Training in progress, step 7000

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dce28954f69ce7f466b50fc774c94fb6da869b76f94baf208c3e276b1365db2
+oid sha256:829e114ab5a9e821c62f695524a70db8ca49a86641b2859ce77fb48a06a52662
 size 500897101

{checkpoint-6600 → checkpoint-6900/adapter_model}/adapter_config.json

@@ -14,13 +14,13 @@
   "r": 32,
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "gate_proj",
     "down_proj",
+    "up_proj",
     "q_proj",
     "k_proj",
-    "o_proj",
-    "v_proj"
+    "gate_proj",
+    "v_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

{checkpoint-6600 → checkpoint-6900/adapter_model}/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d81f9de68995df3ae7fe51e14a4d5a0482b3ff50173f115d320ee99247cb5e3d
+oid sha256:6dce28954f69ce7f466b50fc774c94fb6da869b76f94baf208c3e276b1365db2
 size 500897101

{checkpoint-6600/adapter_model → checkpoint-7000}/adapter_config.json

@@ -14,13 +14,13 @@
   "r": 32,
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "gate_proj",
     "down_proj",
+    "up_proj",
     "q_proj",
     "k_proj",
-    "o_proj",
-    "v_proj"
+    "gate_proj",
+    "v_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

{checkpoint-6600/adapter_model → checkpoint-7000}/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d81f9de68995df3ae7fe51e14a4d5a0482b3ff50173f115d320ee99247cb5e3d
+oid sha256:829e114ab5a9e821c62f695524a70db8ca49a86641b2859ce77fb48a06a52662
 size 500897101

{checkpoint-6600 → checkpoint-7000}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:126ec0322a5714bfa1d9503fe376d8ebf71cc64ffc913454c2c8b48b06bfd15f
+oid sha256:6a9f18d0ef7f096d1b7c973f10ec3ff7564492d5356b822823b9290813bd22af
 size 1001752701

{checkpoint-6600 → checkpoint-7000}/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a6a609c8ce73fc706f6fb966ebfd028a35b6fc2b3ef2c3b90b14c2d9d96c073
+oid sha256:4ffb463444805a626686fb368559bb528c8cad11a439e94e0669fbefa155f5a9
 size 27772

{checkpoint-6600 → checkpoint-7000}/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:513344a4102cc8801ca6a9111665c65ff7e9a337b61788efc4dbd10afd40421e
+oid sha256:23a0c530aab0bbf04ce6a7cdc9a43f74cface45e607ab049dd048298af780c63
 size 27772

{checkpoint-6600 → checkpoint-7000}/rng_state_10.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84bdaf5f54f27ae7dd4367ad1df5dc5c81c793f62be76df32dd2a92891c0ae9f
+oid sha256:a1729a7aa500d02af4fd9210e649b1e1990a9626a717d3df685f3e8d4bbd8972
 size 27789

{checkpoint-6600 → checkpoint-7000}/rng_state_11.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98e58aa58921c7b94e7c72eb60e9c4d6abe4187fa10dfd3dde14df9291075366
+oid sha256:19e5b4b85191400cd5e64e2f8237e15f18b8b594925371005270709c6fdead8f
 size 27789

{checkpoint-6600 → checkpoint-7000}/rng_state_12.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90a0a154457600ec617c2bdbb216fa73b29edafbe85cd1f69bdc45d06510b354
+oid sha256:c3b402b3eb4de19ff6a9f8883a5fcd04a43806b59a03e4efdc8bf4fb9e09b013
 size 27789

{checkpoint-6600 → checkpoint-7000}/rng_state_13.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:702356496f60d3e621103bc084d4848106ba4006fdd2d5ad6640539693a5e42a
+oid sha256:c4fc3b0264037c6adeffe7738e3557c467ef0d8ed53839e47a410daf2fe89dca
 size 27789

{checkpoint-6600 → checkpoint-7000}/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:046a0af63804ca31a141d5015a52b23ee2774bb6e4992759b32c342ddc173129
+oid sha256:010c3d33f4e3de2781a9f0ba558acdebc4c7141cfd907d61f3e048d2e7d39993
 size 27772

{checkpoint-6600 → checkpoint-7000}/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eb3a5e7cd3e2477ec830ebb148f6b3b4ae734efaa4086c861d75bd02f98d32d
+oid sha256:21817ffe90861ca50df336908db88de597bc45f8e09a83382b7c14f1fdacb1a7
 size 27772

{checkpoint-6600 → checkpoint-7000}/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dfd38532c9714d2d07dcbded515916fc4a2a8ebf7809eb89c8e40ba30623300
+oid sha256:94aae1471cb561bdfae8fb9883b0a5cf60945ea0575bb647c07aa05ae3d4ac36
 size 27772

{checkpoint-6600 → checkpoint-7000}/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6d24543c66c5d1f88ce0e125b12e7a3822599ea0fc5c8774770d4b6e36e9a0a
+oid sha256:d3f9bd490917bf4ae8dd3759559f6bd62286b84a1bf4861c8a1e987719cae69b
 size 27772

{checkpoint-6600 → checkpoint-7000}/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e194294db8d8734e6cc4d219d1f312dace676b799dac00f96ab1b32058105929
+oid sha256:6a072639d1100cd5b5b95d4b5e5ca774464ea41404ceeb55917b006dc3bcd0cf
 size 27772

{checkpoint-6600 → checkpoint-7000}/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1970a2d9f7cb4f5fff840955a3b522a1b4bb096917d81f71d05d1ab7512a2d1a
+oid sha256:1ee4287283869a9044a5fb4c2a9726e7e1f6ee58c3cb254a6f7d766de60a14a8
 size 27772

{checkpoint-6600 → checkpoint-7000}/rng_state_8.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4d396595cc95649a6e4b094f41829540f57ac9e24ad4e6eb37d58aac423d45a
+oid sha256:39077828ac43bedfceb19708273b4a740799cc80eb0725b8973a8ef021c0925e
 size 27772

{checkpoint-6600 → checkpoint-7000}/rng_state_9.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aed28956ad5859c504e2fb1745186ccc74f16e74b31582a197cb9dcab20b3d56
+oid sha256:b29f83ff1993eda2c6298d90ac20110f504235dc369af2574075117cf97cf573
 size 27772

{checkpoint-6600 → checkpoint-7000}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:152f426be01aff254cb20a567c7989c603706f46efd9a2a941b2d4911bff72ad
+oid sha256:78b2e1a7576f141a45b1812083ab858caaac51d2b76c32d2a01e78f578acf12e
 size 627

{checkpoint-6600 → checkpoint-7000}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.5591314462970143,
-  "global_step": 6600,
+  "epoch": 2.7142303218301667,
+  "global_step": 7000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1614,11 +1614,115 @@
       "learning_rate": 1.0495933612511976e-05,
       "loss": 0.7729,
       "step": 6600
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.0047251250769175e-05,
+      "loss": 0.772,
+      "step": 6625
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 9.60786216080466e-06,
+      "loss": 0.7702,
+      "step": 6650
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 9.177811737142627e-06,
+      "loss": 0.7711,
+      "step": 6675
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 8.757144409503359e-06,
+      "loss": 0.765,
+      "step": 6700
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 8.34590363821306e-06,
+      "loss": 0.7713,
+      "step": 6725
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 7.944131909713859e-06,
+      "loss": 0.7631,
+      "step": 6750
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 7.551870732174416e-06,
+      "loss": 0.767,
+      "step": 6775
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 7.169160631201566e-06,
+      "loss": 0.7692,
+      "step": 6800
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 6.796041145653553e-06,
+      "loss": 0.7677,
+      "step": 6825
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 6.432550823555128e-06,
+      "loss": 0.7706,
+      "step": 6850
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 6.078727218115043e-06,
+      "loss": 0.7678,
+      "step": 6875
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 5.734606883846338e-06,
+      "loss": 0.7717,
+      "step": 6900
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.40022537278978e-06,
+      "loss": 0.7701,
+      "step": 6925
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.07561723084089e-06,
+      "loss": 0.7694,
+      "step": 6950
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 4.7608159941809e-06,
+      "loss": 0.7659,
+      "step": 6975
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 4.455854185812047e-06,
+      "loss": 0.7639,
+      "step": 7000
+    },
+    {
+      "epoch": 2.71,
+      "eval_loss": 0.8055068850517273,
+      "eval_runtime": 58.7443,
+      "eval_samples_per_second": 12.427,
+      "eval_steps_per_second": 0.902,
+      "step": 7000
     }
   ],
   "max_steps": 7737,
   "num_train_epochs": 3,
-  "total_flos": 2.842466784500515e+19,
+  "total_flos": 3.0145536634921157e+19,
   "trial_name": null,
   "trial_params": null
 }

{checkpoint-6600 → checkpoint-7000}/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e85009bca9623c846e630c294adb80ecbcd9e720da8da9f9ee5311b562908b91
+oid sha256:1c2f4cc723c65538de12d445f71a30b1610b702bfe771edb2385636bb8724bfd
 size 4027