norm": 0.19599683582782745,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.0264,
+      "step": 35
+    },
+    {
+      "epoch": 0.08973360336501013,
+      "grad_norm": 0.2594337463378906,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.0313,
+      "step": 36
+    },
+    {
+      "epoch": 0.09222620345848263,
+      "grad_norm": 0.35799410939216614,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.1004,
+      "step": 37
+    },
+    {
+      "epoch": 0.09471880355195514,
+      "grad_norm": 0.09532549232244492,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.8871,
+      "step": 38
+    },
+    {
+      "epoch": 0.09721140364542763,
+      "grad_norm": 0.088306725025177,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.9009,
+      "step": 39
+    },
+    {
+      "epoch": 0.09970400373890013,
+      "grad_norm": 0.08932317048311234,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.9248,
+      "step": 40
+    },
+    {
+      "epoch": 0.10219660383237264,
+      "grad_norm": 0.08780187368392944,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.9517,
+      "step": 41
+    },
+    {
+      "epoch": 0.10468920392584515,
+      "grad_norm": 0.09193553030490875,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.9641,
+      "step": 42
+    },
+    {
+      "epoch": 0.10718180401931765,
+      "grad_norm": 0.10254494100809097,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.9808,
+      "step": 43
+    },
+    {
+      "epoch": 0.10967440411279016,
+      "grad_norm": 0.11288368701934814,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.9895,
+      "step": 44
+    },
+    {
+      "epoch": 0.11216700420626266,
+      "grad_norm": 0.12878137826919556,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.0026,
+      "step": 45
+    },
+    {
+      "epoch": 0.11465960429973517,
+      "grad_norm": 0.15530207753181458,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.0257,
+      "step": 46
+    },
+    {
+      "epoch": 0.11715220439320767,
+      "grad_norm": 0.17546328902244568,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.0257,
+      "step": 47
+    },
+    {
+      "epoch": 0.11964480448668016,
+      "grad_norm": 0.22210463881492615,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.0215,
+      "step": 48
+    },
+    {
+      "epoch": 0.12213740458015267,
+      "grad_norm": 0.2874910533428192,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.051,
+      "step": 49
+    },
+    {
+      "epoch": 0.12463000467362517,
+      "grad_norm": 0.4640187621116638,
+      "learning_rate": 1e-05,
+      "loss": 1.1391,
+      "step": 50
+    },
+    {
+      "epoch": 0.12463000467362517,
+      "eval_loss": 1.064849615097046,
+      "eval_runtime": 1.4728,
+      "eval_samples_per_second": 33.95,
+      "eval_steps_per_second": 8.827,
+      "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": 4.490030805627699e+16,
+  "total_flos": 9.0399634261803e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null