Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d5316a48f9002d1fccf18244912fdfb807737205318848e7aef680a47f6c2fc
+oid sha256:d407a82c9643e88d0fdcd0d5ea2b5dd88ab24cb89631d34eca3901d455ca4a2b
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c6200a24af45d5730535c87600275f6e69e865c4f0ee5943c7368ac0dc7c215
+oid sha256:c179d83521645f9899ee08122559478c4f067eb7da8388f43a5335224ea1b247
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10ea3b1a157d7461118802daf4df2e4202e623a2576cd8e68f514d7398c0e026
+oid sha256:24153e1d65d8b602bd019fdc6a40c98223bf3ea042490cdb160a90dc57b7c325
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05bf592dc02af4e422c171bb7d2c7146ebc189eb370461305430f5919aef0fd4
+oid sha256:317efaf52e95ad570c77dfbe7a83d825fa3650013c8fc6e65561d68008dd8829
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c94d8f8eea0932b87aa307359258901e52b5eae7d965d274a3c0119399e48d6
+oid sha256:9d9ae7a00b8c17fae1ed4ae4229c765b7beae47c507f53a5bba69ebce9ed27b7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1448c44cc4af7636805c25fdc6adb4b5c9f334905f932394a2d23359c917584a
+oid sha256:5ce14c721fe11951118e647771ad1f6893351c81dc54bbfb0c696b13d9af9e1e
 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": 0.05739292632183084,
+  "epoch": 0.11478585264366167,
   "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": 282.412,
       "eval_steps_per_second": 73.427,
       "step": 25
+    },
+    {
+      "epoch": 0.059688643374704066,
+      "grad_norm": 0.03297346457839012,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.931,
+      "step": 26
+    },
+    {
+      "epoch": 0.0619843604275773,
+      "grad_norm": 0.03240511566400528,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.9304,
+      "step": 27
+    },
+    {
+      "epoch": 0.06428007748045053,
+      "grad_norm": 0.030236361548304558,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.9319,
+      "step": 28
+    },
+    {
+      "epoch": 0.06657579453332377,
+      "grad_norm": 0.02867850475013256,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.9315,
+      "step": 29
+    },
+    {
+      "epoch": 0.068871511586197,
+      "grad_norm": 0.033412039279937744,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.9306,
+      "step": 30
+    },
+    {
+      "epoch": 0.07116722863907024,
+      "grad_norm": 0.031119193881750107,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.9311,
+      "step": 31
+    },
+    {
+      "epoch": 0.07346294569194346,
+      "grad_norm": 0.03084520809352398,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.9302,
+      "step": 32
+    },
+    {
+      "epoch": 0.0757586627448167,
+      "grad_norm": 0.030229168012738228,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.9302,
+      "step": 33
+    },
+    {
+      "epoch": 0.07805437979768994,
+      "grad_norm": 0.027583809569478035,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.9302,
+      "step": 34
+    },
+    {
+      "epoch": 0.08035009685056317,
+      "grad_norm": 0.023065637797117233,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.9309,
+      "step": 35
+    },
+    {
+      "epoch": 0.08264581390343641,
+      "grad_norm": 0.017537105828523636,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.9303,
+      "step": 36
+    },
+    {
+      "epoch": 0.08494153095630963,
+      "grad_norm": 0.01801358535885811,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.9312,
+      "step": 37
+    },
+    {
+      "epoch": 0.08723724800918287,
+      "grad_norm": 0.03332036733627319,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.9313,
+      "step": 38
+    },
+    {
+      "epoch": 0.0895329650620561,
+      "grad_norm": 0.04296748340129852,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.9302,
+      "step": 39
+    },
+    {
+      "epoch": 0.09182868211492934,
+      "grad_norm": 0.03908509761095047,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.93,
+      "step": 40
+    },
+    {
+      "epoch": 0.09412439916780257,
+      "grad_norm": 0.03531024605035782,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.9302,
+      "step": 41
+    },
+    {
+      "epoch": 0.0964201162206758,
+      "grad_norm": 0.03801163285970688,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.9311,
+      "step": 42
+    },
+    {
+      "epoch": 0.09871583327354903,
+      "grad_norm": 0.036971934139728546,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.931,
+      "step": 43
+    },
+    {
+      "epoch": 0.10101155032642227,
+      "grad_norm": 0.033191367983818054,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.9305,
+      "step": 44
+    },
+    {
+      "epoch": 0.1033072673792955,
+      "grad_norm": 0.03528426215052605,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.9296,
+      "step": 45
+    },
+    {
+      "epoch": 0.10560298443216873,
+      "grad_norm": 0.02626977674663067,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.9298,
+      "step": 46
+    },
+    {
+      "epoch": 0.10789870148504196,
+      "grad_norm": 0.026993898674845695,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.9309,
+      "step": 47
+    },
+    {
+      "epoch": 0.1101944185379152,
+      "grad_norm": 0.024933425709605217,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.9299,
+      "step": 48
+    },
+    {
+      "epoch": 0.11249013559078844,
+      "grad_norm": 0.018691590055823326,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.9317,
+      "step": 49
+    },
+    {
+      "epoch": 0.11478585264366167,
+      "grad_norm": 0.02374712936580181,
+      "learning_rate": 1e-05,
+      "loss": 11.9307,
+      "step": 50
+    },
+    {
+      "epoch": 0.11478585264366167,
+      "eval_loss": 11.927669525146484,
+      "eval_runtime": 0.1788,
+      "eval_samples_per_second": 279.696,
+      "eval_steps_per_second": 72.721,
+      "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": 522224467968.0,
+  "total_flos": 1043797377024.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null