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:ba49b98b86267ea00cb4c0c6ecd9f699cc6485013af5062e1ea0b97d248dacff
+oid sha256:53ffd25915f71a936a1943840ee2e251fd6de062abc6961756117b349bcce0fb
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f774c5041994dad843de7c0b97857577bd0153864af7b0f98c50e798756552bd
+oid sha256:3a8b6d3c8e0aad2e09e2af46b00783f4f170c968b459647226bae7c4b17cbf33
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a117574bcd3a28d389b2ac1c66b250384e2931befe746d30aff6f9b791b5507
+oid sha256:a4735a91a4dfc22def01efc2570e6527206c44b4bd1136059fc576b3c93809ee
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72efbd81230b872693790da679f94fcadcd075d05ec8d945e330ce2b1b1a3a3c
+oid sha256:0b3f9aa6ee1daab46415981fd36d8c65007d7fa9e138df7195022faad2c426f2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:253c1f305a3d6490529abea03fd225f07188bc38cce8351cd2dadf9bfdeeee02
+oid sha256:ca0b714b2fe19cbb254c491b1cf0d99586fd2242f2337b4c5be8a97b1b0c8fa5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdca3b746124f402068267481108e6d264678e836baa7b21def5b1bb6aca4ccd
+oid sha256:2380ba65a4d16193585f866d4ebfe8c6d717e6b7d4d8f2bccf814d768da2087a
 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": 0.0038535645472061657,
+  "epoch": 0.007707129094412331,
   "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": 15.185,
       "eval_steps_per_second": 3.948,
       "step": 25
+    },
+    {
+      "epoch": 0.004007707129094412,
+      "grad_norm": 0.2780517339706421,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.1835,
+      "step": 26
+    },
+    {
+      "epoch": 0.004161849710982659,
+      "grad_norm": 0.2748948931694031,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.1004,
+      "step": 27
+    },
+    {
+      "epoch": 0.004315992292870906,
+      "grad_norm": 0.3136284351348877,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.2712,
+      "step": 28
+    },
+    {
+      "epoch": 0.004470134874759152,
+      "grad_norm": 0.2965591847896576,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.2592,
+      "step": 29
+    },
+    {
+      "epoch": 0.004624277456647399,
+      "grad_norm": 0.3082920014858246,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.2643,
+      "step": 30
+    },
+    {
+      "epoch": 0.004778420038535645,
+      "grad_norm": 0.3298587501049042,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.4209,
+      "step": 31
+    },
+    {
+      "epoch": 0.0049325626204238925,
+      "grad_norm": 0.30679869651794434,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.3488,
+      "step": 32
+    },
+    {
+      "epoch": 0.005086705202312139,
+      "grad_norm": 0.3360414505004883,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.4167,
+      "step": 33
+    },
+    {
+      "epoch": 0.005240847784200385,
+      "grad_norm": 0.34086665511131287,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.5297,
+      "step": 34
+    },
+    {
+      "epoch": 0.005394990366088632,
+      "grad_norm": 0.39216431975364685,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.5874,
+      "step": 35
+    },
+    {
+      "epoch": 0.0055491329479768784,
+      "grad_norm": 0.4349631667137146,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.6172,
+      "step": 36
+    },
+    {
+      "epoch": 0.005703275529865126,
+      "grad_norm": 0.5350357294082642,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.496,
+      "step": 37
+    },
+    {
+      "epoch": 0.005857418111753372,
+      "grad_norm": 0.2876313328742981,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.209,
+      "step": 38
+    },
+    {
+      "epoch": 0.006011560693641618,
+      "grad_norm": 0.2404983937740326,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.2665,
+      "step": 39
+    },
+    {
+      "epoch": 0.006165703275529865,
+      "grad_norm": 0.266658216714859,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.357,
+      "step": 40
+    },
+    {
+      "epoch": 0.0063198458574181115,
+      "grad_norm": 0.29665255546569824,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.2722,
+      "step": 41
+    },
+    {
+      "epoch": 0.006473988439306359,
+      "grad_norm": 0.2774446904659271,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.2849,
+      "step": 42
+    },
+    {
+      "epoch": 0.006628131021194605,
+      "grad_norm": 0.2746015191078186,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.2507,
+      "step": 43
+    },
+    {
+      "epoch": 0.006782273603082852,
+      "grad_norm": 0.29231736063957214,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.2986,
+      "step": 44
+    },
+    {
+      "epoch": 0.006936416184971098,
+      "grad_norm": 0.31806090474128723,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.4726,
+      "step": 45
+    },
+    {
+      "epoch": 0.0070905587668593445,
+      "grad_norm": 0.3273776173591614,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.4034,
+      "step": 46
+    },
+    {
+      "epoch": 0.007244701348747592,
+      "grad_norm": 0.3434179127216339,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.4006,
+      "step": 47
+    },
+    {
+      "epoch": 0.007398843930635838,
+      "grad_norm": 0.38592585921287537,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.487,
+      "step": 48
+    },
+    {
+      "epoch": 0.007552986512524085,
+      "grad_norm": 0.4318895936012268,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.4787,
+      "step": 49
+    },
+    {
+      "epoch": 0.007707129094412331,
+      "grad_norm": 0.569764256477356,
+      "learning_rate": 1e-05,
+      "loss": 1.4057,
+      "step": 50
+    },
+    {
+      "epoch": 0.007707129094412331,
+      "eval_loss": 1.3222453594207764,
+      "eval_runtime": 3.3045,
+      "eval_samples_per_second": 15.131,
+      "eval_steps_per_second": 3.934,
+      "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": 2.987771858905989e+17,
+  "total_flos": 5.971813667564421e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null